Search Results (1 - 25 of 48 Results)

Sort By  
Sort Dir
 
Results per page  

Al-Humaidi, Hanouf M.A fuzzy logic approach to model delays in construction projects
Doctor of Philosophy, The Ohio State University, 2007, Civil Engineering
Delays in construction projects are inevitable; as a result claims and disputes arise among different construction parties. Different causes of delay can come into play, therefore, there is a need to identify and classify different causes of project delay. Estimation of the likelihood of delay resulting from different factors that contribute to project delay is essential to project success. Different factors that contribute to project delay affect the likelihood of project delay in different effectiveness degrees. There is a pressing need to estimate the likelihood of delay by implementing analysis methods and examining these methods. Probabilistic fault tree analysis and fuzzy fault tree analysis are two methods suggested by this research to estimate the likelihood of delay. Fuzzy fault tree analysis is performed by planners and managers since they select the delay causes that are applicable to a given project and categorize these delay causes into enabling, triggering, and procedural causes. Then, managers assess the degree of effectiveness of each cause of delay to overall project delay. Assessment of the contributing causes of delay and their degree of effectiveness on project delay uses subjective judgment linguistic terms. The result of the fuzzy fault tree analysis is a likelihood of delay membership function that is compared to the predefined fuzzy logic model to assess the degree of severity of the likelihood of delay. Likelihood of delay membership function is further quantified using the weighted average defuzzification method. Different fuzzy logic models are implemented into the fuzzy fault tree analysis, using Visual Basic software, these models are Baldwin’s rotational model, the Angular model, the Translational model and the Triangular model. Recommendation of the fuzzy logic model that is best applied to a given scenario needs further sensitivity analysis and is beyond the scope of this research. Validation of the fuzzy fault tree analysis computer model is performed. Some suggestions by experts are implemented into the computer model while other suggestions are deferred to future research. The computer software suggested by this study is an attempt to help reduce delays in construction projects that can cause time loss.

Committee:

Fabian Tan (Advisor)

Subjects:

Engineering, Civil

Keywords:

Fuzzy Logic; Likelihood of Project Delay; Fuzzy Fault Tree Analysis; Fuzzy Logic Models; Translational Fuzzy Logic Model; Rotational Fuzzy Logic Model; Triangular Fuzzy Logic Model; Angular Fuzzy Logic Model; Delays in Projects

Mathur, GarimaFuzzy logic control for infant-incubator systems
Master of Science in Engineering, University of Akron, 2006, Biomedical Engineering
Premature birth is a world wide problem. Neonates, who are born premature, often don’t have enough maturity to regulate their temperature. These infants have low metabolic heat production rate and may have high heat loss from the skin. Premature infants are kept in infant incubators which provide convective heating. There are two kinds of techniques available to control the incubator temperature. Currently either the incubator air temperature is sensed and used to control the heat flow, or infant’s skin temperature is sensed and used in the close loop control. Skin control often leads to large fluctuations in the incubator air temperature. Air control also leads to skin temperature fluctuations. The question remains if both the skin temperature and the air temperature can be simultaneously used in the control. The purpose of the present study was to address this question by developing a fuzzy logic control which incorporates both incubator air temperature and infant’s skin temperature. The temperature space was divided into a number of sub-domains. The crisp values of skin and air temperature were first fuzzified to obtain membership values which were then input to a rule base to obtain the output. This output was defuzzified to obtain a crisp value for the heat flow parameter. This fuzzy logic control system was evaluated using a mathematical model of the infant incubator system (Simon, Reddy, and Kantak, 1994). Simulation results revealed that fuzzy logic system, incorporating both skin and air temperatures, provide a smooth control when compared to either the air or skin control.

Committee:

Narender Reddy (Advisor)

Subjects:

Engineering, Biomedical

Keywords:

Incubator ; Neonate; Fuzzy logic; Temperature control; infant; servo control; temperature; core; skin

Sabo, ChelseaUAV Two-Dimensional Path Planning In Real-Time Using Fuzzy Logic
MS, University of Cincinnati, 2011, Engineering and Applied Science: Aerospace Engineering
There are a variety of scenarios in which the mission objectives rely on a UAV being capable of maneuvering in an environment containing obstacles in which there is little prior knowledge of the surroundings. In these situations, not only can these obstacles be dynamic, but sometimes there is no way to plan ahead of the mission to avoid them. Additionally, there are many situations in which it is desirable to send in an exploratory robot where the environment is dangerous/ contaminated and there is a great deal of uncertainty. These scenarios could either be too risky to send people or not available to humans. With an appropriate dynamic motion planning algorithm in these situations, robots or UAVs would be able to maneuver in any unknown and/or dynamic environment towards a target in real-time. An autonomous system that can handle these varying conditions rapidly and efficiently without failure is imperative to the future of unmanned aerial vehicle (UAV). This paper presents a methodology for two-dimensional path planning of a UAV using fuzzy logic. This approach is selected due to its ability to emulate human decision making and relative ease of implementation. The fuzzy inference system takes information in real time about obstacles (if within the agent’s sensing range) and target location and outputs a change in heading angle and speed. The FL controller was validated for both simple (polygon obstacles in a sparse space) and complex environments (i.e. non-polygon obstacles, symmetrical/concave obstacles, dense environments, etc). Additionally, Monte Carlo testing was completed to evaluate the performance of the control method. Not only was the path traversed by the UAV often the exact path computed using an optimal method, the low failure rate makes the Fuzzy Logic Controller (FLC) feasible for exploration. The FLC showed only a total of 3% failure rate, whereas an Artificial Potential Field (APF) solution, a commonly used intelligent control method, had an average of 18% failure rate. Also, the APF method failed about 1/3 of the time for very dense environments (the FLC only had 5% failure rate). These results highlighted one of the advantages of the FLC method: its adaptability to additional rules while maintaining low control effort. Furthermore, the solutions showed superior results when compared to the APF solutions when compared to distance traversed. Overall, the FLC produced solutions that were on average only about 7.7% greater distance traveled (as opposed to 9.7% for the APF).

Committee:

Kelly Cohen, PhD (Committee Chair); Shaaban Abdallah, PhD (Committee Member); Manish Kumar, PhD (Committee Member)

Subjects:

Aerospace Materials

Keywords:

UAV;Path Planning;Fuzzy Logic;Online;Real-Time;Motion Planning

Shankar, ArunprasathONTOLOGY-DRIVEN SEMI-SUPERVISED MODEL FOR CONCEPTUAL ANALYSIS OF DESIGN SPECIFICATIONS
Master of Sciences (Engineering), Case Western Reserve University, 2014, EECS - Computer Engineering
The integration of reusable IP blocks/cores is a common process in system-on-chip design and involves manually comparing/mapping IP specifications against system requirements. The informal nature of specification limits its automatic analysis. Ex- isting techniques fail to utilize the underlying conceptual information embedded in specifications. In this thesis, we present a methodology for specification analysis, which involves concept mining of specifications to generate domain ontologies. We employ a semi-supervised model with semantic analysis capability to create a col- laborative framework for cumulative knowledge acquisition. Our system then uses the generated ontologies to perform component retrieval and spec comparisons. We demonstrate our approach by evaluating several IP specifications.

Committee:

Christos Papachristou (Advisor)

Subjects:

Computer Engineering; Computer Science; Information Systems; Systems Design

Keywords:

Ontology, Specification Mining, Neuro-fuzzy, Information Retrieval, Artificial Intelligence, Expert Systems, Fuzzy Logic, Knowledge Representation, Data Mining, Specification Analysis, Natural Language Processing

Lafountain, CodyMatlab-based Development of Intelligent Systems for Aerospace Applications
MS, University of Cincinnati, 2015, Engineering and Applied Science: Aerospace Engineering
In recent times, there have been a growing number of aerospace application utilizing “Intelligent Systems” methods. These methods include Genetic Algorithms and Fuzzy Logic. Genetic Algorithms were used as an optimization tool for morphing wing airfoils and to optimize Fuzzy Logic path planning algorithms. Fuzzy Logic was used to guide an agent through a hazard field while minimizing exposure to the hazard. Additionally, advanced statistical techniques such as Proper Orthogonal Decomposition were used in the investigation of creating low-order models of supersonic cavity flows, and attempting to remove noise (such as smoke) from video taken during fire-fighting operations. The main goal of this research was take these intelligent systems methods and utilize them to develop user-friendly software applications which can be used by undergraduate and graduate students. It is for this reason that the source code is being included in this thesis, to allow future students to utilize and build upon these applications. AeroMorph provides the user with a graphical interface which can be used to optimize airfoils shapes for a given flight scenario. It uses XFOIL as a virtual wind tunnel to provide quick results which are then optimized using the genetic algorithm. Then the optimized airfoil can be tested against the original to see the improvement. GAPPER provides graphical tools to build hazard maps and solve them using different Fuzzy Logic path-planning routines. The user can use a genetic algorithm to optimize a path-planning routine and then the user can directly control the agent to benchmark the path-planning routine against a human. ssPOD provides a graphical environment in which Proper Orthogonal Decomposition can be performed on a variety of different problems. It quickly and efficiently provides results for a number of useful variables, and includes plotting tools to make communication of results easy. The MATLAB programs were benchmarked to determine their efficacy at the problems they were built to tackle, with good results. AeroMorph has been used by students in morphing wing projects, GAPPER can out-perform humans at hazard navigation, and ssPOD produces results which correlate well to theoretical predictions.

Committee:

Kelly Cohen, Ph.D. (Committee Chair); Shaaban Abdallah, Ph.D. (Committee Member); Awatef Hamed, Ph.D. (Committee Member); Manish Kumar, Ph.D. (Committee Member)

Subjects:

Aerospace Materials

Keywords:

Matlab;Genetic Algorithm;Morphing;Fuzzy Logic;POD;Path Planning

Wang, ShuoControl of a Uni-Axial Magnetorheological Vibration Isolator
Doctor of Philosophy in Engineering, University of Toledo, 2011, College of Engineering

The technologies of hybridization of vehicles have been proven to significantly improve the fuel economy and reduce the environmental pollution. These technologies combine additional power sources with a traditional internal combustion engine. In some other modern vehicles, advanced cylinder management is the means to reduce fuel consumption and emissions. While these advanced technologies aim at energy savings and preserving the environment they create additional noise, vibration and harshness (NVH) problem.

The noise, vibration and harshness problem has been a major area of research in the automotive industry. Vibration is the main cause for noise. With the advent of alternative energy and hybrid vehicles come new vibration problems and challenges that require nontraditional solutions. Semi-active vibration isolation devices are preferred to address the problem due to their effectiveness and affordability. A magnetorheological (MR) fluid mount can provide effective vibration isolation for applications such as hybrid vehicles. The MR fluid can produce different levels of damping when exposed to different levels of magnetic field. The fluid can be working in three modes which are the flow mode, shear mode and squeeze mode. A mixed mode MR fluid mount was designed to operate in a combination of the flow mode and the squeeze mode. Each of the working modes and the combined working mode has been studied. The mount's performance has been verified in simulation and experiments.

The focus of the current study is on the design of a control system for the mixed mode MR fluid mount. Based on a model for the uni-axial MR mount a controller has been designed to achieve the lowest possible vibration transmissibility. Furthermore, the MR mount in two degree of freedom structure has been modeled. Displacement transmissibility and force transmissibility are considered in this scenario. It is desirable to minimize both transmissibilities. The controllers to achieve the lowest value for each type of transmissibility were designed. Moreover, a hierarchical controller for realizing the tradeoff between these two types of transmissibility was also constructed. At last, a fuzzy logic controller is devised to closely reproduce the effect of the hierarchical controller. The experiments are set up to realize the hardware-in-the-loop tests. Results from the experiments show that the mixed mode MR fluid mount is able to achieve desired dynamic stiffness which is directly related to vibration transmissibility.

This study provided a fundamental understanding on the behavior of MR fluid mount in a single degree of freedom model and a two degree of freedom model. The significantly reduced transmissibility demonstrates effectiveness of the designed control system. The results of this research can shed some light on developing the control system for other effective isolation devices.

Committee:

Mohammad Elahinia, PhD (Committee Chair); Mansoor Alam, PhD (Committee Member); Mohamed Hefzy, PhD (Committee Member); Ezzatollah Salari, PhD (Committee Member); Mohsin Jamali, PhD (Committee Member)

Subjects:

Automotive Engineering; Electrical Engineering; Mechanical Engineering

Keywords:

MR fluid mount; hybrid vehicles; transmissibility; Vibration Isolator; NVH; fuzzy logic control; hardware-in-the-loop

Al-Kaabi, Noura SalemA fuzzy-based construction safety advisor (CSA) for construction safety in the United Arab
Doctor of Philosophy, The Ohio State University, 2006, Civil Engineering
Construction safety is a concern for many researchers and people in the construction industry. The field of safety has been a topic of research, development and improvement for many decades, but little has been done in studying and improving construction safety in countries like The United Arab Emirates (UAE). The UAE has one of the fastest growing economies in the Middle East, where construction constitutes a major percentage of the gross domestic product. The government and regulatory agencies of UAE are working hard to regulate the industry and improve construction safety, but a more specialized study is needed. This research focuses on creating an automated tool, a construction safety advisor (CSA), that has the capability of assisting UAE construction contractor in improving their construction safety, and the UAE government agencies in establishing a basis for comprehensive construction safety codes. CSA has two main modules, each of which represents a model for improving construction safety. The first module evaluates the performance of a construction firm safety program using a program from OSHA and HSE. The module uses fuzzy logic to define two variables, significance and availability, for each unit of the safety program and evaluates the total safety program performance using two fuzzy membership forms. The second module evaluates the construction site safety setting using the ecological approach of environmental psychology. This module performs fault tree analysis to derive the basic events that contribute to the undesired construction site safety setting. The module is designed with default probabilities values that have been assigned for approximation based on literature reviews and subjective judgment. CSA also provides users with a number of resources including CSA help file, glossary of technical terms, links to construction safety resources on the web, and printable checklists for different units of the safety program, which could be used for onsite inspections. CSA was evaluated by safety engineers and construction managers in the USA whom rated it as very good. CSA can be used by construction firms wishing to evaluate their basic safety requirements before or during construction and to perform an onsite inspection using CSA printable checklists.

Committee:

Fabian Hadipriono (Advisor)

Subjects:

Engineering, Civil

Keywords:

Construction Safety; Safety Performance; Fuzzy Logic; United Arab Emirates

Jiang, XiaomoDynamic fuzzy wavelet neural network for system identification, damage detection and active control of highrise buildings
Doctor of Philosophy, The Ohio State University, 2005, Civil Engineering
A multi-paradigm nonparametric model, dynamic fuzzy wavelet neural network (WNN) model, is developed for structural system identification of three dimensional highrise buildings. The model integrates chaos theory (nonlinear dynamics theory), a signal processing method (wavelets), and two complementary soft computing methods (fuzzy logic and neural network). An adaptive Levenberg-Marquardt-least-squares learning algorithm is developed for adjusting parameters of the dynamic fuzzy WNN model. The methodology is applied to one five-story test frame and two highrise moment-resisting building structures. Results demonstrate that the methodology incorporates the imprecision existing in the sensor data effectively and balances the global and local influences of the training data. It therefore provides more accurate system identifications and nonlinear approximation with a fast training convergence. A nonparametric system identification-based model is developed for damage detection of highrise building structures subjected to seismic excitations using the dynamic fuzzy WNN model. The model does not require complete measurements of the dynamic responses of the whole structure. A damage evaluation method is proposed based on a power density spectrum method. The multiple signal classification method is employed to compute the pseudospectrum from the structural response time series. The methodology is validated using experimental data obtained for a 38-story concrete test model. It is demonstrated that the WNN model together with the pseudospectrum method is effective for damage detection of highrise buildings based on a small amount of sensed data. A nonlinear control model is developed for active control of highrise three dimensional building structures including geometrical and material nonlinearities, coupling action between lateral and torsional motions, and actuator dynamics. A dynamic fuzzy wavelet neuroemulator is developed for predicting the structural response in future time steps. A neuro-genetic algorithm is developed for finding the optimal control forces without the pre-training required in a neural network-based controller. Both neuroemulator and neuro-genetic algorithm are validated using two irregular three-dimensional steel building structures, a twelve-story structure with vertical setbacks and an eight-story structure with plan irregularity. Numerical validations demonstrate that the control methodology can significantly reduce the structural displacements of three-dimensional buildings subjected to various seismic excitations.

Committee:

Hojjat Adeli (Advisor)

Subjects:

Engineering, Civil

Keywords:

Structural System Identification; Damage Detection; Structural Health Monitoring; Active Control; Dynamic Neural Network; Wavelets; Fuzzy Logic; Genetic Algorithm; Nonlinear Optimization

Tiley, Jaimie S.Modeling of Microstructure Property Relationships in Ti-6Al-4V
Doctor of Philosophy, The Ohio State University, 2003, Materials Science and Engineering
Fuzzy logic neural network models were developed to predict the room temperature tensile behavior of Ti-6Al-4V. This involved the development of a database relating microstructure to properties. This necessitated establishing heat treatment processes to develop microstructural features, mechanical testing of samples, creating rigorous stereology procedures, developing numerical models to predict mechanical behavior, and determining trends and inter-relationships relating microstructural features to mechanical properties. Microstructural features were developed using a Gleeble™ 1500 Thermal-mechanical simulator. The system used computer controlled resistive heating equipment to provide rapid cooling and heating abilities. Samples were obtained from mill annealed plate material and both alpha + beta forged and beta forged materials. A total of 72 samples were beta solutionized and heat treated using different heating and cooling conditions. Rigorous stereology procedures were developed to characterize the important microstructural features. The features included Widmanstätten alpha lath thickness, volume fraction of total alpha, volume fraction of Widmanstätten alpha, grain boundary alpha thickness, mean edge length, colony scale factor, and prior beta grain size factor. Chemical composition was also determined using standard chemical analysis and microscopy techniques. The samples were tested for yield strength, ultimate tensile strength, and elongation at room temperature. The samples were imaged using various microscopy techniques. Results from the tests and the characterization were used to develop fuzzy logic neural network models to predict the mechanical behaviors and develop relationships between the microstructural features (using CubiCalc RTC™). Results were compared to standard multi-variable regression models. The fuzzy logic neural network models were able to predict the yield, and ultimate tensile strength, within acceptable error ranges with a limited number of input data samples. The models also predicted the elongation values but with larger errors. The models also provided trends detailing the relative importance of the input parameters and the inter-relationships between the features. Of particular importance, the models identified the importance of the Widmanstätten alpha lath widths, the mean edge length of the Widmanstätten alpha laths, the colony scale factor, and the prior beta grain size to the tensile behavior.

Committee:

Hamish Fraser (Advisor)

Subjects:

Engineering, Materials Science

Keywords:

Ti-6Al-4V; fuzzy logic; neural networks; microstructure

Sathyan, AnoopIntelligent Machine Learning Approaches for Aerospace Applications
PhD, University of Cincinnati, 2017, Engineering and Applied Science: Aerospace Engineering
Machine Learning is a type of artificial intelligence that provides machines or networks the ability to learn from data without the need to explicitly program them. There are different kinds of machine learning techniques. This thesis discusses the applications of two of these approaches: Genetic Fuzzy Logic and Convolutional Neural Networks (CNN). Fuzzy Logic System (FLS) is a powerful tool that can be used for a wide variety of applications. FLS is a universal approximator that reduces the need for complex mathematics and replaces it with expert knowledge of the system to produce an input-output mapping using If-Then rules. The expert knowledge of a system can help in obtaining the parameters for small-scale FLSs, but for larger networks we will need to use sophisticated approaches that can automatically train the network to meet the design requirements. This is where Genetic Algorithms (GA) and EVE come into the picture. Both GA and EVE can tune the FLS parameters to minimize a cost function that is designed to meet the requirements of the specific problem. EVE is an artificial intelligence developed by Psibernetix that is trained to tune large scale FLSs. The parameters of an FLS can include the membership functions and rulebase of the inherent Fuzzy Inference Systems (FISs). The main issue with using the GFS is that the number of parameters in a FIS increase exponentially with the number of inputs thus making it increasingly harder to tune them. To reduce this issue, the FLSs discussed in this thesis consist of 2-input-1-output FISs in cascade (Chapter 4) or as a layer of parallel FISs (Chapter 7). We have obtained extremely good results using GFS for different applications at a reduced computational cost compared to other algorithms that are commonly used to solve the corresponding problems. In this thesis, GFSs have been designed for controlling an inverted double pendulum, a task allocation problem of clustering targets amongst a set of UAVs, a fire detection problem and the aircraft conflict resolution problem. During the last decade, CNNs have become increasingly popular in the domain of image and speech processing. CNNs have a lot more parameters compared to GFSs that are tuned using the back-propagation algorithm. CNNs typically have hundreds of thousands or maybe millions of parameters that are tuned using common cost functions such as integral squared error, softmax loss etc. Chapter 5 discusses a classification problem to classify images as humans or not and Chapter 6 discusses a regression task using CNN for producing an approximate near-optimal route for the Traveling Salesman Problem (TSP) which is regarded as one of the most complicated decision making problem. Both the GFS and CNN are used to develop intelligent systems specific to the application providing them computational efficiency, robustness in the face of uncertainties and scalability.

Committee:

Kelly Cohen, Ph.D. (Committee Chair); Raj Bhatnagar, Ph.D. (Committee Member); Franck Cazaurang, Ph.D. (Committee Member); Nicholas C. Ernest, Ph.D. (Committee Member); Manish Kumar, Ph.D. (Committee Member)

Subjects:

Aerospace Materials

Keywords:

Genetic fuzzy logic;Convolutional neural networks;Fire detection;Aircraft conflict resolution;Multiple traveling salesman problem;Dynamic systems

Sypher, Sloan MFuzzy Cognitive Maps: A Design Research Tool to Address Systems of Scaled Complexity
MDES, University of Cincinnati, 2017, Design, Architecture, Art and Planning: Design
It is the contention of this thesis that Fuzzy Cognitive Mapping is one tool to manage the design research process under conditions of scaled complexity as design plays a larger role in the “wicked problems” of the 21st century. Fuzzy Cognitive Maps (FCMs) are an appropriate tool for design research as they are born out of the constructivist philosophy and the notion that knowledge creation is a socially rooted process of human-centered discovery in which connections are made between different ideas and areas of knowledge. The “fuzzy” component (Fuzzy Logic) of FCMs allows for better decision making when the information is not always complete and data is noisy, when thresholds are ambiguous and interactions are not accurately assessed. FCMs are graphical representations of structured knowledge, represented by concepts linked by directed, weighted, and signed (positive, negative) edges. The hope is that such a tool will be a meaningful addition to designers’ knowledge-base when applying their design abilities to solve complex, societal issues.

Committee:

Craig Vogel, M.I.D. (Committee Chair); Vittoria Daiello, Ph.D. (Committee Member)

Subjects:

Design

Keywords:

Fuzzy Cognitive Mapping;Design Methodology;Fuzzy Logic;Constructivism;Wicked Problems;Design Theory

FNU, Vijaykumar SureshkumarAutonomous Control of A Quadrotor UAV Using Fuzzy Logic
MS, University of Cincinnati, 2015, Engineering and Applied Science: Aerospace Engineering
UAVs are being increasingly used today than ever before in both military and civil applications. They are heavily preferred in “dull, dirty or dangerous” mission scenarios. Increasingly, UAVs of all kinds are being used in policing, fire-fighting, inspection of structures, pipelines etc. Recently, the FAA gave its permission for UAVs to be used on film sets for motion capture and high definition video recording. The rapid development in MEMS and actuator technology has made possible a plethora of UAVs that are suited for commercial applications in an increasingly cost effective manner. An emerging popular rotary wing UAV platform is the Quadrotor A Quadrotor is a helicopter with four rotors, that make it more stable; but more complex to model and control. Characteristics that provide a clear advantage over other fixed wing UAVs are VTOL and hovering capabilities as well as a greater maneuverability. It is also simple in construction and design compared to a scaled single rotorcraft. Flying such UAVs using a traditional radio Transmitter-Receiver setup can be a daunting task especially in high stress situations. In order to make such platforms widely applicable, a certain level of autonomy is imperative to the future of such UAVs. This thesis paper presents a methodology for the autonomous control of a Quadrotor UAV using Fuzzy Logic. Fuzzy logic control has been chosen over conventional control methods as it can deal effectively with highly nonlinear systems, allows for imprecise data and is extremely modular. Modularity and adaptability are the key cornerstones of FLC. The objective of this thesis is to present the steps of designing, building and simulating an intelligent flight control module for a Quadrotor UAV. In the course of this research effort, a Quadrotor UAV is indigenously developed utilizing the resources of an online open source project called Aeroquad. System design is comprehensively dealt with. A math model for the Quadrotor is developed and a simulation environment is built in the MATLAB/Simulink framework. The Fuzzy flight controller development is discussed intensively. Validation of the math model developed is presented using actual flight data. Excellent attitude tracking is demonstrated for near hover flight regimes. The responses are analyzed and future work involving implementation is discussed.

Committee:

Kelly Cohen, Ph.D. (Committee Chair); Elad Kivelevitch, Ph.D. (Committee Member); Bruce Walker, Sc.D. (Committee Member)

Subjects:

Aerospace Materials

Keywords:

Quadrotor;Fuzzy Logic;Autonomous Control;Attitude Control;Simulation;Math Model

Cook, Brandon MMulti-Agent Control Using Fuzzy Logic
MS, University of Cincinnati, 2015, Engineering and Applied Science: Aerospace Engineering
In the coming years, operations in low altitude airspace will vastly increase as the capabilities and applications of Unmanned Aerial Systems (UAS) continue to multiply. Therefore, solutions to managing vehicles in highly congested airspace must be explored. In this study, an intelligent systems approach was used to help mitigate the risk of collision between aircraft in uncontrolled airspace using a UAS Traffic Management (UTM) System. To test the effectiveness of this system, a three-dimensional environment was created using MATLAB to simulate a fully autonomous heterogeneous fleet of UAS attempting to accomplish a variety of realistic missions, including precision agriculture, package delivery services, natural resource monitoring, and disaster management. Main research challenges include situational awareness, decision making, and multi-agent control in an uncertain, time-critical, spatio-temporal environment. To gain the knowledge, experience, and expertise necessary to solve this large-scale real-world problem, two preliminary research efforts were conducted. First, a simulated gaming platform known as Pong, originally created by ATARI, was used to demonstrate the effectiveness of a fully autonomous team to accomplish a desired task using a cascading Fuzzy system. With this knowledge, a simplified UTM system was developed to test a preliminary design of a fuzzy collision avoidance system. Once complete, this knowledge was used to develop the final UTM system platform capable of using intelligent separation assurance and collision avoidance techniques to mitigate the risk for Near Mid-Air Collisions between aircraft. This fuzzy solution utilizes only current state information and can resolve potential conflicts without knowledge of intruder intent. The collision avoidance system was tested in extreme conditions, including close proximity, high closure rates, and conservative maximum turn rates. In the preliminary homogenous case, the collision avoidance techniques were on average 99.977% successful over a span of nearly 2,485 flight hours. Whereas, in the final UTM platform consisting of heterogeneous agents, the collision avoidance system was on average 99.88% successful over a span of 16,255 flight hours. Lastly, it was found that the techniques employed for separation assurance drastically mitigated the risk for Near Mid-Air Collisions. Comparing the unmitigated and mitigated cases, the number of losses of separation between aircraft reduced from one loss of separation per two flight hours, to one loss of separation per ten flight hours. This mitigated separation assurance platform was successful at preventing a loss of separation 88.47% of the time, over a span of 7,545 flight hours.

Committee:

Kelly Cohen, Ph.D. (Committee Chair); Manish Kumar, Ph.D. (Committee Member); Grant Schaffner, Ph.D. (Committee Member); Gary Slater, Ph.D. (Committee Member)

Subjects:

Aerospace Materials

Keywords:

Fuzzy Logic;UAS Traffic Management;Unmanned Aerial Systems;Intelligent Systems;UAV Collision Avoidnace;Multi-Agent Control

Yang, Jin RongIntelligent Systems Analyzing Sections of the Great Wall of China for Ming and Pre-Ming Dynasty Construction
Master of Science, The Ohio State University, 2012, Civil Engineering
As society moves into the future, environmental concerns such as global warming increase due to human activity (U.S. EPA 2009:2). In construction, the use of cement in concrete contributes to this problem. Scientists and Engineers believe building green, yet durable, is the key to solving this problem. To achieve this goal, researchers must move backward in time to examine how our predecessors built their structures without modern technology, and then they can incorporate the techniques that were used to reduce waste. One of the most qualified structures to examine is the Great Wall of China. The technology they used was not only environmentally friendly, but the structure is also very durable. Some parts of the structure that were built over two thousand years ago still exist today. The research is focused on Ming and Pre Ming dynasty. The research centers on the similarities and differences between the two time periods in construction techniques. Since the Great Wall is very long in length, this research and the research methods mentioned below are limited to Beijing, Hebei and Gansu province. The author found out that the main construction method that was used was rammed earth. The rammed earth method is a technique of building walls by compressing the raw materials such as earth, gravel and lime into the shape of a wall. The construction materials that they used to construct the Great Wall were mainly fire kiln bricks and mud bricks. Fire kiln bricks are made through chemical change when the clay is fired up in the kilns until it is vitrified. Mud bricks, on the other hand, are made through a physical change by letting the bricks dry out in the sun. The main transportation of the material to construct the Great Wall was using a class 2 lever wheelbarrow, though the workers used animals as well. Since the Great Wall was built a long time ago, many historical records and documents were lost or destroyed. The methods listed above are not binary, meaning they are not completely true or false. The author would have to incorporate fuzzy logic to measure the statements, such as how “true” they are, using subjective values. The author also uses Artificial Intelligence and Multi-Media system in his research to assist the end user in the absence of a Great Wall expert. The research results are shown in the Multi-Media system. The research shows that the Great Wall from the Ming dynasty is far superior to the dynasties before it in terms of construction techniques. However; Pre-Ming Dynasty does incorporate more green construction techniques than the Ming Dynasty. Therefore, the author concludes that the structure is durable when it is from the Ming dynasty. The structure is greener when it is from the Pre-Ming dynasty. However, both Ming and Pre-Ming Dynasty’s construction methods are greener than modern practices. With these conclusions, the author recommends using both construction methods from the Ming and the Pre-Ming dynasties to build green yet durable structures for the future.

Committee:

Fabian Tan (Advisor); Frank Croft (Committee Member); Shive Chaturvedi (Committee Member)

Subjects:

Civil Engineering

Keywords:

Great Wall Construction; Fuzzy Logic; Knowledge&8211;Based Expert System (KBES);

Vick, Andrew W.Genetic Fuzzy Controller for a Gas Turbine Fuel System
MS, University of Cincinnati, 2010, Engineering and Applied Science: Aerospace Engineering
In this study, a fuel system controller for a gas turbine engine was examined. Controller design in this application is challenging due to nonlinearities in the closed loop system, as well as uncertainties associated with hardware components from part variation or degradation. Current closed loop design methodologies are discussed, as are the limitations or challenges facing these systems. Details on fuzzy logic control and its benefits in this type of application are explored. Information on genetic algorithms is presented, along with a study on how this optimization approach can be utilized to enhance the fuzzy logic controller process. A fuzzy logic controller structure was developed for providing closed loop fuel control in the gas turbine application, using a genetic algorithm to tune the system to provide an accurate and fast response to changing input demands. With a genetic fuzzy controller in place, closed loop analysis was performed, along with a stochastic robustness analysis to assess controller performance in an uncertain environment. Results show that the genetic fuzzy system performed well in this application, resulting in a system with fast rise and settling times to stepping inputs, while also minimizing overshoot and steady state error. Robustness characteristics of the fuzzy controller were also demonstrated, as the stochastic robustness analysis yielded acceptable performance in each simulation of the closed loop system with uncertainties included.

Committee:

Kelly Cohen, PhD (Committee Chair); Bruce Walker, ScD (Committee Member); Manish Kumar, PhD (Committee Member)

Subjects:

Aerospace Materials

Keywords:

Genetic Algorithm;Fuzzy Logic;Gas Turbine;Fuel System

Polasik, Alison KThe Role of Microstructure on High Cycle Fatigue Lifetime Variability in Ti-6Al-4V
Doctor of Philosophy, The Ohio State University, 2014, Materials Science and Engineering
The microstructural sources of fatigue lifetime variability were investigated for four different microstructural variations of Ti-6Al-4V. Specimens were tested at lower stresses to investigate the behavior in the HCF (high cycle fatigue) regime, which is characterized by lifetimes near or in excess of 10^6 cycles. Fractography and replication analyses confirmed that the lifetime was dominated by crack nucleation, and thus variations in the lifetime between individual test specimens are primarily attributed to variability in the time to nucleate a dominant crack. Stereology was used to quantify key microstructural features for each tested specimen. These values were used as inputs for a series of microstructurally-based fuzzy logic neural network models. Using these models, virtual experiments were conducted to investigate the individual effect of each microstructural feature on the lifetime, an investigation that is impossible to conduct empirically because of the complex microstructure in these alloy systems. These virtual experiments demonstrated that colony size and alath thickness have the greatest effect on HCF lifetime of ß-processed Ti-6Al-4V alloys, and that colony size is more important that a lath thickness. For the a/ß – processed microstructures, the volume fraction of primary a and the a lath thickness were shown to affect the lifetime, while the ap grain size was not. Defect analyses of failed specimens indicated that damage accumulation is often localized during cyclic loading, with dislocation densities varying from one a lath to another. For all specimens, a-type dislocations are seen and c+a - type dislocations were observed only in regions of localized plastic strain. Investigation of site-specific TEM foils extracted from the crack nucleation region of a/ß – processed specimens provided information about the nature and behavior of dislocations during the crack nucleation event. A comparison of short- and long- life specimens provides information about differences in the evolution of the dislocation structure prior to crack nucleation. The potential of this combinatorial approach for future fatigue lifetime investigations is discussed. In particular, the project demonstrates that such an approach could be useful in developing a quantitative understanding of the role variations in microstructural features have on variations in HCF lifetime.

Committee:

Hamish Fraser, PhD (Advisor); Michael Mills, PhD (Committee Member); Stephen Niezgoda, PhD (Committee Member)

Subjects:

Aerospace Materials; Engineering; Materials Science

Keywords:

Fatigue; Titanium; Fuzzy Logic Modeling; Ti-6-4; stereology; microstructure modeling

Wei, WeiDevelopment of an Effective System Identification and Control Capability for Quad-copter UAVs
PhD, University of Cincinnati, 2015, Engineering and Applied Science: Aerospace Engineering
In recent years, with the promise of extensive commercial applications, the popularity of Unmanned Aerial Vehicles (UAVs) has dramatically increased as witnessed by publications and mushrooming research and educational programs. Over the years, multi-copter aircraft have been chosen as a viable configuration for small-scale VTOL UAVs in the form of quad-copters, hexa-copters and octo-copters. Compared to the single main rotor configuration such as the conventional helicopter, multi-copter airframes require a simpler feedback control system and fewer mechanical parts. These characteristics make these UAV platforms, such as quad-copter which is the main emphasis in this dissertation, a rugged and competitive candidate for many applications in both military and civil areas. Because of its configuration and relative size, the small-scale quad-copter UAV system is inherently very unstable. In order to develop an effective control system through simulation techniques, obtaining an accurate dynamic model of a given quad-copter is imperative. Moreover, given the anticipated stringent safety requirements, fault tolerance will be a crucial component of UAV certification. Accurate dynamic modeling and control of this class of UAV is an enabling technology and is imperative for future commercial applications. In this work, the dynamic model of a quad-copter system in hover flight was identified using frequency-domain system identification techniques. A new and unique experimental system, data acquisition and processing procedure was developed catering specifically to the class of electric powered multi-copter UAV systems. The Comprehensive Identification from FrEquency Responses (CIFER®) software package, developed by US Army Aviation Development Directorate – AFDD, was utilized along with flight tests to develop dynamic models of the quad-copter system. A new set of flight tests were conducted and the predictive capability of the dynamic models were successfully validated. A PID controller and two fuzzy logic controllers were developed based on the validated dynamic models. The controller performances were evaluated and compared in both simulation environment and flight testing. Flight controllers were optimized to comply with US Aeronautical Design Standard Performance Specification Handling Quality Requirements for Military Rotorcraft (ADS-33E-PRF). Results showed a substantial improvement for developed controllers when compared to the nominal controllers based on hand tuning. The scope of this research involves experimental system hardware and software development, flight instrumentation, flight testing, dynamics modeling, system identification, dynamic model validation, control system modeling using PID and fuzzy logic, analysis of handling qualities, flight control optimization and validation. Both closed-loop and open-loop dynamics of the quad-copter system were analyzed. A cost-effective and high quality system identification procedure was applied and results proved in simulations as well as in flight tests.

Committee:

Kelly Cohen, Ph.D. (Committee Chair); George Black, M.S. (Committee Member); Manish Kumar, Ph.D. (Committee Member); Grant Schaffner, Ph.D. (Committee Member); Bruce Walker, Sc.D. (Committee Member)

Subjects:

Aerospace Materials

Keywords:

Quad-copter;system identification;flight control;fuzzy logic;handling quality;multi-copter

Rickey, Matthew R.Fuzzy Logic Learning for Predictive Feedback Estimation in a Radiant Heat System
Master of Science in Engineering (MSEgr), Wright State University, 2010, Electrical Engineering
High temperature thermal testing is used to validate the effectiveness of thermal protection systems (TPS) and to simulate aerodynamic heating in high speed flight vehicle structures. Silicon controlled rectifiers (SCR) are utilized to drive resistive heating elements and producing temperatures up to 5000 degrees Fahrenheit. Thermocouples used to provide feedback to the control system have a high probability of failure at extreme temperatures. Traditional solutions include switching to redundant thermocouples, changing to an open-loop control scheme, or using power as the control signal. The first methods is limited in that redundant thermocouples are also not completely reliable. Both open-loop control and power control do not provide temperature data and require one complete test to be accomplished with temperature data available. In this thesis, fuzzy logic learning is used on previously recorded power data to estimate the temperature of the test article. The results of the learning algorithm fit the recorded data closely. Additionally, a fuzzy logic prediction algorithm is developed to estimate the temperature from the power data in the event of thermocouple failure. The algorithm is shown to be effective in predicting temperature from power data if sufficient data is collected prior to thermocouple failure.

Committee:

Kuldip S. Rattan, Ph.D. (Advisor); Marian K. Kazimierczuk, Ph.D. (Committee Member); Xiaodong Zhang, Ph.D. (Committee Member)

Subjects:

Electrical Engineering

Keywords:

Feedback Estimation; Fuzzy Logic; Learning; PLC; Radiant Heat; Predictive Estimation

Syed, Altaf AhmadApplied Fuzzy Logic Controls for Improving Dynamic Response of Induction Machines
Master of Science in Engineering, Youngstown State University, 2008, Department of Electrical and Computer Engineering
This thesis presents a novel approach in control systems for improving the dynamic response of the induction machine. This approach leads to a better and improved control of the torque and current response of the induction machine when compared to the classical proportional-integral (PI) type controller with de-coupling terms. Mismatches in the actual parameters and the estimated parameters of the induction machine occur for several reasons such as: incorrect parameter estimation, changes in stator and rotor inductance due to saturation, stator and rotor resistance varying with temperature, etc. Under the classical approach, the de-coupling errors resulting from the parameter mismatches can become very large at higher machine rotational speeds. Under such conditions, the classical approach results in poor dynamic control of the torque and current response of the induction machine. Therefore, an advanced fuzzy logic controller is presented as a better alternative to the classical controller. The fuzzy logic-based d-q controller, based on its non-linear approach, provides robust control of the torque and current response of the induction machine even in the presence of mismatched parameters. Furthermore, the performance of the fuzzy logic controller is not dependent on the machine rotational speed. Using MATLABSIMULINK tools, the performance of the fuzzy controller is evaluated with mismatched machine parameters at various machine rotational speeds. The results show that the use of the fuzzy logic controller offers a superior control of the torque and current response of the induction machine, independent of the motor rotational speed when compared with the use of the classical controller.

Committee:

Jalal Jalali, PhD (Advisor); Philip Munro, PhD (Committee Member); Faramarz Mossayebi, PhD (Committee Member)

Subjects:

Electrical Engineering; Systems Design

Keywords:

fuzzy logic controller; induction machine; torque and current response

Collins, Peter ChancellorA combinatorial approach to the development of composition-microstructure-property relationships in titanium alloys using directed laser deposition
Doctor of Philosophy, The Ohio State University, 2004, Materials Science and Engineering
The Laser Engineered Net Shaping (LENS™) system, a type of directed laser manufacturing, has been used to create compositionally graded materials. Using elemental blends, it is possible to quickly vary composition, thus allowing fundamental aspects of phase transformations and microstructural development for particular alloy systems to be explored. In this work, it is shown that the use of elemental blends has been refined, such that bulk homogeneous specimens can be produced. When tested, the mechanical properties are equivalent to conventionally prepared specimens. Additionally, when elemental blends are used in LENS™ process, it is possible to deposit compositionally graded materials. In addition to the increase in design flexibility that such compositionally graded, net shape, unitized structures offer, they also afford the capability to rapidly explore composition-microstructure-property relationships in a variety of alloy systems. This research effort focuses on the titanium alloy system. Several composition gradients based on different classes of alloys (designated a, a+b, and b alloys) have been produced with the LENS™. Once deposited, such composition gradients have been exploited in two ways. Firstly, binary gradients (based on the Ti-xV and Ti-xMo systems) have been heat treated, allowing the relationships between thermal histories and microstructural features (i.e. phase composition and volume fraction) to be explored. Neural networks have been used to aid in the interpretation of strengthening mechanisms in these binary titanium alloy systems. Secondly, digitized steps in composition have been achieved in the Ti-xAl-yV system. Thus, alloy compositions in the neighborhood of Ti-6Al-4V, the most widely used titanium alloy, have been explored. The results of this have allowed for the investigation of composition-microstructure-property relationships in Ti-6-4 based systems.

Committee:

Hamish Fraser (Advisor)

Subjects:

Engineering, Materials Science

Keywords:

combinatorial method; combinatorial approach; laser deposition; directed laser deposition; LENS; titanium; molybdenum; Ti-6-4; Ti-6Al-4V; Timetal 21S; composition; microstructure; property; relationships; neural network; fuzzy logic

Yang, ChengDevelopment of Intelligent Energy Management System Using Natural Computing
Master of Science in Engineering, University of Toledo, 2012, College of Engineering
In this thesis an Intelligent Energy Management System (EMS) for end consumer has been proposed. This system develops an algorithm for smart meter which is integrated between distribution grid and end consumers. The smart meter determines when to draw the energy from the grid or the storage unit for consumption. The first objective of the intelligent EMS is to save the cost for consumers by shifting the power drawn from the grid from high cost period to low cost period. The second objective of the intelligent EMS is to avoid grid overload by shifting the power drawn from the grid from high demand period to low demand period. The algorithm takes into consideration the hourly price and load demand of the grid. The algorithm was tested with the real data collected by ISO New England for the six states of Connecticut, Maine, Massachusetts, New Hampshire, Rhode Island and Vermont, during the period of Jan 1, 2011 to Dec 31, 2011. Two approaches based on Fuzzy Logic and Genetic Algorithm (GA) were used. It was demonstrated the GA based approach outperformed the Fuzzy Logic based approach. The intelligent approach based on GA resulted in more cost saving as compared to what was theoretically foreseen and predicted.

Committee:

Dr. Devinder Kaur, PhD (Committee Chair); Dr. Ezzatollah Salari, PhD (Committee Member); Dr. Mansoor Alam, PhD (Committee Member)

Subjects:

Computer Engineering; Computer Science; Electrical Engineering; Energy; Engineering

Keywords:

smart grid; energy management system; smart meter; fuzzy logic; genetic algorithm

Dicken, Christopher L.An Expert System Approach to Best Management Practice Selection for Nominal Scale Low-Impact Redevelopments
Master of Science, The Ohio State University, 2011, Civil Engineering

Commissioned by a world appealing for sustainable efforts, those charged with the development and restoration of our nation’s infrastructure have discovered a need for alternatives to prior unsustainable designs. In order to contend with this demand for innovation, civil engineers must continue to foster sustainable practices in their profession. This state of affairs requires that alternative construction methods be conveyed to those capable of implementing fresh approaches.

Mechanisms for controlling stormwater runoff are one such item of infrastructure which benefit from this re-evaluation of intrinsic conventions. Stormwater Best Management Practices (BMPs) have emerged as the result addressing the need for more sustainable stormwater control. With the aforementioned interest in sustainable practices and the requisite for new infrastructure, a system to convey the efficacy of BMPs can assist in the adoption of these practices as mainstream applications.

To help realize this premise, a software package was developed to introduce the concept of sustainable hydrological developments to those with the interest, influence, or capability to include these features in their designs. This package includes a fully-customizable BMP database, a knowledge-based expert system able to recommend BMPs for a site, and a component to rate the sustainability of a site’s hydrological function. The customizable BMP database allows for the centralization of alterative stormwater management practices molded to the destination environment. The expert system is an interactive way to provide less-experienced personnel with contending BMPs backed by expert intuition. Sustainability is a subjective topic, and to properly rate a development as sustainable, a more firm definition of sustainability is necessary in order to convey a clear message and provide for dependable comparisons. Therefore, several fuzzy logic applications are incorporated into this software program to clarify measures of hydrological sustainability.

This software package provides an interactive system for those who wish to learn about stormwater BMPs. While several tools exist to aid in the design and placement of BMPs, these programs often expect the user to collect a significant amount of information before they are of use. By using the system developed here, the dissemination of knowledge held by established professionals can be conveyed to those with a lesser understanding of BMPs. This in turn promotes BMPs to a wider audience where the program acts as a higher level application that is able to supplement existing software, or perform independently.

Committee:

Fabian Tan, PhD (Committee Chair); William Wolfe, PhD (Committee Member); Dorota Brzezinska, PhD (Committee Member)

Subjects:

Civil Engineering; Engineering; Hydrology; Sustainability; Transportation

Keywords:

best management practices; expert system; street; road; reconstruction; stormwater; fuzzy logic; sustainability; runoff; low-impact development; residential

Kolakowski, TerryFuzzy Logic Control of a Switched-Inductor PWM DC-DC Buck Converter in CCM
Master of Science in Engineering (MSEgr), Wright State University, 2009, Electrical Engineering

Modern electronics are operating at lower voltages with higher currents, requiring power converters to deliver these requirements efficiently. In this thesis, a switch-inductor buck converter is designed for the required specifications; and for the selected design, component losses and efficiency are calculated. A MATLAB/Simulink model is constructed, and tested in the presence of load and source disturbances to show the converter cannot maintain the desired output voltage when the disturbances are applied.

A fuzzy logic PID controller is designed to regulate the duty cycle of the converter to control the output voltage. Control surfaces are designed for proportional, integral, and derivative gains of the fuzzy PID controller. The compensated power converter is tested using the Simulink model in the presence of the disturbances, and it is shown that the fuzzy controller is capable of keeping the power converter output voltage within the operating requirements, while improving system speed and stability.

Committee:

Kuldip Rattan, PhD (Advisor); Marian Kazimierczuk, PhD (Committee Member); Xiaodong Zhang, PhD (Committee Member); Kefu Xue, PhD (Other); Joseph F. Thomas, Jr., PhD (Other)

Subjects:

Electrical Engineering

Keywords:

fuzzy logic control; buck; DC-DC converter; pulse-width modulation

Seyfried, Aaron WStability of a Fuzzy Logic Based Piecewise Linear Hybrid System
Master of Science in Engineering (MSEgr), Wright State University, 2013, Electrical Engineering
Complex cyber-physical systems are difficult to model and control. However, humans are capable of accomplishing these tasks by constantly adapting and redefining the rules to control these complex systems. Fuzzy logic provides a means of encoding human inference into a control methodology. However, the fuzzy logic controllers are nonlinear and their stability is difficult to verify. Therefore, the widespread usefulness of fuzzy logic controllers is limited. It has been proven that fuzzy logic controllers can be implemented as piecewise linear switched controllers. It has also been shown that the piecewise linear system can be implemented as a hybrid system. Piecewise linear hybrid system stability can be verified by extending the Lyapunov proof for one linear system to multiple decreasing Lyapunov functions. The objective of this thesis is to implement fuzzy logic control systems as a piecewise linear hybrid system and examine their stability. A proportional fuzzy logic controller with constant derivative gain is implemented as a piecewise linear hybrid system using Matlab Simulink Stateflow. Stability of the system is examined by obtaining the Lyapunov function of each subsystem and stitching them according to the fuzzy rules. It is shown that the stitching of Lyapunov functions must successively decrease for the system to be stable. Further implications of robustness are examined by varying the fuzzy logic rules and observing the effect on the corresponding stitched Lyapunov functions.

Committee:

Matthew Clark, M.S.Egr. (Committee Co-Chair); Kuldip Rattan, Ph.D. (Committee Co-Chair); Zhang Xiadong, Ph.D. (Committee Member)

Subjects:

Electrical Engineering

Keywords:

Hybrid Systems; fuzzy logic; Lyapunov functions; stability; Lyapunov stability; Simulink Stateflow; Piecewise Linear Stability

Yellanki, Sampath KumarKidney Compatibility Score Generation for a Donor - Recipient pair using Fuzzy Logic
Master of Science in Engineering, University of Toledo, 2012, College of Engineering
This thesis, proposes and implements a Fuzzy Logic based Hierarchical model to address the problem of filtering the donor recipient pairs by predicting a kidney compatibility score. Donor – Recipient pair incompatibility is one of the major problems encountered in Renal Transplantation. Kidney Paired Donation is a barter system where the pairs exchange the donor organs to overcome the disadvantage of incompatibility. Identification of such pairs requires a Kidney Transplant Surgeon to evaluate the compatibility of swapped pairs. Unfortunately, such incompatible pairs run into huge numbers which is a herculean task for a surgeon and can prone to human fatigue. This work presents a Hierarchical System developed based on Fuzzy Logic to determine the quality of a Kidney Transplant based on various input parameters. A surgeon’s expertise in selecting the incompatible pairs is captured and embedded in this model in the form of rules. Fuzzy membership functions are designed to reflect the characteristics of input parameters. This model has been tested on several data sets. The pairs selected based on the kidney compatibility scores matched with the surgeon’s choice in most of the cases. This application provides many options to explore in future.

Committee:

Devinder Kaur (Committee Chair); Michael Rees (Committee Member); Ezzatollah Salari (Committee Member)

Subjects:

Artificial Intelligence

Keywords:

Paired Kidney Donation; Fuzzy Logic; Combs Method; Kidney Incompatibility; Kidney Compatibility Score; Rule Explosion

Next Page