Fuzzy Control as Self-Organizing Adaptive Constraint-Oriented Problem Solving

by Dana H. Ballard, MIT Press, 1997. $45.00 (xxii+307 pages) ISBN 0 262 02420 9.

In this paper, we study the application of fuzzy set theory, genetic algorithms and rough set theory techniques to the control of the rectifier. A fuzzy adaptive control scheme with the aid of rough set theory via genetic algorithms (GAs) finding the center parameters in place of the classical control is proposed. On the one hand, genetic algorithm gets optimal parameters of an accurate domain model, which tunes the scaling factors of fuzzy adaptive control but is hardly established in a non-liner system. On the other hand, fuzzy adaptive control deals with the dynamics and complexity of responses from rectifier of a HVDC system in the operation points, by adjusting its control parameters with the aid of rough tuner adaptively. Our study includes a brief introduction to fuzzy control and rough set algorithms, both theory and application. We also evaluate the performance of rough fuzzy control by simulation in the paper. The focus of our experiments is on the constant current control in rectifier side of HVDC system. The result shows there are many improvements offered by the fuzzy control scheme based on rough set theory in comparison with the only fuzzy control scheme in the rectifier side of HVDC system.

This paper developed a fuzzy logic controller with a genetic algorithm control system for sensor based pipeline robot navigation in pipe environment. The fuzzy controller creates initial membership functions and fuzzy logic rules. the genetic algorithm, which automatically designs a fuzzy logic controller by modifying the position of controller membership functions and the commands given to the pipeline robot, optimizes the fuzzy controller. This GA-fuzzy system is used to control the mobile pipeline robot, which is equipped with an array of ultrasonic sensors to acquire the distance between the pipeline robot and obstacle. On the basis of this system, a strategy for combining local behavior control with global behavior control planning was proposed in this paper. Finally a pipeline robot runs in simulation environment. The experimental results show that appropriate control mechanisms of the fuzzy controller are obtained by evolution. The controller has evolved well enough to smoothly drive the pipeline robot in different pipe environment.

Artificial neural network framework for the selection of deep eutectic solvents promoted enhanced oil recovery by interfacial tension reduction mechanism

22 - Self-Learning Knowledge Systems and Fuzzy Systems and Their Applications

Carotid plaque is a biomarker of generalized atherosclerosis, and may predict ischemic stroke. Carotid intima-media thickness (C-IMT) measurement with ultrasonography imaging could capture the condition of carotid plaque. However, manual measurement of C-IMT is observer- dependent, resulting in observer bias and low reproducibility. In this study, we develop artificial intelligence (AI) framework that could automatically measure the C-IMT, and compared it with C-IMT measured by board of expert. This is a retrospective study done in Dr. Moewardi General Hospital, Surakarta, Indonesia. Carotid B-mode ultrasonography images were measured by panel of expert and by AI. After annotation process on Neurabot platform, AI could detect region of interest (ROI), and would do segmentation on the area to measure C-IMT autonomously. Dependent T-test was used to evaluate validity, and Cronbach’s alpha was used to find the reliability of C-IMT measured by panel of expert and AI. There was strong correlation (r=0.874; p=0.014) on dependent t-test for C-IMT measured by AI with C-IMT measured by board of expert. The internal consistency reliability coefficients (Cronbach’s alpha) were 0.938 and 0.909, for pretest and posttest, respectively. We also analyzed the test-retest reliability by comparing pretest and posttest score with dependent t-test, and we observed strong correlation with r=0.871 (p=0.000). AI developed on Neurabot platform are valid and reliable to measure C-IMT.

Although fuzzy logic controllers and expert systems have been successfully applied in many complex industrial processes, they experience a deficiency in knowledge acquisition and rely to a great extent on empirical and heuristic knowledge which, in many cases, cannot be objectively elicited. Among the problems to be resolved in fuzzy controller design are the determination of the linguistic state space, definition of the membership functions of each linguistic term and the derivation of the control rules. Some of these problems can be solved by application of machine learning. First, it is desirable to simplify and automate the specification of linguistic rules. Secondly, it is also desirable that modification of control rules is possible in order to cope with previously unknown or changes in process dynamics. Machine learning methods have, in recent years, emerged from the use of learning algorithms modelled on natural and biological systems. These methods attempt to abstract the advanced mechanisms of learning exhibited by such systems, which can consequently be applied to intelligent control. One of these new algorithms is the genetic algorithm which is modelled on the processes of natural evolution. The paper develops the application of genetic algorithm techniques for fuzzy controller design. Genetic algorithms are used to automate and introduce objective criteria in defining fuzzy controller parameters.

This paper presents the fusion of artificial intelligence (AI) learning algorithms that are genetic algorithms (GA) and conjugate gradient (CG) methods. Both methods are used to find the optimum weights for the hidden and output layers of feedforward artificial neural network (ANN) model. Each algorithm is presented in separate module and we proposed three different types of Dynamic Connection Strategies (DyConS) for combining both algorithms to improve the recognition performance of spoken Malay speech recognition. Two different GA techniques are used in this research: a mutated GA technique is proposed and compared with the standard GA technique. One hundred experiments with 5000 words are conducted using the proposed DyConS. Owing to previous facts, GA combined with ANN proved to attain certain advantages with sufficient recognition performance. Thus, from the results, it was observed that the performance of mutated GA algorithm when combined with CG is better than standard GA and CG models. Integrating the GA with feed-forward network improved mean square error (MSE) performance and with good connection strategy by this two stage training scheme, the recognition rate is increased up to 99%.

Mark Watson Morgan Kaufmann Publishers, San Francisco, 1997, 377 pp. ISBN 1-55860-420-0, $44.95 This book is well written and organized to cover how to apply AI (Artificial Intelligence) techniques for practical Internet and Intranet tools by using the Java programming language. In the book, the author uses neural network and genetic algorithms to develop distributed systems that are applied for the Internet and Intranets, such as client/server model and information retrieval tool and so on. Part 1 begins with a good general introduction to AI. The history and survey of Artificial Intelligence research are given briefly. In addition, symbolic processing versus neural networks approaches are discussed. This author opts to use neural network to develop example Internet/Intranet systems in the book. Part 2 consists of Java programs developed for AI, neural networks, genetic algorithms, natural language processing, and expert systems. Chapter 2 illustrates Graphical User Interface (GUI) class that is derived from Applet and Canvas classes in Java, which is used in most example programs in the book. Chapter 3 introduces a frame data structure that is used as a message in distributed systems in the later chapters. Chapter 4 shows neural network classes developed in Java and its theory and implementation. Chapter 5 explains the genetic algorithms and the Java genetic algorithm classes. Chapter 6 describes how to develop and implement natural language processing classes using Java. Chapter 7 shows how to share data objects in distributed systems. For example, distributed AI agent classes are developed to share data objects, WWW data collection agent classes are shown to retrieve documents in the Internet, and small POP (Post Office Protocol) mail classes are developed to send and receive mails. Chapter 8 illustrates how to develop expert systems by using Java Jess, which is based on OPS5/CLIPS expert systems. Part 3 explains how to generate and implement the projects using the Java classes that are developed in Part 2. Chapter 9 shows the project that demonstrates the use of genetic algorithms in chapter 5 to control enemy ships in a scrolling arcade game. Chapter 10 describes the real-time handwriting recognition system developed by using the neural network classes in chapter 4. Chapter 11 illustrates a greedy algorithm to optimize neural networks that is based on the author’s hand-tuning neural training data. Chapter 12 improves neural network training data by applying genetic algorithms, to discard bad training data and to avoid discarding good training data. Chapter 13 describes the distributed natural language processing system that uses natural language processing classes in chapter 6. The data structures in chapter 2 are used to store historical data in a separate server application on any other computer in the Internet or Intranets. The final chapter provides the design and implementation of a complete agent-based information retrieval tool for the Internet. The retrieved documents are stored in ASCII or HTML format. This book is a very good reference book for anyone interested in developing systems using Java in distributed environments, especially applying AI techniques. Also, the author provides the CD-ROM that includes the source code for Java classes developed in the book. Haklin Kimm, University of Tennessee

Fuzzy controller design of micro-unmanned helicopter relying on improved genetic optimization algorithm

Chapter 13 Qualitative Spatial Representation and Reasoning

The mathematical model of the turbine governing system is obtained by modeling analysis. Under the premise of this model, the improved genetic algorithm is used to optimize the parameters in the parameter identification of the turbine governing system, and the high-precision parameter identification of the turbine governing system is realized, and an accurate mathematical model of the turbine governing system is established. In terms of control strategy, through theoretical analysis of conventional PID, fuzzy control and genetic algorithm, a fuzzy PID control based on genetic algorithm optimization (GA-fuzzy PID) is designed to realize the adaptive and adjustment ability of PID control. Compared with the traditional PID control, it has better control effect, and it is easier to make the turbine adjustment system achieve stability, quickness and accuracy.

Robot human interaction requires use of safe, compliant and light weight actuators. Conventional linear motors and pneumatic cylinders are normally used to actuate robots to assist and augment human motions. Lately it has been realized that these actuators are not suitable and safe for applications involving human actor. Their large weight, size and stiffer design raise concerns. Pneumatic muscle actuators (PMA) on the other hand are very light weight, compact and have inherent compliance which make them potential candidate for applications involving robot human interaction. Taking on the advantages, these actuators are now being experimented for a variety of medical and rehabilitation applications. However they are not very popular due to their highly nonlinear and time dependent behavior which poses control problems. In this paper, an attempt is being made to accurately predict the uncertain and ambiguous characteristics of PMA using Artificial Intelligence (AI). Conventional tools such as analytical and numerical methods can only model a nonlinear system which is time independent. Time varying nonlinear system characteristics can be best modeled using artificial intelligence-based regression models. In this research, Artificial Neural Network (ANN), Mamdani Fuzzy Inference System (FIS) and Takagi-Sugeno (TS)-based fuzzy system are developed after carefully analyzing the time series data obtained from a real system. To achieve higher accuracy from these models, their parameters are tuned. Parameters of ANN are tuned using back propagation algorithm whereas fuzzy parameters are tuned using three different methods, namely, gradient descent method (GD), genetic algorithms (GA) and Modified Genetic Algorithm (MGA). It was found that the TS fuzzy inference system tuned by MGA provides better accuracy and can also model the time dependent behavior of PMA. The proposed TS fuzzy system is found to perform better in terms of accuracy and maximum deviation when compared to the previous approaches in the literature.

Fuzzy control strategy is developed for the dual-clutch single-axis torque coupling parallel hybrid electric vehicle. In this paper the torque distribution fuzzy controller which has been designed for the hybrid vehicle which is optimized by genetic algorithms. The simulation model of the hybrid vehicle was built upon matlab / simulink and ADVISOR software. Then a fuzzy rules and correspondent membership functions had been established and the input language variable and output language variable use trapeziform and deltoid membership functions. After design of fuzzy logic torque controller, the genetic algorithm was introduced and used it to optimize the fuzzy logic torque controller. Under typical condition NEDC, the fuzzy control strategy is optimized both by genetic algorithms with the constraint condition of economy performance and by integrated constraint conditions of economy performance and emission performance. Optimization results show that when the controller is only optimize fuzzy control strategy for economy performance the fuel consumption decreased by 5.3% but the emission of CO and NOx both increased, but when the controller both optimize fuzzy control strategy for economy performance and emission performance the fuel consumption decreased by 4.3% with emission quality improved. So the fuzzy control strategy optimize by the genetic algorithm can improve the fuel consumption obvious.

Genetic fuzzy system for damage detection in beams and helicopter rotor blades