Yasuhiko Dote

Industrial applications of soft computing: a review

Fuzzy logic, neural networks, and evolutionary computation are the core methodologies of soft computing (SC). SC is causing a paradigm shift in engineering and science fields since it can solve problems that have not been able to be solved by traditional analytic methods. In addition, SC yields rich knowledge representation, flexible knowledge acquisition, and flexible knowledge processing, which enable intelligent systems to be constructed at low cost. This paper reviews applications of SC in several industrial fields to show the various innovations by TR, HMIQ, and low cost in industries that have been made possible by the use of SC. Our paper intends to remove the gap between theory and practice and attempts to learn how to apply soft computing practically to industrial systems from examples/analogy, reviewing many application papers.

Variable-structured robust controller by fuzzy logic for servomotors

A variable-structure robust controller whose structure is continuously changed by fuzzy logic so that the system responds quickly if the error or its rate is large and vice versa is proposed. Such a controller is insensitive to both the plant noise and the observation noise. It is applied to speed control for an induction servomotor. Experiments show that the controller is superior to both a sliding-mode controller and a proportional integral-derivative (PID) controller. The paper includes the stability analysis of the overall system and the design procedure by using Lyapunovs method. >

Soft Computing in Industrial Applications

The research has developed a fuzzy logic approach to handling missing data. A prototype fuzzy model was developed, using the FuzzyTech software, to assess the quality of the steel production in terms of composition, time, and temperature. As tools like FuzzyTech are not able to handle missing data, the research has introduced a fuzzy logic approach to decision making with less data. A number of workshops were carried out in the plant, and the aired expertss knowledge was the basis for the researchs development. This paper will present the state of the art research on the application of artificial intelligence and statistical techniques for handling the missing data problem

Neuro fuzzy transmission control for automobile with variable loads

A transmission controller for an automobile with variable loads is designed and tested by using a transmission system (Isuzu NAVi-5) consisting of actuators and sensors besides gears, a throttle, and a clutch. This system engages and disengages the clutch and gears up and down automatically. In other words, a manual gear-shift system is automated. As neuro and fuzzy approaches are promising methods to interface between a vehicle operator and an automobile, they are used to design a transmission controller. Automobile loads are estimated from the signals of status sensors by fuzzy logic. Vehicle drivers intention is inferred by fuzzy logic using the information from automobile status sensors on which drivers intention is reflected. These are then fed into a neural network. An experienced driver (much data) teachers the neural network an optimal gear-shift scheduling such that a vehicle operator feels comfortable even when automobile loads change (for example when an automobile is traveling up and down hill). >

Application of modern control techniques to motor control

An overview is presented of digital control problems arising in the use of microprocessors and the application of modern control theory, from both the theoretical and practical viewpoints. The discussion covers optimal control, robust control, feedback and feed-forward control, and active and passive adaptive control. Various application are described, drawing on the authors own experience. It is concluded that a robust optimal digital controller for motor control can be practically designed and implemented with currently available techniques and hardware. >

Fuzzy and neural network controller

There are many applications of fuzzy control to practical systems such as electric appliances and factory automation in Japan. On the other hand, applications of neural networks to military and industrial fields attract a lot of researchers in the United States. It is suggested that the two approaches be combined and applied to control problems. The use of both methods is recommended for the construction of intelligent controllers (for example, autonomous or self-organizing controllers). Intelligent controllers are summarized. Fuzzy control is illustrated in a tutorial fashion by a simple example. The design and practical aspects of fuzzy control are examined. Neural networks applied to control problems are discussed. By combining the two methodologies, self-organizing controller can be constructed.<<ETX>>

Fuzzy neural network with general parameter adaptation for modeling of nonlinear time-series

By taking advantage of fuzzy systems and neural networks, a fuzzy-neural network with a general parameter (GP) learning algorithm and heuristic model structure determination is proposed in this paper. Our network model is based on the Gaussian radial basis function network (RBFN). We use the flexible GP approach both for initializing the off-line training algorithm and fine-tuning the nonlinear model efficiently in online operation. A modification of the robust unbiasedness criterion using distorter (UCD) is utilized for selecting the structural parameters of this adaptive model. The UCD approach provides the desired modeling accuracy and avoids the risk of over-fitting. In order to illustrate the operation of the proposed modeling scheme, it is experimentally applied to a fault detection application.

Microprocessor-Based Decoupled Control of Manipulator Using Modified Model-Following Method with Sliding Mode

A methodology of discontinuous feedback and continuous feedforward control is developed to achieve accurate decoupled tracking in a class of nonlinear, time varying systems in the presence of disturbances, parameter variations and nonlinear dynamic interactions. The method is based on an improved variable structure control with a sliding mode.

Variable structure control with sliding mode for DC drive speed reguration

The design principles of sliding mode control are studied, and then are applied to speed reguration of a dc motor drive. Each step in the formulation of the control algorithm is clearly defined and explained. The feasibility of this control scheme is experimentally verified. The control strategy is implemented by recently improved analog IC components. The proposed controller is robust in both dynamic and steady state performances and provides extremely good speed reguration independent of system parameter variations and external disturbances. In addition to this, a certain algorithm obtained by rotating the sliding curve adaptively is extensively applied in order to achieve the sub-time optimal control.

Motor fault detection using Elman neural network with genetic algorithm-aided training

Fault detection methods are crucial in acquiring safe and reliable operation in motor drive systems. Remarkable maintenance costs can also be saved by applying advanced detection techniques to find potential failures. However, conventional motor fault detection approaches often have to work with explicit motor models. In addition, most of them are deterministic or non-adaptive, and therefore cannot be used in time-varying cases. We propose an Elman neural network-based motor fault detection scheme to overcome these difficulties. The Elman neural network has the unique time series prediction capability because of its memory nodes as well as local recurrent connections. Motor faults are detected from changes in the expectation of the feature signal prediction error. A genetic algorithm (GA)-aided training strategy for the Elman neural network is further introduced to improve the approximation accuracy and achieve better detection performance. Computer simulations of a practical automobile transmission gear with an artificial fault are carried out to verify the effectiveness of our method. Encouraging fault detection results have been obtained without any prior information of the gear model.