By taking advantages of fuzzy systems and neural networks, a fast and accurate Sugeno's type-I fuzzy system (Type-I fuzzy system) is implemented with the combination of the Gaussian radial basis function network (GP-RBFN) and the time delayed neural network (TDNN), which is based on local modeling using fast general parameter (GP) learning and adaptive algorithms. The proposed GP algorithm applied to adaptation and learning for neural networks is very suitable to parameter optimization of such local linear models in blended multiple model structures. It is applied to a fault detection application. It is experimentally confirmed that the developed fuzzy neural network is more accurate and faster than the RBFN.

The stock markets are well known for wide variations in prices over short and long terms. These fluctuations are due to a large number of deals produced by agents and act independently from each other. However, even in the middle of the apparently chaotic world, there are opportunities for making good predictions. In this paper the Nikkei stock prices over 1500 days from July to Oct. 2002 are analyzed and predicted using a Hurst exponent (H), a fractal dimension (D), and an autocorrelation coefficient (C). They are H=0.6699 D=2-H=1.3301 and C=0.26558 over three days. This obtained knowledge is embedded into the structure of our developed time delayed neural network. It is confirmed that the obtained prediction accuracy is much higher than that by a back propagation-type forward neural network for the short-term. Although this predictor works for the short term, it is embedded into our developed fuzzy neural network to construct multi-blended local nonlinear models. It is applied to general long term prediction whose more accurate prediction is expected than that by the method proposed.

Fault diagnosis schemes for small-scale systems using novel fuzzy-neural networks with general parameter learning and time delay neural networks with linear regressions, are described. Then a new fault diagnosis approach for large-scale systems employing the fuzzy-neural network and immune network is introduced. Results from real world applications are presented.

This paper compares the performance of nonlinear radial basis function network-based (RBFN) and linear autoregressive (AR) model-based general parameter (GP) methods in a fault detection application. We use the efficient GP approach for initializing the weights of the RBFN model in the beginning of the off-line system identification phase, as well as for fine-tuning the modeling accuracy of RBFN and AR models online. Our fault detection scheme is based on monitoring the expectation value of the scalar general parameter. This provides improved robustness and detection sensitivity over such methods where the online prediction error is used directly in the decision-making process. In order to illustrate the performance of the efficient nonlinear and linear schemes, they are applied to fault detection of automobile transmission gears. As the acoustic sound level time-series, providing the necessary basis information for fault detection, is slightly nonlinear, the GP-RBFN outperformed the linear methods: the GP-AR method and conventional AR inverse filtering. Both of the GP-based methods provide competitive alternatives for real-world fault detection and diagnosis.

This paper describes fault diagnosis for small-scale dynamical systems using a new fast fuzzy neural network with general parameter (GP) based radial basis function network (RBFN) and a novel scheme of linear regression and time delay neural network. They are applied to fault diagnosis for an automobile transmission gears. Finally, a fault diagnosis scheme for large-scale and complex dynamical systems using fast fuzzy neural network with GP learning and immune networks is developed. It has been practically applied to sensor fault diagnosis for an uninterruptible power supply feedback control system. It is confirmed by simulations that the proposed methods are feasible for fault diagnosis.

In power electronic systems, many researchers have been investigating troubles caused by a sensor failure. Sensorless vector control of induction motor drives has attracted researchers' attention for a long time. The paper describes a sensor fault detection method for UPS current and voltage feedback systems. Once a certain sensor fails, then its influence propagates through the whole system and may cause a fatal situation. It is usually difficult to identify a failed sensor by observing other sensors' outputs. The proposed detection method uses a fast fuzzy neural network and an immune network. The fast fuzzy neural network roughly but very quickly calculates the failure rate of each sensor. The immune network is decomposed into a decision tree structure, which has only the forward passes in parallel. The density of each antibody, called failure origin ratio, is calculated by a nonlinear differential equation driven by stimulation, suppression, failure rate and dispassion. The sensor that shows the highest failure origin ratio is considered as the failed sensor. The proposed method is applicable to fault diagnosis for large-scale and complex systems such as multi-UPSs operated in parallel.

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.

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.

Prospective authors are requested to submit new, unpublished manuscripts for inclusion in the upcoming event described in this call for papers.

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.

Recently, researches on group robot systems (multi-agent intelligent robots: MAIR) have been reported, where a number of robots behave in a group like birds or ants. It is generally known that each robot has a limited intellectual power, but the robots can behave more intellectually in a group because they can interact each other. It has been reported that the multi-agent robot systems which can do many kinds of tasks efficiently by training the rules between environments and actions using reinforcement learning. Intelligent agent systems are also applied to decision making, human interface, perception and others even in a robot system (intelligent function agent robot: IFAR). This paper first introduces extended soft computing (ESC) which is the fusion/combination of fuzzy, neuro, genetic and chaotic computings and immune network theory in order to explain, what they call, complex systems and cognitive and reactive AIs. Then, contemporary intelligent system concept is discussed while the ESC is promising to realize it. Finally, a decision making robot with multi-agents (antigens and antibodies of immune networks), fuzzy inference and reinforcement learning (genetic computing) is described, as an example. It is confirmed that the ESC plays an important role in constructing intelligent robots.

Proposes a reactive distributed artificial intelligence (dynamic) using immune networks and other soft computing methods. Firstly, extended soft computing is defined by adding immune networks and chaos theory including fractals and wavelets to conventional soft computing which is the fusion or combination of fuzzy systems, neural networks and genetic algorithms and is suited to cognitive distributed artificial intelligence (static). Next, a novel fuzzy neural net (general parameter radial based function neural network) is developed in order to use it for communication among agents in immune networks. The general parameter method is extended to an adaptive structured general algorithm to obtain much faster convergence rate. An unbiasedness criterion using distorter (a radial based function network) in order to optimize parameters resulting in the reactive distributed artificial intelligence kind of GMDH is applied to obtain better generalization properties. Then, this developed neural net is extended to obtain high performance.

This paper proposes a novel fuzzy-neural network for the control of a robotic manipulator. First, soft computing which is the fusion or combination of fuzzy systems, neural networks and genetic algorithms is studied. Then, by taking advantages of fuzzy systems and neural networks a novel fuzzy-neural network with a general parameter learning algorithm and system structure determination is developed. The general parameter method (GP) is based on GMDH (group methods of data handling). The GP is used for a learning algorithm and the structure determination of the developed fuzzy neural network. The GP is extended to an adaptive genetic algorithm for explanation. The resulting network can easily be implemented with a Hitachi RISK+DSP microprocessor and is fast enough for real time operations. The developed fuzzy neural network is applied to chattering free sliding mode nonlinear control of a robotic manipulator generating equivalent 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 author's 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.>