Tadashi Iokibe

A method for automatic rule and membership function generation by discretionary fuzzy performance function and its application to a practical system

In a practical system, the determination of fuzzy rules and membership functions depends on how skillfully the know-how of the experienced operator with an adequate comprehension of the target system can be extracted and developed into such rules and membership functions. In actuality, interviews, field research, etc. are made for collecting the know-how of the skilled operator. Particularly in determination of membership functions, it is no exaggeration to say that tuning is repeated on a trial and error basis. This paper proposes the fuzzy clustering method dependent on the manual operation data by the skilled operator and a discretionary fuzzy performance function, and an automatic generation method of rules and membership functions in case performance function is clearly known.<<ETX>>

Industrial Application of Chaos Engineering

Recently, the study of chaos is attracting attention, and a wide range of academic fields is actively involved. On the other hand, Aihara proposed the term “chaos engineering” to describe the application of chaos theory for engineering purposes, and its possibilities have been demonstrated. Examples of applications reported so far include “Oil Fan Heaters (Sanyo Electric Co., Ltd.),” “Air-conditioners and Dish Washing Dryers (Matsushita Electric Industrial Co., Ltd.),” “Washing Machines (Goldstar Co., Ltd.; Korea)” and other home appliances and “Application to Health Care (Computer Convenience).” However, industrially, there has been only one application which is the “Tap Water Demand Prediction (Meidensha Corporation).” This paper first reviews the history of chaos research. Next, deterministic chaos is described. Time series forecasting and fault diagnosis are discussed as prospective industrial applications, and the related methodology is explained using practical examples.

Industrial applications of short-term prediction on chaotic time series by local fuzzy reconstruction method

The paper describes nonlinear short-term prediction as a possible application of chaos engineering. The authors developed the local fuzzy reconstruction method which is categorized as a nonlinear reconstruction method for nonlinear short-term prediction, and compared prediction performance with linear reconstruction methods, i.e. the Gram-Schumidt orthogonal system method and the tessellation method. The result is that the local fuzzy reconstruction method has advantages in prediction performance and computation time. The authors applied the local fuzzy reconstruction method to practical time series data. The paper considers the local reconstruction method as nonlinear short-term prediction and applications in industrial fields.

Predicting combustion pressure of automobile engine employing chaos theory

Automobile manufacturers continue to put a large effort into developing low emission and fuel-efficient vehicles. One of the most important researches is to develop an engine that can work in the ideal combustion condition using fuel as little as possible. The air fuel ratio is reduced in order to realize high mileage. However, the exhaust gas condition may deteriorate or the engine stops, since the combustion condition becomes unstable. Therefore, high-precision predictive control of ignition timing and air fuel ratio are important in order to retain the engine performance. The preparation of the combustion model of the engine is indispensable for predictive control. But, because the combustion is nonlinear and complex, a practical combustion model is not yet developed. Chaos has been noticed as a theory that can treat nonlinear dynamical systems, and the research has energetically been advanced. For predicting the combustion condition of the automobile engine, we applied chaos theory. That is: the peak pressure of succeeding combustion is forecast, using only the combustion pressure time series of cylinders inside. In the paper, the purpose and results of research are reported.

Chaos Information Criteria to Detect High-pressure Gas Leak in Petroleum Refining Plant

In a petroleum refining plant, the high-pressure gas leaks resulting from equipment failures may lead to disasters. To minimize these disasters, technology for the early detection of leak sound is indispensable. We have employed chaos theory to identify these dominant sounds, and have already reported these results in papers listed in reference. However, the leak sound is not always more regular than the background noise depending on equipments or weather conditions. In order to detect the high-pressure gas leak sound, it is necessary to estimate the steady state range quantitatively using chaos theory from the background noise. Based on the concept, we describe chaos information criteria for the leak sound detection algorithm. Applying the chaos information criteria to characterize the measured sound data, we conducted the leak sound detection experiment by leaking steam artificially using a silencer nozzle near the high-pressure gas unit in Idemitsu Kosan Chiba Refinery

A study for complexity of chaotic time series and prediction accuracy

This article gives relation between complexity of a time series data and an accuracy of prediction. We used logistic map. The time series data exhibit chaotic behavior. First, we estimate Lyapunov exponent and trajectory parallel measure (TPM). Next, we make short term prediction. Finally we compare them.

Fuzzy Control for High Frequency Tube Welding System

The field of application of electric resistance welded (ERW) tubes continues to expand these days, and the quality requirements are becoming more sophisticated from year to year. In order to meet these market conditions, more advanced technology for forming and welding is essential to ERW tube production, in addition to improvement of the quality of materials. Heat input control in welding especially plays a very important role in advancing and stabilizing the quality of ERW tubes. Various engineering processes related to heat control have been studied and developed. From the manual control in early days through PID feedback control to joint feedforward and feedback control based on computerized mathematical models — this sums up the development of heat control to this day. Mill lines today, however, must turn out a greater variety of ERW tubes of superior quality. The heat control functions and performance required for this purpose have been increasingly difficult to come by with the conventional computer control.

Day-trading of Nikkei 225 Index Futures based on Chaos Theory

From the perspective that financial market time series display chaotic property, we composed a pilot fund. The amount of this fund is 10 million yen formed by a limited partnership. We applied the local fuzzy reconstruction method based on chaos theory to predict a financial time series; the Nikkei 225 index futures market price. And we actually traded those index futures daily to produce a track record during the six months from 1 April 2002 to 30 September 2002. This paper reports the prediction, trading method, trading results, salient problems; expected annual return is 12.0% but actual return is −17.6% including brokerage commission, and discusses its cause and countermeasure.

Chaos and Time Series Analysis

Researches on deterministic chaos have been rapidly progressing during the last two decades and our understanding on low-dimensional chaos has been considerably deepened. Theoretical and numerical analyses have shown that a simple deterministic nonlinear system with a few degrees of freedom can naturally produce very complicated chaotic behavior. In addition, it has been reported that there have been discovered many experimental data that imply the presence of low dimensional chaos in various real-world systems.