Rule Extraction through Self-Organizing Map for a Self-Tuning Fuzzy Logic Controller

Abstract

Complex, imprecise, ill-defined and uncertain systems can be identified by fuzzy modeling. The identification of such a linguistic model consists of two parts; structure identification and parameter estimation. In this paper, we proposed Self-Organizing Map (SOM) clustering technique for structure identification. Initial parameters of the input-output membership functions (MFs) will be estimated from the clustering results. In the process of proto-type generation, the gradient descent method is used to refine and tune the parameters effectively. The proposed scheme has been successfully tested to identify the rules required to realize the gain factor of self-tuning fuzzy PI controller, which is highly non-linear in nature. Here, the system identification method is integrated with rule extraction method in such a way that it can pick up required rules from any processes. Finally, examples of various systems are given to illustrate the effectiveness of the proposed approach.

Adaptive Fuzzy Control of Inverted Pendulum with a Fuzzy-Based Set-Point Weighting Scheme

“…The proposed FSW-SAFPDC satisfactorily controls the cart position and sway angle and it stabilizes inverted pendulum in the least possible time and within the specified stability limits. Table IV tabulates the various dynamic response characteristics such as maximum peak overshoot (%OS), rise time (t r ), settling time (t s ) and the values of the different performance indices such as IAE, ISE, ITAE [9,10]. Significant reduction in system overshoot, settling time, steady state error etc with successive incorporation of model uncertainties in the form of load variation establishes the effectiveness of our proposed scheme.…”

An adaptive fuzzy controller for overhead crane

“…So the output SF should be determined very carefully for the successful implementation of a FLC. Depending on the input error (e) and change of error (LIe) of a process, an expert operator always tries to modify the controller gain, i.e., output SF, to enhance the system performance and to improve the stability robustness [11][12][13][14][15][16][17]. Following such an operator's policy, here, we suggest a simple self-tuning scheme of Fuzzy PD Controller (FPDC), where an online gain modifier (/3) is determined from the relation, p=3(l+a).…”

“…But, the tuning of a large number of FLC parameters can be a time-consuming, expensive and difficult task. Such problems may be eliminated by adopting self-tuning or adaptive schemes [11][12][13][14][15][16]. 10 our proposed controller, a simple self-tuning scheme is used to continuously update the controller gain with the help of process error and change of error.…”

A Symmetrical Fuzzy Neural Network Regression Method Coordinating Structure and Parameter Identifications for Regression

“…For methods based on clustering, the clustering number often needs to be determined in advance. Considering that the clustering number has a great impact on the performance and interpretability of the model, some studies [23][24][25] utilize cross-validation or clustering validity indicators to determine it, but this is limited in effectiveness [26]. How to interpret the obtained clustering is also an essential problem.…”