Fault detection and diagnosis for general discrete-time stochastic systems using output probability density estimation

Abstract

Abstract-A new approach of fault detection and diagnosis (FDD) for general stochastic systems in discrete-time is studied. Our work on this problem is motivated by the fact that most of the nonlinear control laws are implemented as digital controllers in reality. Different from the formulation of classical FDD problem, it is supposed that the measured information for the FDD is the probability density functions (PDFs) of the system output rather than its measured value. A radial basis function (RBF) neural network technique is proposed so that the output PDFs can be formulated in terms of the dynamic weighting of the RBFs neural network. Feasible criteria to detect and diagnose the system fault are provided by using linear matrix inequality (LMI) techniques. An illustrated example is included to demonstrate the efficiency of the proposed algorithm, and satisfactory results are obtained.

Fault Diagnosis and Sliding Mode Fault Tolerant Control for Non‐Gaussian Stochastic Distribution Control Systems Using T‐s Fuzzy Model

“…The equations of these systems describe the relationship between the PDF of the system output and the system input rather than the traditional relationship between the system input and the system output. Professor Hong Wang of the University of Manchester has put forward new stochastic distribution control theory for non‐Gaussian stochastic systems , including modeling, controlling the PDF shape, fault diagnosis and fault tolerant control. The model of stochastic distribution control systems includes two parts: one part is the dynamic model between the weight vector and the system input and the other part is about the static model of PDF.…”

Tolerant tracking controller design with guaranteed success rate of output SDC systems

“…Under the comparisons with the existing three B-spline approximation models, the rational square-root model contains n independent weights which means it owns a larger legitimate weights definition domain and there are no constraints except that the weights are not zero simultaneously. What calls for special attention is that the pseudo-weights consist in the rational B-spline model and square-root B-spline model while the weights in linear B-spline model and square-root B-spline model are the real weights [5,6,7].…”

Fault diagnosis and fault tolerant control for the non-Gaussian time-delayed stochastic distribution control system

“…In terms of the FDD for SDC systems, the input and the output PDFs are used as measured signals. Therefore, the objective of FDD of SDC systems is to use the measured input and output PDFs to obtain the information of the fault [5], [6], [8][9][10]. In the non-Gaussian SDC system based on the linear B-spline approximation model, an observer-based algorithm *The authors would like to thank the financial support received from Chinese NSFC project 61104022, 10971202.…”