Fault Modeling, Detection and Classification using Fuzzy Logic, Kalman Filter and Genetic Neuro-Fuzzy Systems

In this paper, an efficient scheme has been proposed to model, detect and classify the fault. The modeling of fault has been proposed with the fuzzy logic using membership function. Fault detection of the unprecedented changes in system reliability and find the failed component state by classifying the faults is proposed using kalman filter and hybrid neurofuzzy computing techniques respectively. A fault is detected whenever the moving average of the Kalman filter residual exceeds a threshold value. The fault classification has been made effective by implementing a hybrid genetic neuro-fuzzy Inference system (GANFIS). By doing so, the critical information about the presence or absence of a fault is gained in the shortest possible time, with not only confirmation of the findings but also an accurate unfolding-in-time of the finer details of the fault, thus completing the overall fault diagnosis picture of the system under test. The proposed scheme is evaluated extensively on a two-tank process used in industry exemplified by a benchmarked laboratory scale coupled-tank system. Keyword: Kalman filter; hybrid neuro-fuzzy; soft computing; ANN; genetic algorithm; ANFIS; GANFIS; fault detection; fault classification; benchmarked laboratory scale two-tank system.

[1]  Masahiro Abe,et al.  Incipient fault diagnosis of chemical processes via artificial neural networks , 1989 .

[2]  Chuei-Tin Chang,et al.  Dynamic process diagnosis via integrated neural networks , 1995 .

[3]  Kenneth A. De Jong,et al.  Using Genetic Algorithms to Solve NP-Complete Problems , 1989, ICGA.

[4]  Biswanath Samanta,et al.  Artificial neural networks and genetic algorithm for bearing fault detection , 2006, Soft Comput..

[5]  Rajamani Doraiswami,et al.  Intelligent Fault Diagnosis using Sensor Network , 2009, ICINCO-ICSO.

[6]  Miss A.O. Penney.  (b) , 1974, The New Yale Book of Quotations.

[7]  Kmc Cheung,et al.  Intelligent fault diagnosis based on neurofuzzy networks for nonlinear dynamic systems , 2001 .

[8]  X. Steven Ding,et al.  Current Developments in the Theory of FDI , 2000 .

[9]  Y. A. Liu,et al.  Artificial intelligence in chemical engineering , 1991 .

[10]  Ramaswamy Vaidyanathan,et al.  Process fault detection and diagnosis using neural networks , 1990 .

[11]  Ching-Hsue Cheng,et al.  The reliability of general vague fault-tree analysis on weapon systems fault diagnosis , 2006, Soft Comput..

[12]  Guoqiang Peter Zhang,et al.  Neural networks for classification: a survey , 2000, IEEE Trans. Syst. Man Cybern. Part C.

[13]  Weihua Gui,et al.  Expert fault diagnosis using rule models with certainty factors for the leaching process , 2000, Proceedings of the 3rd World Congress on Intelligent Control and Automation (Cat. No.00EX393).

[14]  Nicolás J. Scenna,et al.  Some aspects of fault diagnosis in batch processes , 2000, Reliab. Eng. Syst. Saf..

[15]  A. Willsky,et al.  Analytical redundancy and the design of robust failure detection systems , 1984 .

[16]  Jose A. Romagnoli,et al.  Dynamic probabilistic model-based expert system for fault diagnosis , 2000 .

[17]  A. E. Farell,et al.  Framework for enhancing fault diagnosis capabilities of artificial neural networks , 1994 .

[18]  Michael Nikolaou,et al.  An approach to fault diagnosis of chemical processes via neural networks , 1993 .

[19]  J. F. Davis,et al.  Knowledge-based diagnostic systems for continuous process operations based upon the task framework , 1992 .

[20]  Mark A. Kramer,et al.  Diagnosing dynamic faults using modular neural nets , 1993, IEEE Expert.

[21]  R. Doraiswami,et al.  Robust Control of a Closed-Loop Identified System with Parametric/Model Uncertainties and External Disturbances , 2010, 2010 International Conference on Intelligent Systems, Modelling and Simulation.

[22]  Mark A. Kramer,et al.  Comparison of belief networks and rule-based expert systems for fault diagnosis of chemical processes , 1993 .

[23]  Venkat Venkatasubramanian,et al.  Representing and diagnosing dynamic process data using neural networks , 1992 .

[24]  L. Felipe Blázquez,et al.  Fuzzy logic-based decision-making for fault diagnosis in a DC motor , 2005, Eng. Appl. Artif. Intell..

[25]  Janos Gertler,et al.  Fault detection and diagnosis in engineering systems , 1998 .

[26]  David M. Himmelblau,et al.  FAULT DIAGNOSIS IN COMPLEX CHEMICAL PLANTS USING ARTIFICIAL NEURAL NETWORKS , 1991 .

[27]  Kenneth A. Loparo,et al.  A neural-network approach to fault detection and diagnosis in industrial processes , 1997, IEEE Trans. Control. Syst. Technol..

[28]  Rolf Isermann,et al.  Model-based fault-detection and diagnosis - status and applications , 2004, Annu. Rev. Control..

[29]  Rajamani Doraiswami,et al.  Quality monitoring of a closed-loop system with parametric uncertainties and external disturbances: a fault detection and isolation approach , 2011 .

[30]  J. F. Davis,et al.  A structured framework for efficient problem solving in diagnostic expert systems , 1988 .

[31]  Venkat Venkatasubramanian,et al.  A neural network methodology for process fault diagnosis , 1989 .

[32]  Silvio Simani,et al.  Model-based fault diagnosis in dynamic systems using identification techniques , 2003 .

[33]  Liya Hou,et al.  Diagnosis of multiple simultaneous fault via hierarchical artificial neural networks , 1994 .

[34]  B. Babu,et al.  ADAPTIVE NETWORKS FOR FAULT DIAGNOSIS AND PROCESS CONTROL , 2002 .