A statistical-based approach for fault detection in a three tank system

2013 ◽  
Vol 44 (10) ◽  
pp. 1783-1792 ◽  
Author(s):  
A. Kouadri ◽  
A. Namoun ◽  
M. Zelmat ◽  
M.A. Aitouche
Keyword(s):  
2011 ◽  
Vol 467-469 ◽  
pp. 923-927
Author(s):  
Ai She Shui ◽  
Wei Min Chen ◽  
Li Chuan Liu ◽  
Yong Hong Shui

This paper focuses on the problem of detecting sensor faults in feedback control systems with multistage RBF neural network ensemble-based estimators. The sensor fault detection framework is introduced. The modeling process of the estimator is presented. Fault detection is accomplished by evaluating residuals, which are the differences between the actual values of sensor outputs and the estimated values. The particular feature of the fault detection approach is using the data sequences of multi-sensor readings and controller outputs to establish the bank of estimators and fault-sensitive detectors. A detectability study has also been done with the additive type of sensor faults. The effectiveness of the proposed approach is demonstrated by means of three tank system experiment results.


2018 ◽  
Vol 8 (2) ◽  
pp. 42-51
Author(s):  
M Hajizadeh ◽  
M G Lipsett

This paper addresses the problem of designing a fault identification and detection algorithm for non-linear systems. Timely identification and detection of a fault in a system is crucial in condition monitoring systems. However, finding the source of the failure is not trivial in systems with large numbers of components and complex component relationships. In this paper, an efficient scheme to detect adverse changes in system reliability and find the failed component is proposed, based on the interacting multiple model (IMM) algorithm, with fault detection and diagnosis formulated as a hybrid multiple model estimation scheme. The proposed approach provides an integrated framework for fault detection, diagnosis and state estimation. Its performance is illustrated for fault detection of a non-linear two-tank system. The proposed method can be used with different kinds of filters, using the confusion matrix and classification accuracy as comparison metrics. A particle filter is used with the IMM algorithm and its performance is compared to the linear Kalman filter as a comparative case concerning the improvement that can be achieved when going beyond the consideration that the system is linear.


2011 ◽  
Vol 35 (5) ◽  
pp. 806-816 ◽  
Author(s):  
Kris Villez ◽  
Babji Srinivasan ◽  
Raghunathan Rengaswamy ◽  
Shankar Narasimhan ◽  
Venkat Venkatasubramanian

Sign in / Sign up

Export Citation Format

Share Document