ANFIS based sensor fault detection for continuous stirred tank reactor

Authors:
U. Sabura Banu;G. Uma
Affiliations:
BS Abdur Rahman University, Vandalur, Chennai 48, India;Anna University, Chennai 25, India
Venue:
Applied Soft Computing
Year:
2011

Citing 3
Cited 1

Fault diagnosis in dynamic systems using analytical and knowledge-based redundancy—a survey and some new results

Automatica (Journal of IFAC)
Paper: A survey of design methods for failure detection in dynamic systems

Automatica (Journal of IFAC)
Hopfield/ART-1 neural network-based fault detection and isolation

IEEE Transactions on Neural Networks

Enhanced combination modeling method for combustion efficiency in coal-fired boilers

Applied Soft Computing

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, an Adaptive Neuro-Fuzzy Inference System (ANFIS) based Sensor fault detection and isolation for Continuous Stirred Tank Reactor (CSTR) is proposed. CSTR is a highly nonlinear process exhibiting stable and unstable steady state at different operating regions. Fault detection (FD) of such a complicated CSTR process is a mind boggling problem. In this paper, an ANFIS based 'dedicated observer' scheme is dealt along with statistical methods for the detection of the fault. The result shows the feasibility of using the proposed method for the detection of sensor faults in CSTR.