scholarly journals Fault detection and diagnosis for continuous stirred tank reactor using neural network

1970 ◽  
Vol 6 (2) ◽  
pp. 66-74 ◽  
Author(s):  
Ribhan Zafira Abdul Rahman ◽  
Azura Che Soh ◽  
Noor Fadzlina Binti Muhammad
Keyword(s):  
Neural Network ◽  
Fault Detection ◽  
Fault Detection And Diagnosis ◽  
Stirred Tank ◽  
Continuous Stirred Tank Reactor ◽  
Stirred Tank Reactor ◽  
Tank Reactor ◽  
Engineering And Technology ◽  
Continuous Stirred Tank ◽  
Detection And Diagnosis

The paper focuses on the application of neural network techniques in fault detection and diagnosis. The objective of this paper is to detect and diagnose the faults to a continuous stirred tank reactor (CSTR). Fault detection is performed by using the error signals, where when error signal is zero or nearly zero, the system is in normal condition, and when the fault occurs, error signals should distinctively diverge from zero. The fault diagnosis is performed by identifying the amplitude error of the CSTR output error. Keywords: Fault Detection and Diagnosis; Neural Network; CSTR  DOI: 10.3126/kuset.v6i2.4014Kathmandu University Journal of Science, Engineering and Technology Vol.6. No II, November, 2010, pp.66-74

scholarly journals Unknown input observer design for fault detection and diagnosis in a continuous stirred-tank reactor

2019 ◽  
Vol 90 ◽  
pp. 02004
Author(s):  
Ali H. Al-Shatri ◽  
Ahmad Arshad ◽  
Oladokun Olagoke ◽  
Bemgba B. Nyakuma
Keyword(s):  
Fault Detection ◽  
Fault Detection And Diagnosis ◽  
Observer Design ◽  
Stirred Tank ◽  
Unknown Input ◽  
Continuous Stirred Tank Reactor ◽  
Stirred Tank Reactor ◽  
Tank Reactor ◽  
Continuous Stirred Tank ◽  
Detection And Diagnosis

Early and accurate fault detection and diagnosis (FDD) minimises downtime, increases the safety and reliability of plant operation, and reduces manufacturing costs. This paper presents a robust FDD strategy for a nonlinear system using a bank of unknown input observers (UIO). The approach is based on structure residual generation that provides not only decoupling of faults from model uncertainties and unknown input disturbance but also decoupling the effect of a fault from the effects of other faults. The generated residual was evaluated through the statistical threshold to avoid fault missing or false alarm. The performance of the robust FDD scheme was assessed by some sensor fault scenarios created in a continuous stirred-tank reactor (CSTR). The simulation result showed the effectiveness of the proposed approach.

Control of Continuous Stirred Tank Reactor Using Artificial Neural Networks Based Predictive Control

2012 ◽  
Vol 550-553 ◽  
pp. 2908-2912 ◽  
Author(s):  
Ginuga Prabhaker Reddy ◽  
G. Radhika ◽  
K Anil
Keyword(s):  
Neural Network ◽  
Neural Network Model ◽  
Stirred Tank ◽  
Continuous Stirred Tank Reactor ◽  
Model Predictive Controller ◽  
Stirred Tank Reactor ◽  
Tank Reactor ◽  
The Neural Network ◽  
Predictive Controller ◽  
Continuous Stirred Tank

In this work, a Neural network based predictive controller is analyzed to a non linear continuous stirred tank reactor (CSTR) carrying out series and parallel reactions: A→B→C and 2A→D. In the first step, the neural network model of continuous stirred tank reactor is obtained by Levenburg- Marquard training. The data for the training the network is generated using state space model of continuous stirred tank reactor. The neural network model of continuous stirred tank reactor is used in model predictive controller design. The performance of present neural network based model predictive controller (NNMPC) is evaluated through simulations for servo & regulatory problems of CSTR. The performance of neural network based predictive controller is found to be superior than conventional PI controller for setpoint tracking problems.

scholarly journals Fault Detection Approach Based on Weighted Principal Component Analysis Applied to Continuous Stirred Tank Reactor

2015 ◽  
Vol 9 (1) ◽  
pp. 966-972 ◽  
Author(s):  
Shanmao Gu ◽  
Yunlong Liu ◽  
Ni Zhang ◽  
De Du
Keyword(s):  
Principal Component Analysis ◽  
Fault Detection ◽  
Principal Component ◽  
Stirred Tank ◽  
Time Varying ◽  
Continuous Stirred Tank Reactor ◽  
Stirred Tank Reactor ◽  
Tank Reactor ◽  
Detection Approach ◽  
Continuous Stirred Tank

Fault detection approach based on principal component analysis (PCA) may perform not well when the process is time-varying, because it can cause unfavorable influence on feature extraction. To solve this problem, a modified PCA which considering variance maximization is proposed, referred to as weighted PCA (WPCA). WPCA can obtain the slow features information of observed data in time-varying system. The monitoring statistical indices are based on WPCA model and their confidence limits are computed by kernel density estimation (KDE). A simulation example on continuous stirred tank reactor (CSTR) show that the proposed method achieves better performance from the perspective of both fault detection rate and fault detection time than conventional PCA model.

Sign in / Sign up

Export Citation Format

Share Document