Artificial Neural Network Approach for Fault Detection in Pneumatic Valve in Cooler Water Spray System

Abstract

The detection and diagnosis of faults in technical systems are of great practical significance and paramount importance for the safe operation of the plant. The early detection of fault can help avoid system shutdown, breakdown and even catastrophe involving human fatalities and material damage. Since the operator cannot monitor all variables simultaneously, an automated approach is needed for the real time monitoring and diagnosis of the system. This paper presents the design and development of artificial neural network based model for the fault detection of Pneumatic valve in cooler water spray system in cement industry. The network is developed to detect a totally nineteen faults. The training and testing data required to develop the neural network model were generated at different operating conditions by operating the pneumatic valve and by creating various faults in real time in a laboratory experimental model. The performance of the developed back propagation is found to be satisfactory for the real time fault diagnosis.

PLS-based EWMA fault detection strategy for process monitoring

“…A multivariate FD method take into account the correlation between the process variables while univariate FD methods do not. Multivariate statistical monitoring methods include the latent variable methods, e.g., partial least square (PLS) regression, principal component analysis (PCA), canonical variate analysis (CVA), independent component analysis (ICA), (Chaing et al (2001); Venkatasubramanian et al (2003b)), neural networks (Subbaraj and Kannapiran (2010)), Fuzzy systems (Dexter and Benouarets (1996)) as well as the pattern recognition methods (Mohammadi and Asgary (2005)). …”

Stable and Efficient Operation of Gas Compressor With Improving of Surge Detection System

“…After training, the networks are tested with the remaining 20% of all data as test data set, which was not used for training. The follow ing issues are to be addressed while developing the model for residual generation in the compressor [33].…”

Enhanced monitoring using PCA-based GLR fault detection and multiscale filtering

“…In data-based methods, only the availability of historical process data is required [2]. These approaches include the latent variable methods, e.g., partial least square (PLS) regression, principal component analysis (PCA), canonical variate analysis (CVA), independent component analysis (ICA), [2], neural networks [7] and Fuzzy systems [8]. This paper presents a statistical fault detection scheme based on a PCA model.…”