A neural network approach for the real-time detection of faults

Abstract

Fault detection is an essential part of the operation of any chemical plant. Early detection of faults is important in chemical industry since a lot of damage and loss can result before a fault present in the system is detected. Even though fault detection algorithms are designed and implemented for quickly detecting incidents, most these algorithms do not have an optimal property in terms of detection delay with respect to false alarm rate. Based on the optimization property of cumulative sum (CUSUM), a real-time system for detecting changes in dynamic systems is designed in this paper. This work is motivated by combining two fault detection (FD) strategies; a simplified procedure of the incident detection problem is formulated by using both the artificial neural networks (ANN) and the CUSUM statistical test (Page-Hinkley test). The design of a model-based residual generator is intended to reveal any drift from the normal behavior of the process. In order to obtain a reliable model for the normal process dynamics, the neural black-box modeling by means of a nonlinear auto-regressive with eXogenous input (NARX) model has been chosen in this study. This paper also shows the choice and the performance of the neural network in the training and test phases. After describing the system architecture and the proposed methodology of the fault detection, we present a realistic application in order to show the technique's potential. The purpose is to develop and test the fault detection method on a real incident data, to detect the change presence, and pinpoint the moment it occurred. The experimental results demonstrate the robustness of the FD method.

Predictive models and detection methods applicable in water detection framework for industrial electric arc furnaces

“…On the other hand, the data-driven approaches generally require less time and lower cost to be developed. Empirical methods commonly used for data-driven fault detection approaches include artificial neural network (Chetouani, 2008), multiway principal component analysis (Nomikos and MacGregor (1994)), and Bayesian approach (Yu, 2012). Furthermore, Freeman et al (2013) compared and applied both approaches to a small unmanned aerial vehicles (UAV) platform.…”

Simulating urban expansion by coupling a stochastic cellular automata model and socioeconomic indicators

“…Back propagation (BP) algorithm was used to perform training in ANNs. In this algorithm, the errors propagate backwards from the nodes in the output layer to the inner nodes to obtain an optimization ANN (Li and Yeh 2002;Chetouani 2008). To reduce over-fitting, a jittering technique, i.e., the addition of a small amount of stochastic Gaussian noise with l = 0 and r = 0.01 to the input dataset at each training iteration (Scardi 2001), was adopted in the training procedures.…”

“…Another problem frequently encountered in CA models is that linear calibration approaches cannot adequately accommodate the nonlinear characteristics of complex urban systems (Li and Yeh 2002;Liu et al 2008). The artificial neural network (ANN), which adopts a machine learning algorithm, is an effective approach to quantify and model complex behavior and patterns (Chetouani 2008;Zhang et al 2008). Hence, considering aforementioned weaknesses of CA models, we proposed a hybrid urban expansion model (NNSCA model) by coupling the ANN-based stochastic CA model and several simple socioeconomic indicators, and demonstrated its application in an industrial city, Dongying, China.…”

New online kernel method with the Tabu search algorithm for process monitoring

“…Despite proven performance of PCA, it is inefficient to monitor processes have nonlinear relationships. To overcome this problem, many extensions of PCA (Harrou et al, 2016) were developed in literature, such as those that combined the principal curve and Neural Network (NN) (Chetouani, 2008; Dong and McAvoy, 1996; Harkat et al, 2010) and Kernel Principal Components Analysis (KPCA) (Mika et al, 1998; Schölkopf et al, 1998).…”