Fault Detection for Nonlinear Process With Deterministic Disturbances: A Just-In-Time Learning Based Data Driven Method

This paper discusses a framework for fault detection in nonlinear processes. A novel subspace aided parity-based data-driven technique is proposed using the so-called just-in-time learning (JITL) approach. The idea of the proposed technique is to choose a set of the most similar data samples from the database for each test data sample using the JITL approach to address the nonlinearity problem. The parity vector is constructed for each test sample using the selected data samples to generate the residual signal. The salient features of the proposed technique include easy and simple implementation together with effectiveness in fault detection in the presence of disturbances and measurement noise. The fault detection scheme is so designed that it exhibits robustness against sensor noise and disturbances and sensitivity to faults. A case study for the fault detection of a nuclear research reactor (NRR) is presented to demonstrate the efficacy of the technique. The NRR is a highly nonlinear and complex process. Two faults of NRR, namely external reactivity insertion and control rod withdrawal, are successfully detected using the proposed approach.

Download Full-text

Improved Dynamic Optimized Kernel Partial Least Squares for Nonlinear Process Fault Detection

Mathematical Problems in Engineering ◽

10.1155/2021/6677944 ◽

2021 ◽

Vol 2021 ◽

pp. 1-16

Author(s):

Maroua Said ◽

Okba Taouali

Keyword(s):

Fault Detection ◽

Least Squares ◽

Partial Least Squares ◽

Computational Cost ◽

Nonlinear Process ◽

Kernel Functions ◽

Data Driven ◽

Reduced Model ◽

Tennessee Eastman Process ◽

Kernel Partial Least Squares

We suggest in this article a dynamic reduced algorithm in order to enhance the monitoring abilities of nonlinear processes. Dynamic fault detection using data-driven methods is among the key technologies, which shows its ability to improve the performance of dynamic systems. Among the data-driven techniques, we find the kernel partial least squares (KPLS) which is presented as an interesting method for fault detection and monitoring in industrial systems. The dynamic reduced KPLS method is proposed for the fault detection procedure in order to use the advantages of the reduced KPLS models in online mode. Furthermore, the suggested method is developed to monitor the time-varying dynamic system and also update the model of reduced reference. The reduced model is used to minimize the computational cost and time and also to choose a reduced set of kernel functions. Indeed, the dynamic reduced KPLS allows adaptation of the reduced model, observation by observation, without the risk of losing or deleting important information. For each observation, the update of the model is available if and only if a further normal observation that contains new pertinent information is present. The general principle is to take only the normal and the important new observation in the feature space. Then the reduced set is built for the fault detection in the online phase based on a quadratic prediction error chart. Thereafter, the Tennessee Eastman process and air quality are used to precise the performances of the suggested methods. The simulation results of the dynamic reduced KPLS method are compared with the standard one.

Download Full-text