Fault Detection and Diagnosis of Continuous Process Based on Multiblock Principal Component Analysis

Process fault detection and diagnosis plays a very important role in the production security and the product quality. In this paper, in order to improve the accuracy for fault detection and diagnosis, a new method based on principal component analysis (PCA) is proposed in low pressure lost foam casting process. PCA method reduces the dimensionality of the original dataset by the projection of the dataset onto a smaller subspace defined by the principal components. The aim of this method is to establish the normal statistical correlation among the coefficients of the dataset to detect and diagnose the faults. The process faults are detected and diagnosed using multivariate statistical process control (MSPC) parameters such as: Hotelling’s T 2 -statistic, Q-statistic or squared prediction error (SPE) and Q-residual contribution. The monitoring results indicates that the proposed method can detect and diagnose the abnormal change of the process.

Fault detection in continuous industrial processes is crucial to ensure production, quality, safety, environmental and economic aspects. Reliable fault detection systems have become even more necessary due to increasingly stringent regulations. The complexity of processes, on the one hand, and the availability of data, on the other, have spread the adoption of the data-driven approach for industrial fault detection. Deep Reinforcement Learning (RL) has recently been applied for this purpose, mainly in rotating machinery and rolling bearings. In chemical processes, most RL applications are in process control. The main contribution of this work lies in proposing a reinforcement learning (RL)-based framework for fault detection in continuous chemical processes. The challenges are related to the large number of variables, nonlinear relationships and changing operational dynamics, to name a few. The classic Tennessee Eastman Process (TEP) benchmark was used as a case study. The results were compared with Principal Component Analysis (PCA), commonly used for chemical process monitoring, dynamic PCA (DPCA), and neural networks. Compared to PCA, the RL approach showed considerably lower missed detection rate (MDR) and time to detection (TTD) while maintaining reasonable false alarm rate (FAR) for all hard-to-detect faults, contributing to early fault detectability. Similar results were obtained with regard to DPCA. Compared to the supervised approach, RL proved to be more flexible regarding model parameterization, which can be very useful for practical aspects of industrial fault detection. The results show that RL-based approaches can be very useful for fault detection in continuous, non-linear, and time-varying systems, such as chemical processes. For example, with regard to adaptive alarm thresholds and the detection of known and unknown faults. The latter represents a major challenge in industrial practice.

Fault detection and diagnosis for non-linear processes empowered by dynamic neural networks

Dynamic model-based fault diagnosis for (bio)chemical batch processes

A Data-Driven Fault Detection and Diagnosis by NSGAII-t-SNE and Clustering Methods in the Chemical Process Industry

This work presents a framework for fault detection and diagnosis of multimode industrial processes. It is shown that the proposed method to generate features for the faults provides a generalization that can allow the fault diagnosis in modes for which no training was performed. The proposed method is applied to a sophisticated simulator of a continuous stirred tank reactor (CSTR). Experimental results suggest the usefulness of this approach for the detection of faults under operating conditions not considered during training phase.

This paper presents a fault detection and diagnosis approach based on Mahalanobis distance (MD) for monitoring continuous processes. The Mahalanobis distance is first used to detect sensor faults, and its control limit is determined by the empirical method via specification a significance level. The main idea behind Mahalanobis distance is using the whole data information instead of dimensionality techniques such as partial least squares, canonical variate analysis, and principal component analysis. The data reflected by the detection index, MD, is analysed by a fault diagnosis method, i.e, contributions plots. An integrated approach for fault detection and diagnosis is presented and tested by two simulation studies, Monte Carlo simulation data and continuous stirred tank reactor chemical process(CSTR). The results illustrate the reliability of the proposed approach in detecting and diagnosing sensor faults.

A fault detection and diagnosis for the continuous process with load-fluctuations using orthogonal wavelets

Recently, principal component analysis (PCA) and independent component analysis (ICA) have attracted increasing attention for fault detection in industrial processes. However, industrial processes usually have multimodal characteristics, in which case, the performance of traditional PCA and ICA methods is poor. A fault detection method based on the local entropy double subspace (LEDS) is proposed that effectively supervises the multimodal process with multiple steady modes. The proposed method uses the local probability density (LPD) to eliminate the multimodal characteristics of the data. Furthermore, local entropy (LE) is applied to mine the statistical information associated with the process data. The process variables are classified into Gaussian and non-Gaussian subspaces by the Kolmogorov–Smirnov (KS) test. PCA and ICA models are built in Gaussian and non-Gaussian subspaces, respectively, for fault detection. A Bayesian decision method is employed to transform the detection results into fault probabilities, and the detection results are combined with the final statistical information. This method effectively eliminates the multicentre structure of the data and improves the fault detection performance of traditional PCA and ICA. The proposed method is applied to the Tennessee Eastman multimodal process. The simulation results show that the fault detection rate of LEDS is better than the rates of traditional methods when the false alarm rate is low for most faults.

For many on‐line fault diagnosis schemes based on process data, a moving time window is an indispensable technique to track dynamic data. In this paper, a novel approach combining variable moving window and hidden Markov model (HMM) for on‐line identification of abnormal operating conditions is proposed. The main feature of this method is that the window length can be changed with time. Before fault diagnosis, some process measurements are used for fault alarm. As a tool for feature extraction, principal component analysis (PCA) is employed in order to reduce the large number of correlated variables. The effectiveness of the approach is illustrated by case studies from the Tennessee Eastman process.

Due to the increasing interest in safety and consistent product quality over a past few decades, demand for effective quality monitoring and safe operation in the modern industry has propelled research into statistical based fault detection and diagnosis methods. This paper describes the application of Hotelling <TEX>$T^2$</TEX> index based Principal Component Analysis (PCA) method for fault detection and diagnosis in industrial processes. Multivariate statistical process control techniques are now widely used for performance monitoring and fault detection. Conventional methods such as PCA are suitable only for steady state processes. These conventional projection methods causes false alarms or missing data for the systems with transient values of processes. These issues significantly compromise the reliability of the monitoring systems. In this paper, a reliable method is used to overcome false alarms occur due to varying process conditions and missing data problems in transient states. This monitoring method is implemented and validated experimentally along with matlab. Experimental results proved the credibility of this fault detection method for both the steady state and transient operations.

Principal Component Analysis (PCA) is a commonly employed technique in industrial systems for process monitoring and fault diagnosis, owing to its capability to efficiently process large datasets. Traditionally, it is applied to single-valued variables, where critical information can be lost in real scenarios with data uncertainties. Interval-valued PCA methods like Symbolic Covariance PCA (SCPCA) and Complete Information PCA (CIPCA) have been developed to enhance fault detection by incorporating data uncertainties in the PCA model. This paper presents a novel adaptation of SCPCA for detecting incertain sensor faults, marking the first correct implementation of SCPCA for fault detection and isolation (FDI). It aims to compare the performance of the new SCPCA with that of CIPCA, evaluating its reliability and accuracy in detecting sensor faults in a greenhouse prototype system.

Data-driven techniques have been receiving considerable attention in the industrial process monitoring field due to their major advantages of easy implementation and less requirement for the prior knowledge and process mechanism. Principal component analysis (PCA) method is known as a popular method for monitoring and fault detection in industrial systems but as it is basically a linear method. However, most practical systems are nonlinear. To make the extension to nonlinear systems, kernel PCA (KPCA) method has been proposed for process modeling and monitoring. We present in this paper an online reduced rank optimized KPCA (RR-KPCA) technique for fault detection in order to extend the advantages of the KPCA models to online processes. Following the fault detection, the identification of the variables correlated to the fault occurred is of great importance. For this purpose, it is proposed to extend the approaches of localization by partial PCA and by elimination in the linear case to the nonlinear case, by exploiting the solution of reduction of the dimension of the kernel matrix in the feature space. The partial RR-KPCA and the elimination sensor identification (ESI-RRKPCA) are generated based on the static RR-KPCA and the online RR-KPCA methods. The idea of these approaches is to generate partial RR-KPCA models with reduced sets of variables. In other words, their goal is to generate indices of fault detection sensitive to certain faults and insensitive to others. The proposed fault isolation methods are applied for monitoring an air quality monitoring network (AIRLOR) data.

Switch Open-circuit Fault Diagnosis and Fault-Tolerant Control for Boost DC-DC Converter

Two neural network models are compared using a process fault detection and diagnosis problem. Process fault detection and diagnosis using steady-state information is a nonlinear pattern recognition problem. In such problems the measurement pattern vectors are noisy and collection of a complete training data set is time consuming and in some cases impossible. The training data were obtained from a simulated chemical process. The process consists of a reactor and a distillation column. The dynamically capacity allocating network models were found to have the best performance as compared to backpropagation-type network models. These networks can also be used for continuously learning systems and therefore the difficulties of training data collection are avoided. >