Nonlinear Process Fault Diagnosis Based on Serial Principal Component Analysis

Multisource Heterogeneous Data Fusion-Based Process Monitoring of the Reheating Furnace in Steel Production

The reheating furnace is the key piece of equipment in the hot rolling process of steel production. In order to fully exploit all of the data recorded from the production process representing different information, this paper designs a process monitoring algorithm with multisource information fusion by integrating multiple information to comprehensively monitor the operating state of the reheating furnace. Multisource information fusion combines process variable data of the reheating furnace and heating process data of the slab. To overcome the challenge of fusion of heterogeneous data due to different sampling patterns, univariate time series and multivariate time series data are fused by a transformer. In the fusion scheme, univariate time series data are represented by bidirectional gated recurrent unit for one-dimensional temporal representation, multivariate time series data are represented by temporal convolutional network for two-dimensional temporal representation, and multivariate time series data are represented by eigenvalue decomposition for correlation representation between variables. To evaluate the performance of the proposed method, computational experiments based on actual data are carried out. In univariate and multivariate time series representations, the highest predictions are obtained for bidirectional gated recurrent unit and temporal convolutional network by comparison with different regression algorithms, respectively. By comparing with fusing different fusion objects and different fusion schemes, the proposed algorithm achieves the highest accuracy (91.33%), precision (91.46%), and recall (92.59%), proving the effectiveness of the fusion approach. The process monitoring performance is compared with multivariate statistical process monitoring algorithms, which achieve the highest accuracy (95%), precision (93.45%), and recall (97.08%).

Multivariate Fusion Covariance Matrix Network and Its Application in Multichannel Fault Diagnosis With Fewer Training Samples

Due to the large number of monitoring variables in engineering, it is extremely to reflect fault information in machinery and equipment with a single channel signal, which poses a significant challenge for fault diagnosis. Furthermore, most existing intelligent recognition methods rely on label samples, yet ignore the high cost of label interpretation in practical engineering. In this work, a novel multivariate fusion covariance matrix network (MFCMN) is developed for multichannel fault diagnosis with fewer training samples. First, the collected multichannel signals are separated into mode functions by using cyclic autocorrelation analysis. Thereafter, the acquired mode functions are utilized to construct the multivariate fusion covariance matrix (MFCM), which retains the linkage of signals from different channels. Finally, MFCM is fed into the standard autoencoder to form the MFCMN network, which is applied to implement multichannel fault diagnosis. To assess effectiveness, the MFCMN is compared with the deep residual network (ResNet), convolutional neural network (CNN), long short-term memory (LSTM), and K-nearest neighbor (KNN) in two experimental cases with fewer training samples. The results clarify that the MFCMN offers excellent performance and high accuracy in multichannel fault diagnosis.

VAE-Based Interpretable Latent Variable Model for Process Monitoring

Latent variable-based process monitoring (PM) models have been generously developed by shallow learning approaches, such as multivariate statistical analysis and kernel techniques. Owing to their explicit projection objectives, the extracted latent variables are usually meaningful and easily interpretable in mathematical terms. Recently, deep learning (DL) has been introduced to PM and has exhibited excellent performance because of its powerful presentation capability. However, its complex nonlinearity prevents it from being interpreted as human-friendly. It is a mystery how to design a proper network structure to achieve satisfactory PM performance for DL-based latent variable models (LVMs). In this article, a variational autoencoder-based interpretable LVM (VAE-ILVM) is developed for PM. Based on Taylor expansions, two propositions are proposed to guide the design of appropriate activation functions for VAE-ILVM, allowing nondisappearing fault impact terms contained in the generated monitoring metrics (MMs). During threshold learning, the sequence of counting that test statistics exceed the threshold is considered a martingale, a representative of weakly dependent stochastic processes. A de la Peña inequality is then adopted to learn a suitable threshold. Finally, two chemical examples verify the effectiveness of the proposed method. The use of de la Peña inequality significantly reduces the minimum required sample size for modeling.

Transfer Learning-Motivated Intelligent Fault Diagnosis Designs: A Survey, Insights, and Perspectives

Over the last decade, transfer learning has attracted a great deal of attention as a new learning paradigm, based on which fault diagnosis (FD) approaches have been intensively developed to improve the safety and reliability of modern automation systems. Because of inevitable factors such as the varying work environment, performance degradation of components, and heterogeneity among similar automation systems, the FD method having long-term applicabilities becomes attractive. Motivated by these facts, transfer learning has been an indispensable tool that endows the FD methods with self-learning and adaptive abilities. On the presentation of basic knowledge in this field, a comprehensive review of transfer learning-motivated FD methods, whose two subclasses are developed based on knowledge calibration and knowledge compromise, is carried out in this survey article. Finally, some open problems, potential research directions, and conclusions are highlighted. Different from the existing reviews of transfer learning, this survey focuses on how to utilize previous knowledge specifically for the FD tasks, based on which three principles and a new classification strategy of transfer learning-motivated FD techniques are also presented. We hope that this work will constitute a timely contribution to transfer learning-motivated techniques regarding the FD topic.

Interaction-Aware Graph Neural Networks for Fault Diagnosis of Complex Industrial Processes

Fault diagnosis of complex industrial processes becomes a challenging task due to various fault patterns in sensor signals and complex interactions between different units. However, how to explore the interactions and integrate with sensor signals remains an open question. Considering that the sensor signals and their interactions in an industrial process with the form of nodes and edges can be represented as a graph, this article proposes a novel interaction-aware and data fusion method for fault diagnosis of complex industrial processes, named interaction-aware graph neural networks (IAGNNs). First, to describe the complex interactions in an industrial process, the sensor signals are transformed into a heterogeneous graph with multiple edge types, and the edge weights are learned by the attention mechanism, adaptively. Then, multiple independent graph neural network (GNN) blocks are employed to extract the fault feature for each subgraph with one edge type. Finally, each subgraph feature is concatenated or fused by a weighted summation function to generate the final graph embedding. Therefore, the proposed method can learn multiple interactions between sensor signals and extract the fault feature from each subgraph by message passing operation of GNNs. The final fault feature contains the information from raw data and implicit interactions between sensor signals. The experimental results on the three-phase flow facility and power system (PS) demonstrate the reliable and superior performance of the proposed method for fault diagnosis of complex industrial processes.

A Hybrid Design of Fault Detection for Nonlinear Systems Based on Dynamic Optimization

To ensure the safety of an automation system, fault detection (FD) has become an active research topic. With the development of artificial intelligence, model-free FD strategies have been widely investigated over the past 20 years. In this work, a hybrid FD design approach that combines data-driven and model-based is developed for nonlinear dynamic systems whose information is not known beforehand. With the aid of a Takagi-Sugeno (T-S) fuzzy model, the nonlinear system can be identified through a group of least-squares-based optimization. The associated modeling errors are taken into account when designing residual generators. In addition, statistical learning is adopted to obtain an upper bound of modeling errors, based on which an optimization problem is formulated to determine a reliable FD threshold. In the online FD decision, an event-triggered strategy is also involved in saving computational costs and network resources. The effectiveness and feasibility of the proposed hybrid FD method are illustrated through two simulation studies on nonlinear systems.

Deep Neural Network-Embedded Stochastic Nonlinear State-Space Models and Their Applications to Process Monitoring

Process complexities are characterized by strong nonlinearities, dynamics, and uncertainties. Monitoring such a complex process requires a high-quality model describing the corresponding nonlinear dynamic behavior. The proposed model is constructed using deep neural networks (DNNs) to represent the state transition and observation generation, both of which constitute a stochastic nonlinear state-space model. A new bidirectional recurrent neural network (RNN), creating a connection of the hidden layer between a forward RNN and a backward RNN, is proposed to generate the filtering estimation and the smoothing estimation of process states which further generate observations with DNN-based process models. The smoothing estimator and the process model are first learned offline with all collected samples. Then the filtering estimator is fine-tuned by the learned smoother and process models to achieve real-time monitoring since the filter state is estimated based on the past and the current observations. Two indices are designed based on the learned model for monitoring the process anomaly. The proposed process monitoring model can deal with complex nonlinearities, process dynamics, and process uncertainties, all of which can be very challenging for the existing methods, such as kernel mapping and stacked auto-encoder. Two case studies validate that the effectiveness of the proposed method outperforms the other comparative methods by at least 10% when using the averaged fault detection rate in the industrial experimental data.

Fault Diagnosis of Hydraulic Systems Based on Deep Learning Model With Multirate Data Samples

Hydraulic systems are a class of typical complex nonlinear systems, which have been widely used in manufacturing, metallurgy, energy, and other industries. Nowadays, the intelligent fault diagnosis problem of hydraulic systems has received increasing attention for it can increase operational safety and reliability, reduce maintenance cost, and improve productivity. However, because of the high nonlinear and strong fault concealment, the fault diagnosis of hydraulic systems is still a challenging task. Besides, the data samples collected from the hydraulic system are always in different sampling rates, and the coupling relationship between the components brings difficulties to accurate data acquisition. To solve the above issues, a deep learning model with multirate data samples is proposed in this article, which can extract features from the multirate sampling data automatically without expertise, thus it is more suitable in the industrial situation. Experiment results demonstrate that the proposed method achieves high diagnostic and fault pattern recognition accuracy even when the imbalance degree of sample data is as large as 1:100. Moreover, the proposed method can increase about 10% diagnosis accuracy when compared with some state-of-the-art methods.

Data-Driven Designs of Fault Detection Systems via Neural Network-Aided Learning

With the aid of neural networks, this article develops two data-driven designs of fault detection (FD) for dynamic systems. The first neural network is constructed for generating residual signals in the so-called finite impulse response (FIR) filter-based form, and the second one is designed for recursively generating residual signals. By theoretical analysis, we show that two proposed neural networks via self-organizing learning can find their optimal architectures, respectively, corresponding to FIR filter and recursive observer for FD purposes. Additional contributions of this study lie in that we establish bridges that link model- and neural-network-based methods for detecting faults in dynamic systems. An experiment on a three-tank system is adopted to illustrate the effectiveness of two proposed neural network-aided FD algorithms.

Comprehensive Monitoring of Complex Industrial Processes with Multiple Characteristics

Traditional onefold data-driven methods for fault detection in complex process industrial systems with high-dimensional, linear, nonlinear, Gaussian, and non-Gaussian coexistence often have less than satisfactory monitoring performance because only a single distribution of process variables is considered. To address this problem, a hybrid fault detection model based on PCA-KPCA-ICA-KICA-BI (Bayesian inference) is proposed, taking into account the advantages of principal component analysis (PCA), kernel principal component analysis (KPCA), independent component analysis (ICA), and kernel independent component analysis (KICA) in terms of dimensionality reduction and feature extraction. Foremost, this paper proposed a nonlinear evaluation method and divided the feature variables into Gaussian linear blocks, Gaussian nonlinear blocks, non-Gaussian linear blocks, and non-Gaussian nonlinear blocks by using the Jarque–Bera (JB) test and nonlinear discrimination method. Each division was monitored by the PCA-KPCA-ICA-KICA model, and finally the Bayesian fusion strategy proposed in this study is used to synthesize the detection results for each block. The hybrid model helps in evaluating variable features and bettering detection performance. Ultimately, the superiority of this hybrid model was verified through the Tennessee Eastman (TE) process and the Continuous Stirred Tank Reactor (CSTR) process, and the fault monitoring results showed an average accuracy of 85.91% for this hybrid model.

Slow feature analysis-aided detection and diagnosis of incipient faults for running gear systems of high-speed trains

Incipient faults in running gear systems corrupt the overall performance of high-speed trains, increasing the necessity of fault detection and diagnosis whose purpose is to maintain the safe and stable operation of high-speed trains. For this purpose, a novel data-driven method, that utilizes Hellinger distance and slow feature analysis, is proposed in this study. By integrating Hellinger distance into slow feature analysis, a new test statistic is defined for detecting incipient faults in running gear systems. Furthermore, the hidden Markov method is developed for performing reliable fault diagnosis tasks. The salient strengths of the proposed method lie in its satisfactory fault detectability on the one hand and the considerable robustness against high-level noises on the other hand. Finally, the effectiveness of the proposed method is verified through a numerical example and a running gear system of high-speed trains under actual working conditions.

Research on Micro-Fault Detection and Multiple-Fault Isolation for Gas Sensor Arrays Based on Serial Principal Component Analysis

Machine learning algorithms play an important role in fault detection and fault diagnosis of gas sensor arrays. Because the gas sensor array will see stability degradation and a shift in output signal amplitude under long-term operation, it is very important to detect the abnormal output signal of the gas sensor array in time and achieve accurate fault location. In order to solve the problem of low detection accuracy of micro-faults in gas sensor arrays, this paper adopts the serial principal component analysis (SPCA) method, which combines the advantages of principal component analysis (PCA) in the linear part and the advantages of kernel principal component analysis (KPCA) in the nonlinear part. The experimental results show that this method is more sensitive to micro-faults and has better fault detection accuracy than the fault detection methods of PCA and KPCA. In addition, in order to solve the current problem of low accuracy of multiple-fault isolation, a SPCA-based reconstruction contribution fault isolation method is proposed in this paper. The experimental results show that this method has higher fault isolation accuracy than the method based on contribution graph.

An Integrated Counterfactual Sample Generation and Filtering Approach for SAR Automatic Target Recognition with a Small Sample Set

Although automatic target recognition (ATR) models based on data-driven algorithms have achieved excellent performance in recent years, the synthetic aperture radar (SAR) ATR model often suffered from performance degradation when it encountered a small sample set. In this paper, an integrated counterfactual sample generation and filtering approach is proposed to alleviate the negative influence of a small sample set. The proposed method consists of a generation component and a filtering component. First, the proposed generation component utilizes the overfitting characteristics of generative adversarial networks (GANs), which ensures the generation of counterfactual target samples. Second, the proposed filtering component is built by learning different recognition functions. In the proposed filtering component, multiple SVMs trained by different SAR target sample sets provide pseudo-labels to the other SVMs to improve the recognition rate. Then, the proposed approach improves the performance of the recognition model dynamically while it continuously generates counterfactual target samples. At the same time, counterfactual target samples that are beneficial to the ATR model are also filtered. Moreover, ablation experiments demonstrate the effectiveness of the various components of the proposed method. Experimental results based on the Moving and Stationary Target Acquisition and Recognition (MSTAR) and OpenSARship dataset also show the advantages of the proposed approach. Even though the size of the constructed training set was 14.5% of the original training set, the recognition performance of the ATR model reached 91.27% with the proposed approach.

Local-Global Modeling and Distributed Computing Framework for Nonlinear Plant-Wide Process Monitoring With Industrial Big Data

Industrial big data and complex process nonlinearity have introduced new challenges in plant-wide process monitoring. This article proposes a local-global modeling and distributed computing framework to achieve efficient fault detection and isolation for nonlinear plant-wide processes. First, a stacked autoencoder is used to extract dominant representations of each local process unit and establish the local inner monitor. Second, mutual information (MI) is used to determine the neighborhood variables of a local unit. Afterward, a joint representation learning is then performed between the local unit and the neighborhood variables to extract the outer-related representations and establish the outer-related monitor for the local unit. Finally, the outer-related representations from all process units are used to establish global monitoring systems. Given that the modeling of each unit can be performed individually, the computation process can be efficiently completed with different CPUs. The proposed modeling and monitoring method is applied to the Tennessee Eastman (TE) and laboratory-scale glycerol distillation processes to demonstrate the feasibility of the method.

Trends and Challenges in Intelligent Condition Monitoring of Electrical Machines Using Machine Learning

A review of the fault diagnostic techniques based on machine is presented in this paper. As the world is moving towards industry 4.0 standards, the problems of limited computational power and available memory are decreasing day by day. A significant amount of data with a variety of faulty conditions of electrical machines working under different environments can be handled remotely using cloud computation. Moreover, the mathematical models of electrical machines can be utilized for the training of AI algorithms. This is true because the collection of big data is a challenging task for the industry and laboratory because of related limited resources. In this paper, some promising machine learning-based diagnostic techniques are presented in the perspective of their attributes.

Incipient fault detection for nonlinear processes based on dynamic multi-block probability related kernel principal component analysis

In order to detect the incipient faults of nonlinear industrial processes effectively, this paper proposes an enhanced kernel principal component analysis (KPCA) method, called multi-block probability related KPCA method (DMPRKPCA). First of all, one probability related nonlinear statistical monitoring framework is constructed by combining KPCA with Kullback Leibler divergence (KLD), which measures the probability distribution changes caused by small shifts. Second, in view of the problem that the traditional KLD ignores the dynamic characteristic of process data, the dynamic KLD component is designed by applying the exponentially weighted moving average approach, which highlights the temporal data changes in the moving window. Third, considering that the holistic KLD component may submerge the local statistical changes, a multi-block modeling strategy is designed by dividing the whole KLD components into two sub-blocks corresponding to the mean and variance information, respectively. Case studies on one numerical system and the simulated chemical reactor demonstrate the superiority of the DMPRKPCA method over the conventional KPCA method.

Fault Diagnosis of Complex Processes Using Sparse Kernel Local Fisher Discriminant Analysis

As an outstanding discriminant analysis technique, Fisher discriminant analysis (FDA) gained extensive attention in supervised dimensionality reduction and fault diagnosis fields. However, it typically ignores the multimodality within the measured data, which may cause infeasibility in practice. In addition, it generally incorporates all process variables without emphasizing the key faulty ones when modeling the complex process, thus leading to degraded fault classification capability and poor model interpretability. To ease the above two drawbacks of conventional FDA, this brief presents an advantageously sparse local FDA (SLFDA) model, it first preserves the within-class multimodality by introducing local weighting factors into scatter matrix. Then, the responsible faulty variables are identified automatically through the elastic net algorithm, and the current optimization problem is subsequently settled through the feasible gradient direction method. Since then, the local data structure characteristics are exploited from both the sample dimension and variable dimension so that the fault diagnosis performance and model interpretability are significantly enhanced. In addition, we naturally extend SLFDA model to nonlinear variant (i.e., sparse kernel local FDA) by the kernel trick, which is substantially more resistant to strong nonlinearity. The simulation studies on Tennessee Eastman (TE) benchmark process and real-world diesel engine working process both validate that the novel diagnosis strategy is more accurate and reliable than the existing state-of-the-art methods.

A Fault Diagnosis Strategy Based on Multilevel Classification for a Cascaded Photovoltaic Grid-Connected Inverter

In this paper, an effective strategy is presented to realize IGBT open-circuit fault diagnosis for closed-loop cascaded photovoltaic (PV) grid-connected inverters. The approach is based on the analysis of the inverter output voltage time waveforms in healthy and faulty conditions. It is mainly composed of two parts. The first part is to select the similar faults based on Euclidean distance and set the specific labels. The second part is the classification based on Principal Component Analysis and Support Vector Machine. The classification is done in two steps. In the first, similar faults are grouped to do the preliminary diagnosis of all fault types. In the second step the similar faults are discriminated. Compared with existing fault diagnosis strategies for several fundamental periods and under different external environments, the proposed strategy has better robustness and higher fault diagnosis accuracy. The effectiveness of the proposed fault diagnosis strategy is assessed through simulation results.

A Review of Kernel Methods for Feature Extraction in Nonlinear Process Monitoring

Kernel methods are a class of learning machines for the fast recognition of nonlinear patterns in any data set. In this paper, the applications of kernel methods for feature extraction in industrial process monitoring are systematically reviewed. First, we describe the reasons for using kernel methods and contextualize them among other machine learning tools. Second, by reviewing a total of 230 papers, this work has identified 12 major issues surrounding the use of kernel methods for nonlinear feature extraction. Each issue was discussed as to why they are important and how they were addressed through the years by many researchers. We also present a breakdown of the commonly used kernel functions, parameter selection routes, and case studies. Lastly, this review provides an outlook into the future of kernel-based process monitoring, which can hopefully instigate more advanced yet practical solutions in the process industries.

An Enhanced Method to Assess MPC Performance Based on Multi-Step Slow Feature Analysis

Due to the wide application of model predictive control (MPC) in industrial processes, the assessment of MPC performance is essential to ensure product quality and improve energy efficiency. Recently, the slow feature analysis (SFA) algorithm has been successfully applied to assess the performance of MPC. However, the disadvantage of the traditional SFA-based predictable index is that it can only extract one-step predictable information in the monitored variables. In order to better mine the predictable information contained in the monitored variables with large lag, an enhanced method to assess MPC performance based on multi-step SFA (MSSFA) is proposed. Based on the relationship between the slowness of slow features (SFs) and data predictability, an MSSFA model SFA(τ) is built through extending the temporal derivatives of the SFs from one step to multiple steps to extract multi-step predictable information in the monitored variables, which is used to construct a multi-step predictable index. Then, the predictable information in the SFs is further extracted for enhancing the multi-step predictable index to improve its sensitivity to performance changes. The effectiveness of the proposed method has been verified through two process simulation examples.

Kernel Generalized Likelihood Ratio Test for Fault Detection of Biological Systems

In this paper, we develop an improved fault detection (FD) technique in order to enhance the monitoring abilities of nonlinear biological processes. Generalized likelihood ratio test (GLRT)-based kernel principal component analysis (KPCA) (called also kernel GLRT) is an effective data-driven technique for monitoring nonlinear processes. However, it is well known that the data collected from complex and multivariate processes are multiscale due to the variety of changes that could occur in process with different localization in time and frequency. Thus, to enhance the process monitoring abilities, we propose to combine the advantages of kernel GLRT and multiscale representation using wavelets by developing a multiscale kernel GLRT (MS-KGLRT) detection chart. The proposed fault detection approach is addressed so that the KPCA is used to compute the model in the feature space and the MS-KGLRT chart is applied to detect the faults. The detection performance of the new chart is studied using two examples, one using synthetic data and the other using biological process representing a Cad System in E. Coli (CSEC) model for detecting small and moderate shifts (offset or bias and drift). The MS-KGLRT chart is used to enhance fault detection of the CSEC model through monitoring some of the key variables involved in this model such as enzymes, lysine, and cadaverine.

Batch process fault detection and identification based on discriminant global preserving kernel slow feature analysis

As an attractive nonlinear dynamic data analysis tool, global preserving kernel slow feature analysis (GKSFA) has achieved great success in extracting the high nonlinearity and inherently time-varying dynamics of batch process. However, GKSFA is an unsupervised feature extraction method and lacks the ability to utilize batch process class label information, which may not offer the most effective means for dealing with batch process monitoring. To overcome this problem, we propose a novel batch process monitoring method based on the modified GKSFA, referred to as discriminant global preserving kernel slow feature analysis (DGKSFA), by closely integrating discriminant analysis and GKSFA. The proposed DGKSFA method can extract discriminant feature of batch process as well as preserve global and local geometrical structure information of observed data. For the purpose of fault detection, a monitoring statistic is constructed based on the distance between the optimal kernel feature vectors of test data and normal data. To tackle the challenging issue of nonlinear fault variable identification, a new nonlinear contribution plot method is also developed to help identifying the fault variable after a fault is detected, which is derived from the idea of variable pseudo-sample trajectory projection in DGKSFA nonlinear biplot. Simulation results conducted on a numerical nonlinear dynamic system and the benchmark fed-batch penicillin fermentation process demonstrate that the proposed process monitoring and fault diagnosis approach can effectively detect fault and distinguish fault variables from normal variables.