Tennessee Eastman Benchmark Process Research Articles

An efficient and unified statistical monitoring framework for multivariate autocorrelated processes

In current manufacturing and service systems, product quality or process status is typically characterized by multiple variables. The rapid advances of information technologies further make these multiple variables measured at a high-frequent manner and thus generate temporally correlated multivariate data. The statistical monitoring of such a multivariate autocorrelated process (MAP) is quite challenging due to the complicated correlation between different variables and different time lags. To solve this challenge, our paper proposes an efficient and unified MAP monitoring framework. The original serially-dependent multivariate vectors are first represented by a sequence of two-dimensional matrices that contain full information about the mean, cross-correlation and autocorrelation of MAP data. Then a matrix normal distribution with parsimonious properties is adopted to model these constructed matrix data, where a mean parameter is used to characterize the process mean and two covariance matrix parameters are used to capture the cross-correlation and autocorrelation, respectively. Finally, a powerful likelihood ratio test–based charting statistic is analytically derived which can jointly monitor process mean and variability. The superiority of our control chart has been validated by large-scale numerical experiments and a real case study of the Tennessee Eastman benchmark process.

Nonlinear Dynamic Process Monitoring Based on Discriminative Denoising Autoencoder and Canonical Variate Analysis

Modern industrial processes are characterized by increasing complexity, often exhibiting pronounced dynamic behaviors and significant nonlinearity. Addressing these dynamic and nonlinear characteristics is essential for effective process monitoring. However, many existing methods for process monitoring and fault diagnosis are insufficient in handling these challenges. In this article, we present a novel process monitoring approach, CVA-DisDAE, which integrates an improved Denoising Autoencoder (DAE) with Canonical Variate Analysis (CVA) to address the challenges posed by dynamic behaviors and nonlinear relationships in industrial processes. First, CVA is employed to reduce data dimensionality and minimize information redundancy by maximizing correlations between past and future observations, thereby effectively capturing process dynamics. Following this, we introduce a discriminative DAE model (DisDAE) designed to serve as a semi-supervised denoising autoencoder for precise feature extraction. This is achieved by incorporating both between-class separability and within-class variability into the traditional DAE framework. The key distinction between the proposed DisDAE and the conventional DAE lies in the integration of a linear discriminant analysis (LDA) penalty into the DAE’s loss function, resulting in extracted features that are more conducive to fault classification. Finally, we validate the effectiveness of the proposed semi-supervised dynamic process monitoring approach through its application to the Tennessee Eastman benchmark process, demonstrating its superior performance.

Pruned tree-structured temporal convolutional networks for quality variable prediction of industrial process

In real industrial processes, the rapid and accurate acquisition of quality variables is essential. Therefore, this paper proposes a pruned tree-structured temporal convolutional network (PT-TCN) for efficient and accurate variables prediction. First, a novel tree network is developed, utilizing dilated causal convolution blocks as nodes to avoid the loss of local information. Each node extracts distinct local information, and by concatenating all tree nodes, the network can capture a comprehensive range of temporal scales. Then, to avoid the increased complexity caused by the tree structure, we design an online two-stage pruning strategy to compress the tree network without introducing additional computations. During the training process, blocks are initially pruned based on the correlation assessment between quality variables and tree nodes. Subsequently, weight normalization layers are employed to evaluate the importance of output channels in blocks, thereby enabling intra-block channel pruning. The effectiveness of PT-TCN is verified on Tennessee Eastman benchmark process. In addition, experiments on the real zinc flotation process demonstrate that the proposed PT-TCN improves in R2 and MAE by 1.32% and 1.26% respectively in predicting quality variables, and it can reduce 91.8% parameters of the initial tree-structured TCN without sacrificing accuracy.

Quality-related fault detection for dynamic process based on quality-driven long short-term memory network and autoencoder

Fault detection consistently plays a crucial role in industrial dynamic processes as it enables timely prevention of production losses. However, since industrial dynamic processes become increasingly coupled and complex, they introduce uneven dynamics within the collected data, posing significant challenges in effectively extracting dynamic features. In addition, it is a tricky business to distinguish whether the fault that occurs is quality-related or not, resulting in unnecessary repairing and large losses. In order to deal with these issues, this paper comes up with a novel fault detection method based on quality-driven long short-term memory and autoencoder (QLSTM-AE). Specifically, an LSTM network is initially employed to extract dynamic features, while quality variables are simultaneously incorporated in parallel to capture quality-related features. Then, a fault detection strategy based on reconstruction error statistic squared prediction error (SPE) and the quality monitoring statistic Hotelling T2 (H2) is designed, which can distinguish various types of faults to realize accurate monitoring for dynamic processes. Finally, several experiments conducted on numerical simulations and the Tennessee Eastman (TE) benchmark process demonstrate the reliability and effectiveness of the proposed QLSTM-AE method, which indicates it has higher accuracy and can separate different faults efficiently compared to some state-of-the-art methods.

Enhancing fault detection in multivariate industrial processes: Kolmogorov–Smirnov non-parametric statistical approach

The accurate detection of abnormal events in modern process plants is extremely important. The detection of faults of small magnitude and in a noisy process environment is still a challenge that many industries face. In this paper, a Kolmogorov–Smirnov (KS) based non-parametric statistical fault indicator is proposed to identify a variety of sensor faults in process plants. The data collected from most modern process plants are randomly varying and non-Gaussian, due to which the multivariate scheme based on Independent Component Analysis (ICA) is considered. The KS-based indicator is amalgamated with the ICA multivariate model, which yields a novel ICA-KS-based fault detection (FD) scheme. The KS statistical indicator compares any two distributions and checks if they are similar or dissimilar. The potential of the KS indicator is extended in the FD domain, where the residuals of training and testing data are compared in a sliding window. The ability of the proposed ICA-KS-based FD strategy is validated on a simulated Distillation column (DC) process and the benchmark Tennessee Eastman (TE) process to identify a variety of sensor faults. The simulation results demonstrate the effectiveness of the detection performance of the ICA-KS scheme, which outperforms conventional FD-based methods with a high detection rate.

Distributed monitoring of nonlinear plant-wide processes based on GA-regularized kernel canonical correlation analysis

Fault detection and diagnosis is important for ensuring process safety and is gaining increasing attention in the system safety field. A regularized kernel canonical correlation analysis (RKCCA) approach is proposed for monitoring nonlinear plantwide processes. For each local unit, genetic algorithm (GA)-based regularization is performed to determine the communication variables from neighboring units, which preserves the maximum correlations and eliminates the irrelevant variables. Then variables from a local unit and the communication variables are mapped into high-dimensional feature spaces, and the feature space of the local unit is decomposed into three orthogonal subspaces, namely the residual subspace, the inner subspace, and the outer-related subspace. Monitoring statistics to identify both the process status and the characteristic of a detected fault are constructed. The proposed RKCCA-based monitoring method considers both the information of a local unit and the beneficial information of related units to facilitate fault detection, thereby exhibiting superior performance to some state-of-the-arts methods. Applications on the Tennessee Eastman benchmark process and an industrial tail gas treatment process demonstrate the superiority of RKCCA monitoring.

Statistical Process Monitoring Based on Ensemble Structure Analysis

Feature extraction with the aim of dimensionality reduction plays a key role in developing statistical monitoring models. The projection directions obtained from the principal component analysis U+0028 PCA U+0029, locality preserving projections U+0028 LPP U+0029, and even multi-manifold projections U+0028 MMP U+0029 algorithms all can provide useful information for fault detection given that the corresponding models are trained in an unsupervised manner. By taking advantages of all these dimensionality reduction algorithms, a novel process monitoring model based on ensemble structure analysis U+0028 ESA U+0029 is presented in this article. The ESA model takes advantage of PCA, LPP and MMP models and combines the multiple solutions within an ensemble result through Bayesian inference. In the developed ESA model, different structure features of the given dataset are taken into account simultaneously, the suitability and reliability of the ESA-based monitoring model are then illustrated through the Tennessee Eastman benchmark process.

Deep Subdomain Learning Adaptation Network: A Sensor Fault-Tolerant Soft Sensor for Industrial Processes.

Sensor faults are non-negligible issues for soft sensor modeling. However, existing deep learning-based soft sensors are fragile and sensitive when considering sensor faults. To improve the robustness against sensor faults, this article proposes a deep subdomain learning adaptation network (DSLAN) to develop a sensor fault-tolerant soft sensor, which is capable of handling both sensor degradation and sensor failure simultaneously. Primarily, domain adaptation works for process data with sensor degradation in industrial processes. Being founded on the basic structure of deep domain adaptation, a novel subdomain learner is added to automatically learn the subdomain division, enabling DSLAN adaptable to multimode industrial processes. Notably, the subdomain structure of each sample follows a categorical distribution parameterized by output of the subdomain learner. Based on the designed subdomain learner, a new probabilistic local maximum mean discrepancy (PLMMD) is presented to measure the difference in distribution between source and target features. In addition, a generator for failure data imputation is integrated in the framework, making DSLAN handle sensor failure simultaneously. Finally, the Tennessee Eastman (TE) benchmark process and two real industrial processes are used to verify the effectiveness of the proposed method. With the fault tolerance ability, soft sensing technology will take a step toward practical applications.

A propagation path-based interpretable neural network model for fault detection and diagnosis in chemical process systems

Process monitoring through automated fault detection and diagnosis (FDD) plays a crucial role in maintaining a productive and reliable chemical process system. Developments in AI and machine learning have boosted FDD model performances especially with deep learning methods. However, these neural network models are considered black-boxes where the reasoning behind a diagnosis is unclear, preventing industrial adoption. Therefore, in this study, an interpretable neural network model is proposed for FDD in chemical processes. This framework detects and diagnoses faults based on the propagation paths of different faults which are embedded into the architecture through graph convolutional networks. A mechanism for interpreting the node activations which represent process variables is developed for decision verification. The proposed method is evaluated on the benchmark Tennessee Eastman Process where it achieves a 93.56% accuracy on selected faults.

Comparison of autoencoder architectures for fault detection in industrial processes

Fault detection constitutes a fundamental task for predictive maintenance, requiring mathematical models that can be conveniently provided by data-driven techniques. Autoencoders are a particular type of unsupervised Artificial Neural Networks that can be suitable for fault detection applications. Diverse architectures might be used for autoencoders, resulting in different fault detection performances, which are usually compared by means of Fault Detection Rates for a fixed threshold of the False Alarm Rate, limiting the conclusions to particular cases. To improve the comparability, the present work uses the area under the receiver operating characteristic curve to compare autoencoder architectures for a range of false alarm rates using the Tennessee Eastman Process benchmark. Performances obtained for shallow and deep autoencoders were compared with those of the denoising and variational autoencoders for undercomplete and sparse structures. Overall, the results indicate better performances for sparse structures, especially for the variational autoencoder and the deep denoising autoencoder, with area under the curve of 98.35%.

Knowledge-Enhanced Spatiotemporal Analysis for Anomaly Detection in Process Manufacturing

Effective fault detection and diagnosis (FDD) is crucial for proactively identifying irregular states that could jeopardize operator well-being and process integrity. In the era of Industry 4.0, data-driven FDD techniques have received particular attention, driven by the proliferation of stored manufacturing sensor data. While these methods have proven adept at categorizing established process fault scenarios, there remains an imperative to identify and explain anomalies stemming from uncharted faults or the interplay of consecutive anomalies. To address this we present a knowledge-enhanced FDD approach that integrates well-defined chemical engineering knowledge with cutting-edge deep learning techniques. We apply our methodology, named Knowledge-Enhanced Spatiotemporal Analysis (KESA), to identify abnormal process conditions that may be a precursor to failure. Furthermore, we utilize the knowledge of the fundamental relationships governing the process to explain why this fault case has occurred. This type of in-depth fault analysis is only possible through leveraging domain expertise and marks a step forward in FDD technology in comparison to current literature. Using the benchmark Tennessee Eastman process dataset, we establish superiority in the accuracy and efficiency of our KESA model against state-of-the-art FDD algorithms. This work highlights the importance of a knowledge-enhanced approach to deep learning in complex environments, emphasizing the critical role of timely and interpretable fault detection. By providing explanations for model results, our KESA framework not only aids in effective decision-making but also has the potential to significantly reduce the time between fault detection and the implementation of proactive mitigation actions. This capability is paramount for improving overall safety, minimizing downtime, and ultimately contributing to substantial cost savings in industrial processes.

Improved fault detection and diagnosis using graph auto encoder and attention-based graph convolution networks

A powerful fault detection and diagnosis (FDD) system plays a pivotal role in achieving operational excellence by maximizing system performance, optimizing maintenance strategies, and ensuring the longevity and resilience of process plants. In the context of FDD for multivariate sensor data, this study presents an improved FDD approach using graph-based neural networks. This graph neural network uses an adjacency matrix developed by extracting the expert domain knowledge and topological information of the multi-sensor system. This additional graph representation of the system is incorporated along with multivariate sensor data to capture the spatial and temporal information in neural networks efficiently. In this regard, we propose and evaluate: 1) A Graph Auto Encoder (GAE) based fault detection strategy and 2) An Attention-based Spatial Temporal Graph Convolution Network (ASTGCN) based fault diagnosis methodology. By leveraging the additional knowledge in the form of graphs, the GAE captures the complex relationships and dependencies among sensors, enabling effective anomaly detection, which identifies abnormal patterns and deviations from normal behavior, thus indicating potential faults in the system. The ASTGCN incorporates attention mechanisms to selectively focus on relevant sensor nodes and capture their spatial and temporal dependencies for fault diagnosis. The effectiveness of the proposed FDD approach is demonstrated using the benchmark Tennessee Eastman Process (TEP) problem. The results show that the proposed approaches outperform traditional methods and highlight the importance of leveraging graph-based knowledge for FDD in complex systems.

Reweighted Regularized Prototypical Network for Few-Shot Fault Diagnosis.

In this article, we study the challenging few-shot fault diagnosis (FSFD) problem where limited faulty samples are available. Metric-based meta-learning methods have been a prevalent approach toward FSFD; however, most of them rely on learning a generalized distance metric and fall short of leveraging intraclass and interclass distribution information. To this end, we develop a novel reweighted regularized prototypical network to improve the performance of FSFD, where an intraclass reweighting strategy is proposed to reduce the influence of noise and outliers and obtain stable estimations of fault prototypes. In addition, a novel balance-enforcing regularization (BER) is proposed to hedge against the between-class imbalance and improve the discrimination capability. These two remedies help to reduce the intraclass difference and enlarge the interclass difference via episodic training. In this way, an improved metric space and a better diagnostic performance can be attained in a few-shot learning context. Case studies on the Tennessee Eastman benchmark process and a real-world railway turnout dataset demonstrate that the proposed FSFD approach compares favorably against state-of-the-art methodologies with desirable diagnostic performance.

Partial Cross Mapping Based on Sparse Variable Selection for Direct Fault Root Cause Diagnosis for Industrial Processes.

Root cause diagnosis of process industry is of significance to ensure safe production and improve production efficiency. Conventional contribution plot methods have challenges in root cause diagnosis due to the smearing effect. Other traditional root cause diagnosis methods, such as Granger causality (GC) and transfer entropy, have unsatisfactory performance in root cause diagnosis for complex industrial processes due to the existence of indirect causality. In this work, a regularization and partial cross mapping (PCM)-based root cause diagnosis framework is proposed for efficient direct causality inference and fault propagation path tracing. First, generalized Lasso-based variable selection is performed. The Hotelling T2 statistic is formulated and the Lasso-based fault reconstruction is applied to select candidate root cause variables. Second, the root cause is diagnosed through the PCM and the propagation path is drawn out according to the diagnosis result. The proposed framework is studied in four cases to verify its rationality and effectiveness, including a numerical example, the Tennessee Eastman benchmark process, the wastewater treatment process (WWTP), and the decarburization process of high-speed wire rod spring steel.

Efficient and Fast Joint Sparse Constrained Canonical Correlation Analysis for Fault Detection.

The canonical correlation analysis (CCA) has attracted wide attention in fault detection (FD). To improve the detection performance, we propose a new joint sparse constrained CCA (JSCCCA) model that integrates the l2,0 -norm joint sparse constraints into classical CCA. The key idea is that JSCCCA can fully exploit the joint sparse structure to determine the number of extracted variables. We then develop an efficient alternating minimization algorithm using the improved iterative hard thresholding and manifold constrained gradient descent method. More importantly, we establish the convergence guarantee with detailed analysis. Finally, we provide extensive numerical studies on the simulated dataset, the benchmark Tennessee Eastman process, and a practical cylinder-piston process. In some cases, the computing time is reduced by 600 times, and the FD rate is increased by 12.62% compared with classical CCA. The results suggest that the proposed approach is efficient and fast.

Explicit Representation and Customized Fault Isolation Framework for Learning Temporal and Spatial Dependencies in Industrial Processes.

Typically, industrial processes possess both temporal and spatial dependencies due to intravariable dynamics and intervariable couplings. The two dependencies have different manifestations, indicating diverse process characteristics. However, the existing methods fail to separate temporal and spatial information well, leading to inappropriate representation and inaccurate fault detection and isolation results. This study proposes an explicit representation and customized fault isolation framework to tackle temporal and spatial characteristics, so as to identify and locate anomalies affecting different dependencies. First, we design a double-level separation method for temporal and spatial information. In the first level, we construct two independent auto-encoding modules to extract temporal correlation and spatial graph structure in parallel. In the second level, we propose an information aliasing loss function to guild the two modules to distinguish between temporal and spatial characteristics, further facilitating information separation. By monitoring the explicit temporal and spatial statistics obtained by the two modules, spatiotemporal dependencies of anomalies can be determined for subsequent isolation. Furthermore, we propose a customized isolation strategy for anomalies in temporal and spatial characteristics. By quantifying changes in intravariable temporal dynamics and intervariable spatial graph structure individually, temporal impact and spatial propagation of faults can be finely characterized and isolated. Three examples are adopted to verify the performance of the proposed framework, including a numerical example, a real condensing system of the thermal power plant process, and the Tennessee Eastman benchmark process.

Dual-attention LSTM autoencoder for fault detection in industrial complex dynamic processes

Complex dynamic characteristics resulting from multi-system coupling and closed-loop control are ubiquitous in modern industrial process data, presenting significant challenges for process fault detection. However, conventional data-driven fault detection methods assume the data to be static or slightly dynamic. Addressing the complex dynamic characteristics and nonlinearity inherent in industrial processes, this paper proposes a dual-attention long short-term memory autoencoder (DALSTM-AE) for fault detection in dynamic processes. Long short-term memory (LSTM) and autoencoder (AE) are combined into a special encoder-decoder LSTM architecture to learn both dynamic features and deep representations of variables in an unsupervised manner. Then, a dual-attention module is embedded in the decoder to properly learn the temporal dependencies associated with long input sequences and retain the most critical information. In addition, based on the reconstruction results of the DALSTM-AE model, two monitoring statistics are designed for fault detection. Finally, the effectiveness and superiority of the proposed method are fully demonstrated through case studies on a numerical simulation example, the Tennessee Eastman (TE) benchmark process, and practical coal pulverizing systems in power plants.

Distributed temporal–spatial neighbourhood enhanced variational autoencoder for multiunit industrial plant‐wide process monitoring

AbstractProcess monitoring plays an essential role in ensuring the safe and efficient operation of multi‐unit plantwide industrial processes. However, complicated nonlinear dynamics of these processes pose enormous challenges to the plantwide process monitoring approaches. In this paper, a novel distributed temporal–spatial neighbourhood enhanced variational autoencoder (DTS‐VAE) monitoring scheme is proposed. The scheme selects the temporal and spatial neighbourhood sets of a current sample from a local unit. Time‐series correlation is utilized to construct temporal representative samples to obtain process dynamic characteristics. Likewise, spatial similarity is employed to construct spatial representative samples to obtain spatial patterns in the data. Then the reconstructed and current samples serve as the inputs for a variational autoencoder to extract features from the current sample and its neighbourhoods. Subsequently, a distributed monitor that considers the temporal–spatial characteristics is established for each unit. Finally, a comprehensive evaluation index is developed using Bayesian fusion strategy to improve monitoring performance. The proposed DTS‐VAE monitoring scheme was effectively verified on the Tennessee Eastman benchmark process and a wastewater treatment plant.

A multi-feature-based fault diagnosis method based on the weighted timeliness broad learning system

Accurate and timely fault diagnosis is a vital task to ensure process safety of modern industrial facilities. Motivated by the complex variations of process signals and mutual coupling of faults, this paper presents a multi-feature-based fault diagnosis method based on the weighted timeliness Broad Learning System (BLS). The proposed method fuses multiple features extracted from the original process data to improve the fault diagnosis performance, and makes the diagnosis model suitable for dynamic fault diagnosis problems by incorporating the BLS. The major contributions of this study are twofolds: 1) A systematic multi-feature extraction method is proposed to extract long-term trend features, short-term trend features, and binary alarm signals, which reflect the direction and amplitude changes of process signals under faulty conditions; 2) a weighted timeliness BLS structure with multiple fault-sensitive features as the input is proposed to ensure the dynamic characteristics of the fault diagnosis model. The designed fault diagnosis model can be updated in an incremental manner, and thus can improve the model updating efficiency while ensuring accuracy. The effectiveness and superiority of the proposed method is demonstrated by a case study based on the Tennessee Eastman benchmark process.

Reconstruction error‐based fault detection of time series process data using generative adversarial auto‐encoders

AbstractFaults in time series process data are typically difficult to detect due to the complex temporal correlations of data samples. In this context, traditional unsupervised machine learning algorithms, such as principal component analysis, independent component analysis, and so forth, would yield only limited performance. Deep learning‐based methods have been employed in recent years to address these problems. Recently, generative adversarial networks have emerged as a promising generative modelling approach for learning data distributions. Inspired by the above, in this study, we present a novel reconstruction error‐based fault detection method for time series process data using generative adversarial auto‐encoder (GAAE) with Wasserstein loss, cycle consistency loss, and gradient penalty methods. The proposed method is designed to detect abnormal patterns in the time series data by training a GAAE to learn the underlying normal behaviour of the data. GAAEs help in effectively capturing the data's hidden distribution, and Wasserstein loss with gradient penalty is used to improve the accuracy of the latent space representation of the data, while the cycle consistency loss ensures consistency between the input and output data during the reconstruction process. Based on the extent of the reconstruction error metric of the GAAEs, we identify the potential faults in the process data stream. The proposed method is evaluated on two data process sets, namely, the Tennessee Eastman benchmark process dataset and the nuclear power flux real‐time dataset from a pressurized heavy water nuclear reactor, to validate the efficacy of the proposed approach.