Fault Diagnosis In Industrial Processes Research Articles

Industrial process fault diagnosis based on video recognition and multi-source information fusion

Industrial process fault diagnosis based on video recognition and multi-source information fusion

A deep learning methodology based on adaptive multiscale CNN and enhanced highway LSTM for industrial process fault diagnosis

Intelligent fault diagnostic techniques are crucial for ensuring the long-term reliability of manufacturing. The process variables collected by sensors in real industrial systems typically exhibit diverse time scales and data features. To overcome the above issues, we propose a comprehensive model known as adaptive multiscale CNN and enhanced highway LSTM (ACEL). To begin with, multiscale features under variable operating conditions are automatically extracted by constructing the parallel convolutional module. Then, to selectively focus on the feature representation within the channels, efficient channel attention is introduced to downplay the channels with less important information. In addition, the bidirectional LSTM is designed to generate more fine-grained hybrid features based on contextual information and local features learned by the CNN. An enhanced highway configuration is designed to be used to bolster the global temporal dependencies. Finally, ACEL is applied to the Tennessee Eastman benchmark and CSTR simulation, and multiple statistical metrics show that the proposed model outperforms other advanced fault diagnosis methods.

Enhancing Fault Diagnosis in Industrial Processes through Adversarial Task Augmented Sequential Meta-Learning

This study introduces the Adversarial Task Augmented Sequential Meta-Learning (ATASML) framework, designed to enhance fault diagnosis in industrial processes. ATASML integrates adversarial learning with sequential task learning to improve the model’s adaptability and robustness, facilitating precise fault identification under varied conditions. Key to ATASML’s approach is its novel use of adversarial examples and data-augmentation techniques, including noise injection and temporal warping, which extend the model’s exposure to diverse operational scenarios and fault manifestations. This enriched training environment significantly boosts the model’s ability to generalize from limited data, a critical advantage in industrial applications where anomaly patterns frequently vary. The framework’s performance was rigorously evaluated on two benchmark datasets: the Tennessee Eastman Process (TEP) and the Skoltech Anomaly Benchmark (SKAB), which are representative of complex industrial systems. The results indicate that ATASML outperforms conventional meta-learning models, particularly in scenarios characterized by few-shot learning requirements. Notably, ATASML demonstrated superior accuracy and F1 scores, validating its effectiveness in enhancing fault-diagnosis capabilities. Furthermore, ATASML’s strategic incorporation of task sequencing and adversarial tasks optimizes the training process, which not only refines learning outcomes but also improves computational efficiency. This study confirms the utility of the ATASML framework in significantly enhancing the accuracy and reliability of fault-diagnosis systems under diverse and challenging conditions prevalent in industrial processes.

Industrial process fault diagnosis based on domain adaptive broad echo network

BackgroundIn response to the challenge that traditional fault diagnosis models are difficult to maintain satisfactory accuracy when data distribution changes due to changes in process conditions, a fault diagnosis model of industrial process based on domain adaptive broad echo network (DABEN) is proposed. MethodsThe DABEN model first constructs feature nodes through random feature mapping to extract shallow features of process data, and then inputs feature nodes into cascade reservoirs to extract dynamic features of different levels. On this basis, the objective function of DABEN is constructed, which starts from the four goals of minimizing the prediction error, maximum mean discrepancy distribution alignment, manifold regularization and minimizing cross-domain error to ensure that the features are as similar as possible between the source domain and the target domain. Significant FindingsFinally, two simulation cases show that DABEN can achieve good transfer fault diagnosis performance under different data distributions

Fault diagnosis of industrial process using attention mechanism with 3DCNN-LSTM

Although architectures such as recurrent neural networks (RNN) perform well in time series prediction, there is still challenges for existing deep learning methods in extracting comprehensive spatio-temporal features. This paper proposes a fault diagnosis method (3D-ALCNN) using a three-dimensional convolutional neural network (3DCNN), a long-short-term memory network (LSTM) and an attentional mechanism to enhance the correlation perception among important features. The 3DCNN and LSTM are firstly used to extract temporal features and a data stacking method to adapt the one-dimensional data to the input requirements of 3DCNN is adopted. Then, the correlation between different features is identified through the attention mechanism and the neural network is guided to focus on more important features. Eventually, the model output is fed into a classifier for fault classification. Simulation experiments on the industrial coke furnace show that the 3D-ALCNN model outperforms existing methods in terms of fault diagnosis accuracy and efficiency, especially when dealing with chemical data with complex time dependencies.

Industrial process fault diagnosis based on feature enhanced meta-learning toward domain generalization scenarios

With the rise of the Internet of Things, computing science, and artificial intelligence, data-driven fault diagnosis methods for industrial processes have attracted considerable attention. However, these methods typically assume that the distribution of the test data (target domains) is similar to that of the training data (source domains), making it difficult to deploy them in actual scenarios because the distribution of the collected data varies with operating conditions. Faced with this challenge, a novel fault diagnosis method based on feature enhanced meta-learning (FEML) is proposed to learn domain generalization knowledge effectively. It aims to jointly extract domain-invariant information that can be transferred across domains, and domain-specific information related to classification labels. First, feature extractors based on gated recurrent units (GRUs) are designed to capture domain-invariant and domain-specific representations with time-sequence characteristics from industrial process data. Second, a meta-learning strategy is introduced to enhance the domain-specific representation, thus improving the generalization ability of the model without accessing the target domains. Finally, the Tennessee Eastman process (TEP), Fed-Batch Fermentation Penicillin process (FBFP), and Three-Phase Flow process (TPFP) are used to verify the effectiveness of FEML. The results illustrate that the FEML is robust and outperforms other related methods. The diagnostic accuracies for TEP, FBFP, and TPFP are 87.11%, 95.94%, and 83.07%, respectively.

STAGED: A Spatial-Temporal Aware Graph Encoder–Decoder for Fault Diagnosis in Industrial Processes

Data-driven fault diagnosis for critical industrial processes has exhibited promising potential with massive operating data from the supervisory control and data acquisition system. However, automatically extracting the complicated interactions between measurements and subtly integrating it with temporal evolutions have not been fully considered. Besides, with the increasing complexity of industrial processes, accurately locating fault roots is of tremendous significance. In this article, we propose an unsupervised spatial-temporal aware graph encoder-decoder (STAGED) model for industrial fault diagnosis. Firstly, the high-dimensional measurements are constructed as a weighted graph to depict the complicated interactions. Then, the graph convolutional network, long short-term memory network and attention mechanism are applied to learn a comprehensive representation for multi-series. To enforce the model to better capture the temporal evolution, the dual decoder that performs reconstruction and prediction tasks simultaneously is adopted with a well-designed comprehensive loss function. By learning the spatial-temporal evolutions of datasets, faults can be diagnosed and located at a fine-grained level based on reconstruction deviations. To verify the performance of STAGED, experiments on Cranfield three-phase flow facility and secure water treatment datasets are implemented and the results indicate that it can provide insight into fault evolution and accurately diagnose faults.

A network structure for industrial process fault diagnosis based on hyper feature extraction and stacked LSTM

Traditional feature extraction methods are highly dependent on manual work, and manual extraction will inevitably ignore some potentially useful features. For complex systems, there is no simple one-to-one correspondence between faults and symptoms, and fault characteristics often have complex characteristics such as hierarchy, propagation correlation, and delay. In the existing research results, the convolutional neural network (CNN) has been proven to be an effective network structure. But the existing network structure is more like a classifier, and only some features of industrial data are considered in the feature extraction stage, which will cause some feature information to be lost during the training process. To effectively solve the above problems, this paper proposes an industrial process-oriented hyper feature extraction network structure. This method first extracts multi-level CNN fault features, aggregates the hierarchical feature maps and compresses them in a unified feature space to form hyper features. Then the hyper features formed by feature fusion are input to the stacked Long Short Term Memory (LSTM) network for further feature extraction. In this way, the information in the time series can be effectively transmitted, and at the same time, the problem of gradient disappearance caused by long-term training can be solved. We conducted experiments on the Tennessee-Eastman (TE) benchmark process and industrial coking oven datasets. The experimental results show that the proposed method can effectively improve the fault diagnosis accuracy of the industrial production process system.

Bayesian Hierarchical Graph Neural Networks With Uncertainty Feedback for Trustworthy Fault Diagnosis of Industrial Processes.

Deep learning (DL) methods have been widely applied to intelligent fault diagnosis of industrial processes and achieved state-of-the-art performance. However, fault diagnosis with point estimate may provide untrustworthy decisions. Recently, Bayesian inference shows to be a promising approach to trustworthy fault diagnosis by quantifying the uncertainty of the decisions with a DL model. The uncertainty information is not involved in the training process, which does not help the learning of highly uncertain samples and has little effect on improving the fault diagnosis performance. To address this challenge, we propose a Bayesian hierarchical graph neural network (BHGNN) with an uncertainty feedback mechanism, which formulates a trustworthy fault diagnosis on the Bayesian DL (BDL) framework. Specifically, BHGNN captures the epistemic uncertainty and aleatoric uncertainty via a variational dropout approach and utilizes the uncertainty information of each sample to adjust the strength of the temporal consistency (TC) constraint for robust feature learning. Meanwhile, the BHGNN method models the process data as a hierarchical graph (HG) by leveraging the interaction-aware module and physical topology knowledge of the industrial process, which integrates data with domain knowledge to learn fault representation. Moreover, the experiments on a three-phase flow facility (TFF) and secure water treatment (SWaT) show superior and competitive performance in fault diagnosis and verify the trustworthiness of the proposed method.

Explainable Artificial Intelligence for Fault Diagnosis of Industrial Processes

Process monitoring is important for ensuring operational reliability and preventing occupational accidents. In recent years, data-driven methods such as machine learning and deep learning have been preferred for fault detection and diagnosis. In particular, unsupervised learning algorithms, such as auto-encoders, exhibit good detection performance, even for unlabeled data from complex processes. However, decisions generated from deep-neural-network-based models are difficult to interpret and cannot provide explanatory insight to users. We address this issue by proposing a new fault diagnosis method using explainable artificial intelligence to break the traditional trade-off between the accuracy and interpretability of deep learning model. First, an adversarial auto-encoder model for fault detection is built and then interpreted through the integration of Shapley additive explanations (SHAP) with a combined monitoring index. Using SHAP values, a diagnosis is conducted by allocating credit for detected faults, deviations from a normal state, among its input variables. The proposed diagnosis method can consider not only reconstruction space but also latent space unlike conventional method, which evaluate only reconstruction error. The proposed method was applied to two chemical process systems and compared with conventional diagnosis methods. The results highlight that the proposed method achieves the exact fault diagnosis for single and multiple faults and, also, distinguishes the global pattern of various fault types.

Reconstruction-based stacked sparse auto-encoder for nonlinear industrial process fault diagnosis

The reconstruction-based (RB) approach can effectively suppress the misdiagnosis problem due to the smearing effect in fault isolation. However, the current exploration of the RB approach for large-scale nonlinear systems is still limited. Therefore, this paper proposes a reliable and effective fault diagnosis method based on a reconstruction-based stacked sparse autoencoder (RBSSAE) for high-dimensional industrial systems. In RBSSAE, a reconstruction-based index achieved by the Steffensen iterative method is developed to check whether the given variable(s) are responsible for the faults efficiently. However, the number of possible faulty variable combinations grows exponentially with the system dimension or actual abnormal variables, causing an unbearable computational burden. Hence, the proposed RBSSAE utilizes a sequential floating forward selection approach to rapidly isolate the most decisive variable combination, meeting a requirement of online fault diagnosis. Finally, the effectiveness of the RBSSAE is verified on a numerical example and a real industrial case.

An industrial process fault diagnosis method based on independent slow feature analysis and stacked sparse autoencoder network

Deep learning, with its powerful multilayer nonlinear representation of deep neural networks, enables models trained based on deep learning to describe the true distribution of data more accurately and thus have better generalization capabilities. However, the training data are usually assumed to obey independent identical distribution. Industrial process data nowadays usually have complex characteristics such as non-Gaussian, nonlinear, dynamic, strong correlation, and high-dimensional, which make it difficult to meet the assumptions of deep learning. Using industrial process data directly would result in low model accuracy and bias in the model output. This paper proposes a fault diagnosis method based on independent slow feature analysis (ISFA) and stacked sparse autoencoder (SSAE) network. The statistical properties possessed by ISFA are used to perform preliminary feature extraction of industrial process data, and then the extracted preliminary features are input to the SSAE network for fine-grained feature extraction. The proposed two-step feature extraction method not only makes the data input to the SSAE network as close as possible to obey independent identical distribution and provides convincing fault diagnosis results, but also makes full use of the powerful feature extraction capability of the SSAE network, which makes the proposed method also significantly improve the detection accuracy of incipient faults. The feasibility and superiority of the proposed method is verified through the TE process.

Model Fusion and Multiscale Feature Learning for Fault Diagnosis of Industrial Processes.

The data generated by modern industrial processes often exhibit high-dimensional, nonlinear, timing, and multiscale characteristics. Presently, most of the fault diagnosis methods based on deep learning only consider the part of the characteristics of industrial data, which will cause the loss of part of the feature information during training, thereby affecting the final diagnosis effect. In order to solve the above problems, this article proposes an end-to-end multiscale feature learning method based on model fusion, which can simultaneously extract multiscale spatial features and temporal features of data, effectively reducing the loss of feature information. First, this article combines the convolutional neural network (CNN) with residual learning and designs a multiscale residual network (MRCNN) to extract high-dimensional nonlinear spatial features of different scales in the data. Then, the extracted features are input into the long and short-term memory (LSTM) network to further extract the temporal features of the data. After the fully connected layer, it is input into the classifier for final fault classification. The residual learning in MRCNN can effectively avoid the problem of model degradation and improve the training efficiency of the model. Through the fusion of MRCNN and LSTM, we can significantly improve the feature extraction ability of the model, thereby greatly improving the diagnosis effect. In the final case experiment, the method improved the comprehensive diagnostic accuracy of the Tennessee-Eastman (TE) process and industrial coking furnace datasets to 94.43% and 97.80%, respectively, which was significantly better than the existing deep learning model and proves the effectiveness and superiority of this method.

A Novel Distributed Fault Diagnosis Scheme Toward Open-Set Scenarios Based on Extreme Value Theory

Under closed-set scenarios (CSS), distributed modeling performs well in fault diagnosis of plant-wide industrial processes due to its flexibility and robustness. However, a more realistic scenario is often open, where unseen situations may arise unexpectedly, rendering existing methods infeasible. The advent of open-set recognition algorithms that can effectively distinguish known samples and reject unknown ones bridges this gap. Nevertheless, the poor scalability of these algorithms prevents them from being elegantly embedded in popular distributed modeling schemes, which hinders the implementation of plant-wide industrial process fault diagnosis toward open-set scenarios (OSS). In this work, we formulate a novel distributed fault diagnosis scheme toward OSS to solve this problem. Firstly, a mutual information-based local module decomposition and expansion strategy is proposed to minimize the loss of inter-module relevant information. Secondly, a novel generalized basic probability assignments generation technique based on extreme value theory is developed for modeling unknown information. It enables any classifier capable of probabilistic prediction to be applied to OSS and easily embedded in distributed modeling schemes. Finally, a conflict management scheme combining supervised and unsupervised is devised to address the vulnerability of the modified generalized combination rule to counter-intuitive results from fusing conflicting evidence. Experimental results on two plant-wide industrial process datasets demonstrate the proposed approach's feasibility and superiority.

Fusing logic rule-based hybrid variable graph neural network approaches to fault diagnosis of industrial processes

It is practical that industrial processes are regarded as hybrid systems involving both continuous and discrete variables. Particularly, process discrete variables are usually rather crucial to process normal operations. However, existing data-driven fault diagnosis methods have been rarely applied for industrial processes concerning hybrid system characteristics. In response to this issue, this paper proposes a novel industrial process fault diagnosis approach based on fusing logic rule-based hybrid variable graph neural networks (GNNs) able to learn hybrid variable spatial structures. Therein, continuous variables samples are regarded as learning objects, while logic rule information is utilized to guide the learning process. Specifically, a mixed 0–1 integer linear programming algorithm is used to extract logic rules with fault labels from discrete variable data. Subsequently, a rule classification method is used to classify the logic rules with fault labels into independent and interdependent rule classes which are filed in a rule class library using as the basis for topological connections among data samples. In addition, an edge pruning-based graph optimization is employed to reduce redundant connections of the nodes. It is found that the established hybrid variable GNNs is able to learn the spatial topological structure of hybrid industrial process variables, providing rich heuristic knowledge for process fault classifications so as to effectively improve the fault diagnose performance. Simulation experiments are carried out in an industrial coal gasification process platform and a storage tank systems simulation platform, achieving satisfactory results.

Variational autoencoder based on distributional semantic embedding and cross-modal reconstruction for generalized zero-shot fault diagnosis of industrial processes

The traditional fault diagnosis models cannot achieve good fault diagnosis accuracy when a new unseen fault class appears in the test set, but there is no training sample of this fault in the training set. To solve this problem, a generalized zero-shot fault diagnosis model for industrial processes based on distributional semantic embedding and cross-modal reconstruction variational autoencoder (DSECMR-VAE) is proposed. DSECMR-VAE uses two variational autocoders (VAEs) to encode the features from two different modalities of fault samples and fault attribute semantic vectors into latent variables, and then uses the latent variables to generate fault samples belonging to the seen and unseen fault classes. In addition, a Barlow matrix is designed specifically for the distribution parameters of the latent variables, this matrix is utilized to measure the consistency between the distribution of fault samples and fault attribute semantic vectors. Subsequently, cross-modal reconstruction is performed on VAE. Cross-modal reconstruction uses the input from different modalities to reconstruct the current input, which can fully combine the information from different modalities. Finally, a classifier is trained based on the obtained latent variables to realize the generalized zero-shot fault diagnosis. Two case studies demonstrate the effectiveness and superiority of the proposed model for zero-shot and generalized zero-shot fault diagnosis.

A zero-sample industrial process fault diagnosis model based on joint explicit and implicit attribute transfer

For fault diagnosis of industrial processes, due to the complexity of working conditions and the uncertainty of abnormality, it is difficult to obtain all types of fault samples of target working conditions. To address this issue, a zero-sample industrial process fault diagnosis model based on joint explicit and implicit attribute transfer (ZS-JEIAT) is proposed, which using partial known fault samples to identify otherwise unknown faults. Firstly, we define the fault attribute space based on fault knowledge, and establish the causal relationship between attributes and faults. Next, considering some problems that the model will encounter in complex industrial environments, we divide the attribute space into explicit and implicit attribute spaces by feasibility of attribute transfer. We judge these two spaces and according to the causal relationship between faults and attributes to realize the zero-sample fault diagnosis. Finally, the effectiveness of the proposed method is verified using an actual industrial process.

A Simple Framework to Generalized Zero-Shot Learning for Fault Diagnosis of Industrial Processes

Dear Editor, This letter provides a simple framework to generalized zero-shot learning for fault diagnosis. For industrial process monitoring, supervised learning and zero-shot learning (ZSL) can only deal with seen and unseen faults, respectively. However, in the online monitoring stage of the actual industrial process, both seen and unseen faults may occur. This makes supervised learning and zero-shot learning impractical in industrial process monitoring. Generalized zero-shot learning (GZSL) can handle this problem, but its implementation process is too complicated. This letter introduces GZSL into industrial process fault diagnosis, and a simple end-to-end framework is provided to implement GZSL-based fault diagnosis. In this framework, GZSL-based fault diagnosis can be realized by using only a binary classification algorithm. Experimental results show that the proposed framework can accomplish this challenging task of GZSL for fault diagnosis.

Gated recurrent unit-enhanced deep convolutional neural network for real-time industrial process fault diagnosis

When deep learning-based models are employed for the fault diagnosis of chemical processes, problems of poor calculation accuracy and efficiency often occur in the scenarios of high-dimensional, nonlinear, and time-varying data, which affects the overall robustness of the fault diagnosis model. This study proposes a novel Gated Recurrent Unit (GRU) - enhanced deep convolutional neural network (EDCNN) model for the improved fault detection and diagnosis of chemical processes. In the GRU-EDCNN model, a maximum smooth function (MSF) is developed and presented to replace the classical activation function for better matching the input data format, which can significantly improve the calculation accuracy and the overall efficiency of DCNN models. Moreover, the convolutional layers in DCNN are optimized by a decentralized convolutional structure, thereby reducing the problem of parameter redundancy. The issue of gradient disappearance is tackled by the embedment of GRU, whose ability to control time series features and gateway information can ensure that no overfitting occurs in the GRU-EDCNN training processes. In two case studies, the GRU-EDCNN model was applied to the benchmark Tennessee Eastman (TE) process and an acid gas absorption process, and the corresponding data of fault diagnosis rate (FDR), false positive rate (FPR), and fault diagnosis time (FDT) of the GRU-EDCNN model were analyzed and compared with those of the other deep learning-based models, verifying the effectiveness of the GRU-EDCNN model for fault diagnosis in both simulated and real-time industrial processes.

Farthest-Nearest Distance Neighborhood and Locality Projections Integrated With Bootstrap for Industrial Process Fault Diagnosis

It has become a big challenge and a hot topic of research to capture the most relevant features from high-dimensional process data for enhancing fault diagnosis. To effectively extract discriminative features from high-dimensional data, a novel dimensionality reduction (DR) approach named neighborhood and locality projections with the farthest and nearest distance (FNDNLP) is first proposed for industrial process fault feature acquisition and diagnosis. By constructing intra-class weights and inter-class weights, FNDNLP takes both the intra-class distance and the inter-class distance into consideration in its objective function, improving the diagnostic ability of extracted features through maximizing the inter-class distance and minimizing the intra-class distance. In addition, bootstrap based FNDNLP (BFNDNLP) is further proposed to handle the matrix decomposition problem in FNDNLP. To find the proper order through DR, the Akaike information criterion (AIC) is adopted. Finally, the Naïve Bayes (NB) based classifier is utilized to achieve acceptable fault diagnosis. The simulation results from two complex industrial cases indicate that the proposed methodology can achieve higher diagnosis accuracy than other related methods. What's more, the DR features are further analyzed to show the effectiveness and benefits of the proposed BFNDNLP extraction approach. The main source code of this paper can be obtained on GitHub soon.