Process Fault Research Articles

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

With the development of technology, industrial monitoring systems can collect not only process data but also video data. Considering the temporal characteristics of video data as well as the correlation and inconsistency between video and process data, and in order to further improve the accuracy of industrial process fault diagnosis, a fault diagnosis method based on video recognition and multi-source heterogeneous information fusion is proposed. In this method, a Visual Geometry Group (VGG) using Adaptive Parameter Rectified Linear Unit (APReLU) embedded Video Vision Transformer (ViViT) is designed firstly to extract the information change of video. It uses the VGG to extract the local information, the Spatial Transformer Encoder to extract global information, and the Temporal Transformer Encoder to extract the temporal features of the sequential video frames. Then one-dimensional Residual Network (ResNet) is adopted to handle the correlated process variables. Since video data and process data reflect different information of industrial processes, Highway Network is used to process the concatenated fusion features of the video data and process data. The Highway Network can assign larger weights to important components, and smaller weights to unimportant components. Experiments show that the accuracy of industrial process fault diagnosis based on video recognition and multi-source data is greater than that based on single-source data.

Interfacial charge and temperature analysis of gate-all-around line tunneling TFET for improved device reliability

In this article, the impact of interface-trap charges (ITCs) on the DC and analog/RF parameters of gate-all-around vertical TFET (GAA-VTFET) are considered to evaluate the reliability of the device. ITCs are included at oxide/semiconductor interface of GAA-VTFET where the probability of occurrence of traps are high owing to faults in the manufacturing process. A detailed investigation is carried out by tuning the temperature, polarities and density of ITCs. It is clearly observed from TCAD based simulation results that the presence of traps alters the flat-band voltage, thereby affecting the overall performance of the device. Transfer characteristics of the device depicts that impact of traps shows more variation in the OFF-state current than the ON-current. However, presence of donor traps improves the analog/RF parameter, such as parasitic capacitances (Cgg), Transconductance (gm), cut-off frequency (fT), output resistance (Rout) etc. Furthermore, the simulation results proclaim that GAA-VTFET shows more resilient to acceptor traps than the positive traps. Moreover, by examining the influence of ambient temperature on device performance, it is revealed that the drain current in the subthreshold region (at low gate bias) is more susceptible to the degradation than the super-threshold region at elevated temperature. This is mainly due to the superiority of the trap-assisted tunneling (TAT) and Shockley-Read-Hall (SRH) recombination mechanisms over the band-to-band tunneling (BTBT). When the raise in ambient temperature is tuned between minimum of 200 K to maximum of 400 K, it is observed that OFF-current increases by ∼7 times. Lastly, voltage-transfer characteristics (VTC) analysis of the resistive-load inverter clearly demonstrates that the influence of traps on the noise margin is within acceptable limits.

An Order-Invariant and Interpretable Dilated Convolution Neural Network for Chemical Process Fault Detection and Diagnosis

An Order-Invariant and Interpretable Dilated Convolution Neural Network for Chemical Process Fault Detection and Diagnosis

Exploring the effects of faults on the performance of a biological wastewater treatment process

ABSTRACT To prioritise which faults should be detected in a biological wastewater treatment process, and with what level of urgency, it is necessary to understand the effect that they have on the process. Using the Benchmark Simulation Model No. 1 and 2. (BSM1 and BSM2), several process and sensor faults were considered and their impacts on various cost, quality, and controller performance evaluation metrics analysed. Both the cost of treating the wastewater and the quality of the effluent were impacted in varying degrees of severity by the faults tested. The most influential faults in both models were decreases to autotrophic and heterotrophic growth rates, decreases to the heterotrophic death rate, and the inhabitation fault. It was shown that only larger fault sizes were significant, and the required speed of detection is dependent on the fault profile. Prioritising detection of the most influential faults was shown to have significant effects on monitoring requirements for fault detection and the subsequent complexity required of a fault detection system. A valuable takeaway was the similarity of results from BSM1 and BSM2; the consistency of the influential process faults suggests that systems that can be described by these models are likely affected by the same faults.

A residual autoencoder-based transformer for fault detection of multivariate processes

The complexity of high-dimensional and noisy process signals reduces the effectiveness of conventional fault detection methods in industrial processes. Based on the hypothesis that data collected from normal and faulty processes has different characteristics, unsupervised deep neural networks, e.g., autoencoders, have been widely applied in process fault detection and achieved good performance. Many variants have been proposed to improve feature learning by combining different network structures. In this paper, a new transformer model, residual autoencoder-based transformer, is proposed for process fault detection. Firstly, autoencoder and transformer are integrated for better unsupervised feature learning of process signals. Secondly, linear embedding and attention mechanisms with bias are proposed to generate effective features from process signals. Finally, residual connections are constructed between the encoder and decoder of RATransformer to address overfitting in training. Four industrial cases are used to test the performance of RATransformer for process fault detection. The results show that the fault detection rate of RATransformer is at least 1 % higher than other comparison methods. Moreover, the testing results show that the model structure improves the fault detection performance of RATransformer. The complex models like RATransformer can be used in the industrial process when sufficient normal process data is available. An end-to-end training method can be further developed to improve the applicability of RATransformer in process fault detection in the future.

A novel Transformer-based model with large kernel temporal convolution for chemical process fault detection

Fault detection and diagnosis (FDD) is an essential tool to ensure safety in chemical industries, and nowadays, many reconstruction-based deep learning methods are active in fault detection. However, many algorithms still suffer from not ideal actual performance. Inspired by the core mechanism of Transformer and large kernel convolution, this paper proposes a novel model combining variate-centric Transformer with large kernel temporal convolution. Variate-centric Transformer depends on self-attention to capture the multivariate correlations of input data, and large kernel temporal convolution collects period information to summarize temporal features. A benchmark dataset Tennessee Eastman process (TEP) and experiment data from the microreactor process are used to test the performance of fault detection. Compared with other reconstruction-based methods, results demonstrate that our model achieves a higher fault detection rate and a lower detection latency, and shows a significant potential for process safety.

Chemical process fault detection and trend analysis based on KESN

AbstractFault detection has great significance for chemical process safety with the development of science and technology. The conventional echo state network‐based fault detection method does not highlight key fault features, and cannot forecast future fault trend after the occurrence of faults. For the above problems, a chemical process fault detection and trend analysis strategy based on key feature enhanced echo state network (KESN) is proposed. First, dynamic features are extracted by a detecting echo state network. Then, a weighting strategy is designed to enhance key features and increase fault detection rates. After detecting a fault, independent component analysis is utilized to extract independent key features. Future fault trend is forecasted based on the forecasting multi‐KESN. Simulation results on the Tennessee Eastman process demonstrate the effectiveness of the proposed method.

Деструктивные явления при некачественном прогреве монолитных железобетонных конструкций

The growth of the number of the building floors inevitably leads to an increase in the construction period and, consequently, to the need for monolithic reinforced concrete structures in winter. Electric heating by means of heating cables is the most widespread method of concrete curing in winter conditions in the Central region of Russia. The risk of defects in monolithic reinforced concrete structures increases under certain conditions. This risk is related to various types of technological process faults. The main types of monolithic structures defects have been repeatedly described. But there are practically no papers describing the types and causes of defects associated with failures during electric heating of concrete. The author has developed a block diagram of the main defects, and the main reasons for their occurrence have been identified. The paper summarizes the experience gained during two winter periods at the construction sites of Moscow city belonging to unique buildings and structures. Operational and quality inspection of the construction was performed. The author identified groups of defect causes: cable installation and installation errors; heating regime errors. The author identified specific types of defects for each group, and also gave recommendations on their avoidance in the future. The paper provides a ‘check list’ of parameters that must be checked during electric heating with heating cables. The checklist shows the control points that minimize the risk of defects.

Fault Detection of Urban Wastewater Treatment Process Based on Combination of Deep Information and Transformer Network.

As one of the hot issues of concerns during modern social development, the wastewater treatment process is acknowledged to be a process with complex biochemical reactions and susceptible to an external environment, featuring strong nonlinear and time correlation characteristics, which are difficult for traditional mechanism-based models to tackle. For many classical data-driven fault detection methods, a complete retraining process is necessary to monitor every new fault, and most of the current neural network-based strategies rarely achieve satisfactory monitoring accuracy or robustness either. Giving full consideration to the aforementioned problems, this article takes advantage of position encoding, residual connection, and multihead attention mechanism embedded in the Transformer structure to establish an effective and efficient wastewater treatment process fault detection model, where offline modeling and online monitoring are performed successively to achieve accurate detection of the faults. In the experimental part, the advantages of the proposed method are strongly verified through the simulation monitoring of 27 faults on the benchmark simulation model 1 (BSM1), where the false alarm rate (FAR) and miss alarm rate (MAR) of the established method are proved to be significantly lower than those of the compared state-of-the-art methods.

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.

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.

Reconstruction and normalization of LISA for spatial analysis.

The local indicators of spatial association (LISA) are important measures for spatial autocorrelation analysis. However, there is an inadvertent fault in the mathematical processes of deriving LISA in literature so that the local Moran and Geary indicators do not satisfy the second basic requirement for LISA: the sum of the local indicators is proportional to a global indicator. This paper aims at reconstructing the calculation formulae of the local Moran indexes and Geary coefficients through mathematical derivation and empirical evidence. Two sets of LISAs were clarified by new mathematical reasoning. One set of LISAs is based on non-normalized weights and non-centralized variable (MI1 and GC1), and the other set is based on row normalized weights and standardized variable (MI2 and GC2). The results show that the first set of LISAs satisfy the above-mentioned second requirement, but the second the set cannot. Then, the third set of LISA was proposed and can be treated as canonical forms (MI3 and GC3). This set of LISAs satisfies the second requirement. The observational data of city population and traffic mileage in Beijing-Tianjin-Hebei region of China were employed to verify the theoretical results. This study helps to clarify the misunderstandings about LISAs in the field of geospatial analysis.

Sparse deep encoded features with enhanced sinogramic red deer optimization for fault inspection in wafer maps

AbstractDue to the complexity and dynamics of the semiconductor manufacturing processes, wafer bin maps (WBM) present various defect patterns caused by various process faults. The defect type detection on wafer maps provides information about the process and equipment in which the defect occurred. Recently, automatic inspection has played a vital role in meeting the high-throughput demand, especially with deep convolutional neural networks (DCNN) which shows promising efficiency. At the same time, the need for a large amount of labeled and balanced datasets limits the performance of such approaches. In addition, complex DCNN in recognition tasks can provide redundant features that cause overfitting and reduce interpretability. In this paper, a new hybrid deep model for wafer map fault detection to get over these challenges is proposed. Firstly, a new convolutional autoencoder (CAE) is employed as a synthetization model to fix the high imbalance problem of the dataset. Secondly, for efficient dimensionality reduction, an embedding procedure is applied to the synthesized maps to get sparse encoded wafer maps by reinforcing a sparsity regularization in an encoder-decoder network to form a sparsity-boosted autoencoder (SBAE). The sparse embedding of wafer maps guarantees more discriminative features with 50% reduction in spatial size compared to the original wafer maps. Then, the 2D encoded sparse maps are converted to 1D sinograms to be fed later into another aggressive feature reduction stage using a new modified red deer algorithm with a new tinkering strategy. The resultant feature pool is reduced to ~ 25 1D feature bases, i.e., ~ 1.5% of the initial size of the 2D wafer maps. Finally, for the prediction stage, a simple 1DCNN model is introduced. The proposed inspection model is tested via different experiments on real-world wafer map dataset (WM-811K). Compared to state-of-the-art techniques, the proposed model outperforms their performance even with small-sized 1D feature pool. The average testing accuracy are 98.77% and 98.8% for 9 and 8 types of faults, respectively.

Toward sustainable process industry based on knowledge graph: a case study of papermaking process fault diagnosis

Process industry suffers from production management in terms of efficiency promotion and waste reduction in large scale manufacturing due to poor organization of the intricate relational databases. In order to enhance the suitability of intelligent manufacturing systems in process industry, this study proposed an innovative top-down structure Knowledge Graph (KG) for process fault diagnosis, and papermaking was taken as a case study. The KG consists of a normalized seven-step-built ontology, which extracted instances of papermaking knowledge via Protégé software. The exported OWL file was imported into Neo4j software for visualization of the KG. The application in papermaking drying process for fault diagnosis shows that it can depict the material and energy flows throughout the process with a clearer relationship visualization than traditional measures. They also enable rationale search for faults and identification of their potential causes. The built KG efficiently manages the vast knowledge of the process, stores unstructured data, and promotes the intelligent development of process with high reusability and dynamicity that can rapidly import new production knowledge as well as flexibly self-updating.

Multirate Nonlinear Process Fault Detection Based on Multiscale Hierarchical Variational Autoencoder

Multirate Nonlinear Process Fault Detection Based on Multiscale Hierarchical Variational Autoencoder

A novel decoupling method of compound faults with incomplete dataset of rotating machinery

Abstract The occurrence of fault in rotating machinery is random and complex, and the diagnosis of the compound faults has been a challenge in industrial production. Accurate diagnosis of the compound faults can be of significant help to practical maintenance and management. However, most existing intelligent diagnostic methods typically require abundant data for training, which is often difficult to collect for compound faults. In this paper, a novel method called impact feature-based decoupling capsule network (IFDCN) is proposed for diagnosing compound faults with incomplete datasets. In this model, an improved Laplace wavelet kernel capsule neural network is proposed to extract and enhance the impact features of vibration signal. A decoupling classifier is designed to decouple the compound faults in the diagnostic process so as to identify the sub-faults contained in the compound faults. In using this proposed model for incomplete datasets, the compound fault data is not trained and is not labeled. Through training on single-fault data, the proposed model is capable of classifying and decoupling the fault types. The feature extraction capability of the network is visualized by heat maps, and the physical significance of feature extraction is explained by deep learning network. The effectiveness of IFDCN is verified through different experimental of gear and bearing and the experiment results indicate that the proposed model has higher identifying precision and can accurately decouple the compound faults without compound fault samples.

Chemical fault diagnosis network based on single domain generalization

Recent developments in fault diagnosis have leveraged domain generalization to address the issue of domain shift. Most existing methods focus on learning domain-invariant representations from multiple source domains. However, collecting valuable fault samples from varying operational conditions is challenging, and it is common for available data to originate from a single operational condition. Thus, this paper introduces a Multi-scale generative and adversarial Metric networks (MGAMN) for Chemical Process Fault Diagnosis. To enhance model generalization, a domain generation module was developed to create augmented domains with significant distributional differences from the source domain. The diagnostic task module then extracts domain-invariant features from both the source and augmented domains. A multi-scale generation strategy is established, utilizing multi-scale deep separable convolutions (Dsc) to ensure that the generated samples contain rich state information. Additionally, an adversarial training and metric learning strategy is designed to learn generalized features capable of resisting unknown domain shifts. Extensive diagnostic experiments on the non-isothermal continuous stirred tank reactor (CSTR) and the Tennessee Eastman Process (TEP) chemical datasets validate the effectiveness of the proposed method. Moreover, ablation studies confirm the effectiveness of the proposed modular strategy, demonstrating significant potential for practical applications.

An adaptive strategy for time‐varying batch process fault prediction based on stochastic configuration network

AbstractFault prediction ensures safe and stable production, and cuts maintenance costs. Due to the changing operating conditions that lead to the changes in the characteristics of industrial processes, there is a need to monitor the fault state of batch processes in real‐time and to accurately predict fault trends. An adaptive slow feature analysis‐neighborhood preserving embedding‐improved stochastic configuration network (SFA‐NPE‐ISCN) algorithm for batch process fault prediction is proposed. Firstly, SFA is used to extract the time‐varying features of process data and establish the update index of the NPE model. Then, to extract local nearest‐neighbor features and reconstruct them by the NPE model with adaptive update capability, square prediction error (SPE) statistics are constructed as fault state features based on the reconstructed error. Further, the hunter‐prey optimization (HPO) algorithm optimizes the weights and biases in the stochastic configuration network, and the singular value decomposition (SVD) and QR decomposition of column rotation are introduced to solve the ill‐posed problem of SCN and obtain the prediction model of ISCN. Finally, the obtained statistics SPE is formed into a time series, and the ISCN model is used to predict the process state trend. The effectiveness of the proposed algorithm is verified by case studies of industrial‐scale penicillin fermentation processes and the Hot strip mill process.

ANFIS and Takagi–Sugeno interval observers for fault diagnosis in bioprocess system

This paper develops a data-driven approach for incipient fault diagnosis based on ANFIS and Takagi–Sugeno (TS) interval observers. First, the nonlinear bioreactor system is identified using an adaptive neuro-fuzzy inference system (ANFIS), which results in a set of polytopic TS models derived from measurement data. Second, a bank of TS interval observers is deployed to detect sensor and process faults using adaptive thresholds. Unlike other works that require training fault data, only fault-free data is considered for ANFIS learning in this work. Fault insolation is based on residual generation and evaluated on a fault signal matrix (FSM). Parametric uncertainty and measurement noise are considered to guarantee the method’s robustness. The effectiveness of the proposed method is tested on a well-known bioreactor Continuous stirred tank reactor system (CSTR) reference simulator.

Optimized data driven fault detection and diagnosis in chemical processes

Fault detection and diagnosis (FDD) is crucial for ensuring process safety and product quality in the chemical industry. Despite the large amounts of process data recorded and stored in chemical plants, most of them are not well-labeled, and their conditions are not adequately specified. In this study, an optimized data-driven FDD model was developed for a chemical process based on automatic clustering algorithms. Due to data preprocessing importance, feature selection was performed by a non-dominated sorting genetic algorithm (NSGAII) based on k-means clustering. The optimal subset of features is selected by comparing clustering results for each subset. The performance of the proposed feature selection method was compared with the Fisher discriminant ratio (FDR), and XGBoost methods. The t-distributed stochastic neighbor embedding (t-SNE), Isomap, and KPCA dimension reduction methods were also employed for feature extraction. Finally, automatic clustering was performed based on metaheuristic algorithms for fault detection and diagnosis. Results were compared with non-automatic clustering methods. The performance of the proposed method was evaluated by examining the Tennessee Eastman and four water tank processes as case studies. The results showed that the proposed method is reliable and capable of online and offline chemical process fault detection and diagnosis. As a result, the findings of this study can be used to stabilize the operation of chemical processes.