Plant-wide Process Monitoring Research Articles

Knowledge-Enhanced Distributed Graph Autoencoder for Multiunit Industrial Plant-Wide Process Monitoring

In multiunit industrial plant-wide processes (MIPPs), data-driven distributed process monitoring methods have played an important role in ensuring process safety and reliability. However, the existing studies fail to leverage the relational knowledge about the underlying process structure of MIPPs, which may lead to inaccurate process modeling and degradation of the monitoring performance. To tackle these issues, this work proposes a novel knowledge-enhanced distributed graph autoencoder (KDGAE) for plant-wide process monitoring. Firstly, a posterior graph structure learning module (PGSL) is designed for relational knowledge discovery, which explicitly characterizes the dependencies between operation units in MIPPs into a directed graph. Prior knowledge is introduced into PGSL as a learning bias that steers the posterior graph to adhere to the underlying physics. Then, a novel distributed graph autoencoder (DGAE) is developed to encode both the local information within each unit and the global information between units for distributed process monitoring. The discovered posterior knowledge is embedded as a relational inductive bias in DGAE to enhance the capability of unsupervised representation learning, thereby improving the monitoring performance. Finally, the effectiveness of the proposed method is demonstrated through the Tennessee Eastman process and a real-world air separation process.

A Novel Distributed CVRAE-Based Spatio-Temporal Process Monitoring Method With Its Application

Due to the interconnected characteristics between subsystems and the strong correlation within subsystems, the monitoring of plant-wide processes has become a challenging problem, especially for tandem plant-wide processes that exist in various industrial fields, such as petrochemicals, metallurgy and sewage treatment. In this paper, a novel spatio-temporal monitoring method is proposed for the hot strip mill process, a typical tandem industrial process. Firstly, the plant-wide process is divided into different sub-blocks based on the tandem structure. Then, a distributed conditional variational recurrent autoencoder (CVRAE)-based process monitoring method is proposed to build the local latent variable model of each subsystem using relevant dynamic features extracted from the previous subsystem. The latent distributions and reconstructed errors are used to design local monitoring statistics for local process monitoring. A global monitoring statistic is established by deep support vector data description (SVDD) to monitor the whole process. Finally, the effectiveness and superiority of the proposed method are demonstrated by a hot strip mill (HSM) process case, which shows better monitoring performance compared to the existing methods.

A Distributed Adaptive Monitoring Method for Performance Indicator in Large-Scale Dynamic Process

The dynamic time-varying characteristic has brought great challenges to the plant-wide process monitoring. In this paper, a distributed adaptive principal component regression algorithm is proposed for the online indicator monitoring of large-scale dynamic process. Firstly, the distributed data subblocks are constructed according to the process operation units. In each subblock, an adaptive re-sampling method based on the subblock data and plant-wide data is presented to construct the modeling sample sets, which can extract the process local and global information simultaneously. Afterwards, the indicator-related feature is extracted, and the Bayesian method is used to integrate the subblock monitoring results. Through the collaborative monitoring of the process local and global feature spaces, a refined monitoring decision can be obtained. Finally, a numerical example and Tennessee Eastman process are used to illustrate the effectiveness of the proposed method.

Association Hierarchical Representation Learning for Plant-Wide Process Monitoring by Using Multilevel Knowledge Graph

In order to satisfy safety requirements of plant-wide processes, distributed process monitoring methods are often used. However, few of them consider the problem on building multi-level knowledge blocks and the associations between different blocks, all of which are beneficial for plant-wide process monitoring in avoiding information conflict and even to improve monitoring accuracy. To handle these issues, a plant-wide process monitoring method is proposed, which is based on hierarchical graph representation learning with differentiable pooling by using multi-level knowledge graph (MLKG). Specifically, MLKG consists of devices level, subprocess level, process level, etc. Each level has numerous blocks (nodes) which is firstly constructed by priori-knowledge on monitoring variables to calculate the status of key components, such as the Hotelling's statistics. And then normalized mutual information (NMI) is used to obtain the associations between monitoring variables, and the status of each block on each level can be updated. Based on this method, MLKG can be completely constructed. In order to consider the association information of hierarchical representations of MLKG, the hierarchical graph representation learning is used to achieve plant-wide process monitoring. Results of case study on practical cobalt and nickel removal from zinc solution demonstrate the effectiveness and applicability of this method.

Industrial Process Monitoring Based on Parallel Global-Local Preserving Projection with Mutual Information

This paper proposes a parallel monitoring method for plant-wide processes by integrating mutual information and Bayesian inference into a global-local preserving projections (GLPP)-based multi-block framework. Unlike traditional multivariate statistic process monitoring (MSPM) methods, the proposed MI-PGLPP method transforms plant-wide monitoring into several sub-block monitoringtasks by fully taking advantage of a parallel distributed framework. First, the original datasets of the process are divided into a group of data blocks by quantifying the mutual information of process variables. The block indexes of new data are generated automatically. Second, each data block is modeled by the GLPP method. The variable information and local structure are well preserved during the whole projection. Third, Bayesian inference is introduced to generate final statistics of the process by the probability framework. To illustrate the algorithm performance, a detailed case study is performed on the Tennessee Eastman process. Compared with the principle component analysis and GLPP-based method, the proposed MI-PGLPP provides higher FDRs and superior performance for plant-wide process monitoring.

Multi-block dynamic weighted principal component regression strategy for dynamic plant-wide process monitoring

To properly monitor dynamic large-scale processes, a new distributed dynamic process monitoring strategy named multi-block dynamic weighted principal component regression (DWPCR) is developed in this paper. Because complex plant-wide processes have multiple operation units and complex correlations among variables, traditional global process monitoring models may suppress local fault information and fail to identify incipient faults and local faults for large-scale processes. Besides, product quality determines the economic benefits of the enterprise. Motivated by these problems, this work studies the distributed quality monitoring strategy. At first, the idea of community partition in complex networks is used for multiple subblock division for a large number of process variables in this new monitoring framework. Then, the monitoring model for each subblock is established by the proposed DWPCR approach. Moreover, a novel weighting key components strategy based on fault information is proposed to monitor the process. Finally, the comprehensive monitoring result is fused by Bayesian inference. The superiority of the proposed distributed DWPCR strategy is testified in the case study.

Performance Supervised Plant-Wide Process Monitoring in Industry 4.0: A Roadmap

The intensive research and development efforts directed towards large-scale complex industrial systems in the context of Industry 4.0 indicate that safety and reliability issues pose significant challenges. During online operation, system performance degradation will lead, not only to economic losses, but also potential safety hazards. In the existing research and technical routes, the target of the fault diagnosis systems is to trigger alarms to report the fact of the existence of malfunctions as well as the underlying reasons accurately. However, it remains unanswered how urgent it is to fix it, and what degrees of fault-tolerance, maintenance, and fault recovery are needed. Further analyses are necessary to evaluate the impact of the detected fault on the plant-wide performance. In this article, to enable a more comprehensive and precise description of the plant-wide operational status, the roles of the commonly used performance metrics, the state-of-the-art performance evaluation approaches, as well as the performance-oriented and plant-wide process monitoring techniques are investigated. On this basis, an alternative straightforward technical route, embedded in the cyber-physical-social system framework is proposed. A roadmap including the key research questions, the future research directions, and an outlook about the future vision is presented.

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.

Data preprocessing for multiblock modelling – A systematization with new methods

With the advance of Industry 4.0, new data collectors are appearing at different points of the process generating blocks of data whose integrity should be preserved during data analysis. This is the scope of multiblock methods, whose potential has been recognized in several areas of application where they are becoming increasingly popular. Multiblock methods can be applied to a wide range of data-driven problems that practitioners face nowadays such as plant-wide process monitoring and diagnosis, process optimization and quality prediction of key product properties. These methods have the ability to find associations and interpretative connections between different data blocks from different sources and carrying complementary or overlapping information, as well as assessing the blocks’ relative contributions to the final outcome. A critical stage in the application of multiblock methods is the selection of the appropriate preprocessing to apply to each block, before proceeding to the modelling. The preprocessing strategy can exponentiate the information extracted from the blocks and their mutual interactions or hide/mask/distort them if inappropriately done. In this article, we present a systematic workflow where both the intra-block and inter-block variation components are considered during preprocessing. We illustrate the application of the framework using two real case studies where a critical comparison is presented for the different preprocessing alternatives.

Mutual information-based sparse multiblock dissimilarity method for incipient fault detection and diagnosis in plant-wide process

Multiblock methods have attracted much attention in monitoring of plant-wide processes. However, most recent works only provide rough division results and do not take the data distribution changes among the process into consideration. To solve these defects, a new multiblock monitoring scheme that integrates a mutual information (MI)-based sparsification method, dissimilarity analysis (DISSIM) method and support vector data description (SVDD) is proposed in this paper. This method makes use of the complex relations between variables and the connections between sub-blocks in process decomposition to produce easy-to-interpret sub-blocks related to the process mechanism. Then DISSIM method is applied in each sub-block for distribution monitoring. The multiblock DISSIM strategy can deal with the local behaviors and distribution changes, improving its sensitivity to incipient changes in plant-wide process. Finally, results in all blocks are combined with SVDD to provide a final decision, and a diagnosis method is proposed for fault diagnosis. Case studies upon a numerical case and Tennessee Eastman (TE) benchmark process demonstrate the effectiveness of our method.

Plant-wide process monitoring by using weighted copula–correlation based multiblock principal component analysis approach and online-horizon Bayesian method

Multiblock methods have been proposed to capture the complex characteristics of plant-wide monitoring due to the enlargement of process industries. These methods based on automatic sub-block division and copula–correlation, which simultaneously describe the correlation degree and correlation patterns, are designed for sub-block partition. However, the selection of variables for each sub-block through copula–correlation analysis requires a pre-defined cutoff parameter which is difficult to be determined without sufficient prior knowledge, and a “bad” parameter leads to a degraded performance. Therefore, a weighted copula-correlation-based multiblock principal component analysis (WCMBPCA) is proposed. First, the variables in each sub-block are obtained through the copula–correlation analysis-based weighted strategy rather than the cutoff parameter, which highly avoids information loss and prevents “noisy” information. Second, a PCA model is established in each sub-block. Third, a Bayesian inference strategy is used to merge the monitoring results of all sub-blocks. Finally, an online-horizon Bayesian fault diagnosis system is established to identify the fault type of the system based on the statistics of each sub-block. The average detection rate and the average diagnosis rate for numerical example are 77.85% and 98.95%, and that for TE example are 80.63% and 89.50%. Comparing with other candidate methods, the proposed method achieves excellent detection and diagnostic performance.

Review and Perspectives of Data-Driven Distributed Monitoring for Industrial Plant-Wide Processes

Process monitoring is crucial for maintaining favorable operating conditions and has received considerable attention in previous decades. Currently, a plant-wide process generally consists of multiple operational units and a large number of measured variables. The correlation among the variables and units is complex and results in the imperative but challenging monitoring of such plant-wide processes. With the rapid advancement of industrial sensing techniques, process data with meaningful process information are collected. Data-driven multivariate statistical plant-wide process monitoring (DMSPPM) has become popular. The key idea of DMSPPM is first decomposing a plant-wide process into multiple subprocesses and then establishing a data-driven model for monitoring the process, in which process variable decomposition is important for guaranteeing the monitoring performance. In the current review, we first introduce the basics of multivariate statistical process monitoring and highlight the necessity of des...

Process monitoring based on distributed principal component analysis with angle-relevant variable selection

Multivariate statistics process monitoring can achieve dimensionality reduction and latent feature extraction on process variables. However, process variables without beneficial information may affect the monitoring performance. This article proposes a distributed principal component analysis method based on the angle-relevant variable selection for plant-wide process monitoring. The directions of principal components are utilized to construct the sub-blocks, where the variables in each sub-block are determined by angle. After establishing the principal component analysis model in each sub-block, the monitoring results are fused by Bayesian inference. The simulation results show that the proposed method can select the responsible variables effectively and enhance the monitoring performance.

A Distributed Canonical Correlation Analysis-Based Fault Detection Method for Plant-Wide Process Monitoring

In this paper, a new data-driven fault detection method based on distributed canonical correlation analysis (D-CCA) is proposed to address the plant-wide process monitoring problem. This paper focuses on the distributed plant-wide processes. The core of the proposed method is to reduce uncertainties using correlation information from the neighboring nodes. Furthermore, the cost of the data transmission between network nodes is also reduced by the D-CCA algorithm. When the proposed method and the existing methods are compared using the Tennessee Eastman benchmark process, the false alarm rate, fault detection rate, and the detection delay are comparable. This suggests that the proposed method is feasible.

A novel plant-wide process monitoring framework based on distributed Gap-SVDD with adaptive radius

With the increasing complexity of modern process industries, plant-wide process monitoring has become a challenging issue. In this paper, a novel monitoring framework based on distributed gap support vector data description (Gap-SVDD) with adaptive radius is proposed for plant-wide processes. Firstly, the plant-wide processes are divided into different subblocks by the mixed similarity measure for handling the heavy coupling process variables. Afterwards, gap metric is introduced as a kind of data preprocessing method, which is combined with SVDD to set up the monitoring model. The feature extraction of Gap-SVDD is more accurate than conventional methods. Finally, an adaptive radius is developed for Gap-SVDD. It is calculated by a modified univariate statistical method with a limited window length. The purpose of this strategy is to enhance the performance of Gap-SVDD. The superiority of the proposed framework is demonstrated by the revised Tennessee Eastman (TE) benchmark. Comparisons with other conventional methods are also provided.

Deep Discriminative Representation Learning for Nonlinear Process Fault Detection

Nonlinear process fault detection remains a challenge, with representation learning being a key step. In this article, a deep neural network (DNN)-based discriminative representation learning approach is proposed to achieve efficient fault detection for nonlinear plant-wide processes. An early-stage fault rarely affects several independent variables concurrently; hence, mutual information-based block division and randomized fault construction are performed to generate faulty validation data. By using the training data from the normal operation training data and the constructed validation data, a DNN with stacked autoencoders and a softmax classifier is trained to generate discriminative representations that maximize the capability of discriminating normal and abnormal statuses. Finally, on the basis of the learned deep discriminative representations, support vector data description is employed to discriminate the normal and abnormal process statuses. The proposed monitoring approach is tested on a numerical example and an industrial tail-gas treatment process, through which the efficiency is verified. Note to Practitioners —A modern process is generally characterized by a large scale and complex nonlinear correlation, and monitoring of such nonlinear plant-wide processes is imperative. Nowadays, a large amount of process data is generally available, and deep neural network-based monitoring is promising in dealing with such data on nonlinear processes. This article proposes a deep discriminative representation learning method for efficient nonlinear plant-wide process monitoring. The key idea is to first decompose a large-scale process into multiple units according to a variable relationship, and then generate faulty validation data based on randomized fault construction. Then, deep discriminative representations are learned by optimizing a stacked autoencoder-based deep neural network (DNN). This article provides guidelines for designing an efficient monitoring algorithm for plant-wide nonlinear processes in the industrial big data environment.

Distributed Gaussian mixture model for monitoring plant-wide processes with multiple operating modes

For large-scale plant-wide processes with multiple operating conditions, a distributed Gaussian mixture modeling and monitoring mechanism is proposed. To overcome the deficient prior modeling knowledge for complex process, a two-dimensional probabilistic topic model based technique named Bayesian co-clustering method is developed to simultaneously conduct the sub-block division and operating mode recognition. With the obtained sub-blocks and operating modes, a global Gaussian mixture model is first built and then several local Gaussian mixture models are extracted and applied for distributed monitoring of plant-wide processes. By conducting distributed modeling and monitoring, both global and local process changes can be reflected and the fault region can be localized more easily for further analyses. The feasibility and effectiveness of the proposed method is confirmed through a numerical example and the Tennessee Eastman benchmark process.

Relevant and independent multi-block approach for plant-wide process and quality-related monitoring based on KPCA and SVDD

Due to prior knowledge being often unavailable in practice, a multi-block strategy totally based on data-driven analytics is an appropriate alternative for plant-wide processes. However, most recent multi-block methods are relatively vague or insufficient for dividing up the process space and lack the comprehensive fault information for quality-related monitoring. This work intends to develop a more reasonable multi-block method and demonstrate the negative impacts of quality-unrelated variables. Both motivations are entirely dependent on the correlation between variables. A major innovation is to determine those independent or related sets of variables, and to provide a more precise indication for those quality-related faults. Sub-blocks with related variables are each modeled by the KPCA, and the rest of the independent variables are treated as an input for a SVDD model. Finally, all of the statistical indicators are aggregated into a single statistic through Bayesian inference. The benefits of the proposed multi-block scheme (MKPCA-SVDD) are elaborated on in detail using numerical simulation, TE benchmark and industrial p-xylene oxidation process.

Distributed Parallel PCA for Modeling and Monitoring of Large-Scale Plant-Wide Processes With Big Data

In order to deal with the modeling and monitoring issue of large-scale industrial processes with big data, a distributed and parallel designed principal component analysis approach is proposed. To handle the high-dimensional process variables, the large-scale process is first decomposed into distributed blocks with a priori process knowledge. Afterward, in order to solve the modeling issue with large-scale data chunks in each block, a distributed and parallel data processing strategy is proposed based on the framework of MapReduce and then principal components are further extracted for each distributed block. With all these steps, statistical modeling of large-scale processes with big data can be established. Finally, a systematic fault detection and isolation scheme is designed so that the whole large-scale process can be hierarchically monitored from the plant-wide level, unit block level, and variable level. The effectiveness of the proposed method is evaluated through the Tennessee Eastman benchmark process.

Sparse probabilistic principal component analysis model for plant-wide process monitoring

In the industrial monitoring process, probabilistic principal component analysis (PPCA) is a popular algorithm for reducing the dimension. However, the principal components (PCs) are not easy to interpret and its preserved number cannot be determined automatically. In this paper, we propose a sparse PPCA (SPPCA) to improve the interpretability by adding a prior and introducing sparsification to the loading matrix of PPCA. An expectation-maximization (EM) algorithm is used to obtain the parameters of the probabilistic formulation, and the dimensionality of the latent variable space can be automatically determined during the iterative process. With the sparse representation, a process monitoring strategy is then developed with the construction of several partial PPCA models. Case studies of SPPCA to a numerical case and Tennessee Eastman (TE) benchmark process demonstrate its feasibility and efficiency.