Search

Process 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. [ABSTRACT FROM AUTHOR]

Representation extraction is crucial in data‐driven process monitoring, and deep neural network (DNN) is an efficient tool for extracting representations from considerable process data. This study proposes a hierarchical representation learning (HRL) method that integrates the deep belief neural (DBN) network and support vector data description (SVDD) for efficient nonlinear chemical process fault diagnosis. First, hierarchical representations containing meaningful process information are generated through a DBN network by utilizing generally massive normal operating process data. Second, an SVDD‐based decision‐making system is constructed using generally small‐sized faulty data. Three experimental studies are then conducted. A comparison of results with those of several state‐of‐the‐art methods reveal the suitability of the HRL method for process monitoring due to its two main advantages. First, DNN has a superior representative ability and generates representations with richer process information than conventional data‐driven methods. Second, the HRL method utilizes available process data and is suitable for practical conditions in which considerable normal operating data but limited small‐sized faulty data are available. [ABSTRACT FROM AUTHOR]

Plant-wide process monitoring is challenging because of the complex relationships among numerous variables in modern industrial processes. The multi-block process monitoring method is an efficient approach applied to plant-wide processes. However, dividing the original space into subspaces remains an open issue. The loading matrix generated by principal component analysis (PCA) describes the correlation between original variables and extracted components and reveals the internal relations within the plant-wide process. Thus, a multi-block PCA method that constructs principal component (PC) sub-blocks according to the generalized Dice coefficient of the loading matrix is proposed. The PCs corresponding to similar loading vectors are divided within the same sub-block. Thus, the PCs in the same sub-block share similar variational behavior for certain faults. This behavior improves the sensitivity of process monitoring in the sub-block. A monitoring statistic T2 corresponding to each sub-block is produced and is integrated into the final probability index based on Bayesian inference. A corresponding contribution plot is also developed to identify the root cause. The superiority of the proposed method is demonstrated by two case studies: a numerical example and the Tennessee Eastman benchmark. Comparisons with other PCA-based methods are also provided. Copyright © 2014 John Wiley & Sons, Ltd. [ABSTRACT FROM AUTHOR]

Although principal component analysis (PCA) is widely used for chemical process monitoring, improvements in the selection of principal components (PCs) are still needed. Given that the determination of complicated and changing fault information is not guaranteed using offline-selected PCs, this study proposes a just-in-time reorganized PCA model that objectively selects the PCs online for process monitoring. The importance of the PCs is evaluated online by kernel density estimation. The PCs indicating more varied information are then selected to reorganize the PCA model. Given that the most useful fault information is concentrated, support vector data description is used to replace traditional statistics, thereby relaxing the Gaussian assumption of the process data. The monitoring performances of the proposed method are evaluated under three cases. Compared with conventional PCA methods, more varied information is captured online, and the monitoring performances are improved. © 2014 American Institute of Chemical Engineers AIChE J, 60: 949-965, 2014 [ABSTRACT FROM AUTHOR]

Batch process data are time‐varying dynamic and non‐Gaussian distributed. In addition, for multivariate statistical process monitoring, their variability can be overwhelmed when considering local variability behavior. To address the abovementioned issues, an improved batch process monitoring approach is presented that integrates just‐in‐time learning and multiple subspace support vector data description (JITL‐MSSVDD). A new multiple subspace segmentation method is proposed that classifies a contribution array that is calculated on the mixing matrix of independent component analysis (ICA). Offline, the variable subspace segmentation rule can be obtained from the proposed method. The subspace monitoring models can reduce the risk of the variability being overwhelmed. Online, local modeling samples are collected through JITL, which can reduce the impact of the time‐varying dynamic on modeling accuracy. Then, in accordance with the variable subspace segmentation rule, which is obtained offline, MSSVDD models are constructed to solve non‐Gaussian problems. The advantage of the proposed JITL‐MSSVDD is demonstrated through the standard test model fed‐batch penicillin fermentation process. A new data‐driven multiple subspace segmentation method is proposed, and an improved batch process monitoring approach is presented that integrates just‐in‐time learning and multiple subspace support vector data description. [ABSTRACT FROM AUTHOR]

Slow feature analysis (SFA) is an efficient technique in exploring process dynamic information and is suitable for quality‐relevant process monitoring. However, involving quality‐irrelevant variables or features may introduce redundant information and degrade the monitoring performance. A novel multiblock monitoring scheme based on mutual information (MI) and SFA is proposed to detect an efficient quality‐relevant fault for dynamic processes. First, all process variables are divided into two blocks in accordance with their MI values with quality variables. Second, slow features (SFs) of two blocks are extracted via the SFA. The SFs, which are extracted from the quality‐relevant variables, are not all related to the quality variable. Thus, these SFs are further partitioned into two blocks in accordance with their MI values with quality variables. The SFs from three blocks are obtained, and monitoring statistics are constructed. Two simulation studies, including a numerical example and Tennessee Eastman process, demonstrate that the proposed method outperforms conventional methods. In this study, an MI‐based multiblock SFA method is proposed for process monitoring of quality‐relevant dynamics, which characterizes the process dynamics via the SFA and reduces the monitoring redundancy via the MI‐based block division. And considering that quality‐irrelevant variables or features may introduce redundant information and degrade the monitoring performance, so, in addition to dividing the process variables, the SFs, extracted from quality‐relevant variables via SFA, are further partitioned to avoid information redundancy. [ABSTRACT FROM AUTHOR]