Data-Driven Process Monitoring Using Structured Joint Sparse Canonical Correlation Analysis

In this article an accurate and efficient technique for tissue typing is presented. The proposed technique is based on Canonical Correlation Analysis, a statistical method able to simultaneously exploit the spectral and spatial information characterizing the Magnetic Resonance Spectroscopic Imaging (MRSI) data. Recently, Canonical Correlation Analysis has been successfully applied to other types of biomedical data, such as functional MRI data. Here, Canonical Correlation Analysis is adapted for MRSI data processing in order to retrieve in an accurate and efficient way the possible tissue types that characterize the organ under investigation. The potential and limitations of the new technique have been investigated by using simulated as well as in vivo prostate MRSI data, and extensive studies demonstrate a high accuracy, robustness, and efficiency. Moreover, the performance of Canonical Correlation Analysis has been compared to that of ordinary correlation analysis. The test results show that Canonical Correlation Analysis performs best in terms of accuracy and robustness.

In recent years, the number of people with Alzheimer’s disease (AD) has grown worldwide. Since no cure has yet been found for the disease, detection and initiation of treatment is the best way to prevent the disease from progressing behavioral and physical symptoms in the patient. There are several methods to diagnose AD, and neuroimaging, as a noninvasive approach, reveals changes in the brain due to the disease. Diagnosis accuracy can be improved by fusion of various neuroimaging modalities. Canonical correlation analysis (CCA) and its extensions have been widely used for fusing multi-modal datasets, where healthy controls (HCs) are differentiated from patients by applying classification methods to canonical variables (CVs) resulting from CCA or its extensions. The goal of our study is to find an optimal method, from the perspective of accuracy and processing complexity, to diagnose patients with AD. This goal is achieved by fusing anatomical magnetic resonance imaging (MRI) and functional MRI (fMRI) data using CCA-based methods. Experimental results illustrate that HCs and AD patients can be classified using CVs obtained from structured and sparse CCA with greater than 90% accuracy.

Objective. Steady-state visual evoked potential (SSVEP) is an important control method of the brain–computer interface (BCI) system. The development of an efficient SSVEP feature decoding algorithm is the core issue in SSVEP-BCI. It has been proposed to use user training data to reduce the spontaneous electroencephalogram activity interference on SSVEP response, thereby improving the feature recognition accuracy of the SSVEP signal. Nevertheless, the tedious data collection process increases the mental fatigue of the user and severely affects the applicability of the BCI system. Approach. A cross-subject spatial filter transfer (CSSFT) method that transfer the existing user model with good SSVEP response to the new user test data without collecting any training data from the new user is proposed. Main results. Experimental results demonstrate that the transfer model increases the distinction of the feature discriminant coefficient between the gaze following target and the non-gaze following target and accurately identifies the wrong target in the fundamental algorithm model. The public datasets show that the CSSFT method significantly increases the recognition performance of canonical correlation analysis (CCA) and filter bank CCA. Additionally, when the data used to calculate the transfer model contains one data block only, the CSSFT method retains its effective feature recognition capabilities. Significance. The proposed method requires no tedious data calibration process for new users, provides an effective technical solution for the transfer of the cross-subject model, and has potential application value for promoting the application of the BCI system.

In recent years, partial least squares (PLS) has become more and more closely linked with the monitoring of key performance indicators (KPI) in large-scale industrial processes. However, the standard PLS and its modifications still have some problems during process monitoring, because these kinds of methods cannot fully utilize the correlation between variables. Instead of using the traditional KPI-related PLS, this paper uses canonical correlation analysis (CCA) to exploit the best correlation among variables. The proposed method decomposes process data into KPI-related and KPI-unrelated parts, and then constructs statistics for process monitoring. For short, the proposed method is termed as KPI-CCA. Finally, the effectiveness and advantages of KPI-CCA are validated by a numerical example and the Tennessee Eastman (TE) benchmark process simulation.

Canonical correlation analysis (CCA) has attracted increasing attention in the field of fault detection because it provides an effective way to explore the relationship between the input and output data. This paper develops a novel rank constrained CCA (RCCCA) framework, which is the first approach that takes the rank prior information into consideration. Technically, the rank constrained optimization is able to capture the global structures of variables, and thus improve the performance of fault detection. In order to solve RCCCA, an alternating minimization algorithm is designed, which aims to preserve the maximum correlation with the low-rank learning. A fault detection residual is then generated, and the test statistic is constructed to determine whether a fault occurs. The RCCCA-based fault detection is finally tested on a numerical example and the Tennessee Eastman benchmark process. Monitoring results indicate the efficiency and feasibility of the proposed method.

In this article, a correlation-aided neural network (CANN) framework is proposed for distributed process monitoring of large-scale industrial automation systems. First, to model the nonlinear data relationship of multiple subsystems, a feature space is learned for each subsystem by means of neural network-based nonlinear projection. Second, different from conventional distributed monitoring methods, a distributed learning method and a novel objective function are proposed, where the influence of uncertainties is decreased by considering the correlation of variables among multiple subsystems. Third, a process monitoring method is proposed based on the CANN framework. The impact of the fault is analyzed, and the optimal monitoring performance is achieved by considering the correlation of all subsystems. To further reduce communication overhead among multiple subsystems, a tradeoff between monitoring performance and communication overhead is made based on gradients of the CANN model. Theoretical analysis demonstrates the superiority of the proposed method. The case studies on a multizone heating, ventilation, and air-conditioning system and the Tennessee Eastman benchmark process are given to evaluate and compare the effectiveness of the proposed method.

This paper proposes a common and individual (CnI) feature extraction-based process monitoring (PM) method for tracking the operating performance and product quality of processes with multiple operating modes. Different from traditional methods that separately develop PM models concerning only the individual feature of each mode data, the new method seeks to build the PM model simultaneously from all mode data, including to acquire the common subspace that captures the common feature behind different modes, and the individual subspace that reflects the unique feature of each mode. The newly proposed framework is achieved using the conventional principal component analysis (PCA) and partial least squares (PLS) based methods. The resulting CnI-PCA-based operating performance monitoring method and CnI-PLS-based product quality monitoring method are applied to the typical multimode finishing mill process (FMP) where common configuration for all steel products and individual setting for each steel are existing. Finally, the practical application result shows that the proposed method can be preferable to detect and identify different faults in the multimode FMP.

Joint-individual monitoring of large-scale chemical processes with multiple interconnected operation units incorporating multiset CCA

This work concerns the issue of quality-related fault detection and diagnosis (QrFDD) for nonlinear process monitoring. A kernel principal component analysis (KPCA) based canonical correlation analysis (CCA) model is proposed in this paper. First, KPCA is utilized to extract the kernel principal components (KPCs) of original variables data to eliminate nonlinear coupling among the variables. Then, the KPCs and output are used for CCA modeling, which not only avoids the complex decomposition of kernel CCA but also maintains high interpretability. Afterwards, under the premise of Gaussian kernel, a proportional relationship between process variables sample and kernel sample is introduced, on the basis of which, the linear regression model between process and quality variables is established. Based on the coefficient matrix of the regression model, a nonlinear QrFDD method is finally implemented which has both the data processing capability of nonlinear methods and the form of linear methods. Therefore, it significantly outperforms existing kernel-based CCA methods in terms of algorithmic complexity and interpretability, which demonstrated by the simulation results of the Tennessee-Eastman (TE) chemical process.

An explainable artificial intelligence based approach for interpretation of fault classification results from deep neural networks

Industrial processes typically have multiple operating modes with complex data distribution and locality faults, which challenges the traditional multivariate statistical process monitoring methods. To address this problem, a double‐level local information‐based local outlier factor (LOF) method is proposed in this work for multimode complex process monitoring. First, to handle the multimodality, the local neighborhood standardization strategy is adopted to utilize the statistical information of local data structure. Second, the variable LOF method is proposed to determine reasonable boundary for complex data distribution and simultaneously reflect local variable behaviors. For better online monitoring, a weighting strategy is applied to emphasize the local variable information, and the Bayesian inference is employed to integrate the LOF value of each variable. To isolate the fault variables, a contribution plot is designed. Finally, a numerical example and the benchmark Tennessee Eastman process are used to demonstrate the effectiveness and superiority of the proposed method.

Fault detection in the Tennessee Eastman benchmark process with nonlinear singular spectrum analysis

Distributed process monitoring based on canonical correlation analysis with partly-connected topology

Industrial processes generally have various operation modes, and fault detection for such processes is important. This paper proposes a method that integrates a variational Bayesian Gaussian mixture model with canonical correlation analysis (VBGMM-CCA) for efficient multimode process monitoring. The proposed VBGMM-CCA method maximizes the advantage of VBGMM in automatic mode identification and the superiority of CCA in local fault detection. First, VBGMM is applied to unlabeled historical process data to determine the number of operation modes and cluster the data in each mode. Second, local CCA models that explore input and output relationships are established. Fault detection residuals are generated in each local CCA model, and monitoring statistics are derived. Finally, a Bayesian inference probability index that integrates monitoring results from all local models is developed to increase the monitoring robustness. The effectiveness of the proposed monitoring scheme is verified through experimental studies on a numerical example and the multiphase batch-fed penicillin fermentation process. Note to Practitioners —Process monitoring is important in guaranteeing process safety and improving product quality. Large amounts of unlabeled process data with multiple operation modes generally exist in industrial processes. Labeling these data is difficult or costly. Hence, this paper presents a VBGMM-CCA method for monitoring multimode processes. The key advantage of the proposed method is that it automatically identifies the number of operation modes in historical data and clusters the data. Then, local CCA monitors are established to model the process input and output relationships. During online monitoring, the running-on operation mode is identified through a density function, and the process status is evaluated by the corresponding CCA monitor. A probabilistic monitoring index is also developed to increase the robustness of the monitoring. In comparison with the results of conventional methods, the monitoring results of the proposed approach are more reliable and informative because the process status and the type of the detected fault are presented.

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.