Process Performance Monitoring Research Articles

VAE-Based Interpretable Latent Variable Model for Process Monitoring.

Latent variable-based process monitoring (PM) models have been generously developed by shallow learning approaches, such as multivariate statistical analysis and kernel techniques. Owing to their explicit projection objectives, the extracted latent variables are usually meaningful and easily interpretable in mathematical terms. Recently, deep learning (DL) has been introduced to PM and has exhibited excellent performance because of its powerful presentation capability. However, its complex nonlinearity prevents it from being interpreted as human-friendly. It is a mystery how to design a proper network structure to achieve satisfactory PM performance for DL-based latent variable models (LVMs). In this article, a variational autoencoder-based interpretable LVM (VAE-ILVM) is developed for PM. Based on Taylor expansions, two propositions are proposed to guide the design of appropriate activation functions for VAE-ILVM, allowing nondisappearing fault impact terms contained in the generated monitoring metrics (MMs). During threshold learning, the sequence of counting that test statistics exceed the threshold is considered a martingale, a representative of weakly dependent stochastic processes. A de la Peña inequality is then adopted to learn a suitable threshold. Finally, two chemical examples verify the effectiveness of the proposed method. The use of de la Peña inequality significantly reduces the minimum required sample size for modeling.

Spiking autoencoder for nonlinear industrial process fault detection

In recent years, artificial neural networks have been found successful applications in process monitoring within metallurgy, chemical engineering and mechanical manufacturing owing to their superior ability to construct flexible models with varying degrees of nonlinearity and effectively handle large-scale data. However, the model's distinctiveness diminishes due to the high cost associated with neural network training and initializations, resulting in a more fluctuating fault detection performance. To alleviate this problem and inspired by the way biological neurons emit spikes to transmit information, the spiking neurons are employed in the construction of a spiking neural network, introducing a shift in parameter optimization from conventional global parameter tuning to two-stage layer-wise process. Based on this, a brain-like discrete model, spiking auto-encoder (SNNAE) is constructed. The SNNAE's training process is firstly compared with that of artificial neural networks with the same structure through modeling a numerical example, results show the superior efficiency and accuracy of SNNAE in modeling highly nonlinear data. To gauge its effectiveness in fault detection, SNNAE is then compared with the state-of-art methods through the same numerical example and a three-phase flow process, indicating its ability to significantly improve process monitoring performance in nonlinear processes while notably reducing its fluctuation.

TSTFNN: Performance Enhancement for Fuzzy Neural Network in Performance Monitoring of Industrial Flotation Processes

TSTFNN: Performance Enhancement for Fuzzy Neural Network in Performance Monitoring of Industrial Flotation Processes

Unsupervised Learning Approach for Anomaly Detection in Industrial Control Systems

Industrial control systems (ICSs) play a crucial role in managing and monitoring critical processes across various industries, such as manufacturing, energy, and water treatment. The connection of equipment from various manufacturers, complex communication methods, and the need for the continuity of operations in a limited environment make it difficult to detect system anomalies. Traditional approaches that rely on supervised machine learning require time and expertise due to the need for labeled datasets. This study suggests an alternative approach to identifying anomalous behavior within ICSs by means of unsupervised machine learning. The approach employs unsupervised machine learning to identify anomalous behavior within ICSs. This study shows that unsupervised learning algorithms can effectively detect and classify anomalous behavior without the need for pre-labeled data using a composite autoencoder model. Based on a dataset that utilizes HIL-augmented ICSs (HAIs), this study shows that the model is capable of accurately identifying important data characteristics and detecting anomalous patterns related to both value and time. Intentional error data injection experiments could potentially be used to validate the model’s robustness in real-time monitoring and industrial process performance optimization. As a result, this approach can improve system reliability and operational efficiency, which can establish a foundation for safe and sustainable ICS operations.

Manifold-constrained trace ratio optimization for nonstationary process performance monitoring

Data-driven control performance monitoring (CPM) is becoming increasingly important in assessing and diagnosing changes in intricate industrial processes that are challenging to investigate with precise prior knowledge. The existing data-driven CPM methods mostly set covariance or other autocorrelation indexes intended to reflect the global deviation from benchmarks and subsequently diagnose the loops or variables responsible for these changes. However, as these methods assume stationary sequences, only steady-state fluctuation is assessed and diagnosed. This limits the application to industrial processes where transient processes are negligible. A comprehensive performance index integrating the transient performance and the steady-state performance is defined in this paper. The manifold constraint is investigated to mine the transient features so that it can be merged into the variance-based assessment framework. Moreover, to address the issue of information redundancy in non-orthogonal directions, which is present in most existing methods, we proposed a trace ratio-driven framework for enhancing the accuracy of assessment and diagnosis. A numerical example and a simulated industrial cascaded continuous stirred tank heater process are used to test the assessment results and demonstrate the effectiveness of the proposed diagnosis strategy.

An "Engage to Sustain" Intervention to Improve Process Performance Measures in Ambulatory Care.

In ambulatory care, monitoring process performance measures (PPMs) is essential to meet regulatory requirements, establish targets for care, seek reimbursement, and evaluate patient care responsibilities. We implemented a comprehensive program, "Engage to Sustain," for licensed practical nurses (LPNs) and certified medical assistants (CMAs) to practice at the top of their licensure/certification. Screening rates for 4 key PPMs (depression screening, fall risk screening, and tobacco use screening and counseling) markedly increased following this intervention across 18 ambulatory departments with more than 2 million patient visits. These results suggest that shifting responsibilities for patient screening from physicians and advanced practitioners to LPNs and CMAs may improve screening rates.

A Novel Incipient Fault Detection and Diagnosis Scheme Based on Kernel Density Weighting Support Vector Data Description: Application on the DAMADICS Benchmark Process

Support vector data description (SVDD) is a classical process monitoring skill and usually uses Euclidean distance to evaluate the status of a process. It should be noted that the proposed evaluation method restricts the detection performance for some faults, when the overall fault data has structural deviation compared with normal data. To address this problem, a novel incipient fault detection and diagnosis scheme based on kernel density weighting SVDD (KDWSVDD) is proposed. Firstly, the multidimensional kernel density estimation function and the density threshold are obtained by training data. Next, the adaptive weight is given to a test sample through measuring the probability density difference between the test sample and the training samples. Then, the statistic in SVDD is reconstructed to complete the fault detection of weighted samples. Finally, the contribution graph method is extended to diagnose the abnormal variable of incipient fault. KDWSVDD can increase the fault scale by giving adaptive weight to the test samples, so as to effectively monitor the incipient fault in a process. The experimental results on two numerical cases and DAMADICS benchwork process show that compared with SVDD, KDWSVDD has better process monitoring performance for incipient fault.

Early identification of process deviation based on convolutional neural network

A novel process monitoring method based on convolutional neural network (CNN) is proposed and applied to detect faults in industrial process. By utilizing the CNN algorithm, cross-correlation and autocorrelation among variables are captured to establish a prediction model for each process variable to approximate the first-principle of physical/chemical relationships among different variables under normal operating conditions. When the process is operated under pre-set operating conditions, prediction residuals can be assumed as noise if a proper model is employed. Once process faults occur, the residuals will increase due to the changes of correlation among variables. A principal component analysis (PCA) model based on the residuals is established to realize process monitoring. By monitoring the changes in main feature of prediction residuals, the faults can be promptly detected. Case studies on a numerical nonlinear example and data from two industrial processes are presented to validate the performance of process monitoring based on CNN.

Novel adaptive fault detection method based on kernel entropy component analysis integrating moving window of dissimilarity for nonlinear dynamic processes

Fault detection of nonlinear dynamic processes can ensure the safety of industrial production processes. Industrial process data are mostly autocorrelated along with strong nonlinear characteristics. And these significant characteristics interact with each other and limit the fault detection performance of traditional methods. Therefore, this paper presents a novel adaptive fault detection method for nonlinear dynamic processes based on kernel entropy component analysis (KECA) integrating the moving window of dissimilarity (DMW) (KECA-DMW). The KECA is used to map the raw data and capture the nonlinear features of the data, which combine with moving window techniques to build the fault detection model. In the process of updating the data in the moving window, the data information of the historical window is combined with that of the current window to obtain a more comprehensive judgment of the current moment. Then a dynamic update fusion method with adaptive weight allocation based on the dissimilarity index is proposed by analyzing the data characteristics of window information at different moments through the dissimilarity. Finally, three example studies with a numerical example, a closed-loop continuously stirred tank reactor and a Tennessee-Eastman process are used to validate the effectiveness of the proposed method. Compared with other nonlinear dynamic process fault detection methods, the results verify the effectiveness of the proposed method in the process monitoring performance of nonlinear dynamic processes in terms of false alarm rate and fault detection rate, where the false alarm rates of the proposed method are only 2%, 1.83%, and 4.33%, while the fault detection rates are 97.4%, 96.83%, and 86.25%, respectively.

Investigating machine learning models to predict microbial activity during ozonation–biofiltration

Continuous online monitoring of water treatment process performance is an essential step in ensuring reliable water quality outcomes.

Trustworthiness of Process Monitoring in IIoT Based on Self-Weighted Dictionary Learning

Process monitoring, a typical application of industrial Internet of Things (IIOT), is crucial to ensure the reliable operation of the industrial system. In practice, due to the harsh environment and unreliable sensors and actuators, it is often difficult for IIoT to collect enough tagged and highly reliable data, which further degrades the process monitoring performance and makes the monitoring results not trustworthy. In order to reduce the negative impact of these unreliable factors, a self-weighted dictionary learning process monitoring method is proposed. In particular, a label propagation classifier is implemented from the labeled data to unlabeled data to obtain a credible label prediction. Subsequently, considering the interference of low-quality data and label information, we reweight the classification loss and label-consistency constraints to enhance the trustworthiness of feature extraction. Finally, a novel iterative optimization algorithm that combines the block coordinate descent method with the alternating direction multiplier method is developed to ensure the convergence speed of the learned classifier and dictionary. Extensive experiments indicate that the proposed method can guarantee the trustworthiness of the process monitoring results.

A supervised functional Bayesian inference model with transfer-learning for performance enhancement of monitoring target batches with limited data

To increase the monitoring performance of the batch process with serious nonlinearity, uneven-length, and limited-data issues, a supervised transfer-learning based functional Bayesian inference method is developed in this study. The raw uneven-length batch data are firstly transformed into functional data by choosing appropriate orthogonal wavelet basis functions (WBFs). Using the approximation coefficients representing the latent features that are inherent to the raw data, a Gaussian process model and a Bayesian inference method are applied based on the coefficients in each source batch process and the established models are transferred to enhance modeling performance for the target process with limited batches. In the proposed functional method, the unfolding operation is not needed for preprocessing, avoiding distortion of the raw data structure. With the compact support property of WBFs, within-batch detection can be implemented effectively to recognize faults earlier. The advantages of the proposed model are verified using a numerical case and an industrial polytetrafluoroethylene process.

Evaluation of Laboratory Performance in Consideration with Pre analytical and Post analytical Quality Indicators.

Implementation of Quality indicators (QIs) plays an imperative role in improving the total testing process, as it provides a quantitative basis for evaluating the laboratory performance. Besides monitoring of analytical quality specifications, several lines of experimental and clinical evidence have alluded a pivotal role of extra-analytical phases in improving the quality of laboratory services and therefore a relevance of pre- and post-analytical steps have been speculated on the overall quality in the total testing process and consequently on clinical decision-making. This was a retrospective study designed to evaluate and review different extra-analytical quality indicators in NABL accredited clinical biochemistry laboratory at BJ Medical College and Civil Hospital, Ahmedabad, Gujarat in an endeavour to ameliorate the performance of the laboratory. All Clinical Chemistry Laboratory test requests with their respective samples from January 2018 to December 2021 were included in the study. A total of 1,439,011samples were processed, and were evaluated for seven QIs [(% of number of suitable samples not received; QI-8), (% of number of samples received in inappropriate container; QI-9), (% of number of samples hemolysed; QI-10), (% of number of samples with inadequate sample volume; QI 12) (% of number of samples received mismatched; QI 15), (% of number of samples reported after turnaround time; QI 21) and (% of number of samples with critical values informed; QI 22)] based on defined criteria of Quality Specification given by International Federation of Clinical Chemistry. Total number of preanalytical errors was 53,669 (3.72%). Among the preanalytical errors, inadequate sample volume (2.37% of total samples; 63.49% of total pre-analytical errors) was the most common anomaly followed by Not received samples (24.18%) hemolysis (8.26%) mismatched (3.91%) and 0.14% samples were received in Inappropriate container; manifesting that the error frequency was unacceptable for QI 21 and QI 8, acceptable for QI 10, minimally acceptable for QI 15 and optimum for QI QI 9. Furthermore, there was year-wise progressive decline in error rate of inadequate sample volume, hemolysed sample received and mismatched samples. Total number of post analytical errors were 19,002 (1.32%). TAT outlier and critical values communicated were the two QIs evaluated for this phase and results of both QI were within acceptable limits. Quality indicators serve as a tool to monitor process performance and consequently derived error rates warrant active intervention to improve the laboratory services and patient health care. Dissemination of certified documents, regular staff training and evaluation needs to be conducted.

A Novel Spatiotemporal Process Feature Learning Method Based On the Pseudo-Siamese Network for Complex Chemical Process Concurrent Condition Monitoring.

The deep learning-based process monitoring method has attracted great attention due to its ability to deal with nonlinear correlation. However, the further modeling of learned deep features from process data to better depict typical process features to obtain more precise monitoring results remains a challenge. In this paper, a novel nonlinear spatiotemporal process feature learning method is proposed to extract high-value slow-varying spatiotemporal process features, with an explicit temporal relationship model for the concurrent monitoring of the static deviation and the dynamic anomaly of complex chemical processes. Different from directly mixed spatiotemporal information methods, the pseudo-Siamese autoencoder network is designed with two different subencoders to separately describe the nonlinear spatial and temporal relationships of the nonlinear dynamic input data. Correspondingly, a cost function including three losses and one orthogonal constraint is proposed to make sure that the extracted spatiotemporal process features change as slowly as possible and contain the most nonlinear dynamic information on the input data. With the explicit spatial and temporal relationship submodel, predictions are utilized to shrink the variability of the nonlinear temporal correlated data and focus on the unpredictable variabilities to improve process monitoring performance. Meanwhile, the linear dynamic information is further extracted in the reconstructed residual space by the general slow feature analysis (SFA) method to provide a more detailed analysis of the process characteristics and improve the monitoring results. The case study monitoring results demonstrate the effectiveness and superiority of the proposed method over other compared methods for concurrent process monitoring.

Interval-valued data correlation modeling approach for uncertain nonlinear and non-Gaussian process monitoring

Process monitoring is a crucial part of ensuring the safety and quality of industrial production, and fault detection is a particularly critical step. As a departure from the dimensionality reduction strategy commonly used in fault detection methods, this paper aims to create a statistical model by directly extracting complex correlations among variables with nonlinearity and non-Gaussian properties. Uncertainties in measurement data in an actual process can significantly impact the control decision based on a monitoring model, so interval-valued description strategy is introduced to effectively take the uncertainties into account. Moreover, we improved upon the traditional interval-valued data generation method using moving window technology combine the receiver-operator characteristic curve to construct intervals based on sample mean and standard deviation (SD), which makes full use of the data information. This paper proposes a mean-SD interval vine copula (MSIVC) model for complex industrial process fault detection. The high density region and density quantile theory are introduced to determine the control boundary. The process monitoring performance of the MSIVC method is evaluated by a numerical example and the Tennessee-Eastman process. The results show that the proposed model is stable, sensitive to process faults, and yields effective monitoring results.

Challenges and Opportunities for Online Simulations for Process Performance Monitoring at Covestro

Challenges and Opportunities for Online Simulations for Process Performance Monitoring at Covestro

A new key performance indicator oriented industrial process monitoring and operating performance assessment method based on improved Hessian locally linear embedding

ABSTRACT The industrial process monitoring and operating performance assessment techniques are of great significance to ensure the safety and efficiency of the production and to improve the comprehensive economic benefits for the modern enterprises. In this paper, a new key performance indicator (KPI) oriented nonlinear process monitoring and operating performance assessment method is proposed based on the improved Hessian locally linear embedding (HLLE), in view of the problems of strong nonlinearity, high dimension and information redundancy in actual industrial process data. Firstly, in order to characterise the similarities of samples in both temporal and spatial dimensions, a new measurement, based on Finite Markov theory, is defined to replace the Euclidean distance in traditional HLLE. Secondly, by mining the relationships between process variables and the key performance indicator, the KPI oriented feature extraction method is developed. On this basis, the monitoring statistics is constructed and the corresponding control limit is determined for the real-time fault detection. After that, a new operating performance assessment approach based on sliding window Kullback–Leibler divergence is put forward to facilitate maintenance or adjustments. Finally, the proposed method is applied to the hot strip mill process, and the results show the effectiveness.

Nonlinear Dynamic Process Monitoring Based on Ensemble Kernel Canonical Variate Analysis and Bayesian Inference.

By considering autocorrelation among process data, canonical variate analysis (CVA) can noticeably enhance fault detection performance. To monitor nonlinear dynamic processes, a kernel CVA (KCVA) model was developed by performing CVA in the kernel space generated by kernel principal component analysis (KPCA). The Gaussian kernel is widely adopted in KPCA for nonlinear process monitoring. In Gaussian kernel-based process monitoring, a single learner is represented by a certain selected kernel bandwidth. However, the selection of kernel bandwidth plays a pivotal role in the performance of process monitoring. Usually, the kernel bandwidth is determined manually. In this paper, a novel ensemble kernel canonical variate analysis (EKCVA) method is developed by integrating ensemble learning and kernel canonical variate analysis. Compared to a single learner, the ensemble learning method usually achieves greatly superior generalization performance through the combination of multiple base learners. Inspired by the ensemble learning method, KCVA models are established by using different kernel bandwidths. Further, two widely used T2 and Q monitoring statistics are constructed for each model. To improve process monitoring performance, these statistics are combined through Bayesian inference. A numerical example and two industrial benchmarks, the continuous stirred-tank reactor process and the Tennessee Eastman process, are carried out to demonstrate the superiority of the proposed method.

A Novel Fault Detection Scheme Based on Mutual k-Nearest Neighbor Method: Application on the Industrial Processes with Outliers

The k-nearest neighbor (kNN) method only uses samples’ paired distance to perform fault detection. It can overcome the nonlinearity, multimodality, and non-Gaussianity of process data. However, the nearest neighbors found by kNN on a data set containing a lot of outliers or noises may not be actual or trustworthy neighbors but a kind of pseudo neighbor, which will degrade process monitoring performance. This paper presents a new fault detection scheme using the mutual k-nearest neighbor (MkNN) method to solve this problem. The primary characteristic of our approach is that the calculation of the distance statistics for process monitoring uses MkNN rule instead of kNN. The advantage of the proposed approach is that the influence of outliers in the training data is eliminated, and the fault samples without MkNNs can be directly detected, which improves the performance of fault detection. In addition, the mutual protection phenomenon of outliers is explored. The numerical examples and Tenessee Eastman process illustrate the effectiveness of the proposed method.

Online Performance Monitoring of Processes Subject to Non-stationary Stochastic Disturbance

Since non-stationary disturbances are common in practical situation due to the varying stochastic disturbance or some deterministic disturbance injected, the traditional algorithm based on FCOR is not valid anymore. This paper develop a new approach, which combines EMD method with FCOR algorithm, to handle this problem such that the minimum variance (MV) performance of the closed-loop system can be monitored online. In the presence of varying stochastic disturbance and step/sine disturbance, the numerical example demonstrates the effectiveness of the proposed algorithm.