Process incipient fault detection using canonical variate analysis

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 designing a distributed monitoring scheme. Then state-of-the-art DMSPPM methods are revisited. Finally, opportunities of and challenges to the DMSPPM methods are discussed.

Variable contribution identification and visualization in multivariate statistical process monitoring

Fault detection and fault identification are consecutive steps of multivariate statistical process monitoring. In recent years, increasing attention has been paid to process dynamics. For dynamic process modeling, canonical variate analysis (CVA) extracts process dynamics effectively. However, process noises are not well analyzed in traditional CVA and corresponding fault identification methods are less studied. To solve these issues, a variational Bayesian CVA (VBCVA) model is proposed for dynamic process monitoring. Through a probabilistic perspective, the inevitable noises in realistic industrial processes can be captured in the new model. Moreover, the proposed model is further extended in the variational Bayesian framework to overcome the common problems in probabilistic methods. Besides, an improved fault identification approach based on fault relevance is introduced, which avoids the smearing effect caused by data reconstruction. Finally, the feasibility of the proposed process monitoring scheme is verified on the TE benchmark and a real wastewater treatment process.

There are two problems in principal component analysis (PCA), which is widely employed in multivariate statistical process monitoring. On one hand, principal components selection according to the variance of the normal training dataset cannot represent the amount of fault information included in the online data. Thus, the useful fault information loss would exist and leads to poor monitoring performance. On the other hand, although the fault information contained in every principal component is different and the principal components are treated equally in traditional PCA-based methods. Then, some useful fault information would be suppressed. In order to reduce the dimension and preserve every original variable information as complete as possible at the same time, this paper selects key principal components using our previously proposed full variable expression method. Moreover, according to the accumulated reachability distance of the online data relative to that of the offline training data, those key principal components with large accumulated reachability distance are emphasized and weighted. Finally, the statistics are constructed to monitor the operation status, and the process monitoring performance of the proposed method is evaluated under an industrial process.

The on-line monitoring of dissolved gas in transformer oil can effectively reflect the abnormal state of transformer. However, abnormal operation of the monitoring equipment will greatly interfere with abnormal transformer identification. It is difficult to identify the abnormal operation of dissolved gas monitoring device. This paper introduces a method of processing of data-driven and presents an anomaly identification method for dissolved gas monitoring device in oil based on multivariate statistical process monitoring(MSPM). Firstly, MSPM abnormal identify model which based on PCA is established. This model can illustrate the data characteristics of the system under normal conditions. Then, identify abnormal data based on T2 statistic and SPE statistic. T2 can reflect most of the information of the principal component subspace, and is more suitable for the case of strong white noise. residual subspace SPE can handle the invisible information of the principal component subspace. It is found that the T2 statistic and the SPE statistic are sensitive to the variation of characteristic gas. Finally, the abnormal work data library of monitoring device is established to identify the abnormal devices. This paper collects historical on-line monitoring data of a regional power grid to build a library, and predict device abnormal situation criterion based on this library. It listed the connection between common features of data and abnormal reason. The cross interference of monitoring equipment and overheat fault of transformer are correctly identifying to justify the method. This device can distinguish the abnormal state and detect transformer insulation cracking.

Root cause analysis in multivariate statistical process monitoring: Integrating reconstruction-based multivariate contribution analysis with fuzzy-signed directed graphs

Quality-related fault detection is an effective way to ensure the stability of product quality and the safety of industrial processes. Quality abnormality is often caused by incipient faults, which propagate through the connectivity path among the equipment and subsystems, and eventually become significant faults that affect product quality and production efficiency. In this paper, a quality-related incipient fault detection method for large-scale industrial process is proposed. Firstly, a fault-relevant variable selection strategy based on Kullback-Leibler divergence (KLD) is proposed to obtain the optimal variable subsets of quality-related and quality-unrelated faults. Secondly, canonical variate analysis is applied to estimate the canonical variables from the collected processes data. Thirdly, considering that KLD has a high sensitivity to incipient faults, it is used to quantify the dissimilarity between the distributions of canonical vectors before and after fault occurs. Finally, Bayesian inference is employed to fuse the detection results of all sub-blocks to get an intuitive global detection result. The advantages and validity of the proposed scheme are verified based on the Tennessee Eastman process.

Modern industrial processes are characterized by increasing complexity, often exhibiting pronounced dynamic behaviors and significant nonlinearity. Addressing these dynamic and nonlinear characteristics is essential for effective process monitoring. However, many existing methods for process monitoring and fault diagnosis are insufficient in handling these challenges. In this article, we present a novel process monitoring approach, CVA-DisDAE, which integrates an improved Denoising Autoencoder (DAE) with Canonical Variate Analysis (CVA) to address the challenges posed by dynamic behaviors and nonlinear relationships in industrial processes. First, CVA is employed to reduce data dimensionality and minimize information redundancy by maximizing correlations between past and future observations, thereby effectively capturing process dynamics. Following this, we introduce a discriminative DAE model (DisDAE) designed to serve as a semi-supervised denoising autoencoder for precise feature extraction. This is achieved by incorporating both between-class separability and within-class variability into the traditional DAE framework. The key distinction between the proposed DisDAE and the conventional DAE lies in the integration of a linear discriminant analysis (LDA) penalty into the DAE’s loss function, resulting in extracted features that are more conducive to fault classification. Finally, we validate the effectiveness of the proposed semi-supervised dynamic process monitoring approach through its application to the Tennessee Eastman benchmark process, demonstrating its superior performance.

Mixed kernel canonical variate dissimilarity analysis for incipient fault monitoring in nonlinear dynamic processes

This chapter illustrates the concept of multivariate statistical process monitoring (MSPM) with data from a biopharmaceutical drug product lyophilization process. It provides the practitioner with steps needed for pretreatment of the data, modeling, and testing phases of the approach. The MSPM applied to the lyophilization process comprised three different models for the freezing, primary drying, and secondary drying steps using a commercially available software. In the presented example, the developed offline MSPM batch model helped diagnose issues with a batch manufactured at a later time using built-in features of the software which allows identification of the variables using their contribution to Hotelling’s T2 and distance to model X measures.

A robust clustering method for detection of abnormal situations in a process with multiple steady-state operation modes

Robust statistical process monitoring

1 - Quality-related fault detection and diagnosis: a technical review and summary

In this paper, a multivariate statistical process monitoring technique based on bottleneck auto-associative neural network is applied on a water treatment plant. First, the nonlinear principal component analysis (NLPCA) is carried out in order to identify and analyze the relationships among the correlated variables in the process by compressing multidimensional data set, extracting the original data from the principal components and then the squared prediction error is evaluated to find the erroneous data samples. So, the information obtained using this intelligent tool is used for diagnosis. The obtained results on realistic data demonstrate the effectiveness of the applied technique for monitoring water treatment plants.

In process industries, multivariate statistical process monitoring (MSPM) has become an important technique for enhancing product quality and operation safety. Among the family of MSPM methods, principal component analysis (PCA) may be the most commonly used one, due to its capabilities of dimensionality reduction and highlighting variation in a data set. However, the performance of a PCA model often degrades significantly when there are gross sparse errors, i.e. outliers, contained in the training data, since PCA assumes that the training data matrix only contains an underlying low-rank structure corrupted by dense noise. In this paper, a robust matrix recovery method named stable principal component pursuit (SPCP) is adopted to solve this problem, based on which a process modeling and online monitoring procedure is developed. Such a method inherits the benefits of PCA while being robust to outliers. The effectiveness of the SPCP-based monitoring method is illustrated using the benchmark Tennessee Eastma...