A distributed principal component regression method for quality-related fault detection and diagnosis

Sun, Chengyuan; Yin, Yizhen; Kang, Haobo; Ma, Hongjun

doi:10.1016/j.ins.2022.03.069

Cited by 25 publications

(4 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We use MI evaluation for the correlation between process variables and quality variables. The solution of MI can be calculated in the way of Renyi entropy according to formula (5). Unfortunately, it is difficult to be widely used in complex multivariate processes by estimating entropy through accurate probability density function.…”

Section: Quality-related and Quality-unrelated Variables Selections B...mentioning

confidence: 99%

See 1 more Smart Citation

Nonlinear Quality‐Related Fault Detection Using Neighborhood Embedding Neural Orthogonal Mapping Algorithm for Batch Process

Liu,

Zhao,

Hui

et al. 2024

Chem Eng & Technol

View full text Add to dashboard Cite

Quality‐related fault detection has become a hot research topic in recent years. It is not reliable to measure quality‐related relationships only by mutual information among process variables and single‐quality variables. Frequent alarms for quality‐unrelated faults seriously affect the normal operation of industrial production. At the same time, the strong nonlinearity of the process data leads to the difficulty of feature extraction. In this paper, we propose a fault detection algorithm based on nonlinear quality‐related neighborhood embedding neural orthogonal mapping (QR‐NENOM). First, quality‐related and quality‐unrelated variables are selected by Bayesian fusion mutual information, and the weighted method of mutual information is used to enhance the quality‐related information and suppress the quality‐unrelated information. Second, local manifold information is obtained by reconstructing nearest neighbors of process data, and key features are extracted by the nonlinear method composed of neural network and orthogonal mapping. Then, statistical indicators are established to complete fault detection. Finally, the nonlinear feature extraction ability of NENOM is verified by numerical examples, and the QR‐NENOM algorithm proposed in this paper is applied to the penicillin fermentation process. Comparative experiments show that QR‐NENOM has better detection performance for quality‐related faults and fewer alarms for quality‐unrelated faults.

show abstract

Section: Quality-related and Quality-unrelated Variables Selections B...mentioning

confidence: 99%

“…In recent years, quality-related fault have gained a lot of attention in the process monitoring field. By reducing quality-unrelated fault alarm rate, it can reduce unnecessary factory downtime, resulting in greater economic benefits for the enterprise [5,6].…”

Section: Introductionmentioning

confidence: 99%

Nonlinear Quality‐Related Fault Detection Using Neighborhood Embedding Neural Orthogonal Mapping Algorithm for Batch Process

Liu,

Zhao,

Hui

et al. 2024

Chem Eng & Technol

View full text Add to dashboard Cite

show abstract

“…Therefore, data-driven quality prediction methods have been widely studied and applied. Principal component regression (PCR), [11] partial least squares (PLS), [12] and canonical correlation analysis (CCA) [13] are the most typical data-driven quality prediction methods. PCR establishes the regression model by selecting the principal components with large covariance, which solves the collinearity problem to some extent.…”

Section: Introductionmentioning

confidence: 99%

Multi‐stage fusion regression network for quality prediction of batch process

Yao

Zhao

et al. 2023

Can J Chem Eng

View full text Add to dashboard Cite

In most batch processes, the correlations of process variables present multi‐stage characteristic as the process progress and operating conditions change. The methods building a local model at each stage ignore the potential correlations among stages, resulting in poor quality prediction of batch process. To solve this problem, a batch process quality prediction method based on multi‐stage fusion regression network (MSFRN) is proposed. First, the affine propagation clustering (AP) algorithm is used to automatically divide the stages for batch process without relying on prior knowledge. Second, the input reconstruction error and quality prediction error are organically combined to develop a stacked isomorphic and quality‐driven autoencoder (SIQAE) for each stage, which fully extracts the quality‐related features for each stage while reducing the input cumulative loss. Then, the self‐attention mechanism is used to integrate the quality‐related features of each stage so as to obtain global features which consider the correlations among stages. Finally, the global features are input into the fully connected regression layer to predict the quality variables of batch process. The effectiveness of the proposed method was verified by applying on penicillin fermentation process.

show abstract

“…This idea has attracted much attention in traditional shallow learning methods, such as partial least squares (PLS) and principal component regression (PCR). [19,20] Under the framework of DL, a variable-wise weighted stacked autoencoder (VWSAE) network was proposed for quality-relevant feature representation. [21] Nevertheless, an unavoidable issue in deep feature extraction is that, as the depth of the network increases, the learned features become more and more abstract, while information loss is constantly accumulating.…”

Section: Introductionmentioning

confidence: 99%

Operating performance assessment based on stacked performance‐relevant enhanced denoising auto‐encoder for industrial processes

Liu,

Ma,

Wang

et al. 2023

Can J Chem Eng

View full text Add to dashboard Cite

As an effective way to ensure the economic benefits of enterprises, process operating performance assessment has attracted more and more attention from industry and academia in recent years. In this paper, a stacked performance‐relevant enhanced denoising autoencoder (SPEDAE) network is designed for the operating performance assessment of industrial processes. Compared to the original denoising auto‐encoder (DAE), each performance‐relevant enhanced denoising auto‐encoder (PEDAE) not only reconstructs the input features in the output layer, but also strives to reconstruct the original input data and the performance grade labels simultaneously. Then the SPEDAE is formed by stacking multiple PEDAEs layer by layer. Through this improved training strategy, SPEDAE can avoid accumulated information loss during the deep feature extraction process, improve the robustness of the network, and extract features closely related to the operating performance, thereby better completing the assessment task. The effectiveness of the proposed assessment method is validated on the case of gold cyanide leaching process. Compared with several methods, the proposed SPEDAE has the highest accuracy and reaches 99.85%, which demonstrates its superiority in operating performance assessment.

show abstract

A distributed principal component regression method for quality-related fault detection and diagnosis

Cited by 25 publications

References 40 publications

Nonlinear Quality‐Related Fault Detection Using Neighborhood Embedding Neural Orthogonal Mapping Algorithm for Batch Process

Nonlinear Quality‐Related Fault Detection Using Neighborhood Embedding Neural Orthogonal Mapping Algorithm for Batch Process

Multi‐stage fusion regression network for quality prediction of batch process

Operating performance assessment based on stacked performance‐relevant enhanced denoising auto‐encoder for industrial processes

Contact Info

Product

Resources

About