Chemical process fault diagnosis based on enchanted machine‐learning approach

Yang, Xiaohui; Zhou, Jingsong; Xie, Zihao; Гонг, Ке

doi:10.1002/cjce.23642

Cited by 7 publications

(8 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The TE process diagram is presented in Figure 10. [33] It has five significant units: reactor, condenser, compressor, stripper, and separator. There are eight types of materials in this process, including four reactants, named A, C, D, and E, containing products named G and H. In addition, there are inertial component B and by-product F. A total of 52 observed variables in the TE process were selected for analysis and divided into two categories: measured and manipulated variables.…”

Section: Fault Diagnosis Proceduresmentioning

confidence: 99%

A novel one‐dimensional convolutional neural network architecture for chemical process fault diagnosis

Niu

Xia

2021

Can J Chem Eng

View full text Add to dashboard Cite

In recent years, industrial production has become increasingly automated, with the widespread application of informational and digital technology. Fault detection and diagnosis (FDD) technology is also playing an increasingly important role in the chemical process industry. However, owing to the weak generalization ability of prior models, or prior methods not being suitable for industrial sensor signal data, the fault detection rate is not satisfactory, which is a significant limitation of many fault diagnosis methods in practical applications. In response to this problem, the one-dimensional convolutional neural network (1D-CNN) model can directly process signal samples without changing the one-dimensional characteristics of the data, which may be more suitable for processing such signal data. Therefore, a new 1D-CNN architecture is proposed for FDD. The network architectures, including convolutional layers, pooling layers, fully connected layers, and various parameters, are optimized in the proposed method. The Tennessee Eastman process (TE process) is employed to assess prominent performance of the method. To comprehensively reflect the performance of the model, three evaluation indexes are selected in this study: accuracy, F1-score, and fault detection rate. The experimental results indicate that compared with other diagnostic methods, the 1D-CNN model has excellent feature extraction ability, which can remarkably improve diagnostic capability in the TE process.

show abstract

Section: Fault Diagnosis Proceduresmentioning

confidence: 99%

A novel one‐dimensional convolutional neural network architecture for chemical process fault diagnosis

Niu

Xia

2021

Can J Chem Eng

View full text Add to dashboard Cite

show abstract

“…The experimental results compared the accuracy and F 1 -score of different fault diagnosis models to evaluate the diagnostic performance of the proposed model. [3] Effective Separation of Aromatic Hydrocarbons by Pyridine-Based Deep Eutectic Solvents-p. 3138…”

Section: Lirong Zhai and Qilong Jiamentioning

confidence: 99%

“…The parameter smoothing factor (σ) in the network was optimized by the modified bat algorithm, which makes the network have a better classification effect. The experimental results compared the accuracy and F 1 ‐score of different fault diagnosis models to evaluate the diagnostic performance of the proposed model …”

mentioning

confidence: 99%

“…The experimental results compared the accuracy and F 1 -score of different fault diagnosis models to evaluate the diagnostic performance of the proposed model. [3] The pyridine-based deep eutectic solvents were designed and synthesized with n-ethylpyridinium bromide and two HBDs (n-formyl morpholine and levulinic acid). Two ternary systems, benzene + cyclohexane + DES and toluene + n-heptane + DES, were studied by liquid-liquid extraction.…”

mentioning

confidence: 99%

See 1 more Smart Citation

Issue Highlights

2019

Can J Chem Eng

View full text Add to dashboard Cite

“…KFDA, as a supervised method, is more suitable for feature extraction. [11][12][13][14][15] However, KFDA only considers the global characteristics of the data and ignores the local characteristics. Considering the local characteristics of the data, flow pattern learning was introduced and kernel local Fisher discriminant analysis (KLFDA) was proposed.…”

Section: Introductionmentioning

confidence: 99%

A novel imbalanced fault diagnosis method integrated KLFDA with improved cost‐sensitive learning ANBSVM

Jiang

et al. 2022

Can J Chem Eng

View full text Add to dashboard Cite

Fault diagnosis, as an important approach to ensure the safety and stability of industrial processes, has been widely studied in recent years. During the running process, it is noted that the normal data are always much more than the fault data, which demonstrates imbalanced characteristics and leads to a negative effect on the overall accuracy of fault diagnosis. Targeting the problem, a novel imbalanced fault diagnosis method integrated kernel local Fisher discriminant analysis (KLFDA) with improved adaptive near-Bayesian support vector machine (ANBSVM) is proposed in this paper. First, KLFDA is used to extract the non-linear features while maintaining the local spatial structure of the data by introducing flow pattern learning. Second, considering the imbalance characteristics of the data, the data set is divided into a majority class (normal data) and a minority class (fault data). The density distributions of the two classes in their overlapping region are characterized by the proportional function of variance. Third, by minimizing the Bayesian error under the proportion function, the weight factors are adaptively obtained and then introduced into the objective function of the support vector machine (SVM). Namely, a cost sensitivity-based ANBSVM classifier for fault diagnosis is constructed. Finally, by the simulation experiment on the Tennessee Eastman (TE) process, the comparison results show that the proposed ANBSVM-based fault diagnosis method makes progress in the performance of fault diagnosis with higher diagnostic accuracy and F1 score.

show abstract

Chemical process fault diagnosis based on enchanted machine‐learning approach

Cited by 7 publications

References 36 publications

A novel one‐dimensional convolutional neural network architecture for chemical process fault diagnosis

A novel one‐dimensional convolutional neural network architecture for chemical process fault diagnosis

Issue Highlights

A novel imbalanced fault diagnosis method integrated KLFDA with improved cost‐sensitive learning ANBSVM

Contact Info

Product

Resources

About