Adaptive multiscale convolutional neural network model for chemical process fault diagnosis

Ruoshi Qin; Jinsong Zhao

Your Location：

Home >

Browse articles >

Adaptive multiscale convolutional neural network model for chemical process fault diagnosis

Process Systems Engineering and Process Safety | Updated：2026-01-06

- Adaptive multiscale convolutional neural network model for chemical process fault diagnosis
- Adaptive multiscale convolutional neural network model for chemical process fault diagnosis
- 中国化学工程学报（英文版） 2022年50卷第10期页码：398-411
- Affiliations：
  
  1. State Key Laboratory of Chemical Engineering, Department of Chemical Engineering, Tsinghua University,Beijing,China,100084
  2. Beijing Key Laboratory of Industrial Big Data System and Application, Tsinghua University,Beijing,China,100084
- Author bio：
- Funds：
- DOI：
  中图分类号：
- 纸质出版：2022
- Accepted：
Scan QR Code
Ruoshi Qin, Jinsong Zhao. Adaptive multiscale convolutional neural network model for chemical process fault diagnosis[J]. 中国化学工程学报（英文版）, 2022,50(10):398-411.

Ruoshi Qin, Jinsong Zhao. Adaptive multiscale convolutional neural network model for chemical process fault diagnosis[J]. Chinese Journal of Chemical Engineering, 2022, 50(10): 398-411.
Ruoshi Qin, Jinsong Zhao. Adaptive multiscale convolutional neural network model for chemical process fault diagnosis[J]. 中国化学工程学报（英文版）, 2022,50(10):398-411. DOI：

Ruoshi Qin, Jinsong Zhao. Adaptive multiscale convolutional neural network model for chemical process fault diagnosis[J]. Chinese Journal of Chemical Engineering, 2022, 50(10): 398-411. DOI：

摘要

Abstract

Intelligent fault recognition techniques are essential to ensure the long-term reliability of manufacturing. Due to the variations in material

equipment and environment

the process variables monitored by sensors contain diverse data characteristics at different time scales or in multiple operating modes. Despite much progress in statistical learning and deep learning for fault recognition

most models are constrained by abundant diagnostic expertise

inefficient multiscale feature extraction and unruly multimode condition. To overcome the above issues

a novel fault diagnosis model called adaptive multiscale convolutional neural network (AMCNN) is developed in this paper. A new multiscale convolutional learning structure is designed to automatically mine multiple-scale features from time-series data

embedding the adaptive attention module to adjust the selection of relevant fault pattern information. The triplet loss optimization is adopted to increase the discrimination capability of the model under the multimode condition. The benchmarks CSTR simulation and Tennessee Eastman process are utilized to verify and illustrate the feasibility and efficiency of the proposed method. Compared with other common models

AMCNN shows its outstanding fault diagnosis performance and great generalization ability.

关键词

Keywords

references

浏览量

187

Downloads

CSCD

文章被引用时，请邮件提醒。

Submit

工具集

关联资源

From data to insight: Building a knowledge graph for risk analysis of hazardous chemical accidents

SmdaNet: A hierarchical hard sample mining and domain adaptation neural network for fault diagnosis in industrial process

Physically-consistent-WGAN based small sample fault diagnosis for industrial processes

Distributed process monitoring based on Kantorovich distance-multiblock variational autoencoder and Bayesian inference

Real-time risk prediction of chemical processes based on attention-based Bi-LSTM