Multiscale Interaction Purification-Based Global Context Network for Industrial Process Fault Diagnosis
Open Access
- 23 April 2025
- journal article
- research article
- Published by MDPI AG in Mathematics
- Vol. 13 (9) , 1371
Abstract
The application of deep convolutional neural networks (CNNs) has gained popularity in the field of industrial process fault diagnosis. However, conventional CNNs primarily extract local features through convolution operations and have limited receptive fields. This leads to insufficient feature expression, as CNNs neglect the temporal correlations in industrial process data, ultimately resulting in lower diagnostic performance. To address this issue, a multiscale interaction purification-based global context network (MIPGC-Net) is proposed. First, we propose a multiscale feature interaction refinement (MFIR) module. The module aims to extract multiscale features enriched with combined information through feature interaction while refining feature representations by employing the efficient channel attention mechanism. Next, we develop a wide temporal dependency feature extraction sub-network (WTD) by integrating the MFIR module with the global context network. This sub-network can capture the temporal correlation information from the input, enhancing the comprehensive perception of global information. Finally, MIPGC-Net is constructed by stacking multiple WTD sub-networks to perform fault diagnosis in industrial processes, effectively capturing both local and global information. The proposed method is validated on both the Tennessee Eastman and the Continuous Stirred-Tank Reactor processes, confirming its effectiveness.Keywords
Funding Information
- National Natural Science Foundation of China (62273080, B16009, 62403112, 62403114, 2023-BSBA-128, 0701-120337)
- 111 Project (62273080, B16009, 62403112, 62403114, 2023-BSBA-128, 0701-120337)
- Youth Fund of the National Natural Science Foundation of China (62273080, B16009, 62403112, 62403114, 2023-BSBA-128, 0701-120337)
- Doctoral Research Initiation Fund of Natural Science Foundation of Liaoning Province (62273080, B16009, 62403112, 62403114, 2023-BSBA-128, 0701-120337)
- Talent Research Grants Program of Dalian Minzu University (62273080, B16009, 62403112, 62403114, 2023-BSBA-128, 0701-120337)
This publication has 46 references indexed in Scilit:
- Dual‐noise autoencoder combining pseudo‐labels and consistency regularization for process fault classificationThe Canadian Journal of Chemical Engineering, 2024
- A novel fault diagnosis framework empowered by LSTM and attention: A case study on the Tennessee Eastman processThe Canadian Journal of Chemical Engineering, 2024
- A transformer-based approach for novel fault detection and fault classification/diagnosis in manufacturing: A rotary system applicationJournal of Manufacturing Systems, 2023
- A multigroup fault detection and diagnosis framework for large-scale industrial systems using nonlinear multivariate analysisExpert Systems with Applications, 2022
- A novel RSG-based intelligent bearing fault diagnosis method for motors in high-noise industrial environmentAdvanced Engineering Informatics, 2022
- Semi-supervised LSTM ladder autoencoder for chemical process fault diagnosis and localizationChemical Engineering Science, 2022
- Fault detection in Tennessee Eastman process with temporal deep learning modelsJournal of Industrial Information Integration, 2021
- Bidirectional deep recurrent neural networks for process fault classificationISA Transactions, 2020
- Identification of abnormal conditions in high-dimensional chemical process based on feature selection and deep learningChinese Journal of Chemical Engineering, 2020
- A novel deep learning based fault diagnosis approach for chemical process with extended deep belief networkISA Transactions, 2020