Quality Prediction Modeling for Industrial Processes Using Multiscale Attention-Based Convolutional Neural Network

• Published in: IEEE transactions on cybernetics Vol. 54; no. 5; pp. 2696 - 2707
• Main Authors: Yuan, Xiaofeng, Huang, Lingfeng, Ye, Lingjian, Wang, Yalin, Wang, Kai, Yang, Chunhua, Gui, Weihua, Shen, Feifan
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.05.2024; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Artificial neural networks; Convolutional neural network (CNN); Convolutional neural networks; Feature extraction; Feature maps; multiscale attention-based CNN (MSACNN); Performance evaluation; Prediction models; Predictive models; quality prediction; Soft sensors; Spatiotemporal phenomena; Topology
• ISSN: 2168-2267; 2168-2275; 2168-2275
• DOI: 10.1109/TCYB.2024.3365068

Soft sensors have been increasingly applied for quality prediction in complex industrial processes, which often have different scales of topology and highly coupled spatiotemporal features. However, the existing soft sensing models usually face difficulties in extracting the multiscale local spatiotemporal features in multicoupled complex process data and harnessing them to their full potential to improve the prediction performance. Therefore, a multiscale attention-based CNN (MSACNN) is proposed in this article to alleviate such problems. In MSACNN, convolutional kernels of different sizes are first designed in parallel in the convolutional layers, which can generate feature maps containing local spatiotemporal features at different scales. Meanwhile, a channel-wise attention mechanism is designed on the feature maps in parallel to get their attention weights, representing the significance of the local spatiotemporal feature at different scales. The superiority of the proposed MSACNN over the other state-of-the-art methods is validated through the performance evaluation in two real industrial processes.