Flexible Clockwork Recurrent Neural Network for multirate industrial soft sensor. (November 2022)

• Record Type: Journal Article
• Authors: Chang, Shuchao; Chen, Xu; Zhao, Chunhui
• Is Part Of: Journal of process control. Volume 119(2022)
• Page Start: 86
• Page End: 100
• Publication Date: 2022-11
• Subjects: Multirate industrial processes -- Soft sensor -- Recurrent neural network -- Flexible clockwork mechanism; Process control -- Periodicals; Fabrication -- Contrôle -- Périodiques; Process control; Periodicals; Electronic journals; 660.281
• DOI: 10.1016/j.jprocont.2022.09.008
• Languages: English
• ISSNs: 0959-1524

Abstract

Abstract: Data-driven-based soft sensors play significant roles in predicting key quality and optimizing the production process. Considering the difficulty and cost of variable acquisition, these variables are generally collected at different sampling rates. However, traditional soft sensor methods assume that data are uniformly sampled, which cannot be directly applied to multirate industrial scenarios. In this paper, a Flexible Clockwork Recurrent Neural Network (FCW-RNN) is proposed for multirate industrial soft sensors. First, the multirate data are divided into different variable groups according to their sampling rates. Then, an FCW-RNN is developed to map these variable groups into a common hidden space separately. A flexible clockwork mechanism is designed to incrementally update the hidden space at each moment based on the specific variable groups that have been sampled. Considering different sampling rates, the hidden space will be updated with time until all variable groups are sampled. In this way, we integrate the information of multirate data into the uniform hidden space step by step. Finally, a prediction module is established to calculate the hard-to-measure variables based on the hidden space. The effectiveness of FCW-RNN is demonstrated in a real coal mill case. Highlights: A soft sensor is proposed for industrial variables with different sampling rates. Multirate data are synergistically integrated within a unified framework. We overcome error accumulation and information loss problems in multirate data. The validity of the proposed method is illustrated with a real coal mill case.