VMD-SEAE-TL-Based Data-Driven soft sensor modeling for a complex industrial batch processes. (July 2022)

• Record Type: Journal Article
• Authors: Ren, Jun-Chao; Liu, Ding; Wan, Yin
• Is Part Of: Measurement. Volume 198(2022)
• Publication Date: 2022-07
• Subjects: Batch industrial processes -- Soft sensor modeling -- Variational mode decomposition -- Stacked enhanced autoencoder -- Transfer learning; Weights and measures -- Periodicals; Measurement -- Periodicals; Measurement; Weights and measures; Periodicals; 530.8
• DOI: 10.1016/j.measurement.2022.111439
• Languages: English
• ISSNs: 0263-2241

Abstract

Highlight: A stack enhanced autoencoder algorithm based on VMD is proposed in this paper. Here, VMD is implemented by decomposing and reconstructing the original data to eliminate the noise in the data. Based on the reconstructed process data, SEAE is able to better extract the deep features of the process data and retain the original data information to the maximum extent, so as to accomplish the accurate prediction of key variables. For the prediction of key quality variables in the target domain of industrial processes, an MMD-based transfer learning algorithm is proposed. The method is integrated into VMD-SEAE for online fine-tuning of SEAE network models to avoid model retraining. Also, the proposed method retains the source domain data feature information, which enables the transferred model to accurately predict the key variables in the target domain, thus solving the domain adaptation problem as well. Based on two actual industrial process cases, the proposed soft-sensor modeling method is used for the online prediction of quality-related variables. The experimental results show that the proposed method has accurate prediction performance. Abstract: On complex batch industrial processes, soft sensor modeling plays a key role in process control and monitoring. Considering the nonlinearity, time-varying, and repetitive nature of the batch process, this paper proposes a soft sensor modeling method (VMD-SEAE-TL) based on variational mode decomposition (VMD), stacked enhanced autoencoder (SEAE) and transfer learning (TL) algorithms for online detection of key variables in batch industrial production processes. Firstly, the raw industrial process data are decomposed and reconstructed using VMD to achieve denoising and reduce the non-smooth characteristics of the data series. Secondly, based on the reconstructed process data, the SEAE network is used to deeply extract data feature information and achieve high accuracy regression prediction. Here, during the SEAE training process, each layer of the enhanced autoencoder (EAE) network reconstructs both the network input and the original input. The purpose of this operation is to extract the deep feature information of the process data and to ensure that there is no cumulative loss of the original input information. Further, it is considered that the working conditions in the batch industrial production process are time-varying, and this often makes it difficult for the model trained on the source domain data to accurately predict the trend of the process variables in the target domain. For this problem, the maximum mean deviation (MMD)-based transfer learning algorithm is introduced, which is used to solve the domain adaption problem with changing working conditions. Finally, based on two actual industrial process cases, the effectiveness and practicality of the proposed soft sensor are verified by various experimental results.