Abstract
Due to the limitations of measurement technology and cost in industrial processes, it is difficult to obtain measured values of variables with different properties, such as flow rate and temperature, under uniform sampling rates. This leads to the ubiquitous multirate sampling characteristics of the collected industrial process data, which brings great challenges to the quality prediction of industrial processes. To address this issue, this paper proposes a novel quality prediction modeling method based on the transformer modal called Multirate-Former for multirate industrial processes. First, the raw data is chunked by arranging data variables to the same sampling rate. Then, the hierarchical coarse-grained and fine-grained complementation of the data is completed by the multi-layer convolution network and transformer. Notably, a novel sampling type coding method is proposed to explore the missing pattern of multirate process data. After the above pre-training, the patched completed dataset and better initial weights are provided for the subsequent fine-tuning process. Finally, the multi-step prediction error of quality variables is exploited to fine-tune the entire network parameters. The proposed method is applied to an industrial debutanizer column and an actual industrial hydrocracking process for multirate multi-step prediction. Experimental results demonstrate that the proposed method outperforms other state-of-the-art methods in dealing with multi-sampling rate types of industrial process data.
Funding Information
  • National Natural Science Foundation of China (92267205, 61988101)
  • science and technology innovation Program of Hunan Province (2021RC4054, 2021JJ10065, 2020RC3003)
  • CAAI-Huawei MindSpore Open Fund (CAAIXSJLJJ-2022-001A)

This publication has 29 references indexed in Scilit: