高级检索

    骆楠, 祁佳康, 罗娜. 基于双向门控循环单元神经网络的间歇过程最终产品质量预测[J]. 华东理工大学学报(自然科学版), 2020, 46(6): 807-814. DOI: 10.14135/j.cnki.1006-3080.20190926001
    引用本文: 骆楠, 祁佳康, 罗娜. 基于双向门控循环单元神经网络的间歇过程最终产品质量预测[J]. 华东理工大学学报(自然科学版), 2020, 46(6): 807-814. DOI: 10.14135/j.cnki.1006-3080.20190926001
    LUO Nan, QI Jiakang, LUO Na. Product Quality Prediction in Batch Process Based on Bidirectional Gated Recurrent Unit Neural Network[J]. Journal of East China University of Science and Technology, 2020, 46(6): 807-814. DOI: 10.14135/j.cnki.1006-3080.20190926001
    Citation: LUO Nan, QI Jiakang, LUO Na. Product Quality Prediction in Batch Process Based on Bidirectional Gated Recurrent Unit Neural Network[J]. Journal of East China University of Science and Technology, 2020, 46(6): 807-814. DOI: 10.14135/j.cnki.1006-3080.20190926001

    基于双向门控循环单元神经网络的间歇过程最终产品质量预测

    Product Quality Prediction in Batch Process Based on Bidirectional Gated Recurrent Unit Neural Network

    • 摘要: 从具有共性的间歇过程终点质量预测问题出发,针对生产过程的时间序列特性进行分析,提出了一种基于双向门控循环单元神经网络的预测模型,对不等长间歇过程进行最终产品质量预测。结合实际生产中对预测值的要求,构建了适应间歇过程的损失函数,使模型在保证预测精度的前提下满足预测要求,从而获得更大的生产效益。将使用不同损失函数的双向门控循环(GRU)单元神经网络与多向偏最小二乘(MPLS)、神经网络(NN)、支持向量回归(SVR)以及门控循环单元神经网络的预测结果进行实验对比,结果表明双向门控循环单元神经网络具有更强的适用性和更高的准确性。

       

      Abstract: Compared with continuous process, batch process is an important industrial production mode with more flexibility. Products from each batch depend on market demands, which will make the process switch between different product stations. So, the final quality of products may become unstable due to various composition of raw materials. This kind of uncertainty brings great challenge to process modeling. Aiming at the problem of raw material uncertainty and the requirement of actual predicted value, the loss function of bidirectional gated recurrent unit neural network is modified, and then, utilized to predict the final quality prediction of unequal-length batch processes. The bidirectional gated recurrent unit neural network can integrate the time series information of the batch data, and fully exploit the inter-batch timing characteristics caused by the uncertainty of the raw materials. The improved loss function imposes different penalties on different predicted values such that the predicted values can meet the requirements in actual production. Finally, the proposed method is compared with multiple partial least squares (MPLS), neural network (NN), support vector regression (SVR) and gated recurrent unit (GRU) via an industrial process. It is shown via the results that the proposed method has better applicability and performs higher accuracy.

       

    /

    返回文章
    返回