CIESC Journal ›› 2018, Vol. 69 ›› Issue (3): 900-906.DOI: 10.11949/j.issn.0438-1157.20171435

Previous Articles     Next Articles

Automatic structure and parameters tuning method for deep neural network soft sensor in chemical industries

WANG Kangcheng1,2, SHANG Chao1,2, KE Wensi1,2, JIANG Yongheng1,2, HUANG Dexian1,2   

  1. 1 Department of Automation, Tsinghua University, Beijing 100084, China;
    2 Tsinghua National Laboratory for Information Science and Technology, Beijing 100084, China
  • Received:2017-10-30 Revised:2017-11-07 Online:2018-03-05 Published:2018-03-05
  • Supported by:

    supported by the National Natural Science Foundation of China (61673236, 61433001) and the Seventh Framework Program of the European Union (P7-PEOPLE-2013-IRSES-612230).

化工过程深度神经网络软测量的结构与参数自动调整方法

王康成1,2, 尚超1,2, 柯文思1,2, 江永亨1,2, 黄德先1,2   

  1. 1 清华大学自动化系, 北京 100084;
    2 清华信息科学与技术国家实验室(筹), 北京 100084
  • 通讯作者: 黄德先
  • 基金资助:

    国家自然科学基金项目(61673236,61433001);欧盟第七框架计划项目(P7-PEOPLE-2013-IRSES-612230)。

Abstract:

Deep learning has been applied to the field of soft sensing in process industries. However, the structure and parameters of deep neural network (DNN) have to be tuned manually, which require solid fundamental knowledge about machine learning and rich experiences on parameters tuning. Complicated tuning procedure restricts generalization application of deep learning in chemical industries. A structure and parameters tuning method for DNN soft sensor with little manual intervention was proposed by systematic analysis on selection process of each essential DNN parameter from massive experiments. The presented method could greatly simplify the tuning procedure and offer a reference for engineers to study and use deep learning. Studies on crude-oil distillation and coal gasification process verified effectiveness and generality of the proposed method.

Key words: deep learning, prediction, parameter tuning, algorithm, neural network

摘要:

深度学习在流程工业的软测量领域已经得到了应用。然而,深度神经网络(DNN)的结构和参数需要人工调整,这需要扎实的机器学习知识基础和丰富的参数调整经验,烦琐的调整过程限制了深度学习在化工领域的推广应用。在大量实验的基础上,对DNN的每个关键参数的选取过程进行了系统化的分析,提出了几乎无须人工干预的基于DNN软测量的结构和参数自动调整方法,极大地简化了参数调整过程,能够给工程技术人员学习及应用深度学习提供参考。对原油蒸馏装置及煤气化装置的案例分析验证了所提出方法的有效性和通用性。

关键词: 深度学习, 预测, 参数调整, 算法, 神经网络

CLC Number: