石油学报(石油加工) ›› 2021, Vol. 37 ›› Issue (1): 121-129.doi: 10.3969/j.issn.1001-8719.2021.01.012

• 研究报告 • 上一篇    下一篇

基于随机森林的不可靠数据化工过程故障诊断方法

冯子芸1,王治红1,戴一阳2   

  1. 1. 西南石油大学 化学化工学院,四川 成都 610500;
    2.  四川大学 化学工程学院,四川 成都 610065
  • 收稿日期:2019-10-28 修回日期:2020-01-08 出版日期:2021-01-25 发布日期:2021-01-12
  • 通讯作者: 戴一阳,男,副研究员,博士,从事油气化工过程模拟与优化,故障诊断及安全管理等研究,E-mail:daiyy@scu.edu.cn E-mail:daiyy@scu.edu.cn
  • 作者简介:第一作者:冯子芸,女,硕士研究生,从事化工过程故障诊断方向的研究,E-mail:fzy1260@126.com
  • 基金资助:
    国家自然科学基金项目(21706220)资助

Random Forest Based Fault Diagnosis Method for Chemical Process With Unreliable Data

FENG Ziyun1, WANG Zhihong1, DAI Yiyang2   

  1. 1. College of Chemistry and Chemical Engineering, Southwest Petroleum University, Chengdu 610500, China; 2. School of Chemical Engineering, Sichuan University, Chengdu 610065, China
  • Received:2019-10-28 Revised:2020-01-08 Online:2021-01-25 Published:2021-01-12

摘要: 针对化工过程的监测数据存在数据缺失、漂移和卡死等不可靠现象可能严重影响故障诊断的准确性问题,提出了一种基于随机森林(RF)的故障诊断方法。利用训练集对RF分类器进行训练和调优,得到最优的RF分类器模型,确定决策树数量和随机属性个数,最后将存在不可靠变量的测试集数据输入RF分类器模型,利用随机森林方法的强抗干扰能力,实现对存在不可靠数据的化工过程进行诊断。将该方法应用到田纳西-伊斯曼(TE)过程的故障诊断,并与反向传播神经网络(BPNN)、径向基函数神经网络(RBFNN)和深度信念网络(DBN)方法相比,结果表明,基于RF的故障诊断方法能在数据不可靠的条件下,更加有效地检测并识别故障类型,在实际工业环境的应用中具有一定的优越性。

关键词: 随机森林, 故障诊断, 数据不可靠, 机器学习, TE过程

Abstract: The monitoring data of chemical process has unreliable problems such as data missing, drifting and stuck, which may seriously affect the accuracy of fault diagnosis. To solve the problem, a fault diagnosis method which is based on random forest (RF) was proposed. The RF classifier was trained and tuned by using the training set to obtain the optimal RF classifier model. The numbers of decision trees and the random attributes were determined. Finally, the test set with unreliable data was input into the RF classifier model to diagnose the faults using the advantage of strong anti-interference ability of RF. Tennessee-Eastman (TE) process was used to test the performance of the proposed RF based fault diagnosis method. Testing results show that compared to the Back Propagation Neural Network (BPNN), Radial Basis Function Neural Network (RBFNN) and Deep Belief Network (DBN), the RF-based fault diagnosis method can detect and identify fault types more effectively with unreliable data. It is shown that the proposed method is superior in the application of practical industrial environment.

Key words: random forest, fault diagnosis, unreliable data, machine learning, TE process

中图分类号: