基于模糊粗糙集和鲸鱼优化支持向量机的化工过程故障诊断

PDF(2133 KB)

振动与冲击 ›› 2022, Vol. 41 ›› Issue (2) : 177-184.

论文

李国友，杨梦琪，杭丙鹏，李晨光，王维江

作者信息 +

Fault diagnosis of chemical processes based on the SVM optimized by fuzzy rough sets and a whale optimization algorithm

LI Guoyou,YANG Mengqi,HANG Bingpeng,LI Chenguang,WANG Weijiang

Author information +

文章历史 +

摘要

针对化工过程复杂，故障数据量大、属性多，难以保证故障诊断准确率和速度的问题，提出了一种基于模糊粗糙集(fuzzy rough sets ，FRS)和鲸鱼优化的支持向量机(support vector machine ，SVM)的化工过程故障诊断方法。通过对化工过程历史数据分析，判别故障类型。首先，利用模糊粗糙集对离散化后的过程数据进行特征选择，经过属性约简得出最小故障特征集合；然后，利用一种新型元启发式算法——鲸鱼优化算法(whale optimization algorithm ，WOA)，对支持向量机的参数进行优化，根据全局最佳适应度函数值，构建故障数据分类模型；最后，将属性约简后的数据集输入到鲸鱼优化的支持向量机故障分类模型中，实现化工过程的故障诊断。利用田纳西-伊斯曼(Tennessee Eastman ，TE)过程对构建的FRS-WOA-SVM故障分类模型进行测试及比较，结果表明，该方法故障诊断准确率高、诊断速度快，可以有效地对化工过程中的故障做出诊断。

Abstract

The chemical process is complex and it is not easy to establish accurate mathematical model. In order to solve the problem that it is difficult to ensure the accuracy and speed of fault diagnosis due to the large amount of fault data and many attributes, a fault diagnosis method of chemical process based on support vector machine (SVM) optimized by fuzzy rough sets (FRS) and whale optimization algorithm (WOA) is proposed. By analyzing the historical data of chemical process, the fault types can be identified. Firstly, the fuzzy rough sets is used to select the features of the discretized process data, and the minimum fault feature set is obtained by attribute reduction. At the same time, whale optimization algorithm, a new meta heuristic algorithm, is used to optimize the parameters of SVM, and a fault data classifier is constructed according to the global optimal fitness function. Finally, the data set after attribute reduction is input into SVM fault classifier optimized by whale to text FRS-WOA-SVM fault classifier, and compare with fault classifiers optimized by genetic algorithm and optimization algorithm to realize the fault diagnosis of chemical process. Using Tennessee Eastman process (TE) particle swarm optimization. The results show that the method has high accuracy and fast diagnosis speed, and can effectively diagnose the faults in the chemical process.

导出引用

李国友，杨梦琪，杭丙鹏，李晨光，王维江. 基于模糊粗糙集和鲸鱼优化支持向量机的化工过程故障诊断[J]. 振动与冲击, 2022, 41(2): 177-184

LI Guoyou,YANG Mengqi,HANG Bingpeng,LI Chenguang,WANG Weijiang. Fault diagnosis of chemical processes based on the SVM optimized by fuzzy rough sets and a whale optimization algorithm[J]. Journal of Vibration and Shock, 2022, 41(2): 177-184

参考文献

[1] Dong Y X, Tian W D, Zhang X. Fault diagnosis of chemical process based on multivariate PCC optimization[C]//2017 36th Chinese Control Conference (CCC). Dalian, China: IEEE, 2017: 7370-7375.
[2] 周东华, 胡艳艳. 动态系统的故障诊断技术[J]. 自动化学报, 2009, 35(6): 748-758.
    Zhou D H, Hu Y Y. Fault diagnosis technology of dynamic system[J]. Acta Automatica Sinica, 2009, 35(6): 748-758.
[3] 周家驹, 许志宏, 石乐明, 等. 人工神经网络方法在材料性能预报及化工过程故障诊断中的应用[J]. 化工冶金, 1993, 14(1): 57-62.
    Zhou J J, Xu H Z, Shi L M, et al. Application of artificial neural network in material property prediction and chemical process fault diagnosis[J]. Engineering Chemistry & Metallurgy, 1993, 14(1): 57-62.
[4] Chang J, Wang G C, Yong W, et al. Based on genetic algorithm and BP network to fault diagnosis of fermentation process[C]//Control & Decision Conference. Yantai, China: IEEE, 2008: 578-581.
[5] Tian J , Gao M , Li K , et al. Fault Detection of Oil Pump Based on Classify Support Vector Machine[C]//2007 IEEE International Conference on Control and Automation. Guangzhou, China: IEEE, 2007: 549-553.
[6] Xiao Y, Hou L, Su C. Research on Fault Diagnosis in Reactor-Regenerator System of FCCU based on PSO-SVM[C]//2011 Chinese Control and Decision Conference (CCDC). Mianyang, China: IEEE, 2011: 2935-2938.
[7] Emary E, Zawbaa H M, Salam M A. A proposed whale search algorithm with adaptive random walk[C]//2017 13th IEEE International Conference on Intelligent Computer Communication and Processing (ICCP). Cluj-Napoca, Romania: IEEE, 2017: 171-177.
[8] Hassib E M, El-Desouky A I, Labib L M, et al. WOA+BRNN: An imbalanced big data classification framework using Whale optimization and deep neural network[J]. Soft Computing A Fusion of Foundations Methodologies & Applications, 2020, 24(8): 5573-5592.
[9] Du A L, Wang Y, Wang J, et al. Research of fault diagnosis based on rough sets and support vector machine[C]//2011 10th International Conference on Electronic Measurement & Instruments. Chengdu, China: IEEE, 2011: 110-113.
[10] Liu C X, The Study of the Application to Data Mining with Rough Sets Theory.[C]//International Conference on Internet Technology and Applications. Wuhan, China: IEEE, 2011: 1-4.
[11] 苗夺谦, 李道国. 粗糙集理论、算法与应用[M]. 北京: 清华大学出版社, 2008: 235.
Miao D Q, Li D G. Rough set theory, algorithm and application[M]. Beijing: Tsinghua University Press, 2008: 235.
[12] 王鲜芳, 王岁花, 杜昊泽, 等. 基于模糊粗糙集和支持向量机的化工过程故障诊断[J]. 控制与决策, 2015, 30(2): 353-356.
Wang X F, Wang S H, Du H Z, et al. Fault diagnosis of chemical process based on fuzzy rough set and support vector machine[J]. Control and Decision, 2015, 30(2): 353-356.
[13] Tsang E C C, Chen D, Yeung D S, et al. Attributes Reduction Using Fuzzy Rough Sets[J]. IEEE Transactions on Fuzzy Systems, 2008, 16(5): 1130-1141.
[14] 赵慧材. 采用模糊粗糙集约简属性的支持向量机短期负荷预测方法[D]. 长沙: 长沙理工大学, 2014.
Zhao H C. Short term load forecasting method of support vector machine using fuzzy rough set reduction attribute[D]. Changsha: Changsha University of technology, 2014.
[15] Wang X Z, Ha Y, Chen D G. On the reduction of fuzzy rough sets[C]//International Conference on Machine Learning and Cybernetics. Guangzhou, China: IEEE, 2005: 3174-3178.
[16] Mirjalili S, Lewis A. The Whale Optimization Algorithm[J]. Advances in Engineering Software, 2016, 95: 51- 67.
[17] Alba E, Dorronsoro B. The exploration/exploitation tradeoff in dynamic cellular genetic algorithms[J]. IEEE Transactions on Evolutionary Computation, 2005, 9(2): 126-142.
[18] Lin L, Gen M. Auto-tuning strategy for evolutionary algorithms: balancing between exploration and exploitation[J]. Soft Computing, 2009, 13(2): 157–168.
[19] 张学工. 关于统计学习理论与支持向量机[J]. 自动化学报, 2000, 26(1): 32-42.
Zhang X G. On statistical learning theory and support vector machine[J]. Acta Automatica Sinica, 2000, 26(1): 32-42.
[20] 杨智明. 面向不平衡数据的支持向量机分类方法研究[D]. 哈尔滨, 哈尔滨工业大学, 2009.
Yang Z M. Research on classification method of support vector machine for unbalanced data[D]. Harbin, Harbin Institute of technology, 2009.
[21] 王革丽, 杨培才, 毛宇清, 等. 基于支持向量机方法对非平稳时间序列的预测[J]. 物理学报, 2008, 57(2): 714-719.
    Wang G L, Yang P C, Mao Y Q, et al. Prediction of nonstationary time series based on support vector machine[J]. Acta Physica Sinica, 2008, 57(2): 714-719.
[22] 吴明圣. 径向基神经网络和支持向量机的参数优化方法研究及应用[D]. 中南大学, 2007.
Wu M S. Research and application of parameter optimization method of radial basis function neural network and support vector machine[D]. Central South University, 2007.
[23] 傅军栋, 陈俐, 康水华, 等. 基于蜻蜓算法和支持向量机的变压器故障诊断[J]. 华东交通大学学报, 2016, 33(4): 103-112.
Fu J D, Chen L, Kang S H, et al. Transformer fault diagnosis based on Dragonfly algorithm and support vector machine[J]. Journal of East China Jiaotong University, 2016, 33(4): 103-112.
[24] 王小川, 史峰, 郁磊, 等. MATLAB神经网络43个案例分析[M]. 北京: 北京航空航天大学出版社, 2013: 133.
Wang X C, Shi F, Yu L, et al. Analysis of 43 cases of MATLAB neural network[M]. Beijing: Beijing University of Aeronautics and Astronautics Press, 2013: 127-128.
[25] Zhang X, Hu J, Zhang L. Performance assessment of fault classifier of chemical plant based on support vector machine[C]//2016 12th International Conference on Natural Computation and 13th Fuzzy Systems and Knowledge Discovery (ICNC-FSKD). Changsha, China: IEEE, 2016: 46-51.
[26] Kazemi Z, Safavi A A, Pouresmaeeli S. An online approach for fault detection and diagnosis of gas pressure reduction stations based on DCS-PCS7[C]//2016 24th Iranian Conference on Electrical Engineering (ICEE). Shiraz, Iran: IEEE, 2016: 1060-1065.
[27] Gao Q, Wang X M, Dong C, et al. Data preprocessing for prediction of rerecirculating water chemistry faults[C]//2010 International Conference on Computer Application and System Modeling (ICCASM 2010), Taiyuan, China: IEEE, 2010, 14: 553-556.
[28] Ms L H C, Russell E L, Braatz R D. Tennessee Eastman Process[M]//Fault Detection and Diagnosis in Industrial Systems. Springer London, 2001: 104.
[29] Li H, Xiao D Y. Fault diagnosis of Tennessee Eastman process using signal geometry matching technique[J]. Journal on Advances in Signal Processing, 2011, 2011(1): 83.
[30] 杨赛楠. 粗糙集神经网络故障诊断系统的方法研究及应用[D]. 无锡: 江南大学, 2007.
Yang S N. Research and application of rough set neural network fault diagnosis system[D]. Wuxi: Jiangnan University, 2007.