基于改进KFDA与DE优化SOM的故障诊断模型及其化工过程诊断

doi:10.16085/j.issn.1000-6613.2021-0821

摘要/Abstract

摘要：

针对化工过程故障诊断数据存在高维度、故障特征不易区分、自组织映射（self-organizing map，SOM）网络易陷入局部最优等问题，提出了一种基于改进核Fisher判别分析（kernel Fisher discriminant analysis，KFDA）与差分进化算法（differential evolution，DE）优化SOM神经网络相结合的故障诊断方法。该方法首先利用欧氏距离对类间距进行加权处理，以避免因类间距离过大造成投影后的数据存在重叠的问题，使故障数据样本获得较好的投影效果，优化分类性能；然后,利用DE算法对SOM神经网络的权值向量进行动态调整，有效避免了由于“死神经元”的出现陷入局部最优的问题；最后，通过对田纳西-伊斯曼（tennessee-eastman，TE）过程和对二甲苯（paraxylene，PX）歧化工艺过程的故障数据进行诊断测试。结果表明，与传统SOM网络相比，提出的KFDA-DE-SOM算法具有较高的分类诊断精度，可有效应用于化工过程的故障诊断。

关键词: 过程控制, 神经网络, 优化设计, 差分进化算法, 故障诊断

Abstract:

Due to the high dimension of fault diagnosis data in chemical process, the fault features are not easy to distinguish, and the SOM network is easy to fall into the problem of local best. A fault diagnosis method based on KFDA and DE algorithm to optimize SOM neural network was proposed. Firstly, Euclidean distance was used to weight the distance between classes, so as to avoid the problem of overlapping of projected data due to the large distance between classes. As a consequence, the fault data samples could obtain better projection effect and optimize the classification performance. Then, the DE algorithm was used to dynamically adjust the weight vectors of SOM neural network, which effectively avoids the problem of falling into local optimum due to the appearance of "dead neurons". The fault data of TE process and PX disproportionation process were tested. The results showed that compared with traditional SOM network, KFDA-DE-SOM algorithm has higher classification diagnosis accuracy and can be effectively applied to the fault diagnosis of the chemical process.

Key words: process control, neural network, optimization design, differential evolution algorithm, fault diagnosis

中图分类号:

TP277

李国友, 张新魁, 才士文, 贾曜宇, 宁泽. 基于改进KFDA与DE优化SOM的故障诊断模型及其化工过程诊断[J]. 化工进展, 2022, 41(4): 1793-1801.

LI Guoyou, ZHANG Xinkui, CAI Shiwen, JIA Yaoyu, NING Ze. Study on fault diagnosis model and chemical process fault diagnosis based on improved KFDA and DE optimized SOM[J]. Chemical Industry and Engineering Progress, 2022, 41(4): 1793-1801.

图/表 13

参考文献 21

1	FENG Y, LI H X. Dynamic spatial-independent-component-analysis-based abnormality localization for distributed parameter systems[J]. IEEE Transactions on Industrial Informatics, 2020, 16(5): 2929-2936.
2	ZHANG Y B, ZHANG Y L, ZHANG J, et al. Collaborative representation cascade for single-image super-resolution[J]. IEEE Transactions on Systems, Man, and Cybernetics: Systems, 2019, 49(5): 845-860.
3	BERNHARD Schölkopf, JOHN Platt, THOMAS Hofmann. Advances in neural information processing systems 19[M]. Cambridge: The MIT Press, 2007.
4	FUREY T S, CRISTIANINI N, DUFFY N, et al. Support vector machine classification and validation of cancer tissue samples using microarray expression data[J]. Bioinformatics, 2000, 16(10): 906-914.
5	ZHANG Z P, ZHAO J S. A deep belief network based fault diagnosis model for complex chemical processes[J]. Computers & Chemical Engineering, 2017, 107: 395-407.
6	ZHANG W, PENG G L, LI C H, et al. A new deep learning model for fault diagnosis with good anti-noise and domain adaptation ability on raw vibration signals[J]. Sensors, 2017, 17(2): 425.
7	MIKA S, RATSCH G, WESTON J, et al. Fisher discriminant analysis with kernels[C]//Neural Networks for Signal Processing IX: Proceedings of the 1999 IEEE Signal Processing Society Workshop, Madison, USA, IEEE, 1999: 41-48.
8	PRINCIPE J C, WANG L. Non-linear time series modeling with self-organization feature maps[C]//Proceedings of 1995 IEEE Workshop on Neural Networks for Signal Processing, Cambridge, USA, IEEE, 1995: 11-20.
9	FORNELLS A, GOLOBARDES E, MARTORELL J M, et al. Measuring the applicability of self-organization maps in a case-based reasoning system[C]//Pattern Recognition and Image Analysis, Girona, Spain, 2007.
10	KOHONEN T. The self-organizing map[J]. Neurocomputing, 1998, 21(1/2/3): 1-6.
11	HAN J W, LI Q X, WU H R, et al. Prediction of cooling efficiency of forced-air precooling systems based on optimized differential evolution and improved BP neural network[J]. Applied Soft Computing, 2019, 84: 105733.
12	CHEN X Y, YAN X F. Using improved self-organizing map for fault diagnosis in chemical industry process[J]. Chemical Engineering Research and Design, 2012, 90(12): 2262-2277.
13	张, 郑晓东, 李劲松, 等. 基于SOM和PSO的非监督地震相分析技术[J]. 地球物理学报, 2015, 58(9): 3412-3423.
	ZHANG Yan, ZHENG Xiaodong, LI Jinsong, et al. Unsupervised seismic facies analysis technology based on SOM and PSO[J]. Chinese Journal of Geophysics, 2015, 58(9): 3412-3423.
14	马立玲, 徐发富, 王军政. 一种基于改进核Fisher的故障诊断方法[J]. 化工学报, 2017, 68(3): 1041-1048.
	MA Liling, XU Fafu, WANG Junzheng. A fault diagnosis method based on improved kernel Fisher[J]. CIESC Journal, 2017, 68(3): 1041-1048.
15	孟亚辉. 基于最优特征集和马氏距离KNN分类的机械故障分类方法研究[J]. 机械设计与制造, 2017(7): 98-102.
	MENG Yahui. A method of mechanical fault classification based on optimal feature subset and K-nearest neighbor using mahalanobis distance[J]. Machinery Design & Manufacture, 2017(7): 98-102.
16	STORN R, PRICE K. Differential evolution—A simple and efficient heuristic for global optimization over continuous spaces[J]. Journal of Global Optimization, 1997, 11(4): 341-359.
17	TUO S H, ZHANG J Y, YUAN X G, et al. A new differential evolution algorithm for solving multimodal optimization problems with high dimensionality[J]. Soft Computing, 2018, 22(13): 4361-4388.
18	QIAO B H, LIU J. Multi-objective dynamic economic emission dispatch based on electric vehicles and wind power integrated system using differential evolution algorithm[J]. Renewable Energy, 2020, 154: 316-336.
19	冯海超. 基于半监督及知识迁移的过程监测方法研究[D]. 沈阳: 东北大学, 2015.
	FENG Haichao. Research on process monitoring method based on semi-supervised and knowledge transfer[D]. Shenyang: Northeastern University, 2015.
20	李宛桐. 典型对二甲苯(PX)装置的危险性分析[D]. 北京: 北京化工大学, 2015.
	LI Wantong. Risk analysis of the typical p-xylene unit[D]. Beijing: Beijing University of Chemical Technology, 2015.
21	钟育恒, 黄佳莉, 李瀚, 等. 基于故障树法的PX生产过程易发爆炸事故风险分析[J]. 广东化工, 2020, 47(11): 97-98, 122.
	ZHONG Yuheng, HUANG Jiali, LI Han, et al. Risk analysis of explosion-prone accidents in PX production process based on FTA method[J]. Guangdong Chemical Industry, 2020, 47(11): 97-98, 122.

故障点	故障状态描述	故障类型
1	A/C进料比例变化，B成分不变（流4）	阶跃型
2	B成分变化，A/C进料比例不变（流4）	阶跃型
4	反应器冷却水入口温度变化	阶跃型
5	冷凝器冷却水入口温度变化	阶跃型
6	A进料损失（流1）	阶跃型
14	反应器冷却水阀门	黏滞型

故障点	故障状态描述	故障类型
1	A/C进料比例变化，B成分不变（流4）	阶跃型
2	B成分变化，A/C进料比例不变（流4）	阶跃型
4	反应器冷却水入口温度变化	阶跃型
5	冷凝器冷却水入口温度变化	阶跃型
6	A进料损失（流1）	阶跃型
14	反应器冷却水阀门	黏滞型

故障点	改进KFDA-DE-SOM	SOM	KFDA-SOM
1	98.9	95.5	96.9
2	99.1	94.9	97.3
4	98.1	52.6	97.7
5	100	30.2	97.5
6	100	100	100
14	97.9	42.3	83.8

故障点	改进KFDA-DE-SOM	SOM	KFDA-SOM
1	98.9	95.5	96.9
2	99.1	94.9	97.3
4	98.1	52.6	97.7
5	100	30.2	97.5
6	100	100	100
14	97.9	42.3	83.8

故障点	故障状态描述	故障类型
1	歧化反应进料变化	阶跃变化
2	汽提塔气体流速过快	阶跃变化
3	氢气补充量不足	阶跃变化
4	歧化反应压力变化	阶跃变化
5	加热炉温度过高	阶跃变化