基于深度置信网络的炼化空压机故障诊断方法

doi:10.11949/j.issn.0438-1157.20181357

化工学报 ›› 2019, Vol. 70 ›› Issue (2): 757-763.DOI: 10.11949/j.issn.0438-1157.20181357

基于深度置信网络的炼化空压机故障诊断方法

鲁春燕^1,^2,³(),李炜^1,^2,³()

1. 兰州理工大学电气工程与信息工程学院，甘肃兰州 730050
2. 甘肃省工业过程先进控制重点实验室，甘肃兰州 730050
3. 兰州理工大学国家级电气与控制工程实验教学中心，甘肃兰州 730050

收稿日期:2018-11-16 修回日期:2018-11-26 出版日期:2019-02-05 发布日期:2019-02-05
通讯作者: 李炜
作者简介:<named-content content-type="corresp-name">鲁春燕</named-content>(1976－)，女，博士研究生，副教授，<email>luchunyan@sina.com</email>|李炜（1963－），女，博导，教授，<email>liwei@lut.cn</email>
基金资助:
国家自然科学基金项目(61364011, 61461028);甘肃省先进控制重点实验室开放基金项目(XJK201809)

Fault diagnosis method of petrochemical air compressor based on deep belief network

Chunyan LU^1,^2,³(),Wei LI^1,^2,³()

1. College of Electrical and Information Engineering, Lanzhou University of Technology, Lanzhou 730050, Gansu, China
2. Key Laboratory of Gansu Advanced Control for Industrial Processes, Lanzhou 730050, Gansu, China
3. National Experimental Teaching Center of Electrical and Control Engineering, Lanzhou University of Technology, Lanzhou 730050, Gansu, China

Received:2018-11-16 Revised:2018-11-26 Online:2019-02-05 Published:2019-02-05
Contact: Wei LI

摘要/Abstract

摘要：

针对炼化空压机故障诊断中故障机理复杂、先验知识欠缺，且传统浅层神经网络诊断精度不高等问题，结合深度置信网络（DBN）在特征提取和处理非线性数据等方面的优势，提出一种基于DBN的炼化空压机故障诊断方法。该方法利用空压机状态监测实测数据，实现训练网络的无监督特征学习和有监督微调，构建空压机故障的深层网络模型，从而实现对空压机故障类型的有效智能诊断。为评估该方法的有效性，与传统的故障诊断方法进行了比较研究，结果表明，该方法的诊断精度优于传统的故障诊断方法，且稳定性更好。

关键词: 空压机, 深度置信网络模型, 故障诊断, 稳定性

Abstract:

According to the complexity of fault mechanism, the lack of prior knowledge, and the low diagnosis precision of traditional shallow layer neural network for the fault diagnosis of petrochemical air compressor, a kind of petrochemical air compressor fault diagnosis method is put forward based on the deep belief network because of its advantage in feature extraction and nonlinear data processing. By using state monitoring data of the air compressor, the method realizes the unsupervised characteristics learning and supervised fine-tuning of training network, constructs the deep network model of the air compressor fault, thus achieving the effective intelligent diagnosis for fault types of the air compressor. The effectiveness of the method is compared with the traditional fault diagnosis method. The results show that the diagnostic accuracy of the method is better than the traditional fault diagnosis method and the stability is better.

Key words: air compressor, deep belief network model, fault diagnosis, stability

中图分类号:

TP273

鲁春燕, 李炜. 基于深度置信网络的炼化空压机故障诊断方法[J]. 化工学报, 2019, 70(2): 757-763.

Chunyan LU, Wei LI. Fault diagnosis method of petrochemical air compressor based on deep belief network[J]. CIESC Journal, 2019, 70(2): 757-763.

图/表 8

图1 深度置信网络结构

Fig.1 Deep belief network architecture

图2 受限Boltzmann机

Fig.2 Restricted Boltzmann machine

图3 空压机故障诊断流程

Fig.3 Flow chart of air compressor fault diagnosis

表1 空压机故障数据集描述

Table 1 Description of air compressor fault datasets

炼化空压机故障状况类型	样本个数	故障类别
正常	2800	1
润滑系统故障	2800	2
轴承故障	2800	3
冷却水槽堵塞	2800	4
级间转子不平衡	2800	5

图4 不同迭代次数的诊断准确率

Fig.4 Diagnostic accuracy of different iterations

图5 不同隐含层的诊断准确率

Fig.5 Diagnostic accuracy of different hidden layers

图6 不同方法10次试验的诊断准确率

Fig.6 Diagnostic accuracy of different methods in 10 experiment

表2 不同方法的诊断结果

Table 2 Diagnostic results with different methods

方法	平均准确率/%	准确率标准差/%	平均训练时间/s
多隐层BP	72.83	2.7113	45.759
PNN	81.50	1.8649	30.536
DBN	94.59	0.4239	52.342

参考文献 30

1	许世勇. 基于主元分析的空气压缩机故障诊断研究[D]. 吉林: 长春工业大学, 2012.
	XuS Y. Research of the fault diagnosis of air compressor based on principal component analysis[D]. Jilin: Changchun University of Technology, 2012.
2	Graham-roweD, GoldstonD, DoctorowC, et al. Big data: science in the petabyte era[J]. Nature, 2008, 455(7209): 8-9.
3	刘帅师, 程曦, 郭文燕, 等. 深度学习方法研究新进展[J]. 智能系统学报, 2016, 11(5): 567-576.
	LiuS S, ChengX, GuoW Y, et al. Progress report on new research in deep learning[J]. CAAI Transactions on Intelligent Systems, 2016, 11(5): 567-576.
4	雷亚国, 贾峰, 周昕, 等. 基于深度学习理论的机械装备大数据监控监测方法[J]. 机械工程学报, 2015, 51(21): 49-56.
	LeiY G, JiaF, ZhouX, et al. A deep learning-based method for machinery health monitoring with big data[J]. Journal of Mechanical Engineering, 2015, 51(21): 49-56.
5	段艳杰, 吕宜生, 张杰, 等. 深度学习在控制领域的研究现状与展望[J]. 自动化学报, 2016, 42(5): 643-654.
	DuanY J, LyuY S, ZhangJ, et al. Deep learning for control: the state of the art and prospects[J]. Acta Automatica Sinica, 2016, 42(5): 643-654.
6	任浩, 屈剑锋, 柴毅, 等. 深度学习在故障诊断领域中的研究现状与挑战[J]. 控制与决策, 2017, 32(8): 1345-1358.
	RenH, QuJ F, ChaiY, et al. Deep learning for fault diagnosis: the state of the art and challenge[J]. Control and Decision, 2017, 32(8): 1345-1358.
7	CarlosA, AndréL D R, FábioH A V, et al. Deep learning for biological image classification[J]. Expert Systems with Applications, 2017, 85: 114-122.
8	伍锡如, 黄国明, 孙立宁. 基于深度学习的工业分拣机器人快速视觉识别与定位算法[J]. 机器人, 2016, 38(6): 711-719.
	WuX R, HuangG M, SunL N. Fast visual identification and location algorithm for industrial sorting robots based on deep learning[J]. Robot, 2016, 38(6): 711-719.
9	吴志勇, 丁香乾, 许晓伟, 等. 基于深度学习和模糊C均值的心电信号分类方法[J]. 自动化学报, 2018, 44(8): 1913-1920.
	WuZ Y, DingX Q, XuX W, et al. A method for ECG classification using deep learning and fuzzy C-means[J]. Acta Automatica Sinica, 2018, 44(10): 1913-1920.
10	GuoD F, ZhongM Y, JiH Q, et al. A hybrid feature model and deep learning based fault diagnosis for unmanned aerial vehicle sensors[J]. Neurocomputing, 2018, 319: 155-163.
11	GuoY B, TanZ H, ChenH X, et al. Deep learning-based fault diagnosis of variable refrigerant flow air-conditioning system for building energy saving[J]. Applied Energy, 2018, 225: 732-745.
12	时培明, 梁凯, 赵娜, 等. 基于深度学习特征提取和粒子群支持向量机状态识别的齿轮智能故障诊断[J]. 中国机械工程, 2017, 28(9): 1056-1068.
	ShiP M, LiangK, ZhaoN, et al. Intelligent fault diagnosis for gears based on deep learning feature extraction and particle swarm optimization SVM state identification[J]. Chinese Journal of Mechanical Engineering, 2017, 28(9): 1056-1068.
13	FengD L, XiaoM Q, LiuY X, et al. Finite-sensor fault-diagnosis simulation study of gas turbine engine using information entropy and deep belief networks[J]. Frontiers of Information Technology & Electronic Engineering, 2016, 17(12): 1287-1304.
14	GeorgH, MatthiasR. Deep learning for fault detection in wind turbines[J]. Renewable and Sustainable Energy Reviews, 2018, 98: 189-198.
15	CaoC S, LiuF, TanH. Deep learning and its applications in biomedicine[J]. Genomics, Proteomics & Bioinformatics, 2018, 16(1): 17-32.
16	王康成, 尚超, 柯文思, 等. 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[J]. 化工学报, 2018, 69(3): 900-906.
	WangK C, ShangC, KeW S, et al. Automatic structure and parameters tuning method for deep neural network soft sensor in chemical industries[J]. CIESC Journal, 2018, 69(3): 900-906.
17	王功明, 李文静, 乔俊飞. 基于PLSR自适应深度信念网络的出水总磷预测[J]. 化工学报, 2017, 68(5): 1987-1997.
	WangG M, LiW J, QiaoJ F. Prediction of effluent total phosphorus using PLSR-based adaptive deep belief network[J]. CIESC Journal, 2017, 68(5): 1987-1997.
18	HintonG E, SalakhutdinovR R. Reducing the dimensionality of data with neural networks[J]. Science, 2006, 313(5786): 504-507.
19	LeeH, GrosseR, RanganathR, et al. Convolutional deep belief networks for scalable unsupervised learning of hierarchical representations[C]//Proceedings of the International Conference on Machine Learning. USA: ACM, 2009: 609-616.
20	金连文, 钟卓耀, 杨钊, 等. 深度学习在手写汉字识别中的应用综述[J]. 自动化学报, 2016, 42(8): 1125-1141.
	JinL W, ZhongZ Y, YangZ, et al. Applications of deep learning for handwritten Chinese character recognition: a review[J]. Acta Automatica Sinica, 2016, 42(8): 1125-1141.
21	BengioY, CourvilleA, VincentP. Representation learning: a review and new perspectives[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2013, 35(8): 1798-1828.
22	管皓, 薛向阳, 安志勇. 深度学习在视频目标跟踪中的应用进展与展望[J]. 自动化学报，2016, 42(6): 834-847.
	GuanH, XueX Y, AnZ Y. Advances on application of deep learning for video object tracking[J]. Acta Automatica Sinica, 2016, 42(6): 834-847.
23	HintonG, DengL, YuD, et al. Deep neural networks for acoustic modeling in speech recognition: the shared views of four research groups[J]. IEEE Signal Processing Magazine, 2012, 29(6): 82-97.
24	TangY C, EliasmithC. Deep networks for robust visual recognition[C]//Proceedings of IEEE International Conference on Machine Learning. 2010:1055-1062.
25	KrizhevskyA, SutskeverI, HintonG E. ImageNet classification with deep convolutional neural networks[C]//Proceeding of Advances in Neural Information Processing Systems. Nevada, USA: MIT Press, 2012: 1097-1105.
26	TamilselvanP, WangP. Failure diagnosis using deep belief learning based health state classification[J]. Reliability Engineering & System Safety, 2013, 115(7): 124-135.
27	TranV T, AlthobianiF, BallA. An approach to fault diagnosis of reciprocating compressor valves using Teager-Kaiser energy operator and deep belief networks[J]. Expert Systems with Applications, 2014, 41(9): 4113-4122.
28	李巍华, 单外平, 曾雪琼. 基于深度信念网络的轴承故障分类识别[J]. 振动工程学报, 2016, 29(2): 340-347.
	LiW H, ShaiW P, ZengX Q. Bearing fault identification based on deep belief network[J]. Journal of Vibration Engineering, 2016, 29(2): 340-347.
29	赵光权, 葛强强, 刘小勇, 等. 基于DBN的故障特征提取及诊断方法研究[J]. 仪器仪表学报, 2016, 37(9): 1946-1953.
	ZhaoG Q, GeQ Q, LiuX Y, et al. Fault feature extraction and diagnosis method based on deep belief network[J]. Chinese Journal of Scientific Instrument, 2016, 37(9): 1946-1953.
30	HintonG, OsinderoS, TehY. A fast learning algorithm for deep belief nets[J]. Neural Computation, 2006, 18(7): 1527-1554.

[1]	江河, 袁俊飞, 王林, 邢谷雨. 均流腔结构对微细通道内相变流动特性影响的实验研究[J]. 化工学报, 2023, 74(S1): 235-244.
[2]	孟令玎, 崇汝青, 孙菲雪, 孟子晖, 刘文芳. 改性聚乙烯膜和氧化硅固定化碳酸酐酶[J]. 化工学报, 2023, 74(8): 3472-3484.
[3]	郑玉圆, 葛志伟, 韩翔宇, 王亮, 陈海生. 中高温钙基材料热化学储热的研究进展与展望[J]. 化工学报, 2023, 74(8): 3171-3192.
[4]	毛磊, 刘冠章, 袁航, 张光亚. 可捕集CO₂的纳米碳酸酐酶粒子的高效制备及性能研究[J]. 化工学报, 2023, 74(6): 2589-2598.
[5]	蔡斌, 张效林, 罗倩, 党江涛, 左栗源, 刘欣梅. 导电薄膜材料的研究进展[J]. 化工学报, 2023, 74(6): 2308-2321.
[6]	徐文超, 孙志高, 李翠敏, 李娟, 黄海峰. 静态条件下表面活性剂E-1310对HCFC-141b水合物生成的影响[J]. 化工学报, 2023, 74(5): 2179-2185.
[7]	明迁, 高逸, 胡剑, 李盛杰, 王金江. 热交换器泄漏故障虚拟感知方法研究[J]. 化工学报, 2023, 74(4): 1836-1846.
[8]	王子健, 柯明, 李佳涵, 李舒婷, 孙巾茹, 童燕兵, 赵治平, 刘加英, 任璐. 短b轴ZSM-5分子筛制备方法及应用研究进展[J]. 化工学报, 2023, 74(4): 1457-1473.
[9]	陈向上, 马振杰, 任希华, 贾悦, 吕晓龙, 陈华艳. 三维网络萃取膜的制备及传质效率研究[J]. 化工学报, 2023, 74(3): 1126-1133.
[10]	刘润竹, 储甜甜, 张孝阿, 王成忠, 张军营. α，ω-端羟基亚苯基氟硅聚合物的合成及性能[J]. 化工学报, 2023, 74(3): 1360-1369.
[11]	高学金, 程琨, 韩华云, 高慧慧, 齐咏生. 基于中心损失的条件生成式对抗网络的冷水机组故障诊断[J]. 化工学报, 2022, 73(9): 3950-3962.
[12]	杨静, 林振康, 汤君, 樊铖, 孙克宁. 电池系统的故障特征以及多故障的诊断与识别[J]. 化工学报, 2022, 73(8): 3394-3405.
[13]	杨宏欣, 李兴亚, 葛亮, 徐铜文. 含哌啶阳离子侧长链型一/二价阴离子选择性分离膜的制备[J]. 化工学报, 2022, 73(8): 3739-3748.
[14]	孙哲, 金华强, 李康, 顾江萍, 黄跃进, 沈希. 基于知识数据化表达的制冷空调系统故障诊断方法[J]. 化工学报, 2022, 73(7): 3131-3144.
[15]	宋健斐, 孙立强, 解明, 魏耀东. 旋风分离器内气相旋转流不稳定性的实验研究[J]. 化工学报, 2022, 73(7): 2858-2864.

基于深度置信网络的炼化空压机故障诊断方法

Fault diagnosis method of petrochemical air compressor based on deep belief network

RichHTML

PDF (PC)

可视化

被引次数

摘要/Abstract

引用本文

使用本文

图/表 8

参考文献 30

相关文章 15

编辑推荐

Metrics

本文评价