基于光学灰度图像辨识的系统故障诊断方法

量子电子学报 ›› 2019, Vol. 36 ›› Issue (6): 699-704.

基于光学灰度图像辨识的系统故障诊断方法

汪炜怡¹,徐青山²,杨明翰³

1中国科学院安徽光学精密机械研究所基础科学中心，安徽合肥 230031；
2中国科学技术大学研究生院科学岛分院，安徽合肥 230026；
3中国科学院核能安全技术研究所，安徽合肥 230031

收稿日期:2018-12-24 修回日期:2019-03-01 出版日期:2019-11-28 发布日期:2019-11-19
通讯作者: 徐青山（1965-），男，研究员，主要从事大气探测、辐射传输、卫星遥感与图像大气订正方面的研究。Email：qshxu@aiofm.ac.cn E-mail:minghan.yang@fds.org.cn
作者简介:汪炜怡（1993-），女，安徽合肥人，博士生，主要从事人工智能以及大数据处理方面的研究。E-mail：wywangjoy@163.com
基金资助:
Supported by Strategic Priority Research Program ofChinese Academy of Sciences(中国科学院战略性先导科技专项资助项目, XDA03040000)

Method of System Fault Diagnosis based on Optical Gray-Image recognition

WANG Weiyi12,XU Qingshan1,YANG Minghan3*

1Center of Fundametal Science, Anhui Institute of Optics and Fine Mechanics,Chinese Academy ofSciences, Heifei 230031, China;
2 Science Island Branch of Graduate School, University of Science and Technology of China, Heifei 230026, China;
3 Institute of Nuclear Energy Safety Technology, Chinese Academy of Sciences,Heifei 230031, China

Received:2018-12-24 Revised:2019-03-01 Published:2019-11-28 Online:2019-11-19

摘要/Abstract

摘要：
摘要：故障诊断系统已成为确保工业系统及设备安全运行的重要辅助工具。在故障发生的早期阶段，故障诊断系统可以快速提供早期预警信息，并为故障缓解方案制定提供参考。为此，提出了一种基于光学灰度图像辨识的故障诊断方法。该方法根据实时监测数据构造系统的运行状态图像，通过CCD摄录的方式截取灰度图像，并从不同分辨率的系统灰度图像近似直方图中提取出系统的灰度图像特征。根据这些特征与标准特征之间的欧式距离比较，将当前状态划分为相距最小的标准特征类。实验结果表明该方法能够快速且正确地检测出故障类型，为系统相关设计与维护人员提供有效的支持信息。

关键词: 图像处理, 故障诊断, 灰度图像, 欧氏距离

Abstract: Fault diagnosis systems have become an important aid to ensure the safe operation of industrial systems and equipments. In the early stages of the failure, the fault diagnosis system can quickly provide early warning information and provide reference for the development of the fault mitigation plan. For this purpose, a fault diagnosis method based on optical gray image recognition is proposed. The method constructs the running state image of the system according to the real-time monitoring data, intercepts the gray image by CCD recording, and extracts the gray image from different resolution systems. The grayscale image features of the system are extracted from the approximate histogram. Based on the Euclidean distance between these features and the standard features, the current state is divided into the standard feature classes with the smallest distance. The experimental results show that the method can detect the fault type quickly and correctly, and can provide effective support information for the system related design and maintenance personnel.

Key words: image processing, fault diagnosis, gray image, Euclidean distance

中图分类号:

TP391.4

汪炜怡, 徐青山, 杨明翰. 基于光学灰度图像辨识的系统故障诊断方法[J]. 量子电子学报, 2019, 36(6): 699-704.

WANG Weiyi, XU Qingshan, YANG Minghan. Method of System Fault Diagnosis based on Optical Gray-Image recognition[J]. Chinese Journal of Quantum Electronics, 2019, 36(6): 699-704.

参考文献 16

[1]	Wang Chuanjun, Li Huaizhen, Yao Jinsheng. Discussion on electric motor and controller fault diagnosis expert system [J]. Electric Machines and Control Application(电机与控制应用), 2016, 43(5): 69-72(in Chinese).
[2]	Lu Baichuan, Zhang Kai, Ma Qinglu, et al. Data fault diagnosis model based on data-driven [J].Journal of Chongqing Jiaotong University(Natural Science)(重庆交通大学学报(自然科学版)), 2014, 33(5):111-115(in Chinese).
[3]	Wang L, Liu Z, Miao Q, et al. Time-frequency analysis based on ensemble local mean decomposition and fast Kurtogram for rotating machinery fault diagnosis[J]. Mechanical Systems and Signal Processing, 2018, 103:60-75.
[4]	Zhao Zhiguo, Li Hangyu, Lei Dan. Fault Diagnosis Based on Dual Kalman Filter of Clutch Brushless DC Actuator Motor for Dry Dual Clutch Transmission [J]. Journal of Mechanical Engineering(机械工程学报), 2018, 54(2):138-149(in Chinese).
[5]	Qi Shaoyang, Cheng Hang, Chen Fafa. Study on fault diagnosis of bearing based on stable distribution parameter estimation [J]. Journal of Taiyuan University of Technology(太原理工大学学报), 47(3): 299-303(in Chinese).
[6]	Xie D, Li B. A hierarchical deep neural network for fault diagnosis on Tennessee-Eastman process[C]. IEEE International Conference on Machine Learning & Applications, 2016.
[7]	Zhang Kailin. Research on Method of TE Process Monitoring based on Principal Component Analysis and Partial Least Squares(基于主元分析和偏最小二乘的TE过程监测方法的研究)[D]. Tianjin: Tianjin University of Technology, 2015(in Chinese).
[8]	Zhu Wenying, Feng Zhipeng. Fault diagnosis of planetary gearbox based on improved empirical wavelet transform [J]. Chinese Journal of Scientific Instrument(仪器仪表学报), 2016,37(10): 2193-2201(in Chinese).
[9]	Sun Guiling, Zhang Cuilan, Fang Yonghua, et al. A method based on wavelet transform for spectra feature extraction [J]. Chinese Journal of Quantum Electronics(量子电子学报), 2006, 23(1): 22-26(in Chinese).
[10]	Zuo W , Zhang L , Song C , et al. Gradient histogram estimation and preservation for texture enhanced image denoising[J]. IEEE Transactions on Image Processing, 2014, 23(6):2459-2472.
[11]	Sun Kai, Gao Jianmin, Gao Zhiyong, et al. Plant-wide quantitative assessment of a process industrysystem’s operating state based on color-spectrum [J] Mechanical Systems and Signal Processing, 2015,60-61,644-655.
[12]	Ma Bin, Ma Degui, Liao Jiangmin. Multimodality images registration based on multi-resolution [J]. Chinese Journal of Quantum Electronics(量子电子学报), 2012,29(1):15-20(in Chinese).
[13]	Liu Z , Geng X , Xie Z , et al. The multi-core parallel algorithms of wavelet/wavelet packet transforms and their applications in power system harmonic analysis and data compression[J]. International Transactions on Electrical Energy Systems, 2015, 25(11): 2800-2818.
[14]	Budinich R. A region-based easy-path wavelet transform for sparse image representation[J]. International Journal of Wavelets Multiresolution and Information Processing, 2017,15(5):1750045.
[15]	Wu Yican, Bai Yunqing, Song Yong, et al. Conceptual design of China lead-based research reactor CLEAR-I [J]. Nuclear Science and Engineering(核科学与工程), 2014,34(2): 201-208.
[16]	Minghan Y , Jianye W , Shuai C , et al. Development of NPP digital I&C system closed-loop online test system based on signal transmission array[J]. Progress in Nuclear Energy, 2018,108:270-280.