基于PSO-SVM-RF的离心泵转子故障诊断研究

范传翰; 宋礼威; 刘厚林; 董亮; 肖幸鑫; 陈泽宇

基于PSO-SVM-RF的离心泵转子故障诊断研究

1. 江苏大学流体机械工程技术研究中心;
2. 中广核工程有限公司核电安全监控技术与装备国家重点实验室

基金项目:

国家自然科学基金项目(51879122,51779108,51779106)

镇江市重点研发计划项目(GY2017001,GY2018025)

西华大学流体及动力机械教育部重点实验室开放课题项目(szjj2017-094,szjj2016-068)

江苏高校优势学科建设工程项目(PAPD)

江苏省“六大人才高峰”高层次人才项目(GBZB-017)

详细信息

作者简介:
范传翰(1993-),男,主要研究方向为离心泵机组故障诊断。E-mail:79675590@qq.com

通讯作者:
董亮(1981-),男,研究员,博士生导师,主要研究方向为泵监测及故障诊断。E-mail:dongliang@ujs.edu.cn

中图分类号: TH311
计量
- 文章访问数: 0
- HTML全文浏览量: 0
- PDF下载量: 0
出版历程
- 收稿日期: 2022-04-05

Research on the Rotor Fault Diagnosis of the Centrifugal Pump Based on PSO-SVM-RF

1. Fluid Machinery Engineering Technology Research Center of Jiangsu University;
2. State Key Laboratory of Nuclear Power Safety Monitoring Technology and Equipment of CGN Engineering Co., Ltd

摘要

摘要: 转子是离心泵的重要组件之一，对转子运行状态的检测和诊断的研究具有重要意义。转子不平衡、不对中故障引发的故障特征较为相似，为了有效识别离心泵这两种转子故障。通过在离心泵进口法兰位置布置振动加速度传感器进行信号采集，提取原信号时频域特征，并利用随机森林算法筛选出重要性较高6个特征并将随机森林得到的分类结果作为PSO-SVM的输入，进而来区分正常、转子不对中、转子不平衡故障，同时还比较了该方法与传统PSO-SVM的故障识别率。结果表明，该模型PSO优化迭代次数更少、具有更高的识别率，对故障的识别率达到99.36%。
- 离心泵 /
- 故障诊断 /
- 支持向量机 /
- 随机森林 /
- 转子不平衡 /
- 转子不对中
Abstract: Rotor is one of the important components of centrifugal pump, which is of great significance to the detection and diagnosis of rotor running state. The characteristics of faults caused by unbalanced and misaligned rotor faults are similar. In order to effectively identify the two rotor faults of centrifugal pump rotation, the influence of location selection of different measuring points on distinguishing faults is effectively understood. Sensors are arranged on the inlet flange of centrifugal pump for signal acquisition, and the time-frequency domain characteristics of the original signal are extracted. The random forest algorithm is used to screen out 6 features with high importance, and the classification results obtained by the random forest are used as the input of PSO-SVM, so as to distinguish the faults of normal, misaligned rotor and unbalanced rotor. At the same time, the fault recognition rate of this method is compared with that of traditional PSO-SVM. The results show that the PSO model has fewer iterations and higher recognition rate, and the recognition rate of faults reaches 99.36%.
- centrifugal pump /
- fault diagnosis /
- support vector machine /
- random forests /
- imbalance of rotary /
- misalignment of rotary

HTML全文

参考文献(17)

[1]	曹冲锋.基于EMD的机械振动分析与诊断方法研究[D].杭州:浙江大学,2009.CAO C F. Study on mechanical vibration analysis and diagnosis methods based on emperical M-ode Decomposition[D]. Hangzhou:Zhejiang University, 2009.
[2]	张彦铎,姜兴渭.多传感器信息融合及在智能故障诊断中的应用[J].传感器技术,1999(3):22-26. ZHANG Y D, WEI X W. Multi-Sensor information fusion technique and its application on intelli-gent fault diagnosis system[J]. Chinese Journal of Sensors and Actuators, 1999(3):22-26.
[3]	屈梁生.机械故障的全息诊断原理[M].北京:科学出版社,2007.
[4]	DONG L, WU K, ZHU J C, et al. Cavitation detection in centrifugal pump based on interior flo-w borne noise using WPD-PCA-RBF[J].Shock and Vibration, 2019.
[5]	董明,孟源源,徐长响,等.基于支持向量机及油中溶解气体分析的大型电力变压器故障诊断模型研究[J].中国电机工程学报,2003(7):88-92. DONG M, MENG Y Y, XU C X, YAN Z. Fault diagnosis model for power transformer based on support vector machine and dissol gas analysis[J]. Proceedings of the CSEE, 2003(7):88-92.
[6]	薛延刚,王勇劲,赵海英,等.基于时序贴近度与改进SVM的水机轴心轨迹诊断[J].排灌机械工程学报,2017,35(12):1 054-1 057+1 062. XUE Y G, WANG J Y, ZHAO H Y, LIU G W, QIAO F. Axis orbit automatic identification on ti-me-series similarity mining for hydropower units[J]. Journal of Drainage and Irrigation Machinery Engineering, 2017,35(12):1 054-1 057+1 062.
[7]	张丽平.粒子群优化算法的理论及实践[D].杭州:浙江大学,2005.ZHANG L P. The theorem and praetice upon the partiele swarm optimzation algorithm[D]. Hangzhou:Zhejiang University, 2005.
[8]	蔡振宇,史乔波.基于PSO-SVM模型的旋转机械故障诊断研究[J].煤矿机械,2011,32(11):276-278. CAI Z Y, SHI Q B. Fault Diagnosis of rotating machinery based on PSO-SVM Model[J]. Coal Mi-ne Machinery, 2011,32(11):276-278.
[9]	WANG Z W, ZHANG Q H, XIONG J B, et al. Fault diagnosis of a rolling bearing using wavelet packet denoising and random forests[J].IEEE Sensors Journal, 2017,17(17):5 581-5 588.
[10]	马富齐.基于复数据经验模态分解和随机森林理论的风电机组多域特征故障诊断研究[D].西安:西安理工大学,2019.MA F Q. Research on muti-domain feature fault diagnosis of wind turbine based on complex e-mpirical mode decomposition and random forest theory[D]. Xi'an:Xi'an University of Technology, 2019.
[11]	单增海,李志远,张旭,等.基于多传感器信息融合和多粒度级联森林模型的液压泵健康状态评估[J].中国机械工程,2021,32(19):2 374-2 382. SAN Z H, LI Z Y, ZHANG X, et al. Health status assess-ment of hydraulic pump based on muti-sensor information fusion and mutigrained cascade forest model[J]. China Mechanical Engineering,2021,32(19):2 374-2 382.
[12]	段智勇,刘才学,艾琼,等.基于随机森林的屏蔽泵故障诊断方法研究[J].核科学与工程,2020,40(4):625-630. DUAN Z Y, LIU C X, AI Q, HE P. Research on fault diagnosis method of canned motor pump based on random forests[J]. Nuclear Science and Engineering, 2020,40(4):625-630.
[13]	徐书凡.电动潜油螺杆泵系统故障诊断研究[D].黑龙江大庆:东北石油大学,2020.XU S F. Fault diagnosis of electric submersible screw pump system[D]. Heilongjang Northeast Petroleum University, 2020.
[14]	BREIMAN L.(2001a). Random Forest. Machine Learning, 45(1):5-32.
[15]	吴侃.离心泵空化状态识别方法研究与实现[D].江苏镇江:江苏大学,2019. WU K. Research and implementation of cavitation state recognition method for centrifugal pump[D]. Zhenjiang:Jiangsu University,2019.
[16]	万书亭,吴美玲.基于时域参数趋势分析的滚动轴承故障诊断[J].机械工程与自动化,2010(3):108-110+113. WAN S T, WU M L. Fault diagnosis for rolling bearing based on trend analysis of time dom-ain parameters[J]. Mechanical Engineering&Automation, 2010(3):108-110+113.
[17]	平源.基于支持向量机的聚类及文本分类研究[D].北京:北京邮电大学,2012.PING Y. Research on clustering and text categorization based on support vector machine[D]. Beijing:Beijing University of Posts and Telecommunications, 2012.