基于自适应MPCA的翻车机液压系统状态监测与故障诊断

摘要
图/表
参考文献(11)
相关文章 (15)

全文: PDF (1686 KB) HTML (1 KB)
输出: BibTeX | EndNote (RIS)

摘要由于翻车机液压系统故障频发，工况复杂多变，对其进行状态监测与故障诊断具有重要的实际意义。根据翻车机工作过程具有间歇性和时变性的特点，采用自适应多向主成分分析(MPCA)对其进行状态监测与故障诊断。应用加权递归算法自适应更新协方差矩阵，并通过权值调整新数据对最终模型参数的影响。针对Q贡献率不能反映各过程变量偏离正常范围的程度，导致故障定位不准。设计了主成分(t)贡献率进行故障定位，其直接揭示了过程变量的变化程度。根据翻车机在线监测系统的运行情况证明自适应MPCA方法可以准确及时的发现故障，基于t贡献率的故障定位方法准确率可以达到90%。

	服务

	把本文推荐给朋友
	加入我的书架
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章
	张立杰1
	2
	鄂东辰1
	2

关键词 ：自适应多向主成分分析, 状态监测, 主成分贡献率, 故障诊断

Abstract：Faults of the hydraulic system of car dumper occurred frequently and the faults bave a serious impact on production. Its condition monitoring and fault diagnosis has important practical significance. According to characteristics of working process of car dumper is intermittent and timevarying, adaptive multiway principal component analysis (MPCA) was used for condition monitoring and fault diagnosis. Covariance matrix was updated adaptively using the weighted recursive algorithm. Impact of new data on final model was adjusted by weight. Contribution rate of Q can not reflect the degree of deviation from normal range of each process variable that leads to inaccurate results of fault diagnosis. Parameter of principal component contribution rate t was used for fault location which directly reveals the change degree of process variables. The operation of the online monitoring system over car dumper proved that the adaptive MPCA method can accurately detect fault in time. The accuracy of fault diagnosis is up to 90% based on the t contribution rate.

Key words： adaptive multiway principal component analysis condition monitoring principal component contribution rate fault diagnosis

收稿日期: 2016-08-30 出版日期: 2018-04-15

引用本文:

张立杰1,2，鄂东辰1,2. 基于自适应MPCA的翻车机液压系统状态监测与故障诊断[J]. 振动与冲击, 2018, 37(8): 245-250.
ZHANG Lijie1,2, E Dongchen1,2. Car dumper hydraulic system state monitoring and fault diagnosis based on adaptive MPCA. JOURNAL OF VIBRATION AND SHOCK, 2018, 37(8): 245-250.

链接本文:

http://jvs.sjtu.edu.cn/CN/ 或 http://jvs.sjtu.edu.cn/CN/Y2018/V37/I8/245

[1] 冯广斌，陆继山，孙华刚，等. 某自行火炮输弹机液压-控制系统故障仿真研究[J]. 振动与冲击，2016,35(14)：130-134.
Feng guang-bin, Lu ji-shan, Sun hua-gang, et al. Failure simulation of the hydraulic control system of an automatic feeding machine[J]. Journal of Vibration and Shock, 2016, 35(14): 130-134.
[2] Paul Nomikos, John F. MacGregor. Monitoring Batch processes using multiway principal component analysis[J]. AIChE Journal, 1994, 40(8): 1361-1375.
[3] Wenfu Ku, Robert H. Storer, Christos Geogakis. Disturbance detection and isolation by dynamic principal component analysis[J]. Chemometrics and intelligent laboratory systems, 1995, 30: 179-196.
[4] 朱荷蕾，孟婥，孙以泽，等. 基于分段线性MPCA的充液氨过程建模及监控[J]. 仪器仪表学报，2015, 36(2)：271-279.
Zhu He-lei, Meng Zhuo, Sun Yi-ze, et al. Modeling and monitoring of ammonia reactor filling process based on piecewise linear MPCA method[J]. Chinese Journal of Scientific Instrument, 2015, 36(2): 271-279.
[5] 齐咏生，王普，高学金，等. 一种新的多阶段间歇过程在线监测策略[J]. 仪器仪表学报，2011,32(6)：1290-1297.
Qi Yong-sheng, Wang Pu, Gao Xue-jin, et al. Novel online monitoring strategy for multiphase batch processes[J]. Chinese Journal of Scientific Instrument, 2011,32(6): 1290-1297.
[6] 许仙珍，谢磊，王树青. 基于PCA混合模型的多工况过程监控[J]. 化工学报，2011, 62(3)：743-752.
Xu Xian-zhen, Xie Lei, Wang Shu-qing. Multi-mode process monitoring method based on PCA mixture model[J]. CIESC Journal, 2011, 62(3): 743-752.
[7] 陆宁云，王福利，高福荣，等. 间歇过程的统计建模与在线监测[J]. 自动化学报，2006, 32(3)：401-410.
Lu Ning-yun, Wang Fu-li, Gao Fu-rong, et al. Statistical modeling and online monitoring for batch process[J]. ACTA AUTOMATICA SINICA, 2006, 32(3): 401-410.
[8] Svante Wold. Exponentially weighted moving principal components analysis and projections to latent structures[J]. Chemometrics and intelligent laboratory systems, 1994, 23: 149-161.
[9] Weihua Li, H. Henry Yue, Sergio Valle-Cervantes, et al. Recursive PCA for adaptive process monitoring[J]. Journal of process control, 2000, 10: 471-486.
[10] 孙靖杰，赵建军，于仕财，等. 基于改进RPCA的某型发射机自适应监测新方法[J]. 仪器仪表学报，2012, 33(4)：82-828.
Sun Jing-jie, Zhao Jian-jun, Yu Shi-cai, et al. New adaptive monitoring approach for a transmitter based on improved RPCA[J]. Chinese Journal of Scientific Instrument, 2012, 33(4): 82-828.
[11] 王姝，常玉清，杨洁，等. 时段划分的多项主元分析间歇过程监测及故障变量追溯[J]. 控制理论与应用，2011, 28(2)：149-156.
Wang Shu, Chang Yu-qing, Yang Jie, et al. Multiway principle component analysis monitoring and fault variable detection based on substage separation for batch process[J]. Control Theory & Application, 2011, 28(2): 149-156.