基于模拟加载系统油压信号的自动测试与识别技术研究

PDF(1663 KB)

振动与冲击 ›› 2013, Vol. 32 ›› Issue (2) : 44-49.

论文

基于模拟加载系统油压信号的自动测试与识别技术研究

王新晴王东赵洋朱会杰谢全民

作者信息 +

Research on automatic measurement and recognition of oil pressure signals of load simulation system

WANG Xin-qing, WANG Dong, ZHAO Yang ZHU Hui-jie XIE Quan-min

Author information +

文章历史 +

摘要

在液压系统模拟加载与自动测试、识别过程中，工作装置油压波动信号是一种典型的非平稳信号。针对其影响因素多、不具备明显频域特征以及任何单一特征参量都无法对信号进行准确识别的难题，提出了对信号先进行状态分割，在分割基础上计算不同工作状态下的特征参量，并进行基于主成分分析（PCA）的特征提取方法，最后采用最小二乘支持向量机（LSSVM）构建多分类器，实现对工作装置6种不同工作状态的准确识别。实验结果验证了该方法的有效性，为同类液压系统的信号特征分析及模式识别提供了参考。

Abstract

In the process of automatic measurement and recognition, the oil pressure signals of working device in the load simulation system are typical non-stationary. The signals with characteristics of many influencing factors, without significant frequency domain features and there is no single feature parameter can recognize the signals exactly. In view of above facts, the method proposed in this paper can exactly recognize the six different working states of the working device. Firstly, divide up the different working states. Then, extract the principal components from the original calculated feature set based on principal component analysis (PCA). Finally, establish the multiple classifiers using least squares support vector machine (LSSVM). The results confirm the effectiveness of the proposed method, and the method can provide some useful references for the characteristic analysis and pattern recognition of the similar hydraulic pressure signals.

导出引用

王新晴王东赵洋朱会杰谢全民. 基于模拟加载系统油压信号的自动测试与识别技术研究[J]. 振动与冲击, 2013, 32(2): 44-49

WANG Xin-qing;WANG Dong;ZHAO Yang ZHU Hui-jie XIE Quan-min. Research on automatic measurement and recognition of oil pressure signals of load simulation system[J]. Journal of Vibration and Shock, 2013, 32(2): 44-49