齿轮传动系统损伤检测与多故障分类研究  被引量:3

Damage detection and multi-faults classification of gear transmission system

在线阅读下载全文

作  者:邵忍平[1] 李永龙[1] 曹精明[1] 徐永强[1] 

机构地区:[1]西北工业大学机电学院,西安710072

出  处:《振动与冲击》2010年第9期185-190,共6页Journal of Vibration and Shock

基  金:国家自然科学基金(50575187);航空科学基金(01I53073);陕西省自然科学基金(2004E219)资助项目

摘  要:研究了数据挖掘的支持向量机的智能故障检测与诊断方法。通过对齿轮系统在不同的运转状态下的工作状况进行试验测试分析,获取了有关的测试信号,并对不同的故障振动特征信号进行了特征提取与分析研究。在此基础上将支持向量机引入到齿轮传动的损伤检测与诊断之中,建立了两分类和多分类分类器,研究了支持向量机的两分类和多类分类算法。通过分析处理、训练和测试仿真数据以及齿轮振动特征信号,对齿轮系统在各种不同转速下不同故障进行了预测、分类和诊断。研究表明,支持向量机能够很好的区分不同运转状况下各种典型齿轮损伤与故障,低转速下识别率更高,为95%,特别是对各种复合类故障具有较高的识别精度、识别率在81%以上。它在齿轮故障诊断中具有较好诊断识别能力与发展前景,是一种有效的损伤检测与诊断的新方法。A method of intelligent fault detection and diagnosis based on the support vector machine(SVM) was proposed.By measuring the vibration signals of the gear system at different rotating speeds with different conditions and faults,the testing signals were collected.The feature signals of system were extracted and analyzed.SVM was used for gear fault diagnosis,the classifiers of two and multi-classifications were set up,and the algorithms for two and multi-classifications of SVM were discussed.By analyzing,training and testing the samples of simulation data and gear vibration signals,the various damages in different running conditions of gear system were detected,classified and diagnosed.Based on these,the various representative gear damages in different conditions can be well distinguished,the detection rate is as higher as 95% in low rotating speed,and especially the identification rate of multi-faults diagnosis is over 81%.The results show that the support vector machine in gear fault diagnosis is of excellent diagnostic and identifying abilities and has development prospect in engineering applications.

关 键 词:特征提取 损伤检测 故障分类 复合故障诊断 齿轮系统 

分 类 号:TH113.1[机械工程—机械设计及理论]

 

参考文献:

正在载入数据...

 

二级参考文献:

正在载入数据...

 

耦合文献:

正在载入数据...

 

引证文献:

正在载入数据...

 

二级引证文献:

正在载入数据...

 

同被引文献:

正在载入数据...

 

相关期刊文献:

正在载入数据...

相关的主题
相关的作者对象
相关的机构对象