详细信息
文献类型:期刊文献
中文题名:基于改进EMD和LSSVM的机械故障诊断
英文题名:Mechanical Fault Diagnosis Based on Improved EMD and LSSVM
作者:肖志勇[1];杨小玲[2];刘爱伦[1]
机构:[1]华东理工大学自动化研究所,上海200237;[2]江西农业大学,江西南昌330045
年份:2008
卷号:29
期号:6
起止页码:24
中文期刊名:自动化仪表
外文期刊名:Process Automation Instrumentation
收录:CSTPCD
语种:中文
中文关键词:特征提取;经验模态分解;支持向量机;故障诊断;汽轮机
外文关键词:Feature extraction Empirical mode decomposition (EMD) SVM Fault diagnosis Steam turbine
摘要:故障特征提取的精确性和故障分类识别的高效率是提高故障诊断正确率和速度的关键,提出了一种改进的经验模态分解与最小二乘支持向量机相结合优化算法。该算法实现了故障特征精确提取和快速收敛,有效地提高了故障诊断性能。基于汽轮机的仿真实例验证了该方法的有效性。
The precision of fault feature extraction as well as classification and identification of faults are the key point of enhancing accuracy and speed of fault diagnosis. A new optimization algorithm that combines improved empirical mode decomposition (EMD) and least square support vector machine(LSSVM) is proposed, The algorithm implements fault feature extraction and fast speed convergence. Based on simulation of steam turbine, the effectiveness of this method has been proven.
参考文献:
正在载入数据...
