BDE-LSSVM在柴油机气门故障诊断中的应用  

Application of BDE-LSSVM in diesel engine fault diagnosis

作　　者：曹龙汉[1,2] 唐超[1] 何俊强[1] 武明亮[1] 田力[1] 吴珍毅[1] 

机构地区：[1]重庆通信学院控制工程重点实验室,重庆400035 [2]重庆理工大学汽车零部件制造及检测技术教育部重点实验室,重庆400050

出　　处：《计算机工程与应用》2013年第13期241-244,共4页Computer Engineering and Applications

基　　金：国家科技部国际科技合作项目(No.2007DFR10420);重庆理工大学汽车零部件制造及检测技术教育部重点实验室开放基金(No.2009-10)

摘　　要：针对柴油机气门故障的诊断样本少和非线性数据特征等问题,最小二乘法的支持向量机(LSSVM)能够较好地进行诊断研究,但由于惩罚因子C和内核参数σ的选取对诊断结果影响较大,有必要对其进行参数优化,因此提出了基于二进制微分进化算法(BDE)的最小二乘法支持向量机算法。利用柴油机气门振动信号作为数据,经小波变换作为模型特征,建立了基于BDE-LSSVM故障诊断模型,并与基于遗传和基于粒子群算法的LSSVM模型进行柴油机气门故障诊断的性能对比。比较结果证明,基于BDE优化的LSSVM模型在故障特征选取前后具有更好的适应度值和稳定度,故障分类准确性高且运算速度更快。Aiming at problem of few samples and non-linear characteristics in diesel engine fault diagnosis, Least Squares Sup-port Vector Machine（LSSVM） can be better to diagnostic studies, but the results of diagnosis are greatly influenced by the pen-alty factor and the selection of kernel parameters, it is necessary to optimize its parameters, LSSVM algorithm based on Binary Differential Evolution（BDE） is proposed. For the data of diesel engine valve vibration signal used as the characteristics values of model, and wavelet transformed, the fault diagnosis model based on BDE-LSSVM is established. Compared with LSSVM model based on the particle swarm algorithm and genetic algorithm, the results show that LSSVM with BDE has better fitness value and stability, as well as more perfect accuracy and speed in the diagnosis classification.

关 键 词：最小二乘支持向量机 二进制微分进化 故障诊断 小波变换 

分 类 号：TP206[自动化与计算机技术—检测技术与自动化装置]