基于PSODACCIW-VPMCD的滚动轴承智能检测方法  

An intelligent detection method for rolling bearings based on PSODACCIW-VPMCD

作　　者：刘吉彪[1] 程军圣[2] 马利[2] 

机构地区：[1]河南工业职业技术学院机械工程系,河南南阳473000 [2]湖南大学机械与运载工程学院,长沙410082

出　　处：《振动与冲击》2015年第23期42-47,共6页Journal of Vibration and Shock

基　　金：国家自然科学基金(51175158;51075131);湖南省自然科学基金(11JJ2026)

摘　　要：针对VPMCD中模型选择方法的不合理和小样本多分类时识别率降低的缺陷,结合动态加速常数协同惯性权重的粒子群(Particle swarm optimization with dynamic accelerating constant and coordinating with inertia weight,PSODACCIW)算法的全局优化能力和加权融合理论,提出基于PSODACCIW-VPMCD的滚动轴承智能检测方法。首先对样本提取特征变量,然后采用PSODACCIW算法优化诊断融合权值矩阵,最后对滚动轴承的故障类型和工作状态进行分类和识别。实验结果表明,该方法能够有效地应用于滚动轴承的智能检测中。Aiming at the unreasonable model selection method and the defect of lower recognition rate for smaller samples and multi-classification,combining the global optimization ability of the particle swarm optimization with dynamic accelerating constant and coordinating with inertia weight（ PSODACCIW） algorithm and the weighted fusion theory,an intelligent detection method for rolling bearings based on PSODACCIW-VPMCD was put forward. Firstly, the characteristic variables of samples were extracted,then the PSODACCIW algorithm was used to optimize the diagnosis fusion weighting matrix. Finally,the operation status and fault pattern of rolling bearings were classified and identified.The test results showed that the proposed method can be applied in o rolling bearing intelligent detection effectively.

关 键 词：动态加速常数协同惯性权重的粒子群算法(PSODACCIW) 基于变量预测模型的模式识别(VPMCD) 加权融合 滚动轴承 智能检测 

分 类 号：TH165.3[机械工程—机械制造及自动化] TH132.41