摘要
为有效描述滚动轴承的退化趋势,提出结合威布尔分布及最小二乘支持向量机的滚动轴承退化趋势预测新方法。用威布尔分布形状参数作为滚动轴承的性能退化指标,将该指标作为最小二乘支持向量机的输入构造退化趋势预测模型。鉴于最小二乘支持向量机模型参数对模型的推广预测能力影响较大,选粒子群算法(PSO)优化最小二乘支持向量机模型参数,并用实测滚动轴承全寿命实验数据进行检验。结果表明该方法能获得准确的预测结果。
A new prediction method was proposed based on Weibull distribution and least squares support vector machine to analyse the degradation trend of rolling bearings.The shape parameters of Weibull distribution were used as bearing recession performance indicators.The indicators act as the input of the least squares support vector machine and on this basis,a prediction model was constructed.In the light of the important influence of model parameters of least squares support vector machine on the predictive ability of the model,in the proposed method,particle swarm （PSO） algorithm was adopted to optimize the model parameters.The rolling bearing run-to-failure tests were carried out to inspect the prediction model,and the results demonstrate the effectiveness and accurateness of the proposed method.
出处
《振动与冲击》
EI
CSCD
北大核心
2014年第20期52-56,共5页
Journal of Vibration and Shock
基金
国家自然科学基金(51275546)
高等学校博士学科点专项科研基金(20130191130001)
