基于数学形态学和IFOA-SVR的滚动轴承可靠度预测方法

发布时间：2018-06-18 04:22

本文选题：滚动轴承 + 数学形态学　；参考：《机械工程学报》2017年08期

【摘要】：为了保证滚动轴承运行状态可靠度的预测精度同时增加预测步长,提出一种数学形态学分形维数结合改进果蝇优化算法-支持向量回归(Improved fruit fly optimization algorithm-support vector regression,IFOA-SVR)的滚动轴承可靠度预测方法。提取振动信号的包络信号,计算该包络信号的数学形态学分形维数,将其作为滚动轴承性能退化状态特征。利用IFOA对SVR中的参数C、g以及ε同时进行寻优,建立IFOA-SVR预测模型。利用极大似然估计结合IFOA建立威布尔比例故障率模型(Weibull proportional hazard model,WPHM),进而得到可靠度模型。将退化状态特征作为IFOA-SVR预测模型的输入,采用长期迭代预测法获取特征预测结果,并将该结果嵌入到可靠度模型中,从而预测出轴承运行状态的可靠度。试验结果表明,利用所提方法对滚动轴承可靠度进行预测,能在保证预测精度的前提下增加预测步长。
[Abstract]:In order to ensure the reliability prediction accuracy of rolling bearings and increase the prediction step, A new method for predicting the reliability of rolling bearings based on the fractal dimension of mathematical morphology and improved fruit fly optimization algorithm-support vector regression (IFOA-SVR), an improved algorithm for Drosophila melanogaster, is presented. The envelope signal of vibration signal is extracted, and the fractal dimension of mathematical morphology of the envelope signal is calculated, which is regarded as the characteristic of rolling bearing performance degradation state. IFOA is used to optimize the parameters of SVR, such as Cogg and 蔚, and IFOA-SVR prediction model is established. The Weibull proportional hazard model is established by using the maximum likelihood estimation (MLE) combined with the IFOA, and the reliability model is obtained. The degenerate state feature is used as the input of IFOA-SVR prediction model, and the feature prediction result is obtained by using the long-term iterative prediction method, and the result is embedded into the reliability model to predict the reliability of the bearing running state. The experimental results show that the prediction step can be increased by using the proposed method to predict the reliability of rolling bearings.
【作者单位】：哈尔滨理工大学电气与电子工程学院;白俄罗斯国立大学;
【基金】：国家自然科学基金(51305109) 黑龙江省青年科学基金(QC2014C075) 哈尔滨理工大学青年拔尖创新人才(201511)资助项目
【分类号】：TH133.33;TP18

【相似文献】