蝙蝠算法优化极限学习机的滚动轴承故障分类

针对传统智能故障诊断方法在滚动轴承的故障诊断中诊断准确率不高的问题,引入了一种启发式搜索算法——蝙蝠算法(BA)优化极限学习机(ELM)的方法,利用ELM构建滚动轴承故障诊断分类模型。首先采用滚动轴承振动信号的五种代表性时域无量纲指标作为诊断模型输入特征,然后,利用蝙蝠算法的全局寻优能力对ELM模型的参数进行优化,获取最优输入权重和隐含层偏置的ELM分类模型,最后采用美国西储大学轴承数据中心网站公开发布的轴承探伤数据集验证算法诊断效果。实验结果表明：该方法可以有效地对滚动轴承不同故障状态进行识别,与BP神经网络、支持向量机(SVM)和极限学习机(ELM)方法比较,所提出的方法能够提高故障诊断准确率,达到99.17%。

Rolling Bearing Fault Diagnosis Method based on Extreme Learning Machine Optimized by Bat Algorithm

Aiming at the problem that the traditional intelligent fault diagnosis method has low diagnostic accuracy in the fault diagnosis of rolling bearings, a classification algorithm for rolling bearing fault diagnosis based on bat algorithm (BA) optimized Extreme Learning Machine (ELM) is proposed. Firstly, five time-domain dimensionless parameters of rolling bearing vibration signal are selected as inputs of the model, and then the input weight and hidden layer bias of ELM was optimized by BA with powerful capability in global-optimization, thus the most superior diagnosis model of ELM is obtained to be validated by the actual Rolling experimental data from Case Western Reserve University. The experimental results show that compared with the BP,SVM and ELM, the proposed method can improve the accuracy of fault diagnosis, and the accuracy of fault diagnosis reaches up to 99.17%.