| 基于改进GWO-LightGBM的滚动轴承未知故障诊断 |
| |
| 引用本文： | 柴琴琴,陈舒迪,王武,黄捷.基于改进GWO-LightGBM的滚动轴承未知故障诊断[J].航空动力学报,2022,37(4):848-855. |
| |
| 作者姓名： | 柴琴琴 陈舒迪 王武 黄捷 |
| |
| 作者单位： | 福州大学 电气工程与自动化学院，福州 350108 |
| |
| 基金项目： | 国家自然科学基金（61603094）； 福州市科技计划项目（2019-G-44） |
| |
| 摘 要： | 针对滚动轴承未知新故障误判影响轴承安全性和检修效率的问题，提出了一种基于改进灰狼算法（GWO）和轻量级梯度提升机（LightGBM）的故障诊断模型，实现已知/未知故障的高精度判别。为避免单一尺度下特征提取的缺失，对滚动轴承振动信号分别提取时域、频域和小波域特征建立多域特征集。设计了带未知新故障判别机制的GWO-LightGBM模型，并构造含有Halton序列和模拟退火策略的GWO实现了模型参数有效优化。实例试验结果表明，模型对已知和未知类故障平均识别率达99.57%，10次随机试验平均识别率分别比单一分类模型逻辑回归（LR）、最近邻分类器（KNN）和支持向量机（SVM）高21.98%、17.00%、9.27%，验证了模型的有效性和优越性，能高准确率地识别出已知或以前从未出现的新故障。
|
| 关 键 词： | 滚动轴承 特征提取 集成学习 轻量级梯度提升机 改进灰狼算法 未知故障诊断 |
| 收稿时间： | 2021/5/9 0:00:00 |
Unknown fault diagnosis of rolling bearing based on improved GWO-LightGBM |
| |
| CHAI Qinqin,CHEN Shudi,WANG Wu,HUANG Jie.Unknown fault diagnosis of rolling bearing based on improved GWO-LightGBM[J].Journal of Aerospace Power,2022,37(4):848-855. |
| |
| Authors: | CHAI Qinqin CHEN Shudi WANG Wu HUANG Jie |
| |
| Affiliation: | College of Electrical Engineering and Automation， Fuzhou University，Fuzhou 350108，China |
| |
| Abstract: | In view of misjudgment of unknown new faults of rolling bearing affects bearing safety and maintenance efficienc，a fault diagnosis model based on improved gray wolf optimization （GWO） and light gradient boosting machine （LightGBM） was proposed to realize high precision discrimination about the known and unknown faults.The time domain，frequency domain and wavelet domain features were extracted separately from the vibration signal of the rolling bearing to avoid the lack of feature extraction at a single scale.The GWO-LightGBM model with unknown new fault diagnosis mechanism was designed，and the improved gray wolf algorithm with Halton sequence and simulated annealing strategy was constructed to realize the effective optimization of model parameters.The experimental results showed that the average recognition rate of the model for known and unknown faults was 99.57%.The average recognition rates for 10 times random experiments were 21.98%，17.00% and 9.27% higher than logistic regression （LR），K-nearest neighbor （KNN） and support vector machine （SVM），respectively.The comparative experiments verified the effectiveness and superiority of the model，which can identify known or unknown new faults with high accuracy. |
| |
| Keywords: | rolling bearing feature extraction ensemble learning LightGBM improved GWO unknown fault diagnosis |
| 本文献已被 万方数据 等数据库收录！ |
| 点击此处可从《航空动力学报》浏览原始摘要信息 |
|
点击此处可从《航空动力学报》下载全文 |
