国外文献 > 1.轴承 > 5. 监测与诊断 > 寿命与维护
关键词搜索：
| 标 题： |
A Method for Predicting the Remaining Useful Life of Bearings Based on Genetic Programming
基于遗传编程的轴承剩余使用寿命预测方法 |
| 作 者： |
Guan Wang
Shaoliang Hu
Bowen Feng
Huimin Liu
Zhibing Zhu |
| 关键词： |
Genetic programming [遗传编程]
Remaining useful life [ 剩余使用寿命]
Feature extraction [ 特征提取]
Bearing [ 轴承]
Fault diagnosis [ 故障诊断] |
| 出版年： |
2022 |
| 文集名： |
5th IEEE Advanced Information Management, Communicates, Electronic and Automation Control Conference (IMCEC 2022)
第五届IEEE高级信息管理、通信、电子与自动化控制会议（IMCEC 2022） |
| 会议名： |
5th IEEE Advanced Information Management, Communicates, Electronic and Automation Control Conference (IMCEC 2022)
第五届IEEE高级信息管理、通信、电子与自动化控制会议（IMCEC 2022） |
| 届 次： |
5th |
| 摘 要： |
In the remaining life prediction of bearings, feature extraction is crucial because it directly determines the prediction accuracy of the model. In response to this problem, this paper proposes a feature extraction method based on genetic programming. First, the multi-dimensional features are combined into an independent feature combination in the form of a feature tree, and then an improved fitness function is designed. After many iterations, The feature combination with the highest fitness is finally output, which is called the optimization feature. Finally, the least square method is used to predict the optimization characteristic curve, and the life prediction can be carried out by combining with the failure model. Finally, the public data set of bearing full life is used to predict the remaining service life of the bearing with the optimization feature as the model, which verifies the accuracy of the algorithm prediction.
在轴承剩余寿命预测中，特征提取至关重要，因为它直接影响模型的预测精度。针对这一问题，本文提出了一种基于遗传编程的特征提取方法。首先，将多维特征组合成以特征树形式表示的独立特征组合，然后设计一种改进的适应度函数。经过多次迭代后，最终输出适应度最高的特征组合，即优化特征。接着，采用最小二乘法拟合优化特征曲线，并结合故障模型进行寿命预测。最后，利用轴承全寿命公共数据集，以优化特征作为模型，预测轴承的剩余使用寿命，从而验证了该算法预测的准确性。 |
| 中文内容为网络AI翻译，专业术语未必准确，仅供参考。 |
京公网安备 11010202009788