Research on fault diagnosis model of rolling bearing based on ARIMA and XGBoost
-
摘要: 针对滚动轴承现有故障预测模型精度和准确率较低的问题，提出一种基于ARIMA时间序列预测和XGBoost分类算法的滚动轴承故障预测模型。首先，采用LMD联合FPA解决盲源欠定的问题；其次，使用KPCA选取敏感特征作为预测模型的输入，以提高轴承故障的分类精度；第三，通过Arima自回归模型预测轴承振动信号未来短期内变化情况，将预测结果输入XGBoost模型进行故障分类预测，实现滚动轴承故障识别，提高预测准确率；最后，通过美国凯斯西储大学使用的轴承数据集，进行实例验证，实验结果表明，该方法可以更准确地预测出轴承短期内振动信号变化并诊断出可能发生的故障，证明了该方法在滚动轴承信号含噪情况下，有效提取特征、识别故障和故障预警中具有可行性与可靠性。Abstract: In view of the low accuracy and accuracy of the existing fault prediction models of rolling bearing, a rolling bearing fault prediction model based on ARIMA time series prediction and XGBoost classification algorithm is proposed in this paper. Firstly, LMD combined with FPA is used to solve the problem of blind source underdetermination. Secondly, KPCA is used to select sensitive features as the input of the prediction model to improve the classification accuracy of bearing faults. Thirdly, Arima autoregressive model is used to predict the short-term change of bearing vibration signal in the future, and the prediction results are input into XGBoost model for fault classification and prediction, so as to realize rolling bearing fault identification and improve the prediction accuracy. Finally, an example is verified by the bearing data set used by Case Western Reserve University in the United States. The experimental results show that this method can more accurately predict the short-term vibration signal change of the bearing and diagnose the possible faults. It is proved that this method can effectively extract the features under the condition of rolling bearing signal noise. It is feasible and reliable in fault identification and fault early warning.
-
Key words:
- bearings /
- ARIMA /
- XGBoost /
- fault diagnosis
-
表 1 几种常见的模型评估标准
模型评估指标 评价方法 准确率（accuracy） F1-Score（F-Measure方法） 精确率（precision） 混淆矩阵（Confuse Matrix） 召回率（recall） ROC P-R曲线
（precision-recall curve）AUC 
下载: 导出CSV
表 2 ARIMA预测振动信号性能
准确率/(%) 精确率/(%) 召回率/(%) 时间/s 95.7 92.2 90.2 135 内存占比/(%) CPU占比/(%) 内存使用/MB 18.9 11.5 287.01
下载: 导出CSV
-
[1] 刘军委. 基于盲源分离的滚动轴承复合故障诊断方法研究[D]. 重庆: 重庆大学, 2016. [2] 魏乐, 胡晓东, 尹诗. 基于优化XGBoost的风电机组发电机前轴承故障预警[J]. 系统仿真学报, 2021, 33(10): 2335-2343. [3] 陈勇, 安汪悦, 刘焕淋, 等. 利用FBG传感信号诊断滚动轴承故障的检测方法[J]. 中国激光, 2020, 47(11): 136-145. [4] 王望望, 邓林峰, 赵荣珍, 等. 集成KPCA与t-SNE的滚动轴承故障特征提取方法[J]. 振动工程学报, 2021, 34(2): 431-440. [5] 王普, 李天垚, 高学金, 等. 基于LMD和MSEE的滚动轴承复合故障特征提取方法[J]. 轴承, 2019(3): 63-69. [6] 李辉. 相关熵的降噪机理及其在轴承故障诊断中的应用[J]. 轴承, 2021(3): 36-44. [7] 吴东升, 杨青, 张继云, 等. 基于VMD-LMD-CNN的集合型故障诊断方法[J]. 轴承, 2020(10): 57-63. [8] 房昕宇, 金隼, 唐水龙. 基于S变换和XGBoost算法的进给系统轴承故障诊断方法[J]. 机械设计与研究, 2020, 36(4): 69-74. [9] 曹现刚, 罗璇, 雷一楠, 等. 基于ARIMA和SVR的滚动轴承状态预测方法研究[J]. 机床与液压, 2020, 48(22): 178-181. doi: 10.3969/j.issn.1001-3881.2020.22.035 [10] 马怀祥, 冯旭威, 李东升, 等. 基于CNN和XGBoost的滚动轴承故障诊断方法[J]. 中国工程机械学报, 2021, 19(3): 254-259. [11] Zhang R T, Li B B, Jiao B. Application of XGboost algorithm in bearing fault diagnosis[J]. IOP Conference Series:Materials Science and Engineering, 2019, 490(7): 119-127. [12] Hu X, Xiao Z, Liu D, et al. KPCA and AE based local-global feature extraction method for vibration signals of rotating machinery[J]. Mathematical Problems in Engineering, 2020: 1-17. [13] Ma J, Wu J, Fan Y, et al. The rolling bearing fault feature extraction based on the LMD and envelope demodulation[J]. Mathematical Problems in Engineering, 2015(2): 429185.1-429185.13. [14] 孙伟, 李新民, 金小强, 等. 基于LMD和频谱校正的滚动轴承故障诊断方法[J]. 制造技术与机床, 2018(6): 54-57. [15] 龚立雄, 黄敏. 基于KPCA的轴承故障状态分类研究[J]. 现代制造工程, 2015(7): 149-153. doi: 10.3969/j.issn.1671-3133.2015.07.030 [16] 郑恒, 姜宏, 章翔峰. 聚KPCA在高维轴承故障诊断中的应用[J]. 机床与液压, 2021, 49(11): 179-182. doi: 10.3969/j.issn.1001-3881.2021.11.037 [17] Mursalin M, Zhang Y, Chen Y, et al. Automated epileptic seizure detection using improved correlation-based feature selection with random forest classifier[J]. Neurocomputing, 2017, 241(7): 204-214. [18] Ye T, Wang Z, Chen L. Self-adaptive bearing fault diagnosis based on permutation entropy and manifold-based dynamic time warping[J]. Mechanical Systems and Signal Processing, 2019, 114: 658-673. doi: 10.1016/j.ymssp.2016.04.028 [19] Ma Y B, Lv Y, Yuan R, et al. Synchro spline-kernelled chirplet extracting transform: A useful tool for characterizing time-varying features under noisy environments and applications to bearing fault diagnosis[J]. Measurement, 2021, 181: 109574. doi: 10.1016/j.measurement.2021.109574 [20] 郇钰莹. 旋转流体机械中滚动轴承故障识别的研究[D].杭州: 浙江理工大学, 2020. -
下载:
点击查看大图
图(7) / 表(2)
计量
- 文章访问数: 181
- HTML全文浏览量: 19
- PDF下载量: 54
- 被引次数: 0
