作者：王坤章, 蒋书波, 张豪, 晁征

作者单位：南京工业大学，江苏 南京 211816

关键词：涡扇发动机;剩余寿命预测;有效预测值;XGBoost

摘要：

针对现有使用单个模型的剩余寿命预测方法存在精度较低的问题，提出一种基于XGBoost（极端梯度提升）的回归-分类-回归参数优化算法的预测模型。首先对涡扇发动机数据进行预处理，观察各特征与剩余寿命的相关性，筛选出初步的可用特征。然后根据故障预测与健康管理协会制定的有效剩余寿命预测值标准对连续寿命值进行离散标定，以信息增益法筛选出最终特征集。最后利用XGBoost算法分别建立离散标定后的多分类寿命预测模型和各个类别的寿命回归模型，并采用遗传算法优化各模型的参数，通过集成方式得出寿命的预测值。结果表明，基于XGBoost的回归-分类-回归算法预测模型明显优于XGBoost，其中均方根误差（RMSE）降低了27.5%，准确度（accuracy）提高了30%。

Regression-classification-regression life prediction model based on XGBoost
WANG Kunzhang, JIANG Shubo, ZHANG Hao, CHAO Zheng
Nanjing Tech University, Nanjing 211816, China
Abstract: To address the problem of low accuracy of existing methods for remaining life prediction using individual models, a prediction model based on XGBoost (extreme random tree) regression-classification-regression parameter optimization algorithm is proposed. The turbofan engine data were first pre-processed to observe the correlation between each feature and the remaining life and to filter out the initial available features. The continuous life values are then discrete calibrated according to the effective remaining life prediction value criteria established by the Failure Prediction and Health Management Association, and the final feature set is filtered by the information gain method. Finally, the discretely calibrated multi-class life prediction model and the life regression model of each category are established by using the XGBoost algorithm, and the parameters of each model are optimized by genetic algorithm, and the predicted value of life is obtained by integration. The results show that the prediction model of XGBoost-based regression-classification-regression algorithm is significantly better than XGBoost, in which the root mean square error is reduced by 27.5% and the accuracy is improved by 30%.
Keywords: turbofan engine;remaining useful life prediction;valid prediction value;XGBoost
2023, 49(8):104-109  收稿日期: 2022-03-02;收到修改稿日期: 2022-05-17
基金项目: 国家重点研发计划项目（2019YFB1705803）
作者简介: 王坤章(1996-),男,江苏泰州市人,硕士研究生,专业方向为机器学习,寿命预测
参考文献
[1] 师璐. 飞行器关键部件可靠性建模与评估方法研究[D]. 陕西: 西安理工大学, 2018.
[2] 朱霖, 宁芊, 雷印杰, 等. 基于遗传算法选优的集成手段与时序卷积网络的涡扇发动机剩余寿命预测[J]. 计算机应用, 2020, 40(12): 3534-3540
[3] YAN M, WANG X, WANG B, etal. Bearing remaining useful life prediction using support vector machine and hybrid degradation tracking model[J]. ISA Transactions, 2020, 98(58): 471-482
[4] 胡城豪, 胡昌华, 司小胜, 等. 基于MSCNN-LSTM的滚动轴承剩余寿命预测方法[J]. 中国测试, 2020, 46(9): 103-110
[5] GIANTOMASSI A, FERRACUTI F, BENINI A, et al. Hidden Markov model for health estimation and prognosis of turbofan engines[C]. //ASME 2011 International Design Engineering Technical Conferences & Computers and Information in Engineering Conference, 2011: 48174-48182.
[6] AHMADZADEH F, LUNDBERG J. Remaining useful life estimation: review[J]. International Journal of System Assurance Engineering & Management, 2014, 5(4): 461-474
[7] 张豹, 刘琼, 吴细宝, 等. 基于集成学习的涡扇发动机剩余寿命预测[J/OL]. 中国测试: 1-7[2021-12-14]. http://kns.cnki.net/kcms/detail/51.1714.TB.20210817.1329.008.html.
[8] 张一鸣, 刘晓锋, 崔宝等. 基于集成学习的涡扇发动机剩余寿命预测模型[J/OL]. 热能动力工程, 2022(4): 64-70
2-05-23]. DOI:10.16146/j.cnki.rndlgc.2022.04.009.
[9] CHUI K T, GUPTA B B, VASANT P. A genetic algorithm optimized rnn-lstm model for remaining useful life prediction of turbofan engine[J]. Electronics, 2021, 10(3): 285-299
[10] LI X, DING Q, SUN J Q. Remaining useful life estimation in prognostics using deep convolution neural networks[J]. Reliability Engineering & System Safety, 2018, 172(APR.): 1-11
[11] HE K, ZHANG X, REN S, et al. Deep residual learning for image recognition[J]. IEEE, 2016: 770-778
[12] HUANG C, HUANG H, LI Y. A bidirectional LSTM prognostics method under multiple operational conditions[J]. IEEE Trans. Industrial Electronics, 2019, 66(11): 8792-8802
[13] HEIMES F O. Recurrent neural networks for remaining useful life estimation [C]// Prognostics and Health Management, 2008. PHM 2008. International Conference on. IEEE, 2008: 1-6.
[14] CHEN T Q, GUESTRIN C. XGBoost: A Scalable Tree Boosting system[C]//KDD'16: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 2016.
[15] 董乐红, 耿国华, 高原. Boosting算法综述[J]. 计算机应用与软件, 2006(8): 27-29
[16] 于会越. 基于数据驱动的涡扇发动机剩余寿命预测[D]. 哈尔滨: 哈尔滨理工大学, 2020.