A New Hybrid Ensemble Deep Learning Model for Train Axle Temperature Short Term Forecasting

被引:19
作者
Yan, Guangxi [1 ]
Yu, Chengqing [1 ]
Bai, Yu [2 ]
机构
[1] Cent South Univ, Sch Traff & Transportat Engn, Changsha 410075, Peoples R China
[2] Hebei Univ Sci & Technol, Sch Informat & Engn, Shijiazhuang 050001, Hebei, Peoples R China
基金
中国国家自然科学基金;
关键词
axle temperature forecasting; hybrid model; data decomposition; optimization algorithm; REMAINING USEFUL LIFE; NEURAL-NETWORK; PREDICTION; DECOMPOSITION; OPTIMIZATION; ALGORITHM;
D O I
10.3390/machines9120312
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
The axle temperature is an index factor of the train operating conditions. The axle temperature forecasting technology is very meaningful in condition monitoring and fault diagnosis to realize early warning and to prevent accidents. In this study, a data-driven hybrid approach consisting of three steps is utilized for the prediction of locomotive axle temperatures. In stage I, the Complementary empirical mode decomposition (CEEMD) method is applied for preprocessing of datasets. In stage II, the Bi-directional long short-term memory (BILSTM) will be conducted for the prediction of subseries. In stage III, the Particle swarm optimization and gravitational search algorithm (PSOGSA) can optimize and ensemble the weights of the objective function, and combine them to achieve the final forecasting. Each part of the combined structure contributes its functions to achieve better prediction accuracy than single models, the verification processes of which are conducted in the three measured datasets for forecasting experiments. The comparative experiments are chosen to test the performance of the proposed model. A sensitive analysis of the hybrid model is also conducted to test its robustness and stability. The results prove that the proposed model can obtain the best prediction results with fewer errors between the comparative models and effectively represent the changing trend in axle temperature.
引用
收藏
页数:22
相关论文
共 53 条
[1]   An ensemble long short-term memory neural network for hourly PM2.5 concentration forecasting [J].
Bai, Yun ;
Zeng, Bo ;
Li, Chuan ;
Zhang, Jin .
CHEMOSPHERE, 2019, 222 :286-294
[2]  
Bing C., 2016, P CHIN CONTR C CHENG
[3]   PSO-GSA based fuzzy sliding mode controller for DFIG-based wind turbine [J].
Bounar, N. ;
Labdai, S. ;
Boulkroune, A. .
ISA TRANSACTIONS, 2019, 85 :177-188
[4]   A new hybrid method for the prediction of the remaining useful life of a lithium-ion battery [J].
Chang, Yang ;
Fang, Huajing ;
Zhang, Yong .
APPLIED ENERGY, 2017, 206 :1564-1578
[5]   A hybrid electricity price forecasting model with Bayesian optimization for German energy exchange [J].
Cheng, Hangyang ;
Ding, Xiangwu ;
Zhou, Wuneng ;
Ding, Renqiang .
INTERNATIONAL JOURNAL OF ELECTRICAL POWER & ENERGY SYSTEMS, 2019, 110 :653-666
[6]   A novel modified hybrid PSOGSA based on fuzzy logic for non-convex economic dispatch problem with valve-point effect [J].
Duman, Serhat ;
Yorukeren, Nuran ;
Altas, Ismail H. .
INTERNATIONAL JOURNAL OF ELECTRICAL POWER & ENERGY SYSTEMS, 2015, 64 :121-135
[7]   Forecasting Model of Photovoltaic Power Based on KPCA-MCS-DCNN [J].
Gou, Huizhi ;
Ning, Yuncai .
CMES-COMPUTER MODELING IN ENGINEERING & SCIENCES, 2021, 128 (02) :803-822
[8]   Axle Temperature Monitoring and Neural Network Prediction Analysis for High-Speed Train under Operation [J].
Hao, Wei ;
Liu, Feng .
SYMMETRY-BASEL, 2020, 12 (10) :1-13
[9]  
Hochreiter S, 1997, NEURAL COMPUT, V9, P1735, DOI [10.1162/neco.1997.9.8.1735, 10.1162/neco.1997.9.1.1, 10.1007/978-3-642-24797-2]
[10]   An adaptive method for health trend prediction of rotating bearings [J].
Hong, Sheng ;
Zhou, Zheng ;
Zio, Enrico ;
Wang, Wenbin .
DIGITAL SIGNAL PROCESSING, 2014, 35 :117-123