A novel axle temperature forecasting method based on decomposition, reinforcement learning optimization and neural network

•The axle temperature is predicted by time series method.•Q-learning method is used to optimize the initial parameters of neural network.•EWT decomposition algorithm can preprocess the original axle temperature data.•A novel hybrid model is used to predict the trend of axle temperature. Axle tempera...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	Advanced engineering informatics 2020-04, Vol.44 (C), p.101089, Article 101089
Hauptverfasser:	Liu, Hui, Yu, Chengming, Yu, Chengqing, Chen, Chao, Wu, Haiping
Format:	Artikel
Sprache:	eng
Schlagworte:	Axle temperature forecasting Empirical wavelet transform Hybrid model Parameter optimization Q-BPNN network Q-learning algorithm
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!