Search

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. [ABSTRACT FROM AUTHOR]

• The oil temperature series is predicted by time series method. • The Sarsa method is applied as the feature selection method. • The SRU is used as the main predictor to predict the oil temperature. • The proposed model is compared with twenty-three mainstream forecasting models. Oil temperature forecasting technology can realize real-time detection of the gearbox status of wind turbines. To make the oil temperature forecasting more accurate, a new hybrid model is presented in this study. The main modeling process of the presented method consists of three main steps. In step I, the proposed secondary decomposition method is utilized to preprocess the raw oil temperature data. In step II, the feature selection algorithm based on reinforcement learning selects the features of each sub-series. In step III, the simple recurrent unit network establishes forecasting models for each sub-series after feature selection and obtains the final forecasting results. By analyzing the forecasting results of multiple experiments, it can be concluded that: (1) the presented hybrid model can obtain satisfying forecasting results. Its RMSE values are 0.1101 °C, 0.1683 °C, and 0.1784 °C in three cases. (2) The presented hybrid model can get higher forecasting accuracy than the seventeen alternative models and six existing models in all cases. It improves the performance of traditional neural networks by over 90 percent. [ABSTRACT FROM AUTHOR]

• 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 temperature forecasting technology is important for monitoring the status of the train bogie and preventing the hot axle and other dangerous accidents. In order to achieve high-precision forecasting of axle temperature, a hybrid axle temperature time series forecasting model based on decomposition preprocessing method, parameter optimization method, and the Back Propagation (BP) neural network is proposed in this study. The modeling process consists of three phases. In stage I, the empirical wavelet transform (EWT) method is used to preprocess the original axle temperature series by decomposing them into several subseries. In stage II, the Q-learning algorithm is used to optimize the initial weights and thresholds of the BP neural network. In stage III, the Q-BPNN network is used to build the forecasting model and complete predicting all subseries. And the final forecasting results are generated by combining all prediction results of subseries. By comparing all results over three case predictions, it can be concluded that: (a) the proposed Q-learning based parameter optimization method is effective in improving the accuracy of the BP neural network and works better than the traditional population-based optimization methods; (b) the proposed hybrid axle temperature forecasting model can get accurate prediction results in all cases and provides the best accuracy among eight general models. [ABSTRACT FROM AUTHOR]