Gearbox temperature prediction method based on 1DCNN-LSTM and BiLSTM parallel network

The invention provides a gearbox temperature prediction method based on a 1DCNN-LSTM and BiLSTM parallel network. The gearbox temperature prediction method comprises the following steps: acquiring temperature signals of key parts of a to-be-predicted gearbox; the method comprises the following steps: constructing a 1DCNN-LSTM model and a BiLSTM model; inputting a temperature signal, extracting feature vectors of spatial-temporal features and periodic features through a 1DCNN-LSTM model and a BiLSTM model, and performing feature rear-end fusion through a feature vector series splicing mode to obtain a fused feature vector; and inputting the fused features into a full connection layer for regression analysis to obtain a regression analysis result, and predicting a short-term temperature data value of the gearbox according to the regression analysis result. The problems that in an existing method, prediction precision is insufficient, and a single network is insufficient in the aspect of feature extraction are s