Fan gear box temperature prediction method, device, equipment and medium

• Main Authors: YAO GUOQIANG, FANG MING, WEI XIANG, LAI JIANJING, ZHANG HUI, ZHANG GUANGMING, HE QINGYUE, LI JIN, YUAN SHINENG, SHI KAIDI
• Format: Patent
• Language: Chinese; English
• Published: 22.12.2023
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; ELECTRIC DIGITAL DATA PROCESSING; MEASURING; MEASURING QUANTITY OF HEAT; MEASURING TEMPERATURE; PHYSICS; TESTING; THERMALLY-SENSITIVE ELEMENTS NOT OTHERWISE PROVIDED FOR

The invention discloses a fan gearbox temperature prediction method, device and equipment and a medium, and relates to the technical field of computers. The method comprises the following steps: acquiring historical temperature data in the operation process of a fan gearbox, and dividing sample data and labels; then, feature extraction is carried out through a residual network formed by residual blocks formed by a depth divisible convolutional neural network model and a bidirectional long-short-term memory neural network model in parallel, regression analysis is carried out according to the obtained features, and a predicted temperature is determined; and training the residual network by taking the minimum deviation between the predicted temperature and the future real temperature as an optimization target, and finally predicting the temperature of the fan gearbox through the trained residual network. By using the residual structure, the model has the capability of keeping features in the process of advancing