The fire source location and heat release rate(HRR)are crucial information guiding emergency firefighting and rescue operations during tunnel fires.However,in practice,the informa-tion that can be obtained about the fire is limited.It is difficult to get the fire source key parameters directly.Therefore,we re-searched the deep learning-based method for inversing thefire source location and HRR in tunnel fires.Firstly,a tunnel fire data-set under different boundary conditions is established based on nu-merical simulations validated by experimental data.Based on con-volutional neural network(CNN)and long short-term memory network(LSTM),the mapping relationship between fixed tem-perature sensor data and fire source location and HRR was estab-lished.The inversion effectiveness of the model for fire source pa-rameters was evaluated.And the effect of time series length and sensor spacing on the inversion effectiveness were evaluated.The results demonstrate that the model has good inversion perfor-mance for both HRR and fire source location.When the time se-ries length was 20 s and the sensor spacing was 30 m,the R2 val-ues of the model inversion for HRR and fire location are 0.97 and 0.99,respectively.
维普
万方数据