Study on forecasting the parameters of gas environment of metro station

In the crowded metro station, it is important to forecast the changes of environmental parameters for the normal operation of metro and the safety of passengers in the future. Artificial Neural Network (ANN) has a good performance on processing time series data. In order to accurately predict environmental parameters, this paper uses ANN method to build the forecasting model of environmental parameters. The forecasting model uses the external environment parameters of the station as input variables. Finally, the accuracy of the model is verified by the field data collected from the metro station. The results show that the mean relative error of the proposed method is within 10%. The forecasting model based on ANN in this paper can accurately forecast the internal environment parameters of the metro station in the future period and is of great significance of emergency prevention and decision-making.