Real-time state monitoring method for refuge chamber based on neural network

The invention discloses a real-time state monitoring method for a refuge chamber based on a neural network. The method comprises the following steps: 1, arranging monitoring points in the refuge chamber, and installing a gas sensor; 2, acquiring historical gas concentration data of monitoring points in the refuge chamber; 3, normalizing a training set and a test set; 4, acquiring an online measurement model for the gas state of the refuge chamber; and 5, according to the refuge chamber gas state online measurement model, inputting the gas concentration detected by the gas sensor in real time to realize online measurement so as to obtain a real-time refuge chamber gas state coefficient. The method is simple in step, the refuge chamber gas state online measurement model is obtained by utilizing the historical gas concentration data of the monitoring points in the refuge chamber, and the refuge chamber gas state on-line measurement model is adopted to predict the refuge chamber gas state coefficient, so that the