Multi-objective optimized 1DCNN-GRU-LSTM neural network tunnel face gas concentration prediction method

The invention relates to a multi-objective optimized 1DCNN-GRU-LSTM neural network tunnel face gas concentration prediction method, and belongs to the field of coal penetrating tunnel engineering gas concentration prediction. The method comprises the following steps: acquiring a gas concentration data set; carrying out missing value filling on the obtained gas concentration data set; carrying out data set division and normalization processing on the data; slicing the data set according to the length of the selected time window; introducing a convolutional neural network to process historical gas concentration sequence data with time sequence, and setting parameters; introducing a gating circulation unit neural network and a long-short-term memory neural network to process historical gas concentration sequence data with time sequence; and the model is optimized and solved more effectively in a multi-target mode. According to the method, the prediction model is established for the gas concentration sequence dat