Foundation pit suspension type waterproof curtain water inflow prediction method based on neural network

The invention provides a foundation pit suspension type waterproof curtain water inflow prediction method based on a neural network, and the method comprises the steps: building a foundation pit suspension type waterproof curtain water inflow prediction data model which comprises parameters such as an initial underground water level, a soil property parameter, a foundation pit size and a suspension waterproof curtain insertion depth, and carrying out the prediction of the water inflow through a neural network algorithm. According to the method, the initial underground water level is measured and recorded before foundation pit construction, the actual water inflow is replaced by measuring the water pumping amount at the bottom of a foundation pit, soil samples are collected, foundation pit geometric data are measured, data are normalized, model training is conducted through a neural network algorithm, and the foundation pit is constructed. Therefore, accurate prediction of the water inflow of the suspended wat