Shield tunneling machine attitude subentry prediction method based on machine learning

The invention discloses a shield tunneling machine attitude subentry prediction method based on machine learning, and relates to the field of shield tunneling machine attitude prediction. The method comprises the following steps: obtaining a trend item and a fluctuation item of attitude parameter data and a trend item and a fluctuation item of construction parameter data; strong correlation parameters are determined, and trend items and fluctuation items of strong correlation parameter data are determined; constructing and training a first long-short term memory network model and a second long-short term memory network model; and performing hyper-parameter optimization and a second round of training on the trained first long-short-term memory network model and the second long-short-term memory network model to obtain a shield tunneling machine attitude subentry prediction result. According to the method, the influence of the construction parameters of the shield tunneling machine on the posture of the shield