Jixie chuandong (Jul 2021)

Research on Solving the Excavation Pose of Shield Machine based on Neural Network-Newton Hybrid Algorithm

  • Qiang Zhang,
  • Dongchen Qin,
  • Qiang Zhu,
  • Jiangyi Chen

Journal volume & issue
Vol. 45
pp. 24 – 29

Abstract

Read online

In order to solve the problems such as the kinematics modeling of the shield machine propulsion system and the difficulty of forward solution, the simplified equivalent model method is adopted to construct a simplified model of the shield machine propulsion system, and the parallel shield propulsion system of n-SPS is simplified to 4-SPS equivalent parallel propulsion mechanism and construct its kinematics model. According to the established equivalent mechanism kinematics model, a neural network-Newton hybrid algorithm is used to solve the shield tunneling pose, and the solution domain search function of the neural network is used to predict the initial value and substitute the prediction result into the Newton iteration method for calculation and solution. The pros and cons of the single neural network predicted value and the calculated results of the BP neural network-Newton iterative hybrid algorithm are analyzed and compared. The study found that the establishment of the equivalent model of the shield machine propulsion system can greatly simplify the complexity of kinematics modeling, and the use of hybrid algorithms to solve the kinematics positive solution has higher accuracy, which can improve the control accuracy of the shield machine excavation attitude, thereby improving the tunneling tunnel quality.

Keywords