A Method of Tool Wear Detection for Shield Machine Based on Hidden Markov Model Algorithm

The tool wear of shield machine is a key problem that affects the quality and progress of the project. In order to solve the problem of tool wear detection during shield tunneling, this paper proposes a method of using hidden Markov model (HMM) to evaluate the tool wear of shield machine. Firstly, four main propulsion parameters, including total thrust, cutterhead torque, propulsion speed and cutter speed, are selected as the research objects. The influence of the four propulsion parameters on tool wear is analyzed, and the fitting expression between the tool wear and the four propulsion parameters is established. The deviation between the predicted tunneling speed and the actual tunneling speed is obtained by fitting expression, and then the HMM method is used to train it, and the statistical model of tool wear is established. Then the observation signal is input into the statistical model, and the output probability is compared with the original model, so as to evaluate the development trend of tool wear state. Simulation and actual test show that the method is accurate.