摘要：It is easy to cause safety accidents due to the lowprecision and poor effect of earth pressure balance (EPB)control during shield machine tunneling process at present. So adata-driven optimization control method for earth pressurebalance in sealed cabin of shield machine is proposed. Firstly,the earth pressure prediction model of four pressuremonitoring points in the sealed cabin is established by usingleast squares support vector machine (LSSVM) method, and thepenalty coefficientC and kernel parameters are optimized byparticle swarm optimization (PSO). Then, an optimizationfunction is established with the minimum sum of multi-pointearth pressure prediction errors as the target. The optimalsolution is obtained by using the fruit fly optimization algorithm(FOA) to solve the optimal screw conveyor speed, so as torealize the balance control of the earth pressure in sealed cabin.Finally, the simulation experiments are carried out based onfield construction data. The results show that the method hasgreat performance such as higher accuracy of calculation andbetter control effect, which can control the excavation face ofshield machine more steady.
关键词：Shield machine; earth pressure balance; least squares support vector machine; optimal control
