Abstract
Intelligent optimization algorithms are widely used to determine the critical slip surface of slopes. However, the critical slip surface may not converge to a proper solution because of the nonconvex and discontinuous nature of the objective function. An intelligent optimization algorithm is developed by combining the improved quantum genetic algorithm (QGA) and random forest (RF) regression method to identify the critical slip surface of the slope. A dynamic adjustment strategy is used to control the update and evolution direction of the population to obtain the global optimal solution, which not only ensures the convergence of the results but also effectively avoids premature convergence. The RF regression method is applied to estimate the fitness, which can help avoid the mechanical analysis of the slide body of the slope and increase the calculation efficiency. An external penalty function is used to penalize solutions that do not meet the constraints of the slip surface. This aspect reduces probability of such solutions appearing in the next generation, thereby ensuring that the identified critical slip surface has practical significance. The results obtained for four slope cases are in agreement with those of previous investigations, which demonstrates the accuracy and effectiveness of the proposed method. In addition, the results of the four slope cases show that the convergence speed is higher for a larger population.
Published Version
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call