Research on Optimization Model of Supply Chain Robot Task Allocation Based on Genetic Algorithm and Software Practice

Abstract

In the context of Research on Optimization Model of Supply Chain Robot Task Allocation Based on Genetic Algorithm and Software Practice, aiming at solving the problems of premature convergence of genetic algorithm (GA) in the path planning involved in supply chain robot task allocation and the generation of a large number of infeasible paths due to crossover and mutation, this study improves the traditional genetic algorithm. Binary coding is adopted to store paths, providing a basis for subsequent genetic operations such as crossover and mutation, which is conducive to the efficient implementation of the supply chain robot task allocation optimization model in software practice. By combining with particle swarm optimization (PSO) for local search, the search speed of genetic algorithm is accelerated and the search efficiency is improved, which lays a good foundation for the rapid solving of the task allocation optimization model. Meanwhile, a repair mechanism is introduced to study all infeasible paths, determine the reasons for their infeasibility and carry out corrections, ensuring the feasibility of paths in the task allocation process. Simulation results show that in simple single - target scenarios of supply chain robot task allocation, the improved algorithm has a faster convergence speed and avoids local optimization; in multi - objective complex environments, it can obtain appropriate path solutions. This improved genetic algorithm provides strong algorithm support for the establishment and software implementation of the supply chain robot task allocation optimization model.