Optimization problems, especially multi-objective optimization problem using intelligent algorithm is one of the focus areas of evolutionary computation. Particle swarm optimization algorithm as a relatively new optimization technique, the concept is simple, less control parameters, the optimization result has nothing to do with the initial value, with a certain parallelism, and it has been widespread and has good prospects for development. However, the traditional particle swarm algorithm still has some deficiencies in global search and convergence, the algorithm has attracted the interest of many researchers and scholars and almost all of them are devoted to the study of the performance improvement algorithm. It is confirmed that the particle swarm algorithm has a very good application for single objective optimization problems, but the multi-objective particle swarm optimization algorithm and its application remains to be further studied. Based on the standard particle swarm algorithm and multi-objective optimization theory, the multi-objective particle swarm optimization algorithm (Multi-Objective Particle Swarm Optimization algorithm referred to as "MOPSO algorithm ") is studied intensively in this paper, the concrete content and innovative points can be summarized as follows:(1) The basic concepts and the standard particle of multi-objective optimization algorithm is analyzed and summarized to establish the theoretical basis for the further study of multi-objective particle swarm optimization algorithm.(2) By using the niche technology for fitness, adopting the roulette method, the global best position is selected according to the fitness of elite of each particle, and a adjustment has made in the running process of the algorithm-joined the small probability of mutation strategy, proposed a multi-objective particle swarm algorithm with a niche technology and the elite set strategy, this improved algorithm not only improves the efficiency of the algorithm, but also keeps the convergence of the algorithm and the uniformity of the solution distribution.(3) A novel multi-objective particle swarm optimization algorithm is proposed in this paper, improving the speed of the particle populations update formula, combining with Chaos theory and Gauss mutation.(4) The combination of multi-objective particle swarm optimization algorithm is applied to the process of solving practical problem in transportation, enhances the practicability of the algorithm. |