Research On AGV Path Planning Of Welding Production Line Based On Improved Intelligent Optimization Algorith

In the era of Industry 4.0,information technology has made traditional manufacturing more intelligent.The emergence of AGV is one of the signs that traditional manufacturing has entered the era of intelligence.Planning a better path plan for AGV has become an important research content.In this paper,by improving the whale optimization algorithm to improve the search performance of the algorithm,it further attempts to provide a better solution to the path planning problem of the AGV.The whale optimization algorithm is an intelligent optimization algorithm that is derived from the study of the unique predation behavior of humpback whales and simulates the cooperative predation between humpback whale groups.In the whale optimization algorithm,the unique foraging method of humpback whales is simulated as two stages of shrinking encircling and spiral updating position.These two stages are carried out at the same time,so as to realize this special predation method--bubble-net feeding method.The bubble-net feeding method is the advantage of the whale optimization algorithm.Although the performance of the whale optimization algorithm is better than other intelligent optimization algorithms,it also has problems such as insufficient convergence and easy to fall into local optimum.To deal with these problems,this paper deeply analyzes the various stages of the whale optimization algorithm,and proposes a multi-population whale optimization algorithm based on orthogonal learning.The improved whale optimization algorithm is mainly improved from the following aspects:(1)Aiming at the problem that the population is easy to fall into local optimality,this paper proposes a multi-population strategy,and at the same time proposes an information exchange method based on orthogonal learning strategy,so that the sub-populations can evolve independently and at the same time,information can be exchanged between the sub-populations.It is effective to avoid the algorithm falling into the local optimum.(2)Aiming at the effect of uneven distribution of the initial population on the results,this paper introduces a generalized opposition-based learning strategy to increase the diversity of the initial population,so that individuals in the search space can be evenly distributed,and further improve the convergence speed of the algorithm.At the same time,the generalized opposition-based learning strategy is used to carry out the generation jump operation to reduce the situation that the population falls into the local optimum.(3)To ameliorate the convergence performance of the algorithm,this paper proposes a nonlinear convergence factor and an adaptive weight strategy.According to the iterative situation,the search strategy is executed adaptively,thereby balancing the algorithm’s global search capability and local development capability.To achieve improve the effect of algorithm convergence speed and solution accuracy.This paper compares the multi-population whale optimization algorithm based on orthogonal learning with other optimization algorithms in simulation experiments,and further verifies that the multi-population whale optimization algorithm based on orthogonal learning has better performance than other improved methods of whale optimization algorithms.In addition,this paper applies the improved whale optimization algorithm to the path planning problem of the AGV on the welding production line.First,the grid method is used to model the operating environment of the AGV,and then the improved whale optimization algorithm is used for path planning.Finally,simulation experiments show that the multi-population whale optimization algorithm based on orthogonal learning can reflect its better search performance in the path planning problem.