Abstract:  An improved cuckoo algorithm is proposed to solve the path planning problem in the process of PCB welding. This paper adds 2opt neighborhood search strategy to the classic cuckoo algorithm. After the original algorithm produces a new solution， 2opt neighborhood search operation is performed on the new solution， and whether the better solution nearby to be replaced is judged by search， so as to improve the local search ability and solution accuracy of the algorithm. In order to verify the effectiveness of the improved algorithm， this paper carries out simulation experiments on three kinds of PCB boards with different hole numbers and hole distribution complexity， and compares the optimization effects among the classic cuckoo algorithm， the algorithm in Reference［28］ and the improved algorithm proposed in this paper. The experimental results show that， among the three PCB boards， the improved algorithm not only has the shortest optimization path distance， but also has the highest solution accuracy， and also the convergence speed is improved. When the number of holes increases and the complexity of hole distribution increases， the improved algorithm shows greater advantages in path optimization effect than the other two algorithms. To sum up， the improved cuckoo algorithm has certain effect in optimizing the welding path of PCB， and has the advantages of strong search ability， high solution accuracy and fast convergence speed.

Key words:  , printed circuit board, path planning, cuckoo algorithm, 2opt neighborhood search