.png){kind=icon}
.png){kind=icon}
Return
Assembly sequence planning based on hybrid SOS-PSO algorithm
.png){kind=icon}
PRE
AI
DOI：10.1007/s00170-025-15172-z.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Assembly sequence planning (ASP) is a crucial part of the product life cycle, directly affecting production efficiency and costs. Firstly, a multi-constraint ASP model is introduced that considers the influencing factors during the assembly process. Secondly, the SOS-PSO hybrid algorithm, integrating symbiotic organism search (SOS) with particle swarm optimization (PSO), is proposed for optimal assembly sequence calculation. To address the issues with the traditional PSO algorithm, such as heavy dependence on parameters and a tendency to get trapped in local optima, a feasible population adjustment strategy has been designed to reduce the search space of the algorithm. Logistic chaotic mapping is used to optimize the inertia weight, and an asynchronous learning factor strategy is employed to ensure a balance between global and local searches in the PSO algorithm. In the hybrid SOS-PSO algorithm, the initial population for the SOS provides a diverse range of initial parameter values for the PSO, enhancing parameter range adjustment flexibility. Finally, in experiments on planetary gear reducers, it was shown that the error of the hybrid SOS-PSO algorithm in solving the ASP problem is within 5% and a smaller variance, while the single PSO algorithm has a peak error of 41%, indicating that the hybrid SOS-PSO algorithm outperforms the single PSO algorithm in terms of robustness and stability and has good adaptability to key parameters, significantly improving the quality of the solution.
Keywords:
Assembly sequence planning
Particle swarm optimization
Symbiotic organisms search
Population adjustment strategy
Parameter optimization
Journal
IF:
3.1
Papers:
1.8K
Citations:
6.4W
Organization
No organization information available