Objective Aiming at the shortcomings of particle swarm optimization PSO in layout optimization such as low convergence precision and a tendency to premature convergence an improved PSO algorithm based on chaotic mapping is proposed. Methods First an adaptive dynamic inertia weight was set to measure global and local search capabilities. Subsequently chaotic mapping was introduced and an appropriate chaotic mapping method was selected to enhance the diversity of the population. Finally a differential evolution algorithm was incorporated to improve the search ability of the algorithm. Adaptive mutation parameters and crossover parameters were set to control the magnitude of mutation so as to enhance the performance of the differential evolution algorithm and prevent the improved PSO from falling into local optima. Results Taking the transmission assembly workshop as a case study the improved PSO algorithm was applied to solve the problem by constructing an objective function aimed at minimizing total cost and maximizing non-logistical relationship closeness. Data analysis demonstrated that the proposed algorithm can effectively mitigate the premature convergence inherent in the standard PSO. The optimized layout achieved a 32. 83% reduction in material handling distance and a 34. 37% decrease in logistics cost. Conclusion The case study results confirm the feasibility and effectiveness of the proposed algorithm for workshop layout optimization.