Motion path optimization of truss manipulator based on simulated annealing and BP neural network

Introduction This research focuses on optimizing the motion path of truss manipulators and proposes a path optimization method based on a simulated annealing algorithm and a neural network to address the positioning deviation problem that occurs in industrial production. Methods The research method first uses a simulated annealing algorithm to initially improve the path parameters and avoid falling into local optima. The path is then further optimized through a neural network to ensure the precision and energy productivity of the motion path. Results The experimental outcomes indicated that the proposed algorithm performs well across multiple indicators, reducing the path length to 12.486 m, improving energy consumption optimization by 23.78%, controlling the path error at 2.14 cm, and achieving a convergence speed of 147 iterations. Compared with other algorithms, the algorithm proposed in the study also has significant advantages in path smoothness and computation time. Discussion The significance of the research lies in providing an efficient and energy-saving optimization strategy for the motion path of truss manipulators in industrial automation, which is expected to improve production efficiency and reduce industrial energy consumption.