Research on Structural Measuring Point Optimization Method Based on Improved Particle Swarm Optimization

Aiming at the problem of too many measuring points and difficult optimization in the process of I-beam structure stress state analysis, an improved particle swarm optimization algorithm based on simulated annealing and genetic algorithm is proposed, which considers the identification error of stress state and the optimization of measuring points comprehensively to screen the measuring points. Firstly, the initialization, selection, crossover and mutation of genetic algorithm are integrated into particle swarm optimization; secondly, the idea of simulated annealing is introduced into the mutation part. The improved particle swarm optimization algorithm improves the premature and poor local optimization of the standard particle swarm optimization algorithm. Compared with the standard particle swarm optimization, the improved particle swarm optimization has better stability, stronger anti-premature ability and 60% higher accuracy. The simulation results of measuring point selection and stress state identification of I-beam show that the improved particle swarm optimization algorithm has high efficiency in the process of point selection of stress state identification. The error of force state identification to select points is less than 3%. In engineering application, it provides a better method for stress state identification.