Optimisation of transmission towers under multiple load cases and constraint conditions with the KSM-GA method

Transmission towers operate in complex engineering environments, such as gravity, strong winds, ice and snow, wire breaking unbalanced loads. Owing to complicated structural parameters, multiple load cases constraint conditions, the optimal design plan of structure is difficult acquire. Popular intelligent algorithms (Genetic Algorithm, GA; Particle Swarm Optimisation, PSO; others) need spend time mechanical computation search processes. To solve this problem, commercial FE software ABAQUS was used build full parametric analytical computational sub-procedures (general static, linear buckling cost computation) for transmission tower under conditions. Then, main algorithm procedure, KSM-GA, developed based on GA optimiser Kriging Surrogate Model (KSM). The KSM-GA could import variables (such cross-section properties dimensions) into read results (including stresses, displacements, weight). show that can reduce more than 30% compared with GA, PSO BO-GP( Bayesian Optimisation Gaussian Process) while training precision KSM above 99% accuracy results.