Optimal sensor placement for large-scale stadium based on improved genetic algorithm
In order to efficiently and accurately monitor the health of large-scale stadium structures,a sensor optimization layout method based on multi population non-dominated recombination genetic algorithm(MP-RGA)was proposed according to the structural characteristics of large-scale stadium.Introducing dual encoding to solve discrete optimization problems,improving the search ability of the algorithm through multiple population strategies,and solving the diversity loss problem in the later stage of genetic algorithm optimization through non-dominated recombination.Finally,adaptive crossover and mutation strategies were adopted to improve the convergence speed of the algorithm in the early stage and the optimization ability in the later stage.Taking the roof of Xi'an international football center as an example,the effectiveness of the algorithm in determining the sensor layout scheme under different sensor layout numbers was verified through numerical examples.The results show that compared with quantum genetic algorithm(QGA)and particle swarm optimization algorithm(PSO),multi population non-dominated recombination genetic algorithm has a faster convergence speed,and the optimization effect with modal confidence criterion as the objective can be improved by 41.88％and 91.27％,respectively.The actual application effect of the sensor layout scheme optimized based on the proposed algorithm is good,indicating that the algorithm is suitable for the sensor optimization layout problem of large-scale stadium.
万方数据
维普
