In order to solve the problems of lack of individual diversity, slow search speed and easy to fall into local optimization in the optimization of standard genetic algorithm, the crossover operator and mutation operator of adaptive adjustment are used to improve the algorithm, and the key parameters of stable control of linear one-stage inverted pendulum model are optimized by using the improved genetic algorithm. The optimization process is simulated on Python3.8 software. The simulation results show that the improved genetic algorithm can better balance the global search and local search ability, and shows good results in the experiment.