Abstract: The temperature and humidity system in a variable air volume air conditioning room is a nonlinear and highly coupled system. The traditional genetic algorithm, due to its limited search range and the tendency to get stuck in local optimal solutions, is difficult to precisely control it. By dynamically adjusting the crossover probability and mutation probability using an adaptive genetic algorithm, the shortcomings of the traditional genetic algorithm are compensated. The traditional genetic algorithm and the adaptive genetic algorithm are respectively used to optimize the PID parameters, and the wind valve opening of the variable air volume air conditioning system and the supply air temperature of the room temperature, as well as the supply air temperature of the room humidity, are decoupled controlled. The simulation results show that compared with the traditional genetic algorithm, the use of the adaptive genetic algorithm effectively reduces the regulation time and overshoot of the temperature and humidity in the air conditioning room, and increases the stability and robustness of the system.