Abstract: In response to the problem that traditional PID control of tunnel jet fans is difficult to cope with complex and variable working conditions, and parameter tuning is challenging, a wind volume automatic adjustment method based on the combination of adaptive neural fuzzy inference system （ANFIS） and PID is proposed. This method utilizes the powerful self-learning and nonlinear mapping capabilities of ANFIS to identify the dynamic relationship between environmental parameters （such as traffic flow, air volume, and pollutant concentration） inside the tunnel and the optimal control parameters of the fan online. The proportional, integral, and differential coefficients of the PID controller are adjusted in real time to achieve online optimization and adaptive tuning of control parameters. By constructing a system simulation model, the response characteristics of traditional PID, fuzzy PID, and the proposed ANFIS-PID control strategy were compared and analyzed under typical operating conditions. The simulation results show that the ANFIS-PID controller can quickly and accurately adjust the speed and air output of the jet fan according to changes in working conditions. Compared with traditional control methods, it has faster response speed, smaller overshoot, and stronger robustness and adaptability. It can effectively maintain the stability of the air volume in the tunnel, reduce energy consumption, and provide an effective solution to improve the intelligent and refined control level of the tunnel ventilation system.