@article{Hung_Zeng_Yu_Huang_Chen_2026, title={Research on PID Control Strategy for Mine Air Conditioning Systems Based on Interval Type-2 Fuzzy Neural Network}, volume={12}, url={http://dx.doi.org/10.22161/ijaems.124.11}, DOI={10.22161/ijaems.124.11}, abstractNote={<jats:p>High-temperature thermal damage in underground mines remains one of the critical bottlenecks restricting deep resource exploitation, posing severe threats to miner safety and equipment reliability. Conventional PID controllers exhibit insufficient adaptability when dealing with the nonlinearity, time-varying dynamics, and strong disturbances characteristic of mine temperature fields. To address these challenges, this paper proposes an optimized temperature control algorithm for mine air conditioning systems based on an Interval Type-2 Fuzzy Neural Network PID (IT2FNN-PID) controller. The proposed algorithm integrates the dynamic uncertainty compensation capability of interval type-2 fuzzy logic with the self-learning mechanism of neural networks, enabling real-time online tuning of PID parameters. A simplified thermodynamic model of the mine environment is first established to construct the transfer function of the temperature control system, with comprehensive analysis of multi-source disturbances including heat sources and surrounding rock heat dissipation. An interval type-2 fuzzy rule base with adaptive membership functions is then designed, and the inference parameters are dynamically optimized through the neural network structure. Comparative simulations are conducted using Matlab/Simulink, evaluating conventional PID, type-1 fuzzy PID (T1F-PID), interval type-2 fuzzy PID (IT2F-PID), and the proposed IT2FNN-PID controllers. Simulation results demonstrate that the IT2FNN-PID controller outperforms the other methods in terms of overshoot reduction, response speed, and steady-state accuracy, exhibiting superior robustness and environmental adaptability in mine temperature regulation applications.</jats:p>}, number={4}, journal={International Journal of Advanced Engineering, Management and Science}, publisher={AI Publications}, author={Hung, Chih-Ching and Zeng, Rui-Ling and Yu, Wen-Jie and Huang, Ming-Hui and Chen, Ho-Sheng}, year={2026}, pages={103–108} }