Huang Haiyang, Luo Yingmao, Zhao Chun, Suo Hui
State Key Laboratory of Integrated Optoelectronics, College of Electronic Science and Engineering, Jilin University, Changchun 130012, China.
Sensors (Basel). 2025 Aug 13;25(16):5020. doi: 10.3390/s25165020.
Electric heating furnaces are widely used in industrial production and scientific research, where the quality of temperature control directly affects product performance and operational safety. However, precise control remains challenging due to the system's nonlinear behaviour, time-varying characteristics, and significant time delays. To overcome these issues, this paper proposes a composite control method that integrates an auto-encoder-based prediction model with fuzzy PI control. Specifically, a discrete-time temperature model is constructed, in which the auto-encoder learns the system dynamics and predicts future temperatures, while the fuzzy controller adaptively tunes the PI parameters in real time. This approach improves both modelling accuracy and the adaptability of the control system. The simulation results on the MATLAB/Simulink platform show that the proposed method maintains the temperature overshoot within 2% under various disturbances, including a maximum delay of 243 s, ±2 °C measurement noise, 10% voltage fluctuation, and abrupt 10% gain variation. These results demonstrate the method's strong robustness and indicate its suitability for advanced control design in complex industrial environments.
电加热炉在工业生产和科学研究中广泛应用，其中温度控制质量直接影响产品性能和操作安全性。然而，由于系统的非线性行为、时变特性和显著的时间延迟，精确控制仍然具有挑战性。为克服这些问题，本文提出一种将基于自动编码器的预测模型与模糊PI控制相结合的复合控制方法。具体而言，构建离散时间温度模型，其中自动编码器学习系统动态并预测未来温度，而模糊控制器实时自适应调整PI参数。这种方法提高了建模精度和控制系统的适应性。在MATLAB/Simulink平台上的仿真结果表明，所提出的方法在各种干扰下，包括最大延迟243秒、±2°C测量噪声、10%电压波动和10%增益突然变化，将温度超调量保持在2%以内。这些结果证明了该方法的强大鲁棒性，并表明其适用于复杂工业环境中的先进控制设计。
