论文部分内容阅读
山梨醇广泛应用于食品行业,针对山梨醇结晶温控系统存在时变大滞后特性,研究了一种融合遗传算法和神经网络的PID控制器。该控制算法采用RBF网络在线辨识被控对象,先利用遗传算法优化神经网络的初始权值,再结合神经网络所具有的自学习和任意非线性表达能力,用BP神经网络自整定PID参数,对结晶过程温度进行控制。仿真结果表明:该控制器提高了系统的控制性能,具有很强的自适应性和鲁棒性,满足山梨醇生产的要求。
Sorbitol is widely used in the food industry. In view of the large lag characteristic of sorbitol crystallization temperature control system, a PID controller based on genetic algorithm and neural network is studied. The control algorithm uses RBF network to identify the controlled object online. The genetic algorithm is used to optimize the initial weight of the neural network. Combined with the self-learning and arbitrary nonlinear expression ability of neural network, BP neural network is used to self-tune the PID parameters. Crystallization process temperature control. Simulation results show that the controller improves the control performance of the system, has strong adaptability and robustness, and meets the requirements of sorbitol production.