基于BP神经网络的集中供热二次网回水温度预测控制研究

Research on Prediction and Control of Return Water Temperature in Central Heating Secondary Network Based on BP Neural Network

针对集中供热系统二次管网存在的水力失调问题,设计了二次网水力平衡调节及回水温度预测模型,并实施智能控制策略,以实现二次网回水温度的精准控制。首先,构建BP神经网络预测模型,将此模型的输出视为二次网回水温度给定值;其次,在整个系统控制中,实施BP神经网络与PID控制器相结合的策略,进行二次网回水温度的控制。以高邑县某小区换热站数据为基础,通过阶跃响应曲线法建立二次网回水温度控制系统的数学模型,并通过BP-PID控制进行仿真实验。实验结果表明,与传统PID控制器相比,BP-PID控制器具有调节时间短、超调量小的优点,能够快速达到平稳状态。

A hydraulic balance regulation and return water temperature prediction model for the secondary network of centralized heating system is designed to address the issue of hydraulic imbalance,and an intelligent control strategy is implemented to achieve precise control of return water temperature in the secondary network.Firstly,a BP neural net-work prediction model is constructed,which treats the output of this model as the given value of the secondary network return water temperature.Secondly,in the entire system control,a strategy combining BP neural network and PID con-troller is implemented to control the return water temperature of the secondary network.Based on the data of a heat exchange station in a residential area of Gaoyi County,a mathematical model of the secondary network return water tem-perature control system is established using the step response curve method,and simulation experiments are conducted using BP-PID control.The experimental results show BP-PID controllers have the advantages of short adjustment time and small overshoot,and can quickly reach a stable state compared with traditional PID controllers.