大型集中供热系统热源温度实时优化

Real-time Optimization of Heat Source Temperature in Large-scale Central Heating System

供热系统中,通过调节热源处供水温度将热源供热量与热力站热负荷相匹配,是实现节能降耗的重要方法。然而在大型集中供热系统中,热力站数量多,且热源至各热力站的温度传导时延各不相同,无法直接通过热力站热负荷计算最优热源供水温度。因此,分析了多热力站情况下温度传导时延如何影响供热量与热负荷的匹配,提出一种基于深度学习的热源温度实时优化方案。该方案将整个供热系统作为整体,通过实时优化热源供水温度,首先使供热量在未来各时刻均与供热系统整体热负荷相匹配,再通过热力站间的流量调节使得供热量与各热力站的热负荷相匹配。该方案在实际系统中能够达到很好的优化效果,数据结果证明,该方案是可行有效的。

In the heating system,matching the heat supply of the heat source with the heat load of the heating station by adjusting the temperature of the water supply at the heat source is an important method to realize energy saving and consumption reduction.However,in a large-scale central heating system,there are a large number of thermal power stations,and the temperature transfer time delay from the heat source to each thermal power station is different,and it is impossible to directly calculate the optimal heat source water supply temperature through the thermal load of the thermal power station.This paper analyzes how the temperature conduction delay affects the matching of heat supply and heat load in the case of multiple thermal stations,and then proposes a real-time optimization scheme for heat source temperature based on deep learning.The plan takes the entire heating system as a whole,and optimizes the water supply temperature of the heat source in real time.First,the heat supply matches the overall heat load of the heating system at all times in the future.The thermal load of each thermal station is matched.This scheme can achieve a good optimization effect in the actual system,and the data results prove that the scheme is feasible and effective.