Huge freedom exists in hybrid ground source heat pump systems (HGSHPS). A new control strategy in HGSHPS coupled with cooling tower is proposed, that is, to compare water temperatures exiting the cooling tower and ground heat exchanger ( GHE) directly. It is necessary to build a predictive ground heat exchanger ( GHE) model because only one of the two temperatures can be measured timely. This paper uses artificial neural network (ANN) to predict the water temperature exiting the GHE and validate its feasibility and accuracy under different run mode of HGSHPS comparing with the 3-D dynamic numerical model. It shows that the ANN can be used to predict the water temperature exiting GHE with a high accuracy and generalization, no matter how the HGSHPS runs. The absolute error is less than 0.25℃.%在复合式地源热泵系统中控制策略存在着极大的优化空间,本文提出以土壤换热器与冷却塔两者出口水温作为控制依据的运行策略,为实现此控制方法,需要建立准确的预测模型.本文运用人工神经网络(ANN)实现土壤换热器侧出口水温的预测,研究复合式地源热泵系统不同运行模式下预测的可行性与准确性,并与动态数值模拟结果比较.结果表明利用人工神经网络可以准确预测土壤换热器的出口水温,且模型具有较好的泛华能力,最大误差不超过0.25℃.
展开▼
