An effective indoor temperature model would assist in improving energy efficiency and indoor thermal comfort of air conditioning system. However, it is difficult to build an accurate model due to lag response characteristic in the regulation process of indoor temperature. To solve this problem, the modeling and prediction methods for indoor temperature lag response characteristic based on time-delay neural network (TDNN) and Elman network neural (ENN) are presented. Then, taking variable air volume (VAV) air conditioning system as the study object, the effectiveness and practicability of proposed methods are validated using simulation sampling data and real-time operating data. Results indicate that ENN could be considered as a better modeling method for indoor temperature prediction for its simpler network structure, smaller storing space and better prediction accuracy. The contribution of this study is to provide an applicable online ANN modeling method for indoor temperature lag characteristic, and detailed training and validation for online implementation are presented, which will benefit for engineers and technicians to use in practical engineering. Meanwhile, this study provides the reference for online application of advanced intelligent algorithms in the building engineering.

有效的室内温度模型将有助于提高空调系统的能源效率和室内热舒适度。但是，由于室内温度调节过程中的滞后响应特性，难以建立精确的模型。针对这一问题，提出了基于时延神经网络（TDNN）和艾尔曼网络神经（ENN）的室内温度滞后响应特性的建模和预测方法。然后，以可变风量（VAV）空调系统为研究对象，利用模拟采样数据和实时运行数据验证了所提方法的有效性和实用性。结果表明，ENN网络结构更简单，可以认为是一种更好的室内温度预测建模方法，较小的存​​储空间和更好的预测精度。这项研究的目的是为室内温度滞后特性提供一种适用的在线ANN建模方法，并对在线实施进行详细的培训和验证，这将有益于工程技术人员在实际工程中使用。同时，本研究为高级智能算法在建筑工程中的在线应用提供参考。