论文部分内容阅读
基于广义生长-剪枝径向基神经网络(GGAP-RBF)对江水源热泵系统(RWHP)建模,通过模型预测江水源热泵系统相关性能参数。性能预估得到的模型有助于实现热泵系统最优化设计和节能运行。而相应模型由广义生长-剪枝(GGAP)算法确定隐层神经元数量为7。相应的均方根值和变异系数的百分比分别为0.0047和0.1363,决定系数R2值0.9998也较适宜。结果表明GGAP-RBF模型对RWHP系统量化模型具有很好的适用性。
The water source heat pump system (RWHP) was modeled based on GGAP-RBF (Generalized Growth-Pruning Radial Basis Function Neural Network) and the model was used to predict the relevant performance parameters of the river water source heat pump system. Predicted performance models help to optimize heat pump system design and energy saving operation. The corresponding model is defined by the GGAP algorithm to determine the number of hidden neurons. The corresponding root mean square and coefficient of variation were 0.0047 and 0.1363, respectively, and the coefficient of determination R2 of 0.9998 was also suitable. The results show that the GGAP-RBF model has good applicability to the quantitative model of RWHP system.