摘要
针对地源热泵(GCHP)系统的能量消耗问题,提出了一种基于自适应粒子群(APSO)优化算法和最邻近聚类径向基神经网络(RBFNN)建模的预测控制策略;首先,利用神经网络建立系统的输出预测模型,然后通过粒子群的滚动优化算法求解得到最优控制量;仿真结果表明,该方法能够在满足负荷要求的前提下,有效地降低GCHP系统在运行过程中的能量消耗。
For reducing the energy consumption of the ground--coupled heat pump （GCHP） systern, a predictive control strategy is proposed based on adaptive particle swarm optimization （APSO） algorithm and nearest neighbor clustering radial basis function neural network （RBFNN）. First, utilize RBFNN to establish the model of the system, then calculated the optimal settings with the rolling optimization algorithm of APSO. The simulation results show that this control strategy can reduce the total energy consumption of the GCHP system efficiently under the requirements of the load.
出处
《计算机测量与控制》
北大核心
2014年第1期106-108,112,共4页
Computer Measurement &Control
关键词
地源热泵系统
径向基神经网络
自适应粒子群算法
预测控制
ground--coupled heat pump system
radial basis function neural network
adaptive particle swarm optimization algorithm
predictive control
