论文部分内容阅读
采用神经网络对冬季运行的空气源热泵冷热水机组中螺杆式压缩机的特性进行了模拟。采用误差反向传播算法 (BP算法 )对网络的连接权值进行学习和调整，以满足给定的精度要求。只要训练样本可靠，采用该方法建模可以达到比较高的精度要求。
Neural network was used to simulate the characteristics of screw compressor in air-source heat pump chiller / heater unit running in winter. The error back propagation algorithm (BP algorithm) is used to learn and adjust the network connection weights to meet the given accuracy requirements. As long as the training samples are reliable, the method can be used to model and achieve higher accuracy requirements.