摘要
由于制冷压缩机热力计算神经网络方法存在不足 ,所以在充分考虑传统制冷压缩机热力计算模型的物理特征后 ,提出改进的神经网络方法。新方法中的多层前向神经网络输入参数少、网络结构紧凑 ,输入、输出参数无需规范化和反规范化。
Artificial neural network (ANN)was utilized as a new method to calculate the thermodynamic performance of refrigeration compressors However,there are some shortcomings in the previous study A modified ANN method is developed by taking into accounts physical features of the classical thermodynamic model of refrigeration compressors The multilayer forward ANN in the new method is of less inputs than the old one,thus its structure is compact The inputs and outputs are naturally normalized Therefore,no operation on nomalization or denomalization is needed Several kinds of small scale refrigeration compressors are modeled with the presented ANN method,satisfactory precision and generalization are obtained
出处
《机械工程学报》
EI
CAS
CSCD
北大核心
2001年第1期75-77,共3页
Journal of Mechanical Engineering
基金
国家教委留学回国人员基金
上海市青年科技启明星计划
上海交通大学科技发展基金
关键词
制冷压缩机
热力计算
人工神经网络
Refrigeration compressor Thermodynamic calculation Artificial neural network
