基于神经网络的压气机特性计算新方法  

A New Approach of Characteristic Map Calculating of Compressor Based on Neural Network

作　　者：冯凤珍 [1] 孙允标  余又红 [1] 

机构地区：[1]海军工程大学,武汉,430033 [2]北京西三环中路19号,北京,100841

出　　处：《计算机与数字工程》2004年第6期45-47,共3页Computer & Digital Engineering

摘　　要：提出一种利用神经网络进行压气机特性计算的新方法。从求解燃气轮机全工况问题出发 ,分析了压气机特性计算的困难所在 ,针对一个实例 ,应用三层反向传播神经网络求出隐含的压气机特性参数间的关系。A new approach of characteristic map calculating of compressor based on neural network are introduced in the paper. From the problem of gas turbine all states performance prediction, the difficulties of characteristic map calculating of compressor are analyzed. The hidden relations of compressor characteristic parameters are found by the training of three-layer back-propagation network by an example.

关 键 词：压气机 神经网络 特性线 

分 类 号：TK47[动力工程及工程热物理—动力机械及工程]