摘要
通过采用遗传算法训练BP神经网络、优化网络权值的技术,对气液两相流的流型进行了辨识研究,在此基础上建立了基于遗传算法/神经网络组合技术的气液两相流流型的预测模型,从而为发动机轴承腔内润滑油气液两相流流型识别提供了技术支持,也为考虑轴承腔气液两相流的相关设计和实验工作提供了技术条件。
By using genetic algorithm to train BP neural network and optimize the weights of the network, identification of the gas-liquid two-phase flow regime is studied. Based on it we build the model with the method in which genetic algorithm and neural network are mixed. The results of this paper can be used in the identification of two-phase flow regime in aero-engine bearing chamber lubrication.
出处
《机械科学与技术》
CSCD
北大核心
2005年第6期670-672,共3页
Mechanical Science and Technology for Aerospace Engineering
关键词
轴承腔
两相流
流型识别
遗传算法
神经网络
Bearing chamber
Two-phase flow
Identification of flow regime
Genetic algorithm
Neural network
