...
首页> 外文期刊>Energy Conversion & Management >Modelling of multiple short-length-scale stall cells in an axial compressor using evolved GMDH neural networks
【24h】

Modelling of multiple short-length-scale stall cells in an axial compressor using evolved GMDH neural networks

机译:使用进化的GMDH神经网络对轴流压气机中多个短尺度失速单元进行建模

获取原文
获取原文并翻译 | 示例
           

摘要

Over the past 15 years there have been several research efforts to capture the stall inception nature in axial flow compressors. However previous analytical models could not explain the formation of short-length-scale stall cells. This paper provides a new model based on evolved GMDH neural network for transient evolution of multiple short-length-scale stall cells in an axial compressor. Genetic Algorithms (GAs) are also employed for optimal design of connectivity configuration of such GMDH-type neural networks. In this way, low-pass filter (LPF) pressure trace near the rotor leading edge is modelled with respect to the variation of pressure coefficient, flow rate coefficient, and number of rotor rotations which are defined as inputs.
机译:在过去的15年中,已经进行了数项研究工作,以捕捉轴流式压缩机的失速开始特性。但是,以前的分析模型无法解释短尺度失速细胞的形成。本文提供了一种基于进化GMDH神经网络的新型模型,用于轴向压缩机中多个短长度失速单元的瞬时演化。遗传算法(GA)也用于此类GMDH型神经网络的连通性配置的最佳设计。这样,就相对于压力系数,流量系数和定义为输入的转子转数的变化,对转子前沿附近的低通滤波器(LPF)压力曲线进行了建模。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号