基于可视化自编码器的无叶扩压器失稳流场降阶分析

黄可心; 吴颖; 竺晓程

doi:10.19805/j.cnki.jcspe.2026.250025

欢迎来到能源电力期刊网！

English Version 期刊登录

您当前的位置：

首页 >

文章列表页 >

基于可视化自编码器的无叶扩压器失稳流场降阶分析

动力设备与系统 | 更新时间：2026-10-10

- 基于可视化自编码器的无叶扩压器失稳流场降阶分析
- Analysis on Reduced Order of Unsteady Flow Fields for a Vaneless Diffuser Based on Visualized Autoencoder
- 动力工程学报 2026年46卷第5期页码：90-96
- 作者机构：
- 作者简介：
  
  黄可心(2002—),女,江苏无锡人,硕士研究生,研究方向为空气动力学,E-mail:hkx2002@sjtu.edu.cn。
- 基金信息：
- DOI：10.19805/j.cnki.jcspe.2026.250025
  中图分类号： TH452
- 纸质出版：2026
- 稿件说明：
移动端阅览
黄可心, 吴颖, 竺晓程. 基于可视化自编码器的无叶扩压器失稳流场降阶分析[J]. 动力工程学报, 2026, 46(5): 90-96.
黄可心, 吴颖, 竺晓程. 基于可视化自编码器的无叶扩压器失稳流场降阶分析[J]. 动力工程学报, 2026, 46(5): 90-96. DOI： 10.19805/j.cnki.jcspe.2026.250025.

DOI： 10.19805/j.cnki.jcspe.2026.250025

摘要

流场降阶技术已开始应用到复杂流场的分析中

以自编码器技术为基础

分别采用通道分解自编码器和分层自编码器技术

实现离心压气机无叶扩压器非稳定流场的降阶和流动特征提取

并与常规本征正交分解(POD)得到的流场模态进行对比。结果表明:通道分解自编码器和分层自编码器技术解决了常规自编码方法无法进行降阶流场可视化的问题

直观地给出了无叶扩压器非稳定流场的演化过程

为非稳定流场分析提供了新的工具。

Abstract

Reduced-order technology has been applied to the analysis on complex flow fields. Based on a fully connected autoencoder network

a multi-channel autoencoder and a hierarchical autoencoder were designed to achieve reduced-order modeling and flow feature extraction of unsteady flow fields in a vaneless diffuser of the centrifugal compressor. Then the results were compared with the flow field modes obtained via conventional proper orthogonal decomposition (POD). Results show that the multi-channel decomposition autoencoder and hierarchical autoencoder techniques address the issue of conventional autoencoder methods being unable to perform reduced-order flow field visualization

providing an intuitive representation of the evolution process of unstable flow fields in the vaneless diffuser and offering a new tool for analyzing unsteady flow fields.

关键词

Keywords

references

JANSEN W. Rotating stall in a radial vaneless diffuser[J]. Journal of Basic Engineering, 1964, 86(4): 750-758.

DOU H S, MIZUKI S. Analysis of the flow in vaneless diffusers with large width-to-radius ratios[J]. Journal of Turbomachinery, 1998, 120(1): 193-201.

FERRARA G, FERRARI L, BALDASSARRE L. Rotating stall in centrifugal compressor vaneless diffuser: experimental analysis of geometrical parameters influence on phenomenon evolution[J]. International Journal of Rotating Machinery, 2004, 10(6): 433-442.

OHUCHIDA S, KAWAKUBO T, TAMAKI H. Experimental study of rotating stall in vaneless diffuser of a centrifugal compressor[C] //ASME Turbo Expo 2013: Turbine Technical Conference and Exposition. San Antonio: American Society of Mechanical Engineers, 2013: GT2013-95468.

LJEVAR S, DE LANGE H C, VAN STEENHOVEN A A. Two-dimensional rotating stall analysis in a wide vaneless diffuser[J]. International Journal of Rotating Machinery, 2006, 2006: 56420.

MEGERLE B, MCBEAN I, RICE T S, et al. Unsteady aerodynamics of low-pressure steam turbines operating under low volume flow[J]. Journal of Turbomachinery, 2014, 136(9): 091008.

胡晨星. 径向无叶扩压器流动稳定性与敏感性研究[D]. 上海: 上海交通大学, 2018.

ZHANG Lei, HE Ruiyang, WANG Songling, et al. A review of rotating stall in vaneless diffuser of centrifugal compressor[J]. Journal of Thermal Science, 2020, 29(2): 323-342.

MEGERLE B. Unsteady aerodynamics of low-pressure steam turbines operating under low volume flow conditions[D]. Lausanne, Switzerland: Swiss Federal Institute of Technology in Lausanne, 2014.

丁杰, 胡晨星, 刘鹏寅, 等. 无叶扩压器中非定常流动的DMD模态分析[J]. 动力工程学报, 2017, 37(6): 447-453.DING Jie, HU Chenxing, LIU Pengyin, et al. Dynamic mode decomposition of the unsteady flow in a vaneless diffuser[J]. Journal of Chinese Society of Power Engineering, 2017, 37(6): 447-453.

赵博, 吴蔚, 竺晓程, 等. 二维无叶扩压器旋转失速的正交模态分析[J]. 热能动力工程, 2020, 35(3): 122-128.ZHAO Bo, WU Wei, ZHU Xiaocheng, et al. Orthogonal modal analysis for rotating stall of two-dimensional vaneless diffuser[J]. Journal of Engineering for Thermal Energy and Power, 2020, 35(3): 122-128.

吴蔚, 赵博, 竺晓程, 等. 基于DMD方法的无叶扩压器流动稳定性分析[J]. 动力工程学报, 2020, 40(5): 365-370.WU Wei, ZHAO Bo, ZHU Xiaocheng, et al. Analysis on the hydrodynamic stability of a vaneless diffuser based on dynamic mode decomposition[J]. Journal of Chinese Society of Power Engineering, 2020, 40(5): 365-370.

武频, 孙俊五, 封卫兵. 基于自编码器和LSTM的模型降阶方法[J]. 空气动力学学报, 2021, 39(1): 73-81.WU Pin, SUN Junwu, FENG Weibing. Reduced order model based on autoencoder and long short-term memory network[J]. Acta Aerodynamica Sinica, 2021, 39(1): 73-81.

肖若冶, 于剑, 马正宵. 卷积自编码器在非定常可压缩流动降阶模型中的适用性[J]. 北京航空航天大学学报, 2023, 49(12): 3445-3455.XIAO Ruoye, YU Jian, MA Zhengxiao. Applicability of convolutional autoencoder in reduced-order model of unsteady compressible flows[J]. Journal of Beijing University of Aeronautics and Astronautics, 2023, 49(12): 3445-3455.

肖颖, 肖翔域, 段壮, 等. 采用本征正交分解和长短期记忆网络模型的离心泵流场预测[J]. 西安交通大学学报, 2024, 58(12): 119-130.XIAO Ying, XIAO Xiangyu, DUAN Zhuang, et al. Prediction of flow fields in centrifugal pumps based on the proper orthogonal decomposition-long short-term memory network model[J]. Journal of Xi'an Jiaotong University, 2024, 58(12): 119-130.

EIVAZI H, VEISI H, NADERI M H, et al. Deep neural networks for nonlinear model order reduction of unsteady flows[J]. Physics of Fluids, 2020, 32(10): 105104.

MURATA T, FUKAMI K, FUKAGATA K. Nonlinear mode decomposition with convolutional neural networks for fluid dynamics[J]. Journal of Fluid Mechanics, 2020, 882: A13.

FUKAMI K, NAKAMURA T, FUKAGATA K. Convolutional neural network based hierarchical autoencoder for nonlinear mode decomposition of fluid field data[J]. Physics of Fluids, 2020, 32(9): 095110.

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

基于Leckner模型的氨掺烧高水蒸气浓度烟气对燃煤锅炉传热特性的影响分析

基于半马尔可夫的风电机组自触发变桨控制

芦竹与典型煤协同燃烧过程中灰成分与结渣特性研究

基于BKA-Transformer-BiGRU的垃圾焚烧炉SNCR脱硝系统动态建模

奇异值分解用于早期摩擦故障诊断的研究