基于卷积神经网络和状态时间序列的参数辨识

武频; 常旭婷; 郎佳林; 潘凯凯; 龚思泉

doi:10.7638/kqdlxxb-2020.0057

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 >

基于卷积神经网络和状态时间序列的参数辨识

研究论文 | 更新时间：2026-05-28

- 基于卷积神经网络和状态时间序列的参数辨识
- Parameter estimation based on convolutional neural network and state sequence
- 空气动力学学报 2021年39卷第4期页码：69-76
- 作者机构：
  
  1. 上海大学计算机工程与科学学院,上海,200444
  2. 中国空气动力研究与发展中心空气动力学国家重点实验室,绵阳,621000
- 作者简介：
  
  武频*（1975-），女，河北石家庄人，副教授，研究方向：计算流体力学，深度学习. E-mail：wupin @shu.edu.cn
- 基金信息：
  
  空气动力学国家重点实验室基金资助(SKLA20180303);上海市自然科学基金(19ZR1417700);TSP牛顿基金(TSPC1086)
- DOI：10.7638/kqdlxxb-2020.0057
  中图分类号： TP181;V211.3
- 纸质出版：2021
- 稿件说明：
移动端阅览
武频, 常旭婷, 郎佳林, 等. 基于卷积神经网络和状态时间序列的参数辨识[J]. 空气动力学学报, 2021, 39(4): 69−76.

WU Pin, CHANG Xuting, LANG Jialin, et al. Parameter estimation based on convolutional neural network and state sequence[J]. 2021, 39(4): 69-76.
武频, 常旭婷, 郎佳林, 等. 基于卷积神经网络和状态时间序列的参数辨识[J]. 空气动力学学报, 2021, 39(4): 69−76. DOI： 10.7638/kqdlxxb-2020.0057

WU Pin, CHANG Xuting, LANG Jialin, et al. Parameter estimation based on convolutional neural network and state sequence[J]. 2021, 39(4): 69-76. DOI： 10.7638/kqdlxxb-2020.0057.

摘要

针对参数辨识过程运算时间长的问题，本文提出一种基于卷积神经网络的参数辨识方案。该方案避免了对数值模型的大量迭代，能够根据多个连续时间步的实测系统状态对多参数进行快速估计，实现参数辨识；同时，为了帮助神经网络更好地提取特征，还引入一种双向标准化的方法对数据进行处理。以Lorenz63为实例，对其参数进行了分析、实验。实验结果表明：该方案能够有效地估计当前物理场状态对应的模型参数，并且计算时间仅为传统方法的4%，大大提升了计算效率。

Abstract

To reduce the time cost in parameter estimation processes

a new parameter estimation scheme based on a Convolutional Neural Network is proposed. This scheme can quickly estimate multiple parameters based on a temporal sequence of system states by avoiding time-consuming iterations of numerical models. At the same time

a two-way standardization method is used to help the neural network extract features better. The scheme has been tested in a Lorenz63 nonlinear system. Results show that it can effectively estimate model parameters corresponding to the current physical state with a calculation time only 4% of the particle swarm optimization method.

关键词

Keywords

references

WANG Q J. The genetic algorithm and its application to calibrating conceptual rainfall-runoff models[J]. Water Resources Research, 1991, 27(9): 2467-2471. DOI: 10.1029/91WR01305.

CHENG C T, OU C P, CHAU K W. Combining a fuzzy optimal model with a genetic algorithm to solve multi-objective rainfall-runoff model calibration[J]. Journal of Hydrology, 2002, 268(1-4): 72-86. DOI: 10.1016/S0022-1694(02)00122-1.

ZHOU Y J, CHEN Y F, DAN J J, et al. Parameter calibration of xin'anjiang model based on complex genetic algorithm[C ] //Proceedings of the 2017 6th International Conference on Energy and Environmental Protection (ICEEP 2017), Zhuhai, China. Paris, France: Atlantis Press, 2017. doi: 10.2991/iceep-17.2017.218

DUAN Q Y, SOROOSHIAN S, GUPTA V. Effective and efficient global optimization for conceptual rainfall-runoff models[J]. Water Resources Research, 1992, 28(4): 1015-1031. DOI: 10.1029/91WR02985.

GILL M K, KAHEIL Y H, KHALIL A, et al. Multiobjective particle swarm optimization for parameter estimation in hydrology[J]. Water Resources Research, 2006, 42(7): W07417. DOI: 10.1029/2005WR004528.

YANG Q D, WU J, LI Y Q, et al. Using the particle swarm optimization algorithm to calibrate the parameters relating to the turbulent flux in the surface layer in the source region of the Yellow River[J]. Agricultural and Forest Meteorology, 2017, 232: 606-622. DOI: 10.1016/j.agrformet.2016.10.019.

WANG G D, CUI E J, CHEN Z L. Study on aerodynamic parameter identification method for aircraft with jet thruster control[J]. Acta Aerodynamica Sinica, 2011, 29(4): 433-438. (in Chinese)

ZHANG T J, WANG Q, HE K F. Application of particle swarm optimization for aerodynamic parameter estimation[J]. Acta Aerodynamica Sinica, 2010, 28(6): 633-638. (in Chinese)

MIYANAWALA T P, JAIMAN R K. An efficient deep learning technique for the Navier-Stokes equations: application to unsteady wake flow dynamics[J]. arXiv preprint arXiv: 1710.09099, 2017.

CHEN H, QIAN W Q, HE L. Aerodynamic coefficient prediction of airfoils based on deep learning[J]. Acta Aerodynamica Sinica, 2018, 36(2): 294-299. (in Chinese)

WANG C, WANG G D, BAI P. Machine learning method for aerodynamic modeling based on flight simulation data[J]. Acta Aerodynamica Sinica, 2019, 37(3): 488-497. (in Chinese)

LORENZ E N. Deterministic nonperiodic flow[J]. Journal of the Atmospheric Sciences, 1963, 20(2): 130-141. DOI: 10.1175/1520-0469(1963)0200130:dnf2.0.co;2.

GOODFELLOW I, BENGIO Y, COURVILLE A. Deep learning ,Vol. 1[M]. Cambridge: MIT press, 2016: 326-366.

GU J X, WANG Z H, KUEN J, et al. Recent advances in convolutional neural networks[J]. Pattern Recognition, 2018, 77: 354-377. DOI: 10.1016/j.patcog.2017.10.013.

Joint Photographic Experts Group committee. Digital compression and coding of continuous-tone still images: requirements and guidelines[S]. ISO/IEC, Feb. 1994: 10918-1.

KINGMA D P, BA J L. A method for stochastic optimization[J]. arXiv preprint arXiv: 1412.6980, 2014.

SHI Y, EBERHART R. A modified particle swarm optimizer[C ] // 1998 IEEE International Conference on Evolutionary Computation Proceedings. IEEE World Congress on Computational Intelligence (Cat. No. 98TH8360), Anchorage, AK, USA. IEEE, 1998: 69-73. doi: 10.1109/ICEC.1998.699146

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

关键区域优化对高速列车横风气动特性影响

考虑近距离海洋下垫面影响的对称风机翼型静气动特性

高速斜板液膜冷却的数值模拟研究

多种SST湍流模型对典型分离流动的预测性能

翼尖链翼组合式无人机气动特性研究