• 文献检索
  • 文档翻译
  • 深度研究
  • 学术资讯
  • Suppr Zotero 插件Zotero 插件
  • 邀请有礼
  • 套餐&价格
  • 历史记录
应用&插件
Suppr Zotero 插件Zotero 插件浏览器插件Mac 客户端Windows 客户端微信小程序
定价
高级版会员购买积分包购买API积分包
服务
文献检索文档翻译深度研究API 文档MCP 服务
关于我们
关于 Suppr公司介绍联系我们用户协议隐私条款
关注我们

Suppr 超能文献

核心技术专利：CN118964589B侵权必究
粤ICP备2023148730 号-1Suppr @ 2026

文献检索

告别复杂PubMed语法，用中文像聊天一样搜索，搜遍4000万医学文献。AI智能推荐，让科研检索更轻松。

立即免费搜索

文件翻译

保留排版，准确专业，支持PDF/Word/PPT等文件格式，支持 12+语言互译。

免费翻译文档

深度研究

AI帮你快速写综述，25分钟生成高质量综述，智能提取关键信息，辅助科研写作。

立即免费体验

用于多输入多输出完全非线性动态模型的神经计算增强参数估计

Neural Computing Enhanced Parameter Estimation for Multi-Input and Multi-Output Total Non-Linear Dynamic Models.

作者信息

Liu Longlong, Ma Di, Azar Ahmad Taher, Zhu Quanmin

机构信息

School of Mathematical Sciences, Ocean University of China, Qingdao 266000, China.

Robotics and Internet-of-Things Lab (RIOTU), Prince Sultan University, Riyadh 11586, Saudi Arabia.

出版信息

Entropy (Basel). 2020 Apr 30;22(5):510. doi: 10.3390/e22050510.

DOI:10.3390/e22050510
PMID:33286282
原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC7517001/
Abstract

In this paper, a gradient descent algorithm is proposed for the parameter estimation of multi-input and multi-output (MIMO) total non-linear dynamic models. Firstly, the MIMO total non-linear model is mapped to a non-completely connected feedforward neural network, that is, the parameters of the total non-linear model are mapped to the connection weights of the neural network. Then, based on the minimization of network error, a weight-updating algorithm, that is, an estimation algorithm of model parameters, is proposed with the convergence conditions of a non-completely connected feedforward network. In further determining the variables of the model set, a method of model structure detection is proposed for selecting a group of important items from the whole variable candidate set. In order to verify the usefulness of the parameter identification process, we provide a virtual bench test example for the numerical analysis and user-friendly instructions for potential applications.

摘要

本文提出了一种用于多输入多输出（MIMO）全非线性动态模型参数估计的梯度下降算法。首先，将MIMO全非线性模型映射到一个非完全连接的前馈神经网络，即全非线性模型的参数被映射到神经网络的连接权重上。然后，基于网络误差的最小化，提出了一种权重更新算法，即模型参数的估计算法，并给出了非完全连接前馈网络的收敛条件。在进一步确定模型集的变量时，提出了一种模型结构检测方法，用于从整个变量候选集中选择一组重要项。为了验证参数识别过程的有效性，我们提供了一个虚拟台架测试示例用于数值分析，并为潜在应用提供了用户友好的说明。

https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b36c/7517001/f61102afab50/entropy-22-00510-g013.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b36c/7517001/769ee3045fa5/entropy-22-00510-g001.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b36c/7517001/b0c562e8012a/entropy-22-00510-g002.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b36c/7517001/80fb835cb185/entropy-22-00510-g003.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b36c/7517001/acf1c77ea617/entropy-22-00510-g004.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b36c/7517001/fcde6e9a6c83/entropy-22-00510-g005.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b36c/7517001/afa26ddbb7ac/entropy-22-00510-g006.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b36c/7517001/8244f79d57be/entropy-22-00510-g007.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b36c/7517001/30dd50cea4f7/entropy-22-00510-g008.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b36c/7517001/08e81bc927be/entropy-22-00510-g009.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b36c/7517001/4c424c61cdfa/entropy-22-00510-g010.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b36c/7517001/c129efb39c99/entropy-22-00510-g011.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b36c/7517001/ca1710b6bc32/entropy-22-00510-g012.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b36c/7517001/f61102afab50/entropy-22-00510-g013.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b36c/7517001/769ee3045fa5/entropy-22-00510-g001.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b36c/7517001/b0c562e8012a/entropy-22-00510-g002.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b36c/7517001/80fb835cb185/entropy-22-00510-g003.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b36c/7517001/acf1c77ea617/entropy-22-00510-g004.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b36c/7517001/fcde6e9a6c83/entropy-22-00510-g005.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b36c/7517001/afa26ddbb7ac/entropy-22-00510-g006.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b36c/7517001/8244f79d57be/entropy-22-00510-g007.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b36c/7517001/30dd50cea4f7/entropy-22-00510-g008.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b36c/7517001/08e81bc927be/entropy-22-00510-g009.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b36c/7517001/4c424c61cdfa/entropy-22-00510-g010.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b36c/7517001/c129efb39c99/entropy-22-00510-g011.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b36c/7517001/ca1710b6bc32/entropy-22-00510-g012.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b36c/7517001/f61102afab50/entropy-22-00510-g013.jpg

相似文献

1
Neural Computing Enhanced Parameter Estimation for Multi-Input and Multi-Output Total Non-Linear Dynamic Models.用于多输入多输出完全非线性动态模型的神经计算增强参数估计
Entropy (Basel). 2020 Apr 30;22(5):510. doi: 10.3390/e22050510.
2
Data classification based on fractional order gradient descent with momentum for RBF neural network.基于分数阶梯度下降和动量的径向基函数神经网络数据分类
Network. 2020 Feb-Nov;31(1-4):166-185. doi: 10.1080/0954898X.2020.1849842. Epub 2020 Dec 6.
3
Quasi-minimal active disturbance rejection control of MIMO perturbed linear systems based on differential neural networks and the attractive ellipsoid method.基于微分神经网络和吸引椭球法的多输入多输出扰动线性系统的准最小有源干扰抑制控制
ISA Trans. 2017 Nov;71(Pt 2):304-316. doi: 10.1016/j.isatra.2017.08.011. Epub 2017 Sep 23.
4
An Alternating Identification Algorithm for a Class of Nonlinear Dynamical Systems.一类非线性动力系统的交替辨识算法。
IEEE Trans Neural Netw Learn Syst. 2017 Jul;28(7):1606-1617. doi: 10.1109/TNNLS.2016.2547968. Epub 2016 Apr 12.
5
Blind Source Separation Method Based on Neural Network with Bias Term and Maximum Likelihood Estimation Criterion.基于带偏置项和最大似然估计准则的神经网络的盲源分离方法。
Sensors (Basel). 2021 Feb 1;21(3):973. doi: 10.3390/s21030973.
6
Low-Complexity Soft-Output Signal Detection Based on Improved Kaczmarz Iteration Algorithm for Uplink Massive MIMO System.基于改进卡兹马尔兹迭代算法的上行大规模MIMO系统低复杂度软输出信号检测
Sensors (Basel). 2020 Mar 11;20(6):1564. doi: 10.3390/s20061564.
7
Linear and nonlinear ARMA model parameter estimation using an artificial neural network.使用人工神经网络进行线性和非线性自回归滑动平均模型参数估计。
IEEE Trans Biomed Eng. 1997 Mar;44(3):168-74. doi: 10.1109/10.554763.
8
Generalized parameter estimation in multi-echo gradient-echo-based chemical species separation.基于多回波梯度回波的化学物质分离中的广义参数估计
Quant Imaging Med Surg. 2020 Mar;10(3):554-567. doi: 10.21037/qims.2020.02.07.
9
A novel optimization algorithm for MIMO Hammerstein model identification under heavy-tailed noise.一种在重尾噪声下用于 MIMO Hammerstein 模型辨识的新型优化算法。
ISA Trans. 2018 Jan;72:77-91. doi: 10.1016/j.isatra.2017.10.001. Epub 2017 Oct 13.
10
Hybrid Neural Network Cerebellar Model Articulation Controller Design for Non-linear Dynamic Time-Varying Plants.用于非线性动态时变对象的混合神经网络小脑模型关节控制器设计
Front Neurosci. 2020 Jul 28;14:695. doi: 10.3389/fnins.2020.00695. eCollection 2020.

引用本文的文献

1
An optimization protocol for MRI examination resource allocation based on demand forecasting and linear programming.一种基于需求预测和线性规划的磁共振成像（MRI）检查资源分配优化方案。
Sci Rep. 2025 Apr 29;15(1):15076. doi: 10.1038/s41598-025-98817-z.
2
Prediction of Biceps Muscle Electromyogram Signal Using a NARX Neural Network.基于NARX神经网络的肱二头肌肌电信号预测
J Med Signals Sens. 2023 Mar 27;13(1):29-39. doi: 10.4103/jmss.jmss_3_22. eCollection 2023 Jan-Mar.
3
Robust Variable-Step Perturb-and-Observe Sliding Mode Controller for Grid-Connected Wind-Energy-Conversion Systems.

本文引用的文献

1
Lyapunov Theory-Based Fusion Neural Networks for the Identification of Dynamic Nonlinear Systems.基于李雅普诺夫理论的融合神经网络在动态非线性系统辨识中的应用。
Int J Neural Syst. 2019 Nov;29(9):1950015. doi: 10.1142/S0129065719500151. Epub 2019 Apr 21.
2
Identification and control of dynamical systems using neural networks.利用神经网络对动态系统进行识别与控制。
IEEE Trans Neural Netw. 1990;1(1):4-27. doi: 10.1109/72.80202.
用于并网型风能转换系统的鲁棒变步长扰动观察滑模控制器
Entropy (Basel). 2022 May 20;24(5):731. doi: 10.3390/e24050731.
4
Nonlinear Dynamics and Entropy of Complex Systems with Hidden and Self-Excited Attractors II.具有隐藏和自激吸引子的复杂系统的非线性动力学与熵II。
Entropy (Basel). 2020 Dec 18;22(12):1428. doi: 10.3390/e22121428.