【模型预测控制】低数据极限下非线性动力学稀疏辨识模型预测控制（Matlab代码实现）

👨‍🎓个人主页：研学社的博客  

💥💥💞💞欢迎来到本博客❤️❤️💥💥

🏆博主优势：🌞🌞🌞博客内容尽量做到思维缜密，逻辑清晰，为了方便读者。

⛳️座右铭：行百里者，半于九十。

📋📋📋本文目录如下：🎁🎁🎁

目录

💥1 概述

📚2 运行结果

🎉3 参考文献

🌈4 Matlab代码实现

---

💥1 概述

​非线性动力学的稀疏识别与模型预测控制（MPC）相结合。该框架从少量测量中学习受外生控制变量影响的非线性动力学模型。由此产生的SINDYc模型能够基于有限的噪声数据增强模型预测控制（MPC）的性能。SINDYc 模型是简洁的，识别模型中解释数据所需的最少项，使它们可解释和推广。

📚2 运行结果

主函数部分代码：

clear all, close all, clcfigpath = '../FIGURES/LORENZ/';datapath = '../DATA/LORENZ/';addpath('../utils');​SystemModel = 'LORENZ';​%% Generate DataONLY_TRAINING_LENGTH = 1;InputSignalType = 'sphs'; % prbs; chirp; noise; sine2; sphs; mixedgetTrainingData​%% NARX: TrainingModelName = 'NARX';Nvar = 3;rng(2,'twister')SUBSTRACT_MEAN = 0;xmean = mean(x)';​if SUBSTRACT_MEAN == 1    xtrain = x' - repmat(xmean',[1 size(x',2)]);    utrain = u; else    xtrain = x';    utrain = u;end​% prepare training datayt = con2seq(xtrain);yi = con2seq(utrain);​% Neural networkstateDelays = 1;        % state delay vectorinputDelays = 1;        % input delay vectorhiddenSizes = [10];     % network structure (number of neurons per layer)​% Nonlinear autoregressive neural networknet = narxnet(inputDelays,stateDelays, hiddenSizes);​% Training parameters %nnstartnet.trainFcn = 'trainlm';net.trainParam.min_grad = 1e-10;net.trainParam.showCommandLine = 1;​% Prepares training data (shifting, copying feedback targets into inputs as needed, etc.)[Us,Ui,Si,Ss] = preparets(net,yi,{},yt); ​% Train net with prepared training data in open-loopticnet = train(net,Us,Ss,Ui,Si);toc% view(net)​% Close loop for recursive predictionnetc = closeloop(net);

🎉3 参考文献

[1]孙涛,沈允文,孙智民等.行星齿轮传动非线性动力学模型与方程[J].机械工程学报,2002(03):6-10.

部分理论引用网络文献，若有侵权联系博主删除。

🌈4 Matlab代码实现