GRU神经网络应力预测.zip

%% gru network % Programmed by qq,2027771338 % Updated 20 jun. 2024. clc clear close all %读取double格式数据 [a,ax,ay] = xlsread('数据.xlsx',1); % t=[]; % for ii =1:4 % y(ii)=myPearson(a(:,ii),a(:,5)); % end % plot(y) for ii =1:2 a(:,5) =smooth(a(:,5),5); end num = []; for ii = 1:length(a)-1 num = [num;a(ii,5) a(ii+1,:)]; end m1=569; n = randperm(m1); m=500; input_train=num(n(1:569),1:5)';%训练数据的输入数据 output_train=num(n(1:569),6)';%训练数据的输出数据 input_test=num((m+1:end),1:5)';%测试数据的输入数据 output_test=num((m+1:end),6)'; %测试数据的输出数据 [inputn,inputps]=mapminmax(input_train,-20,100);%训练数据的输入数据的归一化 [outputn,outputps]=mapminmax(output_train,-20,100);%训练数据的输出数据的归一化de inputn_test=mapminmax('apply',input_test,inputps); %% Define Network Architecture % Define the network architecture. numFeatures = size(num(:,1:5),2);%输入层维度 numResponses = size(num(:,end),2);%输出维度 % 200 hidden units numHiddenUnits = 150;%第一层维度 % a fully connected layer of size 50 & a dropout layer with dropout probability 0.5 fungru % % Specify the training options. % Train for 60 epochs with mini-batches of size 20 using the solver 'adam' maxEpochs = 100;%最大迭代次数 miniBatchSize = 2;%最小批量 % the learning rate == 0.01 % set the gradient threshold to 1 % set 'Shuffle' to 'never' options = trainingOptions('adam', ... %解算器 'MaxEpochs',maxEpochs, ... %最大迭代次数 'MiniBatchSize',miniBatchSize, ... %最小批次 'InitialLearnRate',0.01, ... %初始学习率 'GradientThreshold',inf, ... %梯度阈值 'Shuffle','every-epoch', ... %打乱顺序 'Plots','training-progress',... %画图 'Verbose',0); %不输出训练过程 %% Train the Network net = trainNetwork(inputn,outputn,layers,options);%开始训练 %% Test the Network y_pred = predict(net,inputn_test,'MiniBatchSize',100)';%测试仿真输出 y_pred =(mapminmax('reverse',y_pred,outputps))'; % load maydatalstm.mat % save maydatalstm.mat net y_pred outputps inputps %% figure%打开一个图像窗口 plot(y_pred,'r-')%蓝色实线，点的形状^ hold on%停止画图 plot(output_test,'k-')%黑色实线，点的形状为* hold off%继续画图 title('测试图')%标题 ylabel('')%Y轴名称 legend('测试值','实际值')%标签 error1 = y_pred-output_test;%误差 figure plot(error1,'k-') title('测试误差图') ylabel('误差') [MSE,RMSE,MBE,MAE ] =MSE_RMSE_MBE_MAE(output_test,y_pred) R2 = R_2(output_test,y_pred) numz = [num((m+1:end),:) y_pred']; result_table = table; result_table.Mpa0 = num(m+1:end,1); result_table.ps = num(m+1:end,2); result_table.A = num(m+1:end,3); result_table.AB = num(m+1:end,4); result_table.K = num(m+1:end,5); result_table.true = output_test'; result_table.sim = y_pred'; writetable(result_table,'./结果.csv')