【预测模型】基于RNN-LSTM卷积神经网络实现数据预测Matlab代码-平芜编程栈

1 简介

针对高炉炼铁是一个动态过程,具有大延迟,工况复杂的特性.采用LSTM-RNN模型进行硅含量预测,充分发挥了其处理时间序列时挖掘前后关联信息的优势.首先根据时间序列趋势及相关系数选择自变量,并采用复杂工况的实际生产数据进行验证.然后用程序自动求解最优参数进行硅含量预测.最后将LSTM-RNN模型与PLS模型及RNN模型的结果进行对比,验证该方法的优势.研究发现LSTM-RNN模型预测误差稳定,预测精度较高,比传统的统计学及神经网络方法取得了更好的预测精度.

2 部分代码

%%% LSTM网络结合实例仿真 %% 程序说明 % 1、数据为7天，四个时间点的空调功耗，用前三个推测第四个训练，依次类推。第七天作为检验 % 2、LSTM网络输入结点为12，输出结点为4个，隐藏结点18个 clear all; clc; %% 数据加载，并归一化处理 [train_data,test_data]=LSTM_data_process(); data_length=size(train_data,1); data_num=size(train_data,2); %% 网络参数初始化 % 结点数设置 input_num=12; cell_num=18; output_num=4; % 网络中门的偏置 bias_input_gate=rand(1,cell_num); bias_forget_gate=rand(1,cell_num); bias_output_gate=rand(1,cell_num); % ab=1.2; % bias_input_gate=ones(1,cell_num)/ab; % bias_forget_gate=ones(1,cell_num)/ab; % bias_output_gate=ones(1,cell_num)/ab; %网络权重初始化 ab=20; weight_input_x=rand(input_num,cell_num)/ab; weight_input_h=rand(output_num,cell_num)/ab; weight_inputgate_x=rand(input_num,cell_num)/ab; weight_inputgate_c=rand(cell_num,cell_num)/ab; weight_forgetgate_x=rand(input_num,cell_num)/ab; weight_forgetgate_c=rand(cell_num,cell_num)/ab; weight_outputgate_x=rand(input_num,cell_num)/ab; weight_outputgate_c=rand(cell_num,cell_num)/ab; %hidden_output权重 weight_preh_h=rand(cell_num,output_num); %网络状态初始化 cost_gate=1e-10; h_state=rand(output_num,data_num); cell_state=rand(cell_num,data_num); %% 网络训练学习 for iter=1:4000 yita=0.15; %每次迭代权重调整比例 for m=1:data_num %前馈部分 if(m==1) gate=tanh(train_data(:,m)'*weight_input_x); input_gate_input=train_data(:,m)'*weight_inputgate_x+bias_input_gate; output_gate_input=train_data(:,m)'*weight_outputgate_x+bias_output_gate; for n=1:cell_num input_gate(1,n)=1/(1+exp(-input_gate_input(1,n))); output_gate(1,n)=1/(1+exp(-output_gate_input(1,n))); end forget_gate=zeros(1,cell_num); forget_gate_input=zeros(1,cell_num); cell_state(:,m)=(input_gate.*gate)'; else gate=tanh(train_data(:,m)'*weight_input_x+h_state(:,m-1)'*weight_input_h); input_gate_input=train_data(:,m)'*weight_inputgate_x+cell_state(:,m-1)'*weight_inputgate_c+bias_input_gate; forget_gate_input=train_data(:,m)'*weight_forgetgate_x+cell_state(:,m-1)'*weight_forgetgate_c+bias_forget_gate; output_gate_input=train_data(:,m)'*weight_outputgate_x+cell_state(:,m-1)'*weight_outputgate_c+bias_output_gate; for n=1:cell_num input_gate(1,n)=1/(1+exp(-input_gate_input(1,n))); forget_gate(1,n)=1/(1+exp(-forget_gate_input(1,n))); output_gate(1,n)=1/(1+exp(-output_gate_input(1,n))); end cell_state(:,m)=(input_gate.*gate+cell_state(:,m-1)'.*forget_gate)'; end pre_h_state=tanh(cell_state(:,m)').*output_gate; h_state(:,m)=(pre_h_state*weight_preh_h)'; %误差计算 Error=h_state(:,m)-test_data(:,m); Error_Cost(1,iter)=sum(Error.^2); if(Error_Cost(1,iter)<cost_gate) flag=1; break; else [ weight_input_x,... weight_input_h,... weight_inputgate_x,... weight_inputgate_c,... weight_forgetgate_x,... weight_forgetgate_c,... weight_outputgate_x,... weight_outputgate_c,... weight_preh_h ]=LSTM_updata_weight(m,yita,Error,... weight_input_x,... weight_input_h,... weight_inputgate_x,... weight_inputgate_c,... weight_forgetgate_x,... weight_forgetgate_c,... weight_outputgate_x,... weight_outputgate_c,... weight_preh_h,... cell_state,h_state,... input_gate,forget_gate,... output_gate,gate,... train_data,pre_h_state,... input_gate_input,... output_gate_input,... forget_gate_input); end end if(Error_Cost(1,iter)<cost_gate) break; end end %% 绘制Error-Cost曲线图 % for n=1:1:iter % text(n,Error_Cost(1,n),'*'); % axis([0,iter,0,1]); % title('Error-Cost曲线图'); % end for n=1:1:iter semilogy(n,Error_Cost(1,n),'*'); hold on; title('Error-Cost曲线图'); end %% 使用第七天数据检验 %数据加载 test_final=[0.4557 0.4790 0.7019 0.8211 0.4601 0.4811 0.7101 0.8298 0.4612 0.4845 0.7188 0.8312]'; test_final=test_final/sqrt(sum(test_final.^2)); test_output=test_data(:,4); %前馈 m=4; gate=tanh(test_final'*weight_input_x+h_state(:,m-1)'*weight_input_h); input_gate_input=test_final'*weight_inputgate_x+cell_state(:,m-1)'*weight_inputgate_c+bias_input_gate; forget_gate_input=test_final'*weight_forgetgate_x+cell_state(:,m-1)'*weight_forgetgate_c+bias_forget_gate; output_gate_input=test_final'*weight_outputgate_x+cell_state(:,m-1)'*weight_outputgate_c+bias_output_gate; for n=1:cell_num input_gate(1,n)=1/(1+exp(-input_gate_input(1,n))); forget_gate(1,n)=1/(1+exp(-forget_gate_input(1,n))); output_gate(1,n)=1/(1+exp(-output_gate_input(1,n))); end cell_state_test=(input_gate.*gate+cell_state(:,m-1)'.*forget_gate)'; pre_h_state=tanh(cell_state_test').*output_gate; h_state_test=(pre_h_state*weight_preh_h)' test_output figure plot(h_state_test,'bo-') hold on plot(test_output,'rs-') xlabel('时间') legend('真实值','预测值') ylabel('值')