bp_BPmatlab_

%% clc; clear all; close all; load('fogang_rdm.mat') load('fogongr_ps.mat') % % for k=1:size(p_xtm,2) % r_ps(k)=sqrt((p_xtm(k)/1068*200+100)^2+((p_ytm(k)-1400/2)*150/1400)^2); % end % for kk=1:size(phase_jilei,2) % for k=1:size(p_xtm,2) % r_ps(k)=sqrt((p_xtm(k)-row/2)^2+p_ytm(k)^2); % end %% 生成正弦曲线 % x = linspace(-2*pi, 2*pi, 100); % y = sin(x); % % 对目标值加入噪声 % n = 0.1 * rand(1, length(x)); % y = y + n; % figure(); % plot(x, y, 'b-'); for num_image=1:30 i=0; for k=2:size(r_ps,2) if(mod(k,6)==1) continue; end i=i+1; x(i)=r_ps(1,k); y(i)=rdm(k, num_image); end j=0 for k=1:6:size(r_ps,2) j=j+1; data_test(j) = r_ps(1,k); data_true (j)= rdm(k, num_image); end %% 数据归一化，创建测试数据集 [x_, ps] = mapminmax(x); data_input = x_; data_target = y; % figure(); % plot(data_input, data_target, 'b-'); % data_test = p_ytm; % data_true = phase_jilei; % data_test(find(b==0))=[]; % data_true (find(b==0))=[]; data_t = mapminmax('apply', data_test, ps); % figure(); % plot(data_t, data_true, 'b-'); %% 创建神经网络（也可打开nntool，在matlab中使用gui创建神经网络） hidden_layer_size =15; net = feedforwardnet(hidden_layer_size); [net, tr] = train(net, data_input, data_target); %% 拟合结果 data_y(num_image,:) = sim(net, data_t); data_y_zhen(num_image,:) = data_true; end % end % data_y = net(data_t); figure(1); e = (data_true - data_y)./data_true ; e1=data_true - data_y; plot(e); xlabel('x axis'); ylabel('y axis'); legend('error'); figure(2); hold on; plot(data_test, data_y, '*'); plot(x, y, 'b'); xlabel('x axis'); ylabel('y axis'); legend('prediction', 'real value');