《MATLAB基于BP神经网络PID控制程序》由会员分享，可在线阅读，更多相关《MATLAB基于BP神经网络PID控制程序（7页珍藏版）》请在装配图网上搜索。
1、精选优质文档-倾情为你奉上MATLAB基于BP神经网络PID控制程序 %BP based PID Control clear all; close all; xite=0.20; %学习速率alfa=0.01; %惯性因子IN=4;H=5;Out=3; %NN Structure wi=-0.6394 -0.2696 -0.3756 -0.7023; -0.8603 -0.2013 -0.5024 -0.2596; -1.0749 0.5543 -1.6820 -0.5437; -0.3625 -0.0724 -0.6463 -0.2859; 0.1425 0.0279 -0.5406 -0.
2、7660; %wi=0.50*rands(H,IN); %隐含层加权系数wi初始化wi_1=wi;wi_2=wi;wi_3=wi; wo=0.7576 0.2616 0.5820 -0.1416 -0.1325; -0.1146 0.2949 0.8352 0.2205 0.4508; 0.7201 0.4566 0.7672 0.4962 0.3632; %wo=0.50*rands(Out,H); %输出层加权系数wo初始化wo_1=wo;wo_2=wo;wo_3=wo; ts=20; %采样周期取值x=0,0,0; %比例，积分，微分赋初值u_1=0;u_2=0;u_3=0;u_4=0;
3、u_5=0; y_1=0;y_2=0;y_3=0; Oh=zeros(H,1); %Output from NN middle layer 隐含层的输出I=Oh; %Input to NN middle layer 隐含层输入error_2=0; error_1=0; for k=1:1:500 %仿真开始，共500步time(k)=k*ts; rin(k)=1.0; %Delay plantsys=tf(1.2,208 1,inputdelay,80); %建立被控对象传递函数?dsys=c2d(sys,ts,zoh); %把传递函数离散化?num,den=tfdata(dsys,v); %
4、离散化后提取分子、分母yout(k)=-den(2)*y_1+num(2)*u_5;error(k)=rin(k)-yout(k); xi=rin(k),yout(k),error(k),1; %经典增量式数字PID的控制算式为： BP神经网络PID的控制算式为：x(1)=error(k)-error_1; %比例输出x(2)=error(k); %积分输出x(3)=error(k)-2*error_1+error_2; %微分输出epid=x(1);x(2);x(3); I=xi*wi;% 隐含层的输入，即：输入层输入*权值for j=1:1:H Oh(j)=(exp(I(j)-exp(-I
5、(j)/(exp(I(j)+exp(-I(j); %Middle Layer在激活函数作用下隐含层的输出end K=wo*Oh; %Output Layer 输出层的输入，即：隐含层的输出*权值for l=1:1:Out K(l)=exp(K(l)/(exp(K(l)+exp(-K(l); %Getting kp,ki,kd 输出层的输出，即三个pid控制器的参数end kp(k)=K(1);ki(k)=K(2);kd(k)=K(3); Kpid=kp(k),ki(k),kd(k); du(k)=Kpid*epid; u(k)=u_1+du(k); if u(k)=10 % Restricti
6、ng the output of controller 控制器饱和环节u(k)=10; end if u(k)=-10 u(k)=-10; end %以下为权值wi、wo的在线调整，参考刘金琨的先进PID控制dyu(k)=sign(yout(k)-y_1)/(u(k)-u_1+0.); %Output layer 输出层for j=1:1:Out dK(j)=2/(exp(K(j)+exp(-K(j)2; end for l=1:1:Out delta3(l)=error(k)*dyu(k)*epid(l)*dK(l); end for l=1:1:Out for i=1:1:H d_wo=x
7、ite*delta3(l)*Oh(i)+alfa*(wo_1-wo_2); end end wo=wo_1+d_wo+alfa*(wo_1-wo_2); %Hidden layer for i=1:1:H dO(i)=4/(exp(I(i)+exp(-I(i)2; end segma=delta3*wo; for i=1:1:H delta2(i)=dO(i)*segma(i); end d_wi=xite*delta2*xi; wi=wi_1+d_wi+alfa*(wi_1-wi_2); %Parameters Update 参数更新u_5=u_4;u_4=u_3;u_3=u_2;u_2=u
8、_1;u_1=u(k); y_2=y_1;y_1=yout(k); wo_3=wo_2; wo_2=wo_1; wo_1=wo; wi_3=wi_2; wi_2=wi_1; wi_1=wi; error_2=error_1; error_1=error(k); end %仿真结束，绘图figure(1); plot(time,rin,r,time,yout,b); xlabel(time(s);ylabel(rin,yout); figure(2); plot(time,error,r); xlabel(time(s);ylabel(error); figure(3); plot(time,u,r); xlabel(time(s);ylabel(u); figure(4); subplot(311); plot(time,kp,r); xlabel(time(s);ylabel(kp); subplot(312); plot(time,ki,g); xlabel(time(s);ylabel(ki); subplot(313); plot(time,kd,b); xlabel(time(s);ylabel(kd);专心-专注-专业
MATLAB基于BP神经网络PID控制程序
