基于某BP神经网络地自适应PID控制器设计Word格式文档下载.docx
《基于某BP神经网络地自适应PID控制器设计Word格式文档下载.docx》由会员分享,可在线阅读,更多相关《基于某BP神经网络地自适应PID控制器设计Word格式文档下载.docx(11页珍藏版)》请在冰点文库上搜索。
基于BP神经网络的自适应PID控制器的控制器如图2所示:
该控制器的算法如下:
(1)确定BP神经网络的结构,即确定输入节点数M和隐含层节点数Q,并给各层加权系数的初值
和
,选定学习速率
和惯性系数
,此时k=1;
(2)采样得到rin(k)和yout(k),计算该时刻误差error(k)=rin(k)-yout(k);
(3)计算神经网络NN各层神经元的输入、输出,NN输出层的输出即为PID控制器的三个可调参数
;
(4)根据经典增量数字PID的控制算法(见下式)计算PID控制器的输出u(k);
(5)进行神经网络学习,在线调整加权系数
实现PID控制参数的自适应调整;
(6)置k=k+1,返回到
(1)。
三.仿真程序
%BPbasedPIDControl
clearall;
closeall;
xite=0.25;
alfa=0.05;
S=1;
%Signaltype
IN=4;
H=5;
Out=3;
%NNStructure
ifS==1%StepSignal
wi=[-0.6394-0.2696-0.3756-0.7023;
-0.8603-0.2013-0.5024-0.2596;
-1.07490.5543-1.6820-0.5437;
-0.3625-0.0724-0.6463-0.2859;
0.14250.0279-0.5406-0.7660];
%wi=0.50*rands(H,IN);
wi_1=wi;
wi_2=wi;
wi_3=wi;
wo=[0.75760.26160.5820-0.1416-0.1325;
-0.11460.29490.83520.22050.4508;
0.72010.45660.76720.49620.3632];
%wo=0.50*rands(Out,H);
wo_1=wo;
wo_2=wo;
wo_3=wo;
end
ifS==2%SineSignal
wi=[-0.28460.2193-0.5097-1.0668;
-0.7484-0.1210-0.47080.0988;
-0.71760.8297-1.60000.2049;
-0.08580.1925-0.63460.0347;
0.43580.2369-0.4564-0.1324];
wo=[1.04380.54780.86820.14460.1537;
0.17160.58111.12140.50670.7370;
1.00630.74281.05340.78240.6494];
x=[0,0,0];
u_1=0;
u_2=0;
u_3=0;
u_4=0;
u_5=0;
y_1=0;
y_2=0;
y_3=0;
Oh=zeros(H,1);
%OutputfromNNmiddlelayer
I=Oh;
%InputtoNNmiddlelayer
error_2=0;
error_1=0;
ts=0.001;
fork=1:
1:
6000
time(k)=k*ts;
ifS==1
rin(k)=1.0;
elseifS==2
rin(k)=sin(1*2*pi*k*ts);
%Unlinearmodel
a(k)=1.2*(1-0.8*exp(-0.1*k));
yout(k)=a(k)*y_1/(1+y_1^2)+u_1;
error(k)=rin(k)-yout(k);
xi=[rin(k),yout(k),error(k),1];
x
(1)=error(k)-error_1;
x
(2)=error(k);
x(3)=error(k)-2*error_1+error_2;
epid=[x
(1);
x
(2);
x(3)];
I=xi*wi'
;
forj=1:
H
Oh(j)=(exp(I(j))-exp(-I(j)))/(exp(I(j))+exp(-I(j)));
%MiddleLayer
K=wo*Oh;
%OutputLayer
forl=1:
Out
K(l)=exp(K(l))/(exp(K(l))+exp(-K(l)));
%Gettingkp,ki,kd
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);
ifu(k)>
=10%Restrictingtheoutputofcontroller
u(k)=10;
ifu(k)<
=-10
u(k)=-10;
dyu(k)=sign((yout(k)-y_1)/(u(k)-u_1+0.0000001));
%Outputlayer
dK(j)=2/(exp(K(j))+exp(-K(j)))^2;
delta3(l)=error(k)*dyu(k)*epid(l)*dK(l);
fori=1:
d_wo=xite*delta3(l)*Oh(i)+alfa*(wo_1-wo_2);
end
wo=wo_1+d_wo+alfa*(wo_1-wo_2);
%Hiddenlayer
fori=1:
dO(i)=4/(exp(I(i))+exp(-I(i)))^2;
segma=delta3*wo;
delta2(i)=dO(i)*segma(i);
d_wi=xite*delta2'
*xi;
wi=wi_1+d_wi+alfa*(wi_1-wi_2);
%ParametersUpdate
u_5=u_4;
u_4=u_3;
u_3=u_2;
u_2=u_1;
u_1=u(k);
y_2=y_1;
y_1=yout(k);
wo_3=wo_2;
wo_2=wo_1;
wi_3=wi_2;
wi_2=wi_1;
error_2=error_1;
error_1=error(k);
figure
(1);
plot(time,rin,'
r'
time,yout,'
b'
);
xlabel('
time(s)'
ylabel('
rin,yout'
figure
(2);
plot(time,error,'
error'
figure(3);
plot(time,u,'
u'
figure(4);
subplot(311);
plot(time,kp,'
kp'
subplot(312);
plot(time,ki,'
g'
ki'
subplot(313);
plot(time,kd,'
kd'
四.运行结果