智能控制(神经网络)-作业

智能控制作业

学生： 学 号： 专业班级：

7-2 采用BP 网路、RBF 网路、DRNN 网路逼近线性对象

2)

1(1)1(9.0)1()(-+-?--=k y k y k u k y ，分别进行matlab 仿真。 （一）采用BP 网络仿真

网络结构为2-6-1。采样时间1ms ，输入信号)6sin(5.0)(t k u ?=π，权值21,W W 的初值随机取值，05.0,05.0==αη。

仿真m 文件程序为：

%BP simulation

clear all;

clear all;

xite=0.5;

alfa=0.5;

w1=rands(2,6); % value of w1,initially by random w1_1=w1;w1_2=w1;

w2=rands(6,1); % value of w2,initially by random w2_1=w2;w2_2=w2_1;

dw1=0*w1;

x=[0,0]';

u_1=0;

y_1=0;

I=[0,0,0,0,0,0]'; % input of yinhanceng cell Iout=[0,0,0,0,0,0]'; % output of yinhanceng cell FI=[0,0,0,0,0,0]';

ts=0.001;

for k=1:1:1000

time(k)=k*ts;

u(k)=0.5*sin(3*2*pi*k*ts);

y(k)=(u_1-0.9*y_1)/(1+y_1^2);

for j=1:1:6

I(j)=x'*w1(:,j);

Iout(j)=1/(1+exp(-I(j)));

end

yn(k)=w2'*Iout; %output of network

e(k)=y(k)-yn(k); % error calculation

w2=w2_1+(xite*e(k))*Iout+alfa*(w2_1-w2_2); % rectify of w2

for j=1:1:6

FI(j)=exp(-I(j))/(1+exp(-I(j))^2);

end

for i=1:1:2

for j=1:1:6

dw1(i,j)=e(k)*xite*FI(j)*w2(j)*x(i); % dw1 calculation end

end

w1=w1_1+dw1+alfa*(w1_1-w1_2); % rectify of w1

% jacobian information

yu=0;

for j=1:1:6

yu=yu+w2(j)*w1(1,j)*FI(j);

end

dyu(k)=yu;

x(1)=u(k);

x(2)=y(k);

w1_2=w1_1;w1_1=w1;

w2_2=w2_1;w2_1=w2;

u_1=u(k);

y_1=y(k);

end

figure(1);

plot(time,y,'r',time,yn,'b');

xlabel('times');ylabel('y and yn');

figure(2);

plot(time,y-yn,'r');

xlabel('times');ylabel('error'); figure(3);

plot(time,dyu);

xlabel('times');ylabel('dyu'); 运行结果为：

（二）采用RBF 网络仿真

网路结构为2-4-1，采样时间1ms ，输入信号)2sin(5.0)(t k u ?=π，权值的初值随机取值，05.0,05.0==αη，高斯基函数初值T j C ]5.0,5.0[=，T B ]5.1,5.1,5.1,5.1[=。

仿真m 文件程序如下：

%RBF simulation

clear all

clear all

alfa=0.05;

xite=0.5;

x=[0,0]';

b=1.5*ones(4,1);

c=0.5*ones(2,4);

w=rands(4,1);

w_1=w;w_2=w_1;

c_1=c;c_2=c_1;

b_1=b;b_2=b_1

d_w=0*w;

d_b=0*b;

y_1=0;

ts=0.001;

for k=1:1:2000;

time(k)=k*ts;

u(k)=0.5*sin(1*2*pi*k*ts);

y(k)=(u(k)-0.9*y_1)/(1+y_1^2);

x(1)=u(k);

x(2)=y_1;

for j=1:1:4

h(j)=exp(-norm(x-c(:,j))^2/(2*b(j)*b(j)));

end

ym(k)=w'*h';

em(k)=y(k)-ym(k);

for j=1:1:4

d_w(j)=xite*em(k)*h(j);

d_b(j)=xite*em(k)*w(j)*h(j)*(b(j)^-3)*norm(x-c(:,j))^2;

for i=1:1:2

d_c(i,j)=xite*em(k)*w(j)*h(j)*(x(i)-c(i,j))*(b(j)^-2); end

end

w=w_1+d_w+alfa*(w_1-w_1);

b=b_1+d_b+alfa*(b_1-b_2);

c=c_1+d_c+alfa*(c_1-c_2);

% Jacobian information

yu=0;

for j=1:1:4

yu=yu+w(j)*h(j)*(c(1,j)-x(1))/b(j)^2;

end

dyu(k)=yu;