📄 bg_pso.html
字号:
<html xmlns:mwsh="http://www.mathworks.com/namespace/mcode/v1/syntaxhighlight.dtd"> <head> <meta http-equiv="Content-Type" content="text/html; charset=utf-8"> <!--This HTML is auto-generated from an M-file.To make changes, update the M-file and republish this document. --> <title>Tunning of PID controller using Bacterial Foraging Orientec by Particle swarm optimization</title> <meta name="generator" content="MATLAB 7.2"> <meta name="date" content="2008-06-14"> <meta name="m-file" content="BG_PSO"><style>body { background-color: white; margin:10px;}h1 { color: #990000; font-size: x-large;}h2 { color: #990000; font-size: medium;}/* Make the text shrink to fit narrow windows, but not stretch too far in wide windows. On Gecko-based browsers, the shrink-to-fit doesn't work. */ p,h1,h2,div.content div { /* for MATLAB's browser */ width: 600px; /* for Mozilla, but the "width" tag overrides it anyway */ max-width: 600px; /* for IE */ width:expression(document.body.clientWidth > 620 ? "600px": "auto" );}pre.codeinput { background: #EEEEEE; padding: 10px;}@media print { pre.codeinput {word-wrap:break-word; width:100%;}} span.keyword {color: #0000FF}span.comment {color: #228B22}span.string {color: #A020F0}span.untermstring {color: #B20000}span.syscmd {color: #B28C00}pre.codeoutput { color: #666666; padding: 10px;}pre.error { color: red;}p.footer { text-align: right; font-size: xx-small; font-weight: lighter; font-style: italic; color: gray;} </style></head> <body> <div class="content"> <h1>Tunning of PID controller using Bacterial Foraging Orientec by Particle swarm optimization</h1><pre class="codeinput"><span class="comment">%My work has been accpepted in GECCO 2008 as Graduat Student workshop. I</span><span class="comment">%have used this techique in PID tunning and i got better result thatn BG</span><span class="comment">%and PSO</span><span class="comment">%</span><span class="comment">% Author: Wael Mansour (wael192@yahoo.com)</span><span class="comment">%</span><span class="comment">% MSc Student, Electrical Enginering Dept,</span><span class="comment">% Faculty of Engineering Cairo University, Egypt</span></pre><pre class="codeinput"><span class="comment">%Initialization</span>clear <span class="string">all</span>clcp=2; <span class="comment">% dimension of search space</span>s=10; <span class="comment">% The number of bacteria</span>Nc=10; <span class="comment">% Number of chemotactic steps</span>Ns=4; <span class="comment">% Limits the length of a swim</span>Nre=4; <span class="comment">% The number of reproduction steps</span>Ned=2; <span class="comment">% The number of elimination-dispersal events</span>Sr=s/2; <span class="comment">% The number of bacteria reproductions (splits) per generation</span>Ped=0.25; <span class="comment">% The probabilty that each bacteria will be eliminated/dispersed</span>c(:,1)=0.5*ones(s,1); <span class="comment">% the run length</span><span class="keyword">for</span> i = 1:s Delta(:,i)=(2*round(rand(p,1))-1).*rand(p,1);<span class="keyword">end</span><span class="keyword">for</span> m=1:s <span class="comment">% the initital posistions</span> P(1,:,1,1,1)= 50*rand(s,1)'; P(2,:,1,1,1)= 0.2*rand(s,1)'; <span class="comment">%P(3,:,1,1,1)= .2*rand(s,1)';</span><span class="keyword">end</span>c1 =1.2; <span class="comment">% PSO parameter C1 1.2</span>c2 = 0.5; <span class="comment">% PSO parameter C2 .5</span>R1 = rand(p,s); <span class="comment">% PSO parameter</span>R2 = rand(p,s); <span class="comment">% PSO parameter</span>Plocal_best_position=0*ones(p,s,Nc); <span class="comment">% PSO</span>Pglobal_best_position=0*ones(p,s,Nc); <span class="comment">% PSO</span>velocity = .3*randn(p,s); <span class="comment">% PSO</span>current_position=0*ones(p,s,Nc); <span class="comment">% PSO</span></pre><pre class="codeinput"><span class="comment">%Main loop</span><span class="comment">%Elimination and dispersal loop</span><span class="keyword">for</span> ell=1:Ned<span class="comment">%Reprodution loop</span> <span class="keyword">for</span> K=1:Nre<span class="comment">% swim/tumble(chemotaxis)loop</span> <span class="keyword">for</span> j=1:Nc <span class="keyword">for</span> i=1:s J(i,j,K,ell)=tracklsq(P(:,i,j,K,ell));<span class="comment">% Tumble</span> Jlast=J(i,j,K,ell); Jlocal(i,j)=Jlast; P(:,i,j+1,K,ell)=P(:,i,j,K,ell)+c(i,K)*Delta(:,i); <span class="comment">% This adds a unit vector in the random direction</span><span class="comment">% Swim (for bacteria that seem to be headed in the right direction)</span> J(i,j+1,K,ell)=tracklsq(P(:,i,j+1,K,ell)); m=0; <span class="comment">% Initialize counter for swim length</span> <span class="keyword">while</span> m<Ns m=m+1; <span class="keyword">if</span> J(i,j+1,K,ell)<Jlast Jlast=J(i,j+1,K,ell); P(:,i,j+1,K,ell)=P(:,i,j+1,K,ell)+c(i,K)*Delta(:,i) ; J(i,j+1,K,ell)=tracklsq(P(:,i,j+1,K,ell)); current_position(:,i,j+1)= P(:,i,j+1,K,ell) ; <span class="comment">% PSO</span> Jlocal(i,j+1) = J(i,j+1,K,ell) ; <span class="comment">% PSO</span> <span class="keyword">else</span> Jlocal(i,j+1) = J(i,j+1,K,ell) ; current_position(:,i,j+1)= P(:,i,j+1,K,ell); m=Ns ; <span class="keyword">end</span> <span class="keyword">end</span> sprintf(<span class="string">'The value of interation i %3.0f ,j = %3.0f , K= %3.0f, ell= %3.0f'</span> , i, j, K ,ell ); <span class="keyword">end</span> <span class="comment">% Go to next bacterium</span><span class="comment">%For each chemotactic evaluate the local and global best position</span><span class="comment">%Local best position over all chemotactic that each bacteria move through it</span> [Jmin_for_each_chemotactic,index]=min(Jlocal,[],2); <span class="keyword">for</span> m=1:s Plocal_best_position(:,m,j) = current_position(:,m,index(m,:)); <span class="keyword">end</span><span class="comment">%Global best position over all chemotactic and for each bacteria</span> [Y,I]=min(Jmin_for_each_chemotactic); global_best_position =current_position(:,I,index(I,:)); <span class="keyword">for</span> m =1:s Pglobal_best_position(:,m,j)=global_best_position; <span class="keyword">end</span><span class="comment">%Caluculate the new direction for each bacteria</span>velocity =.9* velocity + c1*(R1.*(Plocal_best_position(:,:,j)-current_position(:,:,j+1))) + c2*(R2.*(Pglobal_best_position(:,:,j)-current_position(:,:,j+1)));Delta = velocity ; <span class="keyword">end</span> <span class="comment">% Go to the next chemotactic</span><span class="comment">%Reprodution</span> Jhealth=sum(J(:,:,K,ell),2); <span class="comment">% Set the health of each of the S bacteria</span> [Jhealth,sortind]=sort(Jhealth); <span class="comment">% Sorts the nutrient concentration in order of ascending</span> P(:,:,1,K+1,ell)=P(:,sortind,Nc+1,K,ell); c(:,K+1)=c(sortind,K); <span class="comment">% And keeps the chemotaxis parameters with each bacterium at the next generation</span><span class="comment">%Split the bacteria (reproduction)</span> <span class="keyword">for</span> i=1:Sr P(:,i+Sr,1,K+1,ell)=P(:,i,1,K+1,ell); <span class="comment">% The least fit do not reproduce, the most fit ones split into two identical copies</span> c(i+Sr,K+1)=c(i,K+1); <span class="keyword">end</span> <span class="keyword">end</span> <span class="comment">% Go to next reproduction</span><span class="comment">%Eliminatoin and dispersal</span>⌨️ 快捷键说明
复制代码
Ctrl + C
搜索代码
Ctrl + F
全屏模式
F11
切换主题
Ctrl + Shift + D
显示快捷键
?
增大字号
Ctrl + =
减小字号
Ctrl + -