matlab與機械優(yōu)化設計三級項目

matlab與機械優(yōu)化設計三級項目--BP神經(jīng)網(wǎng)絡的建立與matlab實現(xiàn)組員：齊意媛指導教師：任素波PAGEPAGE6目錄一、BP二、BP三、應用matlab進行計算四、結論一、BP神經(jīng)網(wǎng)絡的概述BP（Back-ProPagationNetwork）又稱反向傳播神經(jīng)網(wǎng)絡，通過樣本數(shù)數(shù)據(jù)壓縮和時間序列預測等。BP網(wǎng)絡由輸入層隱層和輸出層組成隱層可以有一層或多層圖2是的三層BP網(wǎng)絡模型，網(wǎng)絡選用S型傳遞函數(shù)， 通過反傳誤差函數(shù) （ （Ti為期望輸出、Oi為網(wǎng)絡的計算輸出），不斷調(diào)網(wǎng)絡權值和閾值使誤差函數(shù)E達到極小。BP網(wǎng)絡具有高度非線性和較強的泛化能力，但也存在收斂速度慢、迭代步數(shù)多、易于陷入局部極小和全局搜索能力差等缺點?？梢韵扔眠z傳算法對“BPBP間內(nèi)搜索最優(yōu)解。二、BP網(wǎng)絡的構建下面選取一個例子作為研究對象，選取運動員測試各項素質(zhì)指標下面選取一個例子作為研究對象，選取運動員測試各項素質(zhì)指標序號跳高成績30行進跑立定三級跳遠助跑摸高助跑4—6步跳高負重深蹲杠鈴杠鈴半蹲系數(shù)100m抓舉12.243.29.63.452.151402.8115022.333.210.33.752.21203.410.97032.24393.52.21403.511.45042.323.210.33.652.21502.810.88052.23.210.13.52801.511.35062.273.4103.42.151303.211.56072.23.29.63.552.141303.511.86582.26393.52.11001.811.34092.23.29.63.552.11303.511.865102.243.29.23.52.11402.51150112.243.29.53.42.151152.811.950122.23.993.12802.21350132.23.19.53.62.1902.711.170142.353.29.73.452.151304.610.8570153.09.33.32.051002.811.250輸入輸出層的設計8，1。隱層設計有關研究表明有一個隱層的神經(jīng)網(wǎng)絡只要隱節(jié)點足夠多就可以以任意精網(wǎng)絡建立預測模型。在網(wǎng)絡設計過程中隱層神經(jīng)元數(shù)的確定十分重要。隱層神經(jīng)元個數(shù)過多會加大網(wǎng)絡計算量并容易產(chǎn)生過度擬合問題神經(jīng)元個數(shù)過少則會影響網(wǎng)絡性能達不到預期效果。網(wǎng)絡中隱層神經(jīng)元的數(shù)目與實際問題的復雜于隱層中神經(jīng)元數(shù)目的確定并沒有明確的公式只有一些經(jīng)驗公式,神經(jīng)元個數(shù)問題上參照了以下的經(jīng)驗公式:其中n為輸入層神經(jīng)元個數(shù)m為輸出層神經(jīng)元個數(shù)a為1,10]之間的常數(shù)。4-136.網(wǎng)絡結構示意圖如下：BPSigmoid可微函數(shù)和線性函數(shù)作為網(wǎng)絡的激勵函數(shù)。Stansig一到[-1,1]范圍內(nèi),因此預測模型選取Stansig作為輸出層神經(jīng)元的激勵函數(shù)。tansiglogsig函數(shù),網(wǎng)絡訓練函數(shù)traingdx,mse,6epochs5000次,goal0.00000001lr0.01。設定完參數(shù)后開始訓練網(wǎng)絡。三、應用matlab進行計算代碼如下代碼如下P=[3.23.233.23.23.43.233.23.23.23.93.13.2;9.610.3910.310.1109.699.69.29.599.59.7;3.453.753.53.653.53.43.553.53.553.53.43.13.63.45;2.152.22.22.222.152.142.12.12.12.1522.12.15;140120140150801301301001301401158090130;2.83.43.52.81.53.23.51.83.52.52.82.22.74.6;1110.911.410.811.311.511.811.311.81111.91311.110.85;5070508050606540655050507070];T=[2.242.332.242.322.22.272.22.262.22.242.242.22.22.35];[p1,minp,maxp,t1,mint,maxt]=premnmx(P,T);%創(chuàng)建網(wǎng)絡net=newff(minmax(p1),[8,6,1],{'tansig','tansig','purelin'},'trainlm');%設置訓練次數(shù)net.trainParam.epochs=5000;%設置收斂誤差net.trainParam.goal=0.0000001;%訓練網(wǎng)絡[net,tr]=train(net,p1,t1);計算顯示如下%輸入數(shù)據(jù)a=[3.0;9.3;3.3;2.05;100;2.8;11.2;50];%a=premnmx(a);%b=sim(net,a);%將得到的數(shù)據(jù)反歸一化得到預測數(shù)據(jù)c=postmnmx(b,mint,maxt);再根據(jù)以上代碼輸入數(shù)據(jù)進行模擬運算的結果為c=2