请教一个关于matlab进行自定义曲线参数拟合的问题
\u5982\u4f55\u7528MATLAB\u62df\u5408\u66f2\u7ebf\u6765\u6c42\u53c2\u6570\uff1f\u4ee4x\uff1d(cos(k)./sin(k))./c\uff0c\u8fd9\u4e2a\u5c31\u662fxdata\u5411\u91cf
y=252/(2.016129032*10^9)*a*x^b
\u53d6log\u5f97\u5230
log(y)=b*log(x)+log(252/(2.016129032*10^9)*a)
\u6240\u4ee5log(y)\u4e0elog(x)\u662f\u7ebf\u6027\u5173\u7cfb\uff0c\u7528p=polyfit(log(xdata),log(y),1)\u6c42\u51fa
b=p(1);
a=exp(p(2))/252*(2.016129032*10^9); % \u56e0\u4e3alog(252/(2.016129032*10^9)*a)=p(2)
\u6240\u4ee5\u6700\u7ec8\u7a0b\u5e8f\u662f\u5982\u4e0b\uff1a
clear all
c=[2.7,2.8,2.9,3,3.1,3.2,3.45,3.7,3.95,4.2,4.45,4.7,4.95,5.2];
k=[0,47,93,140,186,279,372,465,558,651];
y=[18.98,27.35,34.86,38.52,38.44,37.73,38.43,43.87,42.77,46.22];
xdata=(cos(k)./sin(k))./c;
p=polyfit(log(xdata),log(y),1);
b=p(1);
a=exp(p(2))/252*(2.016129032*10^9);
\u65e2\u7136\u4f60\u5df2\u7ecf\u77e5\u9053\u5f85\u62df\u5408\u7684\u51fd\u6570\u8868\u73b0\u5f62\u5f0f\u4e86\uff0c\u7528\u5185\u8054\u51fd\u6570\u5427
可以用cftool工具箱拟合。但拟合精度偏低，R²=0.8444。
General model:
f(x) = a*erfc(x/(2*sqrt(b*(28/315360000)^c*315360000)))
where x is normalized by mean 27.5 and std 15.14
Coefficients (with 95% confidence bounds):
a = 3.24 (3.002, 3.477)
b = 10.54 (-4.122e+008, 4.122e+008)
c = 1.243 (-2.409e+006, 2.409e+006)
Goodness of fit:
SSE: 0.7045
R-square: 0.879
Adjusted R-square: 0.8444
RMSE: 0.3172
这个拟合是很不好啊！不知道怎么得出的？
你可以试试用 多项式拟合polyfit(x,y,n)
绛旓細鍦MATLAB涓紝涓涓嚱鏁板彲浠ヨ皟鐢ㄥ叾瀹冨嚱鏁帮紝涔熷彲浠ヨ皟鐢ㄨ嚜韬紙鍗抽掑綊璋冪敤锛夈傚埄鐢ㄩ掑綊绠楁硶缂栧啓鍑芥暟鐨勫吀鍨嬩緥瀛愭槸璁＄畻Fibonacci鏁板垪銆侻-鍑芥暟鏂囦欢锛歠unction a = my_fibo(k)if k == 1 || k == 2 a = 1;else a = my_fibo(k-1) + my_fibo(k-2);end灏嗚繖涓枃浠跺啓鍏-鏂囦欢缂栬緫鍣ㄥ苟浠ュ悕绉扳...
绛旓細绗竴姝ュ湪matlab涓垱寤轰簡涓涓嚜瀹氫箟鍑芥暟test_data锛屽苟灏唗est_data鍑芥暟鏀惧湪褰撳墠鏂囦欢澶癸紝绗簩姝ュ湪鍛戒护琛岀獥鍙ｄ腑杈撳叆test_data(3)杩涜璋冪敤鍑芥暟锛岃繑鍥炵粨鏋9锛岀涓夋鍦ㄥ懡浠よ绐楀彛涓皟鐢ㄥ嚱鏁帮紝闇瑕佹敞鎰鐨鏄皟鐢ㄥ嚱鏁拌鍦ㄥ綋鍓嶆枃浠跺す涓紝灏辨槸瑕佸湪鑷畾涔夊嚱鏁皌est_data鐨勮矾寰勬枃浠跺す涓嬶紝涓嶇劧浼氬嚭鐜版壘涓嶅埌鐨勬儏鍐碉紝绗...
绛旓細=鑷畾涔夊嚱鏁(A:D,F2)浠ｇ爜鏂囨湰锛欶unction 鑷畾涔夊嚱鏁(a As Range, b As String)For i = 2 To 10000 If a.Cells(i, 1) = "" Then Exit For If a.Cells(i, 1) = b And a.Cells(i, 3) + a.Cells(i, 4) > 8000 Then 鑷畾涔夊嚱鏁 = 鑷畾涔夊嚱鏁 + 1 Next End Function ...
绛旓細鍙互鐢╟ftool宸ュ叿绠辨嫙鍚堛備絾鎷熷悎绮惧害鍋忎綆锛孯²=0.8444銆侴eneral model: f(x) = a*erfc(x/(2*sqrt(b*(28/315360000)^c*315360000))) where x is normalized by mean 27.5 and std 15.14Coefficients (with 95% confidence bounds): a = 3.24 (3.002, 3.477) ...
绛旓細1銆佷笁鑰呭睘浜庝笉鍚鐨鏁版嵁绫诲瀷锛岀涓涓鏄痵ym瀵硅薄锛岀浜屼釜鏄痠nline瀵硅薄锛岀涓変釜鏄瓧绗︿覆銆傚彟澶栵紝鐢ㄤ互琛ㄧず鍑芥暟鐨勮繕鏈変竴绉嶅尶鍚嶅嚱鏁颁細缁忓父鐢ㄥ埌锛Matlab 7.0浠ヤ笂锛夈2銆佹煇涓壒瀹氱殑鍑芥暟锛堝solve銆乪zplot绛夛級鏄惁鏀寔杩欏嚑绉嶅嚱鏁板舰寮忥紝鍙栧喅浜庡嚱鏁拌嚜韬杈撳叆鐨勫鐞嗘柟寮忋備緥濡傚浜庡瓧绗︿覆锛宔zplot浼氬厛灏嗗叾杞崲涓...
绛旓細瀹炵幇浠ｇ爜锛歝lc,clear all,close all a1=?;a2=?;b1=?;b2=?;d=?;s=?; %闇瑕佸凡鐭 lambda=[...]; %鏁版嵁 T=[...]; %鏁版嵁 n=a1./lambda.^2+a2;alpha=10^(b1./lambda.^2+b2);A=16*n^2*s;B=(n-l)^3*(n+s^2);C=2*(n^2-l*(n^2-s^2));D=(n-l)^3...
绛旓細mu1=2.5;mu2=3;sigma1=0.5;sigma2=0.6;x=(mu2-4*sigma2):0.01:(mu2+4*sigma2);鑰冨療鍧囧肩殑褰卞搷锛氬潎鍊间笉鍚岋紝鏂瑰樊鐩稿悓 y1=normpdf(x,mu1,sigma1);y2=normpdf(x,mu2,sigma1);鑰冨療鏂瑰樊鐨勫奖鍝嶏細鍧囧肩浉鍚岋紝鏂瑰樊涓嶅悓 y3=normpdf(x,mu1,sigma1);y4=normpdf(x,mu1,sigma2);缁撴灉鍙鍖...
绛旓細1. 棣栧厛璇磋鑷浉鍏冲拰浜掔浉鍏鐨姒傚康銆傝繖涓槸淇″彿鍒嗘瀽閲岀殑姒傚康锛屼粬浠垎鍒〃绀虹殑鏄袱涓椂闂村簭鍒椾箣闂村拰鍚涓涓鏃堕棿搴忓垪鍦ㄤ换鎰忎袱涓笉鍚屾椂鍒荤殑鍙栧间箣闂寸殑鐩稿叧绋嬪害锛屽嵆浜掔浉鍏冲嚱鏁版槸鎻忚堪闅忔満淇″彿 x(t),y(t)鍦ㄤ换鎰忎袱涓笉鍚屾椂鍒籺1锛宼2鐨勫彇鍊间箣闂寸殑鐩稿叧绋嬪害锛岃嚜鐩稿叧鍑芥暟鏄弿杩伴殢鏈轰俊鍙穢(t)鍦ㄤ换鎰忎袱涓笉鍚屾椂鍒籺1...
绛旓細鑷浉鍏冲嚱鏁版槸鎻忚堪闅忔満淇″彿X(t)鍦ㄤ换鎰忎袱涓笉鍚屾椂鍒籺1锛宼2鐨鍙栧间箣闂寸殑鐩稿叧绋嬪害.璁惧師鍑芥暟鏄痜(t)锛屽垯鑷浉鍏冲嚱鏁板畾涔変负R(u)=f(t)*f(-t)锛屽叾涓*琛ㄧず鍗风Н.缁欎釜渚嬪瓙:dt=.1;t=[0:dt:100];x=cos(t);[a,b]=xcorr(x,'unbiased');plot(b*dt,a)涓婇潰浠ｇ爜鏄眰鑷浉鍏冲嚱鏁板苟浣滃浘锛matlab涓煡鐪...
绛旓細1銆佸嚱鏁版枃浠+璋冪敤鍛戒护鏂囦欢锛氶渶鍗曠嫭瀹氫箟涓涓嚜瀹氫箟鍑芥暟鐨M鏂囦欢;2銆佸嚱鏁版枃浠+瀛愬嚱鏁帮細瀹氫箟涓涓叿鏈夊涓嚜瀹氫箟鍑芥暟鐨凪鏂囦欢锛3銆両nline:鏃犻渶M鏂囦欢锛岀洿鎺ュ畾涔夛紱4銆佸尶鍚嶅嚱鏁帮紱5銆丼yms+subs: 鏃犻渶M鏂囦欢,鐩存帴瀹氫箟锛6銆佸瓧绗︿覆+subs锛氭棤闇M鏂囦欢,鐩存帴瀹氫箟锛7銆佺洿鎺ラ氳繃@绗﹀彿瀹氫箟.1銆佸嚱鏁版枃浠+璋冪敤鍑芥暟鏂囦欢锛...
