<html xmlns="http://www.w3.org/1999/xhtml">
<head>
<meta charset="utf-8">
<meta name="generator" content="pdf2htmlEX">
<meta http-equiv="X-UA-Compatible" content="IE=edge,chrome=1">
<link rel="stylesheet" href="https://static.pudn.com/base/css/base.min.css">
<link rel="stylesheet" href="https://static.pudn.com/base/css/fancy.min.css">
<link rel="stylesheet" href="https://static.pudn.com/prod/directory_preview_static/62741d42445c3651d26bc59c/raw.css">
<script src="https://static.pudn.com/base/js/compatibility.min.js"></script>
<script src="https://static.pudn.com/base/js/pdf2htmlEX.min.js"></script>
<script>
try{
pdf2htmlEX.defaultViewer = new pdf2htmlEX.Viewer({});
}catch(e){}
</script>
<title></title>
</head>
<body>
<div id="sidebar" style="display: none">
<div id="outline">
</div>
</div>
<div id="pf1" class="pf w0 h0" data-page-no="1"><div class="pc pc1 w0 h0"><img class="bi x0 y0 w1 h1" alt="" src="https://static.pudn.com/prod/directory_preview_static/62741d42445c3651d26bc59c/bg1.jpg"><div class="c x0 y1 w2 h2"><div class="t m0 x1 h3 y2 ff1 fs0 fc0 sc0 ls0 ws0">系统辨识大作业</div><div class="t m0 x2 h4 y3 ff1 fs1 fc0 sc1 ls0 ws0">学 院：<span class="_ _0"> </span>电气与控制工程学院</div></div></div><div class="pi" data-data='{"ctm":[1.611850,0.000000,0.000000,1.611850,0.000000,0.000000]}'></div></div>
</body>
</html>
<div id="pf2" class="pf w0 h0" data-page-no="2"><div class="pc pc2 w0 h0"><img class="bi x0 y0 w1 h1" alt="" src="https://static.pudn.com/prod/directory_preview_static/62741d42445c3651d26bc59c/bg2.jpg"><div class="c x0 y1 w2 h2"><div class="t m0 x3 h5 y4 ff2 fs2 fc0 sc1 ls0 ws0">1.<span class="_ _1"> </span><span class="ff1 sc0">设计内容</span></div><div class="t m0 x3 h6 y5 ff1 fs3 fc0 sc1 ls0 ws0">设<span class="_ _2"> </span><span class="ff3">SISO<span class="_ _2"> </span></span>系统的差分方程为：</div><div class="t m0 x4 h6 y6 ff3 fs3 fc0 sc1 ls0 ws0"> <span class="ff1">式（</span>1-1<span class="ff1">）</span></div><div class="t m0 x3 h6 y7 ff1 fs3 fc0 sc1 ls0 ws0">参<span class="_ _3"></span>数<span class="_ _3"></span>取<span class="_ _3"></span>真<span class="_ _3"></span>值<span class="_ _3"></span>为<span class="_ _4"></span>：<span class="_ _5"> </span>，<span class="_ _3"></span>利<span class="_ _3"></span>用<span class="_ _6"> </span><span class="ff3">MA<span class="_ _7"></span>TL<span class="_ _3"></span>AB<span class="_ _3"></span> <span class="_ _3"></span><span class="ff1">的<span class="_ _6"> </span></span>M<span class="_ _8"> </span><span class="ff1">语<span class="_ _3"></span>言<span class="_ _3"></span>辨<span class="_ _3"></span>识<span class="_ _3"></span>系</span></span></div><div class="t m0 x3 h6 y8 ff1 fs3 fc0 sc1 ls0 ws0">统中的未知参数<span class="_ _9"> </span>、<span class="_ _a"> </span>、<span class="_ _b"> </span>、<span class="_ _c"> </span>。</div><div class="t m0 x3 h5 y9 ff2 fs2 fc0 sc1 ls0 ws0">2.<span class="_ _1"> </span><span class="ff1 sc0">设计过程</span></div><div class="t m0 x3 h7 ya ff4 fs4 fc0 sc1 ls0 ws0">2.1<span class="_ _d"> </span><span class="ff1 sc0">问题重述。</span></div><div class="t m0 x3 h6 yb ff1 fs3 fc0 sc1 ls0 ws0">设<span class="_ _2"> </span><span class="ff3">SISO<span class="_ _2"> </span></span>系统的差分方程为：</div><div class="t m0 x4 h6 yc ff3 fs3 fc0 sc1 ls0 ws0"> <span class="ff1">式（</span>2-1<span class="ff1">）</span></div><div class="t m0 x3 h6 yd ff1 fs3 fc0 sc1 ls0 ws0">参<span class="_ _3"></span>数<span class="_ _3"></span>取<span class="_ _3"></span>真<span class="_ _3"></span>值<span class="_ _3"></span>为<span class="_ _4"></span>：<span class="_ _5"> </span>，<span class="_ _3"></span>利<span class="_ _3"></span>用<span class="_ _6"> </span><span class="ff3">MA<span class="_ _7"></span>TL<span class="_ _3"></span>AB<span class="_ _3"></span> <span class="_ _3"></span><span class="ff1">的<span class="_ _8"> </span></span>M<span class="_ _6"> </span><span class="ff1">语<span class="_ _3"></span>言<span class="_ _3"></span>辨<span class="_ _3"></span>识<span class="_ _3"></span>系</span></span></div><div class="t m0 x3 h6 ye ff1 fs3 fc0 sc1 ls0 ws0">统中的未知参数<span class="_ _9"> </span>、<span class="_ _a"> </span>、<span class="_ _b"> </span>、<span class="_ _c"> </span>。</div><div class="t m0 x5 h6 yf ff1 fs3 fc0 sc1 ls0 ws0">要求<span class="_ _3"></span>：用<span class="_ _3"></span>参数<span class="_ _3"></span>的真<span class="_ _3"></span>值利<span class="_ _3"></span>用差<span class="_ _3"></span>分方<span class="_ _3"></span>程求<span class="_ _3"></span>出<span class="_ _e"> </span>作为<span class="_ _3"></span>测量<span class="_ _3"></span>值，<span class="_ _e"> </span>是均值</div><div class="t m0 x6 h6 y10 ff1 fs3 fc0 sc1 ls0 ws0">为<span class="_ _2"> </span><span class="ff3">0</span>，方差为<span class="_ _2"> </span><span class="ff3">0.01<span class="_ _2"> </span></span>的不相关随机序列。取一种最小二乘算法辨识。</div></div><div class="t m0 x7 h8 y11 ff5 fs5 fc0 sc1 ls0 ws0">1</div></div><div class="pi" data-data='{"ctm":[1.611850,0.000000,0.000000,1.611850,0.000000,0.000000]}'></div></div>
<div id="pf3" class="pf w0 h0" data-page-no="3"><div class="pc pc3 w0 h0"><img class="bi x0 y0 w1 h1" alt="" src="https://static.pudn.com/prod/directory_preview_static/62741d42445c3651d26bc59c/bg3.jpg"><div class="c x0 y1 w2 h2"><div class="t m0 x3 h7 y12 ff4 fs4 fc0 sc1 ls0 ws0">2.2<span class="_ _d"> </span><span class="ff1 sc0">最小二乘参数辨识</span></div><div class="t m0 x3 h6 y13 ff4 fs3 fc0 sc1 ls0 ws0">2.2.1<span class="ff1 sc0">、<span class="_ _f"> </span>最小二乘法的概念与应用</span></div><div class="t m0 x5 h6 y14 ff1 fs3 fc0 sc1 ls0 ws0">对工<span class="_ _3"></span>程实<span class="_ _3"></span>践中测<span class="_ _3"></span>得的<span class="_ _3"></span>数据进<span class="_ _3"></span>行理论<span class="_ _3"></span>分析<span class="_ _3"></span>，用恰<span class="_ _3"></span>当的<span class="_ _3"></span>函数去<span class="_ _3"></span>模拟<span class="_ _3"></span>数据原<span class="_ _3"></span>型</div><div class="t m0 x6 h6 y15 ff1 fs3 fc0 sc1 ls0 ws0">是一类十分重要的问题，最常用的逼近原则是让实测数据和估计数据之间的距</div><div class="t m0 x6 h6 y16 ff1 fs3 fc0 sc1 ls0 ws0">离平方和最小，这即是最小二乘法。最小二乘法是一种经典的数据处理方法。</div><div class="t m0 x6 h6 y17 ff1 fs3 fc0 sc1 ls0 ws0">在系<span class="_ _3"></span>统辨<span class="_ _3"></span>识领<span class="_ _3"></span>域中<span class="_ _3"></span> <span class="_ _3"></span><span class="ff3">,</span>最<span class="_ _3"></span>小二<span class="_ _3"></span>乘法<span class="_ _3"></span>是一<span class="_ _3"></span>种得<span class="_ _3"></span>到广<span class="_ _3"></span>泛应<span class="_ _3"></span>用的<span class="_ _3"></span>估计<span class="_ _3"></span>方法<span class="_ _3"></span> <span class="_ _4"></span><span class="ff3">,<span class="_ _3"></span></span>可用<span class="_ _3"></span>于动<span class="_ _3"></span>态</div><div class="t m0 x6 h6 y18 ff1 fs3 fc0 sc1 ls0 ws0">系统<span class="_ _3"></span> <span class="_ _3"></span><span class="ff3">,</span>静<span class="_ _3"></span>态系<span class="_ _3"></span>统 <span class="_ _3"></span><span class="ff3">, <span class="_ _3"></span></span>线<span class="_ _3"></span>性系<span class="_ _3"></span>统 <span class="_ _3"></span><span class="ff3">,<span class="_ _3"></span></span>非线<span class="_ _3"></span>性系<span class="_ _3"></span>统。<span class="_ _3"></span>可用于<span class="_ _3"></span>离线<span class="_ _3"></span>估计<span class="_ _3"></span>，也<span class="_ _3"></span>可用<span class="_ _3"></span>于在<span class="_ _3"></span>线估</div><div class="t m0 x6 h6 y19 ff1 fs3 fc0 sc1 ls0 ws0">计。这种辨识方法主要用于在线辨识。在随机的环境下，利用最小二乘法时，</div><div class="t m0 x6 h6 y1a ff1 fs3 fc0 sc1 ls0 ws0">并不要求观测数据提供其概率统计方面的信息，而其估计结果，却有相当好的</div><div class="t m0 x6 h6 y1b ff1 fs3 fc0 sc1 ls0 ws0">统计特性。</div><div class="t m0 x5 h6 y1c ff3 fs3 fc0 sc1 ls0 ws0">MA<span class="_ _7"></span>TL<span class="_ _3"></span>AB<span class="_ _2"> </span><span class="ff1">是一套高性能数字计算和可视化软件 <span class="_ _3"></span></span>,<span class="ff1">它集成概念设计 </span>,<span class="ff1">算法开</span></div><div class="t m0 x6 h6 y1d ff1 fs3 fc0 sc1 ls0 ws0">发 <span class="_ _3"></span><span class="ff3">,</span>建模<span class="_ _3"></span>仿真 <span class="_ _3"></span><span class="ff3">,</span>实时<span class="_ _3"></span>实现于<span class="_ _3"></span>一体 <span class="_ _3"></span><span class="ff3">,</span>构<span class="_ _3"></span>成了一个<span class="_ _3"></span>使用方<span class="_ _3"></span>便、界<span class="_ _3"></span>面友好的<span class="_ _3"></span>用户环境<span class="_ _3"></span> <span class="_ _4"></span><span class="ff3">,</span></div><div class="t m0 x6 h6 y1e ff1 fs3 fc0 sc1 ls0 ws0">其强<span class="_ _3"></span>大的扩展<span class="_ _3"></span>功能为各<span class="_ _3"></span>领域的<span class="_ _3"></span>应用提供<span class="_ _3"></span>了基础<span class="_ _3"></span>。对于比<span class="_ _3"></span>较复杂的<span class="_ _3"></span>生产过<span class="_ _3"></span>程 <span class="_ _3"></span><span class="ff3">,<span class="_ _3"></span></span>由</div><div class="t m0 x6 h6 y1f ff1 fs3 fc0 sc1 ls0 ws0">于过<span class="_ _3"></span>程的输入<span class="_ _3"></span>输出信号<span class="_ _3"></span>一般总<span class="_ _3"></span>是可以测<span class="_ _3"></span>量的 <span class="_ _3"></span><span class="ff3">,<span class="_ _3"></span></span>而且过程<span class="_ _3"></span>的动态特<span class="_ _3"></span>性必然表<span class="_ _3"></span>现在</div><div class="t m0 x6 h6 y20 ff1 fs3 fc0 sc1 ls0 ws0">这些<span class="_ _3"></span>输入输出<span class="_ _3"></span>数据中 <span class="_ _3"></span><span class="ff3">,</span>那<span class="_ _3"></span>么就可以<span class="_ _3"></span>利用输<span class="_ _3"></span>入输出数<span class="_ _3"></span>据所提<span class="_ _3"></span>供的信息<span class="_ _3"></span>来建立过<span class="_ _3"></span>程</div><div class="t m0 x6 h6 y21 ff1 fs3 fc0 sc1 ls0 ws0">的数学模型。这种建模方法就称为系统辨识。把辨识建模称作“黑箱建模”。</div><div class="t m0 x3 h6 y22 ff4 fs3 fc0 sc1 ls0 ws0">2.2.2<span class="ff1 sc0">、<span class="_ _f"> </span>最小二乘法系统辨识结构：</span></div><div class="t m0 x8 h6 y23 ff1 fs3 fc0 sc1 ls0 ws0">本文把待辨识<span class="_ _3"></span>的过程看作“黑箱”。只考虑<span class="_ _3"></span>过程的输入输出特性，而不<span class="_ _3"></span>强调过</div><div class="t m0 x3 h6 y24 ff1 fs3 fc0 sc1 ls0 ws0">程的内部机理。</div><div class="t m0 x3 h6 y25 ff1 fs3 fc0 sc1 ls0 ws0">图中，输入<span class="_ _2"> </span><span class="ff3">u(k)<span class="_ _3"></span></span>和输出<span class="_ _2"> </span><span class="ff3">z(k)</span>是可以观测<span class="_ _3"></span>的；<span class="ff3">G</span>（<span class="_ _d"> </span>）是系统<span class="_ _3"></span>模型，用来描述系</div><div class="t m0 x3 h6 y26 ff1 fs3 fc0 sc1 ls0 ws0">统的<span class="_ _3"></span>输入<span class="_ _3"></span>输出特<span class="_ _3"></span>性；<span class="_ _3"></span><span class="ff3">N</span>（<span class="_ _10"> </span>）是<span class="_ _3"></span>噪声<span class="_ _3"></span>模型，<span class="_ _3"></span><span class="ff3">v(k)</span>是<span class="_ _3"></span>白噪声<span class="_ _3"></span>，<span class="ff3">e(k)<span class="_ _3"></span></span>是有色<span class="_ _3"></span>噪声<span class="_ _3"></span>，</div><div class="t m0 x3 h6 y27 ff1 fs3 fc0 sc1 ls0 ws0">根据表示定理：</div><div class="t m0 x3 h6 y28 ff1 fs3 fc0 sc1 ls0 ws0">可以表示为</div></div><div class="t m0 x7 h8 y11 ff5 fs5 fc0 sc1 ls0 ws0">2</div></div><div class="pi" data-data='{"ctm":[1.611850,0.000000,0.000000,1.611850,0.000000,0.000000]}'></div></div>
<div id="pf4" class="pf w0 h0" data-page-no="4"><div class="pc pc4 w0 h0"><img class="bi x0 y0 w1 h1" alt="" src="https://static.pudn.com/prod/directory_preview_static/62741d42445c3651d26bc59c/bg4.jpg"><div class="c x0 y1 w2 h2"><div class="t m0 x3 h9 y29 ff3 fs6 fc0 sc1 ls0 ws0">e(k) =N<span class="ff1">（<span class="_ _11"> </span>）</span>v(k)</div><div class="t m0 x9 ha y2a ff3 fs7 fc0 sc1 ls0 ws0"> <span class="_ _12"> </span> </div></div><div class="c x3 y2b w3 hb"><div class="t m1 xa hc y2c ff5 fs8 fc0 sc1 ls0 ws0">1<span class="_ _13"> </span>1<span class="_ _14"> </span>2</div><div class="t m1 xb hc y2d ff5 fs8 fc0 sc1 ls0 ws0">1<span class="_ _15"> </span>2</div><div class="t m1 xa hc y2e ff5 fs8 fc0 sc1 ls0 ws0">1<span class="_ _16"> </span>1<span class="_ _17"> </span>2</div><div class="t m1 xc hc y2f ff5 fs8 fc0 sc1 ls0 ws0">1<span class="_ _18"> </span>2</div><div class="t m2 xd hd y30 ff5 fs9 fc0 sc1 ls0 ws0">(<span class="_ _19"> </span>)<span class="_ _1a"> </span>1</div><div class="t m2 xd hd y31 ff5 fs9 fc0 sc1 ls0 ws0">(<span class="_ _19"> </span>)</div><div class="t m3 xe he y32 ff6 fsa fc0 sc1 ls0 ws0">a</div><div class="t m3 xf he y33 ff6 fsa fc0 sc1 ls0 ws0">a</div><div class="t m3 xf he y34 ff6 fsa fc0 sc1 ls0 ws0">b</div><div class="t m3 x10 he y35 ff6 fsa fc0 sc1 ls0 ws0">b</div><div class="t m1 x11 hc y36 ff6 fs8 fc0 sc1 ls0 ws0">n</div><div class="t m1 x12 hc y2d ff6 fs8 fc0 sc1 ls0 ws0">n</div><div class="t m1 x12 hc y37 ff6 fs8 fc0 sc1 ls0 ws0">n</div><div class="t m1 x13 hc y2f ff6 fs8 fc0 sc1 ls0 ws0">n</div><div class="t m2 x14 hd y30 ff6 fs9 fc0 sc1 ls0 ws0">A<span class="_ _1b"> </span>z<span class="_ _1c"> </span>a<span class="_ _1d"> </span>z<span class="_ _1e"> </span>a<span class="_ _1b"> </span>z<span class="_ _1f"> </span>a<span class="_ _b"> </span>z</div><div class="t m2 x15 hd y31 ff6 fs9 fc0 sc1 ls0 ws0">B<span class="_ _1"> </span>z<span class="_ _20"> </span>b<span class="_ _21"> </span>z<span class="_ _1e"> </span>b<span class="_ _1d"> </span>z<span class="_ _1f"> </span>b<span class="_ _22"> </span>z</div><div class="t m1 x16 hf y36 ff7 fs8 fc0 sc1 ls0 ws0"></div><div class="t m1 x17 hf y2c ff7 fs8 fc0 sc1 ls0 ws0"><span class="_ _23"> </span><span class="_ _24"> </span></div><div class="t m1 x18 hf y37 ff7 fs8 fc0 sc1 ls0 ws0"></div><div class="t m1 x17 hf y2e ff7 fs8 fc0 sc1 ls0 ws0"><span class="_ _25"> </span><span class="_ _14"> </span></div><div class="t m2 x19 h10 y38 ff7 fs9 fc0 sc1 ls0 ws0"></div><div class="t m2 x1a h10 y30 ff7 fs9 fc0 sc1 ls0 ws0"><span class="_ _26"> </span><span class="_ _27"> </span><span class="_ _28"> </span><span class="_ _29"> </span></div><div class="t m2 x19 h10 y39 ff7 fs9 fc0 sc1 ls0 ws0"></div><div class="t m2 x19 h10 y3a ff7 fs9 fc0 sc1 ls0 ws0"></div><div class="t m2 x1a h10 y31 ff7 fs9 fc0 sc1 ls0 ws0"><span class="_ _2a"> </span><span class="_ _2b"> </span><span class="_ _29"> </span></div><div class="t m2 x19 h10 y3b ff7 fs9 fc0 sc1 ls0 ws0"></div><div class="t m2 x19 h10 y35 ff7 fs9 fc0 sc1 ls0 ws0"></div><div class="t m2 x9 h10 y30 ff7 fs9 fc0 sc1 ls0 ws0"></div><div class="t m2 x1b h10 y31 ff7 fs9 fc0 sc1 ls0 ws0"></div></div><div class="c x0 y1 w2 h2"><div class="t m0 x3 h11 y3c ff5 fs7 fc0 sc1 ls0 ws0"> </div><div class="t m0 x1c h12 y3d ff5 fsb fc0 sc1 ls0 ws0"> </div><div class="t m0 x3 h7 y3e ff4 fs4 fc0 sc1 ls0 ws0">2.3<span class="_ _d"> </span><span class="ff1 sc0">广义最小二乘法</span></div><div class="t m0 x3 h6 y3f ff4 fs3 fc0 sc1 ls0 ws0">2.4.1<span class="ff1 sc0">、<span class="_ _f"> </span>广义最小二乘递推算法如下</span></div><div class="t m0 x3 h13 y40 ff1 fs7 fc0 sc1 ls0 ws0">式中</div><div class="t m0 x3 h6 y41 ff4 fs3 fc0 sc1 ls0 ws0">2.4.2<span class="ff1 sc0">、<span class="_ _f"> </span>广义最小二乘递推算法的计算步骤：</span></div><div class="t m0 x3 h6 y42 ff3 fs3 fc0 sc1 ls0 ws0">1.<span class="_ _2c"> </span><span class="ff1">给<span class="_ _2c"> </span>定<span class="_ _2c"> </span>初<span class="_ _2c"> </span>始<span class="_ _2c"> </span>条<span class="_ _2c"> </span>件</span></div></div><div class="t m0 x7 h8 y11 ff5 fs5 fc0 sc1 ls0 ws0">3</div></div><div class="pi" data-data='{"ctm":[1.611850,0.000000,0.000000,1.611850,0.000000,0.000000]}'></div></div>
<div id="pf5" class="pf w0 h0" data-page-no="5"><div class="pc pc5 w0 h0"><img class="bi x0 y0 w1 h1" alt="" src="https://static.pudn.com/prod/directory_preview_static/62741d42445c3651d26bc59c/bg5.jpg"><div class="c x0 y1 w2 h2"><div class="t m0 x3 h6 y43 ff3 fs3 fc0 sc1 ls0 ws0">2<span class="_ _2"> </span><span class="ff1">利用式<span class="_ _2d"> </span>，计算<span class="_ _2e"> </span>和<span class="_ _2a"> </span>；</span></div><div class="t m0 x3 h6 y44 ff3 fs3 fc0 sc1 ls0 ws0">3<span class="_ _2f"> </span><span class="ff1">利<span class="_ _30"> </span>用<span class="_ _30"> </span>式<span class="_ _31"> </span>，<span class="_ _30"> </span>构<span class="_ _30"> </span>造</span></div><div class="t m0 x1d h6 y45 ff1 fs3 fc0 sc1 ls0 ws0">；</div><div class="t m0 x3 h6 y46 ff3 fs3 fc0 sc1 ls0 ws0">4<span class="_ _32"> </span><span class="ff1">利<span class="_ _33"> </span>用<span class="_ _33"> </span>式</span></div><div class="t m0 x3 h6 y47 ff1 fs3 fc0 sc1 ls0 ws0">递推计算<span class="_ _34"> </span>；</div><div class="t m0 x3 h6 y48 ff3 fs3 fc0 sc1 ls0 ws0">5<span class="_ _2"> </span><span class="ff1">利用<span class="_ _35"> </span>和</span></div><div class="t m0 x1e h6 y49 ff1 fs3 fc0 sc1 ls0 ws0">计算<span class="_ _36"> </span>；</div><div class="t m0 x3 h6 y4a ff3 fs3 fc0 sc1 ls0 ws0">6<span class="_ _2"> </span><span class="ff1">根据<span class="_ _37"> </span>来构造<span class="_ _2a"> </span>；</span></div><div class="t m0 x3 h6 y4b ff3 fs3 fc0 sc1 ls0 ws0">7<span class="_ _38"> </span><span class="ff1">利<span class="_ _39"> </span>用</span></div><div class="t m0 x3 h6 y4c ff1 fs3 fc0 sc1 ls0 ws0">返回第<span class="_ _2"> </span><span class="ff3">2<span class="_ _2"> </span></span>步进行迭代计算，直至获得满意的辨识结果。</div><div class="t m0 x3 h6 y4d ff4 fs3 fc0 sc1 ls0 ws0">2.4.3<span class="ff1 sc0">、<span class="_ _f"> </span>广义最小二乘递推算法的<span class="_ _2"> </span></span>MA<span class="_ _7"></span>TLAB<span class="_ _2"> </span><span class="ff1 sc0">仿真（程序源代码见附录）</span></div><div class="t m0 x3 h14 y4e ff1 fs3 fc0 sc1 ls0 ws0">考虑仿真对<span class="ff8">象</span></div><div class="t m0 x3 h15 y4f ff3 fs3 fc0 sc1 ls0 ws0">z(k)= -1.642z(k-1)-0.715z(k-2)+0.39u(k-1)+0.<span class="_ _3"></span>3<span class="_ _3a"></span>5u(k-2)+v(k)</div><div class="t m0 x3 h14 y50 ff1 fs3 fc0 sc1 ls0 ws0">式中，<span class="ff3">v(k) </span>是均值为<span class="_ _2"> </span><span class="ff3">0<span class="_ _3"></span></span>，方差为<span class="_ _2"> </span><span class="ff3">0.01</span>、的不相关随机序列。输入信号<span class="ff8">采</span>用<span class="_ _8"> </span><span class="ff3">4<span class="_ _2"> </span><span class="ff8">阶</span></span></div><div class="t m0 x3 h14 y51 ff3 fs3 fc0 sc1 ls0 ws0">M<span class="_ _2"> </span><span class="ff1">序列，<span class="ff8">幅度</span>为<span class="_ _2"> </span></span>1<span class="ff1">。</span></div><div class="t m0 x3 h14 y52 ff8 fs3 fc0 sc1 ls0 ws0">选择<span class="ff1">如下</span>形<span class="ff1">式的辨识模型</span></div></div><div class="t m0 x7 h8 y11 ff5 fs5 fc0 sc1 ls0 ws0"><span class="fc1 sc1">4</span></div></div><div class="pi" data-data='{"ctm":[1.611850,0.000000,0.000000,1.611850,0.000000,0.000000]}'></div></div>
