發(fā)布時(shí)間：2018-03-08 07:42

  本文選題：結(jié)構(gòu)可靠度　切入點(diǎn)：自適應(yīng)　出處：《同濟(jì)大學(xué)學(xué)報(bào)(自然科學(xué)版)》2017年04期 　論文類型：期刊論文

【摘要】：提出了一種Metropolis算法與支持向量機(jī)(SVM)方法相結(jié)合的自適應(yīng)輔助域方法.利用Metropolis算法生成目標(biāo)失效域內(nèi)的條件樣本點(diǎn),并以該過程中的備選點(diǎn)作為初始訓(xùn)練點(diǎn)訓(xùn)練SVM模型.根據(jù)訓(xùn)練得到的SVM模型再自適應(yīng)地選擇一部分樣本點(diǎn)加入訓(xùn)練點(diǎn)集,并對(duì)SVM模型進(jìn)行更新,直至滿足迭代終止條件.以最終得到的SVM模型作為輔助失效域,計(jì)算近似失效概率和兩個(gè)條件失效概率.對(duì)近似失效概率進(jìn)行修正,使最終得到的目標(biāo)失效概率漸進(jìn)無偏且更加穩(wěn)定.算例表明該算法具有較好的計(jì)算精度、效率和魯棒性.
[Abstract]:An adaptive auxiliary domain method combining Metropolis algorithm with support vector machine (SVM) method is proposed. The conditional sample points in the target failure domain are generated by using the Metropolis algorithm. According to the training SVM model, a part of the sample points are selected adaptively to join the training point set, and the SVM model is updated. Until the iterative termination condition is satisfied, the approximate failure probability and the two conditional failure probability are calculated using the final SVM model as the auxiliary failure region, and the approximate failure probability is modified. Finally, the final target failure probability is asymptotically unbiased and more stable. An example shows that the algorithm has good accuracy, efficiency and robustness.
【作者單位】： 同濟(jì)大學(xué)土木工程學(xué)院;
【基金】：國(guó)家自然科學(xué)基金(51261120374)
【分類號(hào)】：TB114.3

【相似文獻(xiàn)】

相關(guān)期刊論文 前2條

1 歐陽培昌;;基礎(chǔ)域方法生成三維彩色對(duì)稱偽球[J];井岡山學(xué)院學(xué)報(bào)(自然科學(xué)版);2007年02期

2 ;[J];;年期

相關(guān)會(huì)議論文 前1條

1 劉新國(guó);;梯度域的幾何編輯方法[A];第四屆全國(guó)幾何設(shè)計(jì)與計(jì)算學(xué)術(shù)會(huì)議論文集[C];2009年

，

本文編號(hào)：1582986