【摘要】：變形監(jiān)測(cè)是采集變形體的變形信息的技術(shù)方法，對(duì)變形信息進(jìn)行處理分析是變形監(jiān)測(cè)的最終目的。變形數(shù)據(jù)的預(yù)處理可以有效地去除數(shù)據(jù)中的誤差，有利于下一步的變形分析和預(yù)報(bào)結(jié)果精度的提高。由于變形體的變形具有非線性、模糊性和不確定性等特點(diǎn)，變形預(yù)測(cè)的傳統(tǒng)精確數(shù)學(xué)模型結(jié)果與實(shí)際情況相差較大。 支持向量機(jī)是由Vapnik等人于上世紀(jì)90年代基于統(tǒng)計(jì)學(xué)習(xí)理論提出的新的機(jī)器學(xué)習(xí)方法。它能夠?qū)で笥邢迾颖緮?shù)據(jù)的最優(yōu)解，并且比經(jīng)驗(yàn)風(fēng)險(xiǎn)原理的神經(jīng)網(wǎng)絡(luò)學(xué)習(xí)算法具有更強(qiáng)的理論依據(jù)和更好的泛化性能。支持向量機(jī)預(yù)測(cè)模型的參數(shù)決定了樣本訓(xùn)練誤差和對(duì)預(yù)測(cè)樣本的推廣性，然而目前尚沒有完備的理論和方法解決這一問題，只能通過實(shí)例仿真以及算法優(yōu)化。果蠅優(yōu)化算法是根據(jù)果蠅尋覓食物的特性，嗅覺記憶與視覺記憶協(xié)同作用下表現(xiàn)出來(lái)的群智能。它對(duì)于參數(shù)的優(yōu)化選擇有著很好的效果，能夠做到全局尋優(yōu)。 本文首先利用集成經(jīng)驗(yàn)?zāi)B(tài)分解方法分離出變形數(shù)據(jù)中的高頻噪聲信號(hào)，并針對(duì)高頻噪聲也含有有用信號(hào)的問題，，對(duì)其進(jìn)行閾值量化處理，保留噪聲中所含有用信號(hào)，完成變形數(shù)據(jù)預(yù)處理工作。然后針對(duì)支持向量機(jī)參數(shù)的選擇這一開放性問題，也是實(shí)際應(yīng)用支持向量機(jī)預(yù)測(cè)模型成功的關(guān)鍵問題，利用果蠅算法進(jìn)行優(yōu)化選擇，結(jié)合工程實(shí)例，證明果蠅優(yōu)化算法簡(jiǎn)化了支持向量機(jī)參數(shù)選擇，避免了實(shí)際工程支持向量機(jī)預(yù)測(cè)應(yīng)用中超參數(shù)選擇的盲目性。
[Abstract]:Deformation monitoring is a technical method for collecting deformation information of deformable bodies. Processing and analysis of deformation information is the ultimate purpose of deformation monitoring. The preprocessing of deformation data can effectively remove the errors in the data, and it is helpful to improve the accuracy of deformation analysis and prediction results in the next step. Because the deformation of deformable body is nonlinear, fuzzy and uncertain, the results of traditional accurate mathematical model for deformation prediction are quite different from the actual situation. Support vector machine (SVM) is a new machine learning method proposed by Vapnik et al in 1990s based on statistical learning theory. It can find the optimal solution of the finite sample data and has stronger theoretical basis and better generalization performance than the neural network learning algorithm based on empirical risk principle. The parameters of support vector machine (SVM) prediction model determine the sample training error and the generalization of prediction samples. However, there is no complete theory and method to solve this problem, which can only be solved by example simulation and algorithm optimization. Drosophila optimization algorithm is based on the characteristics of searching for food, olfactory memory and visual memory under the synergistic action of swarm intelligence. It has a good effect on the optimization of parameters, and can achieve global optimization. In this paper, the high frequency noise signals in the deformation data are separated by the method of integrated empirical mode decomposition. To solve the problem that the high frequency noise also contains useful signals, the threshold quantization is carried out to retain the signals contained in the noise. Finish the preprocessing of deformation data. Then, aiming at the open problem of parameter selection of support vector machine, which is also the key problem in practical application of support vector machine prediction model, we use Drosophila algorithm to optimize selection, and combine with engineering example. It is proved that the optimization algorithm of Drosophila simplifies the parameter selection of support vector machine and avoids the blindness of super-parameter selection in the application of practical engineering support vector machine prediction.
【學(xué)位授予單位】：遼寧工程技術(shù)大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2013
【分類號(hào)】：TP18;P22

【參考文獻(xiàn)】

相關(guān)期刊論文 前8條

1 趙國(guó)忱;蘇運(yùn)強(qiáng);范良;;獨(dú)立分量分析在煤倉(cāng)沉降分析中的應(yīng)用[J];測(cè)繪通報(bào);2012年06期

2 范良;趙國(guó)忱;蘇運(yùn)強(qiáng);;果蠅算法優(yōu)化的廣義回歸神經(jīng)網(wǎng)絡(luò)在變形監(jiān)測(cè)預(yù)報(bào)中的應(yīng)用[J];測(cè)繪通報(bào);2013年11期

3 呂建新;吳虎勝;田杰;;EEMD的非平穩(wěn)信號(hào)降噪及其故障診斷應(yīng)用[J];計(jì)算機(jī)工程與應(yīng)用;2011年28期

4 張學(xué)工;關(guān)于統(tǒng)計(jì)學(xué)習(xí)理論與支持向量機(jī)[J];自動(dòng)化學(xué)報(bào);2000年01期

5 肖正安;;基于果蠅優(yōu)化算法的模擬濾波器設(shè)計(jì)[J];湖北第二師范學(xué)院學(xué)報(bào);2012年02期

6 許智慧;王福林;孫丹丹;王吉權(quán);;基于FOA-RBF神經(jīng)網(wǎng)絡(luò)的外貿(mào)出口預(yù)測(cè)[J];數(shù)學(xué)的實(shí)踐與認(rèn)識(shí);2012年13期

7 潘文超;;應(yīng)用果蠅優(yōu)化算法優(yōu)化廣義回歸神經(jīng)網(wǎng)絡(luò)進(jìn)行企業(yè)經(jīng)營(yíng)績(jī)效評(píng)估[J];太原理工大學(xué)學(xué)報(bào)(社會(huì)科學(xué)版);2011年04期

8 榮海娜;張葛祥;金煒東;;系統(tǒng)辨識(shí)中支持向量機(jī)核函數(shù)及其參數(shù)的研究[J];系統(tǒng)仿真學(xué)報(bào);2006年11期

本文編號(hào)：2416772