本文選題：負(fù)載識(shí)別 + 支持向量機(jī)　； 參考：《杭州電子科技大學(xué)》2017年碩士論文

【摘要】：負(fù)載識(shí)別技術(shù)能夠識(shí)別電網(wǎng)中正在使用的負(fù)載類型,可以應(yīng)用于電力公司對(duì)于電網(wǎng)的監(jiān)管以及提高能源的利用效率,也可以應(yīng)用于某些應(yīng)用場(chǎng)合的電網(wǎng)違禁電器監(jiān)管。對(duì)負(fù)載識(shí)別技術(shù)的研究有著重要意義。論文重點(diǎn)研究基于SVM的負(fù)載識(shí)別技術(shù),主要研究工作有:1、提出基于支持向量機(jī)的負(fù)載識(shí)別方法總體框架,方法包括負(fù)載電流數(shù)據(jù)采集、負(fù)載識(shí)別特征量(用于負(fù)載識(shí)別的電流特征量)提取、特征量數(shù)據(jù)預(yù)處理以及負(fù)載識(shí)別多分類器四個(gè)部分,分為離線訓(xùn)練與在線測(cè)試兩個(gè)流程。2、對(duì)采集的各種負(fù)載電流數(shù)據(jù),通過(guò)對(duì)比負(fù)載電流的時(shí)域和頻域特征,分析各種負(fù)載之間的時(shí)域和頻域特征差異,提出若干用于負(fù)載識(shí)別的負(fù)載電流特征量。3、采用one-against-one組合多個(gè)SVM的方法設(shè)計(jì)負(fù)載識(shí)別多分類器,并針對(duì)不同的懲罰參數(shù)和核參數(shù)對(duì)SVM的分類性能影響較大的問(wèn)題,運(yùn)用遺傳算法結(jié)合K折交叉驗(yàn)證尋找最優(yōu)的SVM懲罰參數(shù)c和核參數(shù)g組合,以此訓(xùn)練出來(lái)的SVM二分類器構(gòu)成用于負(fù)載識(shí)別的SVM多分類器。論文構(gòu)建了負(fù)載識(shí)別多分類器訓(xùn)練樣本集和測(cè)試集,然后對(duì)負(fù)載識(shí)別多分類器進(jìn)行了訓(xùn)練和測(cè)試,訓(xùn)練和測(cè)試實(shí)驗(yàn)分為單負(fù)載以及混合負(fù)載兩組。實(shí)驗(yàn)結(jié)果表明,本文提出的基于SVM的負(fù)載識(shí)別方法具有較好的負(fù)載識(shí)別效果。
[Abstract]:Load identification technology can be used to identify the load types used in the power network, can be applied to power companies to regulate the grid and improve the efficiency of energy use, but also can be used in some applications of the monitoring of prohibited electrical appliances. The research of load identification technology is of great significance. This paper focuses on the load recognition technology based on SVM. The main research work is: 1. The overall framework of load recognition method based on support vector machine (SVM) is proposed, which includes load current data acquisition. The load identification feature (current characteristic used for load identification) extraction, feature data preprocessing and load identification multi-classifier are divided into two parts: offline training and on-line testing. By comparing the time-domain and frequency-domain characteristics of the load current, the differences between the time-domain and frequency-domain characteristics of the load are analyzed, and some load current characteristics. 3, which are used to identify the load, are proposed. The method of combining one-against-one with multiple SVM is used to design the multi-classifier for the load identification. Aiming at the problem that different penalty parameters and kernel parameters have great influence on the classification performance of SVM, genetic algorithm combined with K-fold cross-validation is used to find the optimal combination of SVM penalty parameter c and kernel parameter g. The SVM two classifier which is trained by this method is a SVM multi classifier for load recognition. In this paper, the load identification multi-classifier training sample set and test set are constructed, and then the load identification multi-classifier is trained and tested. The training and testing experiments are divided into two groups: single load and mixed load. Experimental results show that the proposed load recognition method based on SVM has better load recognition effect.
【學(xué)位授予單位】：杭州電子科技大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類號(hào)】：TP18;TM732

【參考文獻(xiàn)】

相關(guān)期刊論文 前1條

1 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

，

本文編號(hào)：2115772