發(fā)布時(shí)間：2018-04-01 14:27

  本文選題：決策樹算法　切入點(diǎn)：故障診斷　出處：《制冷學(xué)報(bào)》2017年05期

【摘要】：本文將決策樹算法應(yīng)用于多聯(lián)機(jī)氣分插反故障診斷中,搭建了多聯(lián)機(jī)實(shí)驗(yàn)平臺(tái)采集數(shù)據(jù),根據(jù)專家知識(shí)及數(shù)據(jù)變化模型驗(yàn)證選取了建模的特征變量,采用決策樹C5.0算法構(gòu)建氣分插反故障診斷模型,進(jìn)一步對(duì)由模型分類規(guī)則生成的最優(yōu)變量即過冷器的EEV(電子膨脹閥)進(jìn)行深入分析和驗(yàn)證。結(jié)果表明:將決策樹算法應(yīng)用于多聯(lián)機(jī)氣分插反故障診斷的方法,準(zhǔn)確率為96%,此診斷方法能滿足多聯(lián)機(jī)故障診斷實(shí)際運(yùn)用的需要,并可及時(shí)處理多聯(lián)機(jī)發(fā)生氣分插反故障時(shí),系統(tǒng)過熱度降低,從而保證多聯(lián)機(jī)系統(tǒng)的制冷效果和能效比,可通過增大過冷器EEV開度調(diào)節(jié)。
[Abstract]:In this paper, the decision tree algorithm is applied to the multi-on-line gas division inverse fault diagnosis, a multi-on-line experimental platform is set up to collect data, and the characteristic variables of the model are selected according to the expert knowledge and the data change model. The decision tree C5.0 algorithm is used to construct the gas division interpolation reverse fault diagnosis model. Furthermore, the EEV (electronic expansion valve) of the supercooler, the optimal variable generated by the model classification rule, is analyzed and verified in depth. The results show that the decision tree algorithm is applied to the fault diagnosis method of multi-on-line gas division interpolation. The accuracy is 96. This diagnosis method can meet the needs of the practical application of multi-on-line fault diagnosis, and can deal with the multi-on-line gas division back fault in time, the system superheat is reduced, so as to ensure the refrigeration effect and energy efficiency ratio of the multi-on-line system. It can be adjusted by increasing the EEV opening of the supercooler.
【作者單位】： 華中科技大學(xué)能源與動(dòng)力工程學(xué)院;珠海格力電器有限公司;北京建筑大學(xué)供熱供燃?xì)馔L(fēng)及空調(diào)工程北京市重點(diǎn)實(shí)驗(yàn)室;合肥通用機(jī)械研究院壓縮機(jī)技術(shù)國(guó)家重點(diǎn)實(shí)驗(yàn)室;
【基金】：國(guó)家自然科學(xué)基金(51576074&51328602) 2013年壓縮機(jī)技術(shù)國(guó)家重點(diǎn)實(shí)驗(yàn)室開放基金(0214120035)資助項(xiàng)目 供熱供燃?xì)馔L(fēng)及空調(diào)工程北京市重點(diǎn)實(shí)驗(yàn)室研究基金課題(NR2013K02)項(xiàng)目資助~~
【分類號(hào)】：TB657.2

【相似文獻(xiàn)】

相關(guān)期刊論文 前10條

1 張革俠;王文興;徐琪;;決策樹算法及其在數(shù)據(jù)分析中的應(yīng)用[J];機(jī)械工業(yè)信息與網(wǎng)絡(luò);2007年06期

2 畢朋峰;;遙感監(jiān)督分類的決策樹算法研究[J];電子制作;2012年12期

3 史澤鵬;馬中文;馬友華;王強(qiáng);於忠祥;;基于J48決策樹算法的遙感土地利用變化分析[J];遙感信息;2014年01期

4 小野┮煥，

本文編號(hào)：1695983