本文選題：礦用變壓器　切入點：油浸式變壓器　出處：《工礦自動化》2017年05期 　論文類型：期刊論文

【摘要】：針對用于礦井中有煤塵而無爆炸危險的地方、以油浸式為主的變壓器,提出了一種基于優(yōu)化模糊Petri網(wǎng)的礦用變壓器故障診斷模型。根據(jù)故障征兆與故障之間的關系,利用模糊產(chǎn)生規(guī)則來建立故障診斷模型;利用Elman網(wǎng)絡算法的自學習和自適應能力對模型初始參數(shù)進行優(yōu)化處理,使模糊Petri網(wǎng)初始參數(shù)值的設置更加合理。Matlab仿真結(jié)果表明,優(yōu)化模型和未優(yōu)化模型的故障診斷準確率分別為87.88%和75.76%,驗證了優(yōu)化模型的有效性。
[Abstract]:A fault diagnosis model of mine transformer based on optimized fuzzy Petri net is proposed for coal dust without explosion hazard. According to the relationship between fault symptom and fault, a fault diagnosis model of mine transformer based on optimized fuzzy Petri net is presented. The fault diagnosis model is established by using fuzzy generation rules, and the initial parameters of the model are optimized by using the self-learning and adaptive ability of the Elman network algorithm. The simulation results show that the setting of the initial parameters of the fuzzy Petri net is more reasonable. The accuracy of fault diagnosis of the optimized model and the unoptimized model are 87.88% and 75.76 respectively, which verify the validity of the optimized model.
【作者單位】： 山東科技大學電氣與自動化工程學院;日照市機電工程學校機電系;
【基金】：中國博士后科學基金資助項目(2015T80729) 青島市博士后研究人員應用研究項目(2015190)
【分類號】：TD611.3

【參考文獻】

相關期刊論文 前10條

1 劉景艷;李玉東;郭順京;;基于Elman神經(jīng)網(wǎng)絡的齒輪箱故障診斷[J];工礦自動化;2016年08期

2 戴晨曦;劉志剛;胡軻s，

本文編號：1574421