基于數(shù)據(jù)驅(qū)動的發(fā)電設(shè)備在線預(yù)警研究
黃一楓,茅大鈞
(上海電力學(xué)院 自動化工程學(xué)院,上海 200090)
摘 要:針對發(fā)電設(shè)備故障頻發(fā)的情況,基于現(xiàn)場實時數(shù)據(jù)建立設(shè)備正常的運行狀態(tài)模型并結(jié)合PI實時數(shù)據(jù)庫構(gòu)建了發(fā)電機組及關(guān)鍵設(shè)備的在線預(yù)警系統(tǒng),對所采集的數(shù)據(jù)進行處理、分析、預(yù)測,來判斷設(shè)備的運行狀態(tài)并幫助運行人員確認設(shè)備是否需要檢修。通過電廠實際運用表明,該系統(tǒng)大幅提高了設(shè)備運行的安全水平和效率,降低了運行維護成本。
關(guān)鍵詞:數(shù)據(jù)驅(qū)動;在線預(yù)警;發(fā)電設(shè)備
中圖分類號:TM621.3;TP277 文獻標識碼:A 文章編號:1007-3175(2017)07-0015-05
Research on Online Early Warning of Power Generating Equipment Based on Data Driven
HUANG Yi-feng, MAO Da-jun
(College of Automation Engineering, Shanghai University of Electric Power, Shanghai 200090, China)
Abstract: In allusion to the circumstance of power generating equipment faults taking place frequently, the normal operational state model was established based on the site real-time data, and combined with the PI real-time database, the online early warning system of generator set and key equipment was constructed to carry out disposal, analysis and prediction to judge the equipment operating state and to help the operator determine whether to overhaul the equipment. The practical application of power plant shows that this system drastically improves the safety level and efficiency of equipment operation and reduces the operating maintenance cost.
Key words: data driven; online early warning; power generating equipment
參考文獻
[1] 陳世和. 智能電廠的核心技術(shù)與理念[C]// 國家智能制造論壇,2016.
[2] 張晉賓,周四維,陸星羽. 智能電廠概念、架構(gòu)、功能及實施[J]. 中國儀器儀表,2017(4):33-39.
[3] 鐘陽. 基于數(shù)據(jù)統(tǒng)計分析的變槳系統(tǒng)故障預(yù)警方法[D]. 北京:華北電力大學(xué),2015.
[4] 趙洪山,連莎莎,邵玲. 基于模型的風(fēng)電機組變槳距系統(tǒng)故障檢測[J]. 電網(wǎng)技術(shù),2015,39(2):440-444.
[5] YANG T S, CHEN B, ZHANG H L, et al.State Trend Prediction of Spacecraft Based on BP Neural Network[C]//International Conference on Measurement,2013,2:809-812.
[6] HUANG Y H, ZHOU X X.Knowledge model for electric power big data based on ontology and semantic web[J].CSEE Journal of Power and Energy Systems,2015,1(1):19-27.
[7] ANGELI C, CHATZINIKOLAOU A.On-line fault detection techniques for technical systems:a survey[J].International Journal of Computer Science & Applications,2004,1(1):12-30.
[8] 徐波,韓學(xué)山,李業(yè)勇,等. 電力設(shè)備機會維修決策模型[J]. 中國電機工程學(xué)報,2016,36(23):6379-6388.
[9] 李玉杰. 城郊煤礦機電設(shè)備維修管理現(xiàn)狀分析與提升對策[D]. 南昌:南昌大學(xué),2016.
[10] 富雙進. 電站風(fēng)機故障預(yù)警系統(tǒng)的研究[D]. 保定:華北電力大學(xué),2015.
[11] 王韜. 基于P I 數(shù)據(jù)庫的風(fēng)電場實時監(jiān)控系統(tǒng)應(yīng)用研究[J]. 電氣自動化,2016(6):35-37.
[12] 蔡曉潔,楊小柏.PI 實時數(shù)據(jù)庫在信息化系統(tǒng)中的應(yīng)用[J]. 自動化技術(shù)與應(yīng)用,2016,35(7):161-165.
[13] 郭艷平,顏文俊,包哲靜. 風(fēng)力發(fā)電機組在線故障預(yù)警與診斷一體化系統(tǒng)設(shè)計與應(yīng)用[J]. 電力系統(tǒng)自動化,2010,34(16):83-86.