【摘要】：伴隨國家經(jīng)濟(jì)的持續(xù)增長和城市建設(shè)的不斷推進(jìn),城市照明系統(tǒng)的規(guī)模和復(fù)雜度逐年上升。與之對應(yīng)的,系統(tǒng)提供的服務(wù)質(zhì)量直接影響著越來越多的行人和車輛安全。保持城市照明系統(tǒng)良好的服務(wù)一方面需要及時對系統(tǒng)故障做出診斷,另一方面還需要預(yù)判未來可能發(fā)生的故障從而安排合理的維護(hù)和檢修策略。傳統(tǒng)的城市照明系統(tǒng)故障診斷方法主要針對設(shè)備電氣特征,需要專業(yè)人士參與,而在系統(tǒng)維護(hù)和檢修方面缺乏對故障的準(zhǔn)確預(yù)測,更多地依賴盲目的隨機(jī)巡檢過程。智能城市照明監(jiān)控系統(tǒng)的出現(xiàn)雖然能一定程度上通過監(jiān)控運行數(shù)據(jù)診斷現(xiàn)象型的故障,但缺乏對故障和運行數(shù)據(jù)之間關(guān)聯(lián)性的分析,也沒有提供故障預(yù)測的能力�；谶@樣的研究現(xiàn)狀,論文在四川省科技支撐計劃項目“城市綠色照明節(jié)能系統(tǒng)關(guān)鍵技術(shù)研究和應(yīng)用示范(七大戰(zhàn)略新興)”(項目編號:2016GZ0312)支持下,歸納總結(jié)了城市照明系統(tǒng)的組成和故障成因,分別對系統(tǒng)中的路燈節(jié)點的故障診斷問題和區(qū)域配電系統(tǒng)中的故障預(yù)測問題設(shè)計了相應(yīng)的分析模型,以期達(dá)到高效快速部署和節(jié)約資源的目的。論文的核心工作如下:首先,論文分析了城市照明系統(tǒng)中路燈節(jié)點故障診斷所面臨的大范圍部署問題,并針對快速響應(yīng)和少人工參與的需求使用極限學(xué)習(xí)機(jī)對該問題進(jìn)行了抽象建模。通過分析不同結(jié)構(gòu)的極限學(xué)習(xí)機(jī)的近似逼近能力,結(jié)合增量學(xué)習(xí)過程設(shè)計了具備自適應(yīng)參數(shù)搜索過程的路燈節(jié)點故障診斷模型。其次,論文分析了城市照明系統(tǒng)中通過區(qū)域配電系統(tǒng)運行數(shù)據(jù)和外部數(shù)據(jù)構(gòu)建故障預(yù)測模型的需求,并對預(yù)測模型進(jìn)行了數(shù)學(xué)建模。通過結(jié)合極限學(xué)習(xí)機(jī)、自回歸模型和帶衰減的滑動窗口這三類方法,論文實現(xiàn)了能夠利用實時產(chǎn)生的數(shù)據(jù)進(jìn)行在線學(xué)習(xí)過程的故障預(yù)測模型。最后,論文使用宜賓市城市照明系統(tǒng)運行數(shù)據(jù)對路燈故障診斷模型和區(qū)域配電系統(tǒng)預(yù)測模型進(jìn)行了驗證,并通過引入外部數(shù)據(jù)說明了模型對輸入屬性的擴(kuò)展性。此外,論文還基于所提模型設(shè)計并實現(xiàn)了城市照明智能故障診斷與預(yù)測系統(tǒng)。實驗驗證和系統(tǒng)實現(xiàn)的結(jié)果表明論文所提的兩類模型分別在路燈故障診斷和區(qū)域配電系統(tǒng)故障預(yù)測方面具有較高的分類和預(yù)測準(zhǔn)確率,實現(xiàn)了論文的研究內(nèi)容。
[Abstract]:With the continuous growth of national economy and the development of urban construction, the scale and complexity of urban lighting system are increasing year by year. Correspondingly, the quality of service provided by the system directly affects the safety of more and more pedestrians and vehicles. On the one hand, it is necessary to diagnose the system faults in time, on the other hand, it is necessary to predict the possible future failures and arrange reasonable maintenance and repair strategies. The traditional fault diagnosis method of urban lighting system is mainly aimed at the electrical characteristics of equipment and requires the participation of professionals. However, it lacks accurate prediction of fault in system maintenance and maintenance, and relies more on blind random inspection process. Although the appearance of intelligent city lighting monitoring system can diagnose phenomenal faults through monitoring operation data to some extent, it lacks the ability to analyze the correlation between failure and operation data and to provide fault prediction. Based on this research status, the paper is supported by Sichuan Science and Technology support Project "key Technology Research and Application demonstration of Urban Green Lighting Energy-saving system (Seven Strategies emerging)" (Project number: 2016GZ0312). The composition and causes of failure of urban lighting system are summarized and the corresponding analysis models are designed for the fault diagnosis problem of street lamp node and fault prediction problem in regional distribution system. In order to achieve efficient and rapid deployment and save resources. The core work of the thesis is as follows: firstly, the thesis analyzes the problem of the large-scale deployment of the street lamp node fault diagnosis in the urban lighting system. Aiming at the requirement of quick response and less human participation, the paper uses extreme learning machine to model the problem abstractly. By analyzing the approximate approximation ability of LLMs with different structures and combining the incremental learning process, a fault diagnosis model of street lamp nodes with adaptive parameter search process is designed. Secondly, the paper analyzes the requirement of constructing fault prediction model through the operation data and external data of regional distribution system in the urban lighting system, and carries on the mathematical modeling to the prediction model. By combining the three methods of extreme learning machine, autoregressive model and sliding window with attenuation, a fault prediction model which can make use of the data generated in real time for online learning process is implemented in this paper. Finally, the paper validates the street lamp fault diagnosis model and the regional distribution system prediction model by using the operation data of Yibin city lighting system, and explains the extensibility of the model to the input attributes by introducing external data. In addition, the intelligent fault diagnosis and prediction system of urban lighting is designed and implemented based on the proposed model. The results of experimental verification and system implementation show that the two kinds of models proposed in this paper have high classification and prediction accuracy in street lamp fault diagnosis and regional distribution system fault prediction respectively.
【學(xué)位授予單位】：電子科技大學(xué)
【學(xué)位級別】：碩士
【學(xué)位授予年份】：2017
【分類號】：TP277;TU113.666

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 劉國慶;史小春;廖強;;基于神經(jīng)網(wǎng)絡(luò)分類算法的電機(jī)軸承故障檢測方法[J];微特電機(jī);2017年01期

2 陳維興;曲睿;孫毅剛;;基于改進(jìn)Apriori算法的地面空調(diào)間歇故障預(yù)測[J];計算機(jī)應(yīng)用;2016年12期

3 汪思成;肖林;嚴(yán)慧玲;;基于不同誤差函數(shù)的神經(jīng)網(wǎng)絡(luò)求解線性方程組[J];吉首大學(xué)學(xué)報(自然科學(xué)版);2016年06期

4 趙虎;;基于極限學(xué)習(xí)機(jī)的故障診斷方法研究綜述[J];中國新通信;2016年17期

5 李蔚;俞蕓蘿;盛德仁;陳堅紅;;基于動態(tài)數(shù)據(jù)挖掘的熱力參數(shù)傳感器故障診斷[J];振動.測試與診斷;2016年04期

6 張雨濃;肖爭利;丁思彤;毛明志;劉錦榮;;帶后續(xù)迭代的雙極S函數(shù)激勵的WASD神經(jīng)網(wǎng)絡(luò)[J];中山大學(xué)學(xué)報(自然科學(xué)版);2016年04期

7 李海林;郭崇慧;楊麗彬;;基于時間序列數(shù)據(jù)挖掘的故障檢測方法[J];數(shù)據(jù)采集與處理;2016年04期

8 曾曉勤;周建新;鄭星;鐘水明;;一種高效二進(jìn)前饋神經(jīng)網(wǎng)絡(luò)學(xué)習(xí)算法[J];哈爾濱工業(yè)大學(xué)學(xué)報;2016年05期

9 邊新光;陳俊銘;朱小英;李德山;王芳;;關(guān)于路燈故障檢測系統(tǒng)的設(shè)計[J];山西電子技術(shù);2016年01期

10 董勇;蔣艷凰;盧宇彤;周恩強;;面向磁盤故障預(yù)測的機(jī)器學(xué)習(xí)方法比較[J];計算機(jī)工程與科學(xué);2015年12期

相關(guān)會議論文 前1條

1 陳乃剛;王家瑋;鄭貴德;許彥冰;;基于大數(shù)據(jù)技術(shù)的智慧城市照明節(jié)能研究[A];2014電力行業(yè)信息化年會論文集[C];2014年

相關(guān)博士學(xué)位論文 前2條

1 尚華;兩類時間序列模型的異常值檢測研究[D];首都經(jīng)濟(jì)貿(mào)易大學(xué);2016年

2 范玉剛;基于Kernel的機(jī)器學(xué)習(xí)在建模與分類問題的應(yīng)用研究[D];浙江大學(xué);2006年

相關(guān)碩士學(xué)位論文 前6條

1 翟增輝;基于近域去重法改進(jìn)的BP神經(jīng)網(wǎng)絡(luò)算法[D];安徽大學(xué);2016年

2 劉靜雅;基于極限學(xué)習(xí)機(jī)的航空發(fā)動機(jī)傳感器故障診斷研究[D];中國民航大學(xué);2015年

3 陳建華;基于機(jī)器學(xué)習(xí)的銀行設(shè)備故障告警系統(tǒng)的設(shè)計[D];北京郵電大學(xué);2015年

4 周浩;基于機(jī)器學(xué)習(xí)的E級系統(tǒng)故障預(yù)測關(guān)鍵技術(shù)研究[D];國防科學(xué)技術(shù)大學(xué);2011年

5 李yN;城市照明遠(yuǎn)程監(jiān)控系統(tǒng)的開發(fā)及應(yīng)用[D];鄭州大學(xué);2009年

6 王飛;路燈遠(yuǎn)程監(jiān)控診斷系統(tǒng)的研究開發(fā)[D];南京理工大學(xué);2004年

，

本文編號：2294339