【摘要】：隨著智能水表技術(shù)的發(fā)展,實(shí)時監(jiān)控系統(tǒng)使供水部門可以擁有大量關(guān)于供水管網(wǎng)屬性的數(shù)據(jù)。智能水表包括記錄水量和通信系統(tǒng)兩部分,可以實(shí)時傳輸和儲存用水量數(shù)據(jù)。智能水表已經(jīng)被廣泛應(yīng)用,大多數(shù)城市都具有這樣的設(shè)備,然而智能水表傳送的關(guān)于管網(wǎng)屬性的數(shù)據(jù),水司僅僅用于日常調(diào)度和經(jīng)濟(jì)效益考評,之后這些大量數(shù)據(jù)會被儲存一段時間。智能水表連續(xù)傳送數(shù)據(jù),隨著數(shù)量逐漸增大,水司會因?yàn)閮?nèi)存原因而把這些數(shù)據(jù)刪除,同時刪除的還有這些數(shù)據(jù)所含有的非常有價值的管網(wǎng)信息。隨著數(shù)據(jù)挖掘技術(shù)的發(fā)展,我們有技術(shù)有能力處理分析這些數(shù)據(jù),最大程度地挖掘數(shù)據(jù)所包含信息。分析這些數(shù)據(jù)有助于供水管網(wǎng)革新供水管網(wǎng)管理、計(jì)劃和用戶服務(wù),更加充分利用水資源,保護(hù)水資源。本文根據(jù)DMA分區(qū)流量數(shù)據(jù)特點(diǎn),提出一種聚類方法,即基于DMA分區(qū)用水量曲線距離和形狀的聚類算法(KS),該聚類方法相對經(jīng)典K-means、自主映射(SOM)和模糊C均值而言,更能體現(xiàn)DMA分區(qū)用水量規(guī)律。通過Y市DMA分區(qū)項(xiàng)目中獲得43個DMA分區(qū)的流量數(shù)據(jù),對這43個DMA分區(qū)流量數(shù)據(jù)進(jìn)行數(shù)據(jù)預(yù)處理之后,進(jìn)行聚類分析,比較KS、K-means、SOM和FCM四種聚類算法效果,最終表明KS的聚類效果最好,并且通過分析KS聚類結(jié)果,能夠指導(dǎo)水司檢測異常情況(漏損、偷水)。在對43個DMA分區(qū)流量數(shù)據(jù)處理過程中,通過觀察43個DMA分區(qū)的用水量變化曲線,發(fā)現(xiàn)根據(jù)《給水工程》等教材計(jì)算出的時變化系數(shù),小于大多數(shù)各小時用水量占全天總用水量比例。說明若繼續(xù)采用《給水工程》等教材中的時變化系數(shù)公式,將不能保證如Y市這樣城市的供水安全,建議進(jìn)一步修正時變化系數(shù)公式。
[Abstract]:With the development of intelligent water meter technology, the real-time monitoring system enables the water supply department to have a lot of data about the properties of the water supply network. The intelligent water meter includes two parts: recording water quantity and communication system, which can transmit and store water consumption data in real time. Smart water meters have been widely used, and most cities have such devices. However, the intelligent water meters transmit data about the properties of the pipe network, which are only used by the Water Department for routine operation and economic efficiency evaluation. After that, the bulk of the data will be stored for some time. Intelligent water meters continuously transmit data, and as the number increases, the Water Division removes the data for memory reasons, as well as the valuable pipe network information contained in the data. With the development of data mining technology, we have the ability to process and analyze the data, and to mine the information contained in the data to the maximum extent. The analysis of these data is helpful to the innovation of water supply network management, planning and user service, making better use of water resources and protecting water resources. In this paper, according to the characteristics of DMA traffic data, a clustering algorithm based on the distance and shape of DMA partition water consumption curve is proposed. The clustering method (KS), is relative to classical K-means, autonomous mapping (SOM) and fuzzy C-means. More can reflect the DMA zoning water consumption law. The traffic data of 43 DMA districts were obtained from the DMA sub-area project of Y city. After data preprocessing of 43 DMA partition traffic data, clustering analysis was carried out, and the results of four clustering algorithms, KS,K-means,SOM and FCM, were compared. The result shows that the clustering effect of KS is the best, and by analyzing the clustering results of KS, it can guide the Water Division to detect abnormal conditions (leakage, stealing). In the process of flow data processing in 43 DMA subzones, by observing the variation curves of water consumption in 43 DMA zones, the time-varying coefficients calculated from the teaching materials, such as Water supply Engineering, etc., are found out. Less than most hours of water consumption in the total water consumption of the whole day. It is shown that if the formula of time-varying coefficient in the teaching materials such as Water supply Engineering continues to be used, the safety of water supply in cities such as Y City will not be guaranteed, and it is suggested that the formula of time-varying coefficient should be further revised.
【學(xué)位授予單位】：哈爾濱工業(yè)大學(xué)
【學(xué)位級別】：碩士
【學(xué)位授予年份】：2017
【分類號】：TU991.33

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 周豐;王未央;;基于最小最大模塊化集成特征選擇的改進(jìn)[J];計(jì)算機(jī)技術(shù)與發(fā)展;2016年09期

2 李海林;郭崇慧;;時間序列數(shù)據(jù)挖掘中特征表示與相似性度量研究綜述[J];計(jì)算機(jī)應(yīng)用研究;2013年05期

3 謝福鼎;趙曉慧;嵇敏;平宇;;一種時間序列動態(tài)聚類的算法[J];計(jì)算機(jī)應(yīng)用研究;2012年10期

4 楊通輝;高玲;臧麗;;基于相似性的商品陳列研究[J];微型機(jī)與應(yīng)用;2012年05期

5 張春華;徐衛(wèi);張偉;;數(shù)量關(guān)聯(lián)規(guī)則挖掘及其典型算法分析[J];電腦編程技巧與維護(hù);2012年04期

6 周愛武;崔丹丹;肖云;;一種改進(jìn)的K-means聚類算法[J];微型機(jī)與應(yīng)用;2011年21期

7 陳東寧;崔曉峰;;基于單元格空間的K-Means初始聚類中心選擇算法[J];數(shù)字技術(shù)與應(yīng)用;2011年10期

8 楊照峰;樊愛宛;樊愛京;;改進(jìn)的SOM和K-Means結(jié)合的入侵檢測方法[J];制造業(yè)自動化;2010年15期

9 張玉芳;熊忠陽;耿曉斐;陳劍敏;;Eclat算法的分析及改進(jìn)[J];計(jì)算機(jī)工程;2010年23期

10 錢宏;;數(shù)據(jù)挖掘預(yù)處理技術(shù)的研究[J];電腦知識與技術(shù);2010年17期

相關(guān)博士學(xué)位論文 前3條

1 張滸;時間序列短期預(yù)測模型研究與應(yīng)用[D];華中科技大學(xué);2013年

2 于澝;基于一維SOM神經(jīng)網(wǎng)絡(luò)的聚類及數(shù)據(jù)分析方法研究[D];天津大學(xué);2009年

3 孫玉芬;基于網(wǎng)格方法的聚類算法研究[D];華中科技大學(xué);2006年

相關(guān)碩士學(xué)位論文 前10條

1 王廣;基于改進(jìn)差分進(jìn)化的K均值聚類算法在入侵檢測中的研究[D];北京化工大學(xué);2016年

2 李深洛;基于特征的時間序列聚類[D];廣西師范大學(xué);2014年

3 孫文杰;基于層次的混合聚類算法研究[D];江西理工大學(xué);2013年

4 孟靜;異常數(shù)據(jù)挖掘算法研究與應(yīng)用[D];江南大學(xué);2013年

5 朱曉清;電力負(fù)荷的分類方法及其應(yīng)用[D];華南理工大學(xué);2012年

6 熊尚華;基于半監(jiān)督學(xué)習(xí)的兩種聚類算法研究[D];浙江師范大學(xué);2011年

7 劉長付;數(shù)據(jù)挖掘技術(shù)中的關(guān)聯(lián)規(guī)則挖掘算法研究[D];江西理工大學(xué);2010年

8 李旭濤;基于凝聚模糊K-means的聚類方法研究[D];哈爾濱工業(yè)大學(xué);2009年

9 郭煒星;數(shù)據(jù)挖掘分類算法研究[D];浙江大學(xué);2008年

10 李寧寧;基于粗糙集理論的數(shù)據(jù)挖掘應(yīng)用研究[D];大連理工大學(xué);2007年

，

本文編號：2302258