本文選題：穩(wěn)態(tài)檢測 + SSD算法�。� 參考：《華北電力大學(北京)》2017年碩士論文

【摘要】：穩(wěn)態(tài)檢測對熱工過程中評價設(shè)備的性能優(yōu)異、系統(tǒng)過程建模及優(yōu)化、故障檢測機制建立及過程辨識等均體現(xiàn)出非常重要的意義。在熱電廠海量歷史數(shù)據(jù)預(yù)處理過程當中,只有穩(wěn)態(tài)工況下的數(shù)據(jù)才能真實客觀的反映出系統(tǒng),并且在以后的系統(tǒng)建模及辨識中都要獲得穩(wěn)態(tài)工況,所以將穩(wěn)態(tài)工況下變量的數(shù)據(jù)從海量數(shù)據(jù)庫中挑選出來非常重要。SSD(Steady State Detection)算法作為一種有效的穩(wěn)態(tài)檢測算法得到了廣泛的應(yīng)用,將SSD算法與數(shù)據(jù)濾波相結(jié)合,可以顯著提高監(jiān)測點穩(wěn)態(tài)狀況判斷的準確度。將EWMA(Exponentially Weighted Moving Average,EWMA)濾波與SSD算法結(jié)合,形成EWMA-SSD方法,作為本文的研究對象進行分析研究。本文首先分析了SSD算法和EWMA濾波進行穩(wěn)態(tài)檢測的機制,推導(dǎo)出SSD算法中的窗寬n和EWMA的濾波因子?之間存在的等價關(guān)系。考慮到實際工況中監(jiān)測數(shù)據(jù)分布具有不確定性,在SSD算法的基礎(chǔ)上,對算法在控制限的求取和監(jiān)控指標方面做出了改進。采用基于核函數(shù)的非參數(shù)控制限算法,用核函數(shù)擬合出監(jiān)控指標的概率密度函數(shù),然后計算出該概率密度函數(shù)下滿足檢驗水平α的控制限,并結(jié)合EWMA濾波對監(jiān)控指標進行改進后,對過程數(shù)據(jù)進行穩(wěn)態(tài)檢測。最后將SSD穩(wěn)態(tài)檢測法應(yīng)用到實際過程當中,本文以某火電廠600MW機組1年的歷史數(shù)據(jù)進行穩(wěn)態(tài)檢測,改進后的SSD算法相比較傳統(tǒng)而言,穩(wěn)態(tài)檢出率顯著提高。從而驗證了方法的有效性。最后將多變量穩(wěn)態(tài)檢測后的相近負荷下的穩(wěn)態(tài)數(shù)據(jù)段篩選出來,對涉及的變量兩兩組合后進行聚類分析,發(fā)現(xiàn)在負荷相近下穩(wěn)態(tài)工況可以劃分,對不同的工況下運行的狀態(tài)及經(jīng)濟性分析和進階的優(yōu)化性運行進行分析后,發(fā)現(xiàn)不同聚類群的鍋爐效率存在明顯差異,為后續(xù)針對這種差異所做的研究工作提供了基礎(chǔ)。
[Abstract]:Steady-state detection is very important for evaluating the performance of the equipment in thermal process, modeling and optimizing the system process, establishing the fault detection mechanism and identifying the process. In the preprocessing process of massive historical data in thermal power plant, only the data under steady condition can reflect the system objectively and realistically, and the steady state condition should be obtained in the later modeling and identification of the system. Therefore, it is very important to select the data of variables under steady condition from the massive database. The algorithm is widely used as an effective steady-state detection algorithm. The SSD algorithm is combined with the data filtering. The accuracy of judging the steady state of monitoring points can be improved significantly. The EWMA-SSD method is formed by combining the EWMA(Exponentially Weighted Moving average EWMA(Exponentially Weighted Moving filtering with the SSD algorithm, and it is analyzed and studied as the research object of this paper. In this paper, the mechanism of steady-state detection based on SSD algorithm and EWMA filter is analyzed, and the window width n and the filter factor of EWMA in SSD algorithm are deduced. The equivalent relation that exists between. Considering the uncertainty of the monitoring data distribution in the actual working conditions, based on the SSD algorithm, an improvement is made in the calculation of the control limit and the monitoring index. The nonparametric control limit algorithm based on kernel function is used to fit the probability density function of the monitoring index, and then the control limit satisfying the test level 偽 is calculated under the probability density function. After improving the monitoring index with EWMA filter, the steady state detection of the process data is carried out. Finally, the SSD steady-state detection method is applied to the practical process. The steady-state detection rate of the improved SSD algorithm is significantly higher than that of the traditional one year history data of the 600MW unit in a thermal power plant. The validity of the method is verified. Finally, the steady-state data segment under the similar load after multivariable steady-state detection is screened out, and the cluster analysis is carried out after the combination of the two variables involved, and it is found that the steady-state working condition can be divided under the similar load. After analyzing the state and economy of operation under different operating conditions and the advanced optimal operation, it is found that there are obvious differences in boiler efficiency among different cluster groups, which provides a basis for further research on this difference.
【學位授予單位】：華北電力大學(北京)
【學位級別】：碩士
【學位授予年份】：2017
【分類號】：TM621

【參考文獻】

相關(guān)期刊論文 前10條

1 高萌;劉吉臻;王瑞琪;張恒;張軒;;基于自適應(yīng)高斯濾波的電站歷史數(shù)據(jù)穩(wěn)態(tài)檢測方法[J];動力工程學報;2014年09期

2 王春雷;梁小放;章堅民;張遠揚;;基于用電采集系統(tǒng)的負荷特性曲線聚類分析[J];浙江電力;2014年07期

3 黃毅成;楊洪耕;;改進遺傳K均值算法在負荷特性分類的應(yīng)用[J];電力系統(tǒng)及其自動化學報;2014年07期

4 江麗麗;;淺析教學雙向評價系統(tǒng)中的數(shù)據(jù)挖掘技術(shù)[J];山東工業(yè)技術(shù);2013年10期

5 陳文馳;劉飛;;一種改進的基于多項式濾波的穩(wěn)態(tài)檢測方法[J];控制工程;2012年02期

6 呂游;劉吉臻;趙文杰;楊婷婷;;基于分段曲線擬合的穩(wěn)態(tài)檢測方法[J];儀器儀表學報;2012年01期

7 郭華新;高明;;基于數(shù)據(jù)挖掘的煤質(zhì)特性與電廠輔機能耗的關(guān)聯(lián)分析[J];科技信息;2012年02期

8 李小榮;;數(shù)據(jù)挖掘在企業(yè)歷史數(shù)據(jù)中的應(yīng)用[J];中國管理信息化;2011年02期

9 苑一方;孫建平;;基于電廠工況劃分的雙層聚類算法研究[J];電力科學與工程;2010年09期

10 苑一方;孫建平;田婧;;改進K均值聚類算法在電廠工況劃分中的實現(xiàn)[J];儀器儀表用戶;2010年04期

相關(guān)碩士學位論文 前10條

1 劉文楠;數(shù)據(jù)挖掘在稅收分析中的應(yīng)用研究[D];財政部財政科學研究所;2014年

2 楊曉東;河津發(fā)電廠入爐煤質(zhì)調(diào)整與控制[D];西安工業(yè)大學;2014年

3 譚斌;基于服務(wù)的數(shù)據(jù)挖掘關(guān)聯(lián)規(guī)則技術(shù)的研究[D];湖北工業(yè)大學;2012年

4 苑一方;基于SIS數(shù)據(jù)的過熱汽溫模型參數(shù)的辨識[D];華北電力大學;2011年

5 楊新愛;數(shù)據(jù)挖掘技術(shù)在高校教學評估中的應(yīng)用[D];電子科技大學;2010年

6 毛靈;火電廠實時運行績效管理系統(tǒng)分析與設(shè)計[D];中國電力科學研究院;2010年

7 聶慧明;聯(lián)合循環(huán)機組仿真系統(tǒng)設(shè)計與實現(xiàn)[D];上海交通大學;2009年

8 翟少磊;基于數(shù)據(jù)挖掘的工況分析技術(shù)的研究[D];華北電力大學（北京）;2009年

9 李雪云;數(shù)據(jù)挖掘技術(shù)在火力發(fā)電廠中的應(yīng)用研究[D];華東師范大學;2008年

10 陸怡;電子商務(wù)應(yīng)用系統(tǒng)的設(shè)計與實現(xiàn)[D];南京理工大學;2008年

，

本文編號：1880736