中国电机工程学报
中國電機工程學報
중국전궤공정학보
ZHONGGUO DIANJI GONGCHENG XUEBAO
2011年
32期
129-136
,共8页
郭鹏%David Infield%杨锡运
郭鵬%David Infield%楊錫運
곽붕%David Infield%양석운
状态监测%齿轮箱%非线性状态估计%残差%滑动窗口统计
狀態鑑測%齒輪箱%非線性狀態估計%殘差%滑動窗口統計
상태감측%치륜상%비선성상태고계%잔차%활동창구통계
condition monitoring%gearbox%nonlinear state estimate technique(NSET)%residual%moving window statistic
风电机组状态监测对于风电场特别是海上风电场降低维护成本,提高运行水平具有重要的实用价值。采用温度趋势分析的方法对风电机组齿轮箱的运行状态进行监测。利用非线性状态估计(nonlinear state estimate technology,NSET)方法建立齿轮箱正常工作状态下的温度模型并用其进行温度预测。通过合理构造过程记忆矩阵,使模型覆盖齿轮箱的正常工作空间。当齿轮箱工作异常时,其动态特性偏离正常工作空间,NSET温度模型预测残差的分布特性发生改变。采用滑动窗口方法实时计算残差的统计分布特性,当残差的均值或标准差的置信区间超出预先设定的阈值时,发出报警信息,提示运行人员检查设备状态。为模拟齿轮箱的故障情况,在机组数据采集与监视控制系统(supervisory control anddata acquisition,SCADA)数据中加入人为温度偏移。通过对该模拟故障的分析,新的状态监测方法能够及时发现齿轮箱的异常状态,达到实时在线状态监测的目的。
風電機組狀態鑑測對于風電場特彆是海上風電場降低維護成本,提高運行水平具有重要的實用價值。採用溫度趨勢分析的方法對風電機組齒輪箱的運行狀態進行鑑測。利用非線性狀態估計(nonlinear state estimate technology,NSET)方法建立齒輪箱正常工作狀態下的溫度模型併用其進行溫度預測。通過閤理構造過程記憶矩陣,使模型覆蓋齒輪箱的正常工作空間。噹齒輪箱工作異常時,其動態特性偏離正常工作空間,NSET溫度模型預測殘差的分佈特性髮生改變。採用滑動窗口方法實時計算殘差的統計分佈特性,噹殘差的均值或標準差的置信區間超齣預先設定的閾值時,髮齣報警信息,提示運行人員檢查設備狀態。為模擬齒輪箱的故障情況,在機組數據採集與鑑視控製繫統(supervisory control anddata acquisition,SCADA)數據中加入人為溫度偏移。通過對該模擬故障的分析,新的狀態鑑測方法能夠及時髮現齒輪箱的異常狀態,達到實時在線狀態鑑測的目的。
풍전궤조상태감측대우풍전장특별시해상풍전장강저유호성본,제고운행수평구유중요적실용개치。채용온도추세분석적방법대풍전궤조치륜상적운행상태진행감측。이용비선성상태고계(nonlinear state estimate technology,NSET)방법건립치륜상정상공작상태하적온도모형병용기진행온도예측。통과합리구조과정기억구진,사모형복개치륜상적정상공작공간。당치륜상공작이상시,기동태특성편리정상공작공간,NSET온도모형예측잔차적분포특성발생개변。채용활동창구방법실시계산잔차적통계분포특성,당잔차적균치혹표준차적치신구간초출예선설정적역치시,발출보경신식,제시운행인원검사설비상태。위모의치륜상적고장정황,재궤조수거채집여감시공제계통(supervisory control anddata acquisition,SCADA)수거중가입인위온도편이。통과대해모의고장적분석,신적상태감측방법능구급시발현치륜상적이상상태,체도실시재선상태감측적목적。
Condition monitoring(CM) of wind turbine can greatly reduce the maintenance cost for wind farm especially offshore wind farm.A new condition monitoring method using temperature trend analysis for a wind turbine gearbox was proposed.Nonlinear state estimate technique(NSET) was used to construct the normal behavior model of the gearbox temperature.With a proper construction of memory matrix,the NSET model can cover the normal working space for the gearbox.When the gearbox has an incipient failure,the residuals between NSET model estimates and the measurement temperature will become significant.A moving window statistical method was used to detect the changes of the residual mean value and standard deviation in a timely manner.When one of these parameters exceeds predefined thresholds,an incipient failure was flagged.In order to simulate the gearbox fault,manual temperature drift was added to the initial SCADA data.Analysis of the simulating gearbox fault shows that the new condition monitoring is effective.