化工学报
化工學報
화공학보
JOURNAL OF CHEMICAL INDUSY AND ENGINEERING (CHINA)
2015年
5期
1815-1820
,共6页
李冠男%胡云鹏%陈焕新%黎浩荣%李炅%胡文举
李冠男%鬍雲鵬%陳煥新%黎浩榮%李炅%鬍文舉
리관남%호운붕%진환신%려호영%리경%호문거
冷水机组%过程控制%故障检测%支持向量数据描述%算法%模型简化
冷水機組%過程控製%故障檢測%支持嚮量數據描述%算法%模型簡化
랭수궤조%과정공제%고장검측%지지향량수거묘술%산법%모형간화
chiller%process control%fault detection%support vector data description%algorithm%model reduction
传感器是制冷空调系统的重要组成部分,起着测量数据和监控状态的作用。传感器故障,尤其是输出偏差会引起测量值不准,影响控制策略,导致系统能耗增加。依据模式识别理论,故障检测可处理为一种单分类问题。据此采用一种单分类模式识别工具——支持向量数据描述(SVDD),针对冷水机组进行了偏差故障条件下的传感器故障检测工作。收集冷水机组实测正常运行数据,基于训练集建立SVDD模型,进行冷水机组传感器故障检测;在测试集中引入不同幅值水平的偏差故障,分析检测效率。结果表明:基于SVDD的冷水机组传感器故障检测效果明显,但对于不同传感器的不同幅值偏差故障,故障识别程度并不一致。
傳感器是製冷空調繫統的重要組成部分,起著測量數據和鑑控狀態的作用。傳感器故障,尤其是輸齣偏差會引起測量值不準,影響控製策略,導緻繫統能耗增加。依據模式識彆理論,故障檢測可處理為一種單分類問題。據此採用一種單分類模式識彆工具——支持嚮量數據描述(SVDD),針對冷水機組進行瞭偏差故障條件下的傳感器故障檢測工作。收集冷水機組實測正常運行數據,基于訓練集建立SVDD模型,進行冷水機組傳感器故障檢測;在測試集中引入不同幅值水平的偏差故障,分析檢測效率。結果錶明:基于SVDD的冷水機組傳感器故障檢測效果明顯,但對于不同傳感器的不同幅值偏差故障,故障識彆程度併不一緻。
전감기시제랭공조계통적중요조성부분,기착측량수거화감공상태적작용。전감기고장,우기시수출편차회인기측량치불준,영향공제책략,도치계통능모증가。의거모식식별이론,고장검측가처리위일충단분류문제。거차채용일충단분류모식식별공구——지지향량수거묘술(SVDD),침대랭수궤조진행료편차고장조건하적전감기고장검측공작。수집랭수궤조실측정상운행수거,기우훈련집건립SVDD모형,진행랭수궤조전감기고장검측;재측시집중인입불동폭치수평적편차고장,분석검측효솔。결과표명:기우SVDD적랭수궤조전감기고장검측효과명현,단대우불동전감기적불동폭치편차고장,고장식별정도병불일치。
In the refrigeration and air conditioning system, sensors are independent component for physical data measuring and operating state monitoring. Sensor faults, especially sensor biases output will lead to incorrect measurement, inappropriate controlling strategy and further energy consumption rise. Based on the pattern recognition theory, the fault detection task could be considered as a one-class classification problem. Therefore, a powerful pattern recognition-based one-class classification algorithm, Support Vector Data Description (SVDD) was used to detect the sensor biases occurring in a chiller system. The practical fault-free data were used as training dataset to develop the SVDD model so as to detect the sensor faults. The method and its fault detection efficiency were validated by test dataset with different artificially introduced levels of sensor biases. The SVDD-based fault detection method worked well with chiller practical operating measurements, but the fault detection efficiencies of different sensors with different level faults were inconsistent.