Vol.21 No.3 张惠浩等：三相异步电动机定子绕组温度在线监测 ·297· 通过对数据的分析与讨论，可知温度预测的最 稳态的时间也相应改变 大相对误差为一1.18%，对于温度预测而言，这 参考文献 样的误差是允许的.另外，热电偶存在较大的热 1 Umanand L,Bhat S R.On Line Estimation of Stator Resis 惯性，因此热电偶测温也存在一定的误差，综上 tance of an Induction Motor for Speed Control Applica- 所述，可以认为，过程辨识理论用于温度预测是 tions.IEE ProcElectr Power Appl,1995,142(2):97 比较准确的. 2孟传富，钱庆镳.机电能量转换.北京：机械工业出 从温度随时间变化曲线(t一t曲线)可知，在 版社，1993.36 负载和环境条件改变时，电机的热平衡状态、电 3沈标正.电机故障诊断技术.北京：机械工业出版社， 1996.396 机温度上升速率、热稳定温度，以及电机到达热 On-Line Monitoring the Temperature of Stator Windings of Three-phase Induction Motors Zhang Huihao,Wang Shaochun Information Engineering School,UST Beijing,Beijing 100083,China ABSTRACT Based on the theory of process identification,according to the mathematical model of three- phase induction motors in aBcoordinate,the mathmatical model of the temperature forecast of the stator windings is developed.Based on 80C552 single-chip micro-processor,the hardware and software system of on-line monitoring the temperature of the stator windings of three-phase induction motors are designed. The experiments verify the correctness and feasibility of this method. KEY WORDS induction motors the temperature of the stator windings;on-line monitoring 米米米米米米米米米米米米米米米米米米米米米米米米米米米米米米米米米米米米米米米米米米米米 [Journal of University of Science and Technoloy Beijing(English Edition),1999,6(1):24] Prediction of Enthalpies of Fusion for Divalent Rara Earth Halides Based on Modeling by Artificial Neural Networks and Pattern Recognition Yimin Sun,Zhiyu Oiao,Minghong He Abstract:The artificial neural network(ANN)and the pattern recognition were applied to study the correla- tion of enthalpies of fusion for divalent rare earth halides with their microstructural parameters,such as ionic radius and electronegativity.The model,represented by a back-propagation neural network,was trained with a 12 set of published data for divalent rare earth halides and then was used to predict the unknown ones.Also the crite-rion equations were presented to determine the enthalpies of fusion for divalent rare earth halides using pattern recognition in this work.The results from the model in ANN and criterion equations are in very good agreement with reference data. Key words:BP neural network;pattern recognition;enthalpy of fusion;divalent rare earth halides;micro- structural parametersV匕 l 一 2 1 N O 一 3 张惠浩等 : 三相异步电动机定子绕组温度在线监测 一 2 97 - 通过 对数据 的分析 与讨论 , 可 知温 度预测 的最 大相 对误 差 为 一 1 . 18 % , 对于温度预 测 而言 , 这 样 的误差 是允许 的 . 另外 , 热 电偶存在较大的热 惯性 , 因此热 电偶测 温也 存在一 定 的误差 . 综上 所述 , 可 以认 为 , 过程辨识理论用于温度预测是 比较 准确 的 . 从温度 随时间 变化 曲线 (卜 : 曲线 )可知 , 在 负载和环境条件改 变时 , 电机 的热平衡状态 、 电 机温度上升速率 、 热 稳定温度 , 以及 电机到达热 稳 态的时 间也相应改变 . 参 考 文 献 1 U m an an d L , B h at S R . 0 n L in e E s t im at i o n o f Sat o r R e s i s t a n c e o f an I n du e t i o n M o t o r fo r S P e e d C o n tr o l A PP li c a - it o ns . IE E P r o e E l e e tr P ow e r A P PI , 19 9 5 , 14 2 ( 2 ) : 9 7 2 孟传 富 , 钱 庆镶 . 机 电能量转换 . 北 京 : 机械工 业 出 版社 , 19 9 3 . 3 6 3 沈 标正 . 电机 故障 诊断技 术 . 北 京 : 机 械 工 业 出版 社 , 199 6 . 39 6 O n 一 L i n e M o n iot inr g ht e eT m P e r a h ir e o f S t at o r Wi n d i n g s o f T h r e e 一 P h a s e I n du e t i o n M o t o r s hZ a ng H 扮ih a o, 肠 n g hS a o c h u n Egn in emr g S e h o l , U S T B e ij in g , B e ij in g 10 0 0 8 3 , C h in a A B S T R A C T B a s e d on ht e ht e o ry o f rP o e e s s id e nt iif e at i o n , a e e o r d in g t o ht e m hat e m a t i e a l m o de l o f thr e e - p h as e in du c it o n m o t o r s in 叨c o o r d i n a te , ht e m a ht m at i e a l m o de l o f ht e et m Pe r a t 双 e fo r e e as t o f het s at o r w in d in g s 1 5 de v e l o ep d . B a s e d on 8 0 C 5 5 2 s l n g l e 一 e h iP m i e r o 一 Por c e s s or, ht e h ar dw aer an d s o ft w aer sy s t e m o f on ~ lin e m o in ot inr g ht e t e m Pe r a tLir e o f ht e s at o r w i n d i n g s o f htr e e 一 Ph a s e i n du e t i o n m o t o r s aer d e s ign e d . Th e e xl 姆 r l n e in s , v e ir 勿 het e oer e in e s s an d fe as ib iliyt o f ht i s m e ht ed . K E Y 、 V O R D S in d u e t ion m o t o r s ; het t e m Pe r a tu r e o f ht e s at t o r w in d i n g s : o n 一 lin e m o n it o inr g O[J unr al of nU vlesr 仰 of sc ien c e an d eT e h n o loy B e ij ing (E n g lis h E id rio n) , 19 9 9 , 6 ( l ) : 2 4 ] R 曰五ict on o f E n ht a 】Pi e s o f Fu s ion for D i v a l e nt R a r a E aj rt h H a li d e s B a s e d on M o d e li n g b y A rt iif e i a l N e uar l N e 七刃 o d 留 助d P a t e m eR e o gn it i o n h 初 in su 月 , 肋恤 口沁认 iM 刀 gh o gn eH A b s t r a ct : Th e 翻rt iif e i al n aeur l n e tw o rk ( A N N ) 阴d ht e P at e rn re e o 加t i o n w e re a PPli e d t o s tu 勿 ht e e o r e l a - it on o f e n1 hL a lP i e s o f haf i o n of r d i v a l e in r a r e e 别rt h h a lid e s w iht ht e ir m i e r o s tru e tur a l P a I 田刀 e t e r s , s u e h a s i o in c m 山u s an d e l e e otr n e g at i v i .yt hT e m o de l , er P r e s e nt e d 勿 a b a e k 一 rP o Pa g at i o n n e uar l n e wt o kr , w a s atr in e d w iht a 12 s et o f Pu b 1ihs e d d a at fo r d i v a l e nt r ar e e a rt h h a lid e s an d ht e n w a s u s e d t o Per id e t ht e u ul m o wn on e s . A l s o het e ir et 一on e q u a t l o sn w e r e Per s e in e d t o d e t e mr in e het e n ht a lPi e s o f fus i o n fOr id v a l e nt r ar e e a rt h ha lid e s us ign Pat e m er c o gn lt lon i n ht i s w o r k . hT e r e s u lt s fr o m ht e m o d e l in A N N an d c ir t e ir o n e qu at i o n s ar e in v e yr g o o d a gr e e m e n t w iht er fe er n c e d a t a . K ey w o dr s : B P n e ur a l en wt o kr : Pat e m r e e o gn it i o n : e n ht a lPy o f fu s i o n : d i v a l e nt r ar e e a rt h h a lids s : m i e r o - slt u c tL ir a 1 Pa r 田叭 e et r s