Elliptical novelty grouping for on-line short-turn detection of excited running rotors

被引:46
作者
Guttormsson, SE [1 ]
Marks, RJ
El-Sharkawi, MA
Kerszenbaum, I
机构
[1] Univ Washington, Dept Elect Engn, Seattle, WA 98195 USA
[2] So Calif Edison Co, Res Ctr, Irwindale, CA 91702 USA
基金
美国国家科学基金会;
关键词
novelty-detection; shorted-turn-defection; on-line-fault-detection; twin-signal-sensing; outlier-detection; synchronous-machines; condition-based-maintenance;
D O I
10.1109/60.749142
中图分类号
TE [石油、天然气工业]; TK [能源与动力工程];
学科分类号
0807 ; 0820 ;
摘要
A technique for the detection of shorted turns in the field-windings of operating synchronous turbine-generators is described. The measuring method used is the twin-signal sensing method, where pulses are injected into each terminal of the. rotor, The reflected signals are subtracted to produce a signature signals that contains information about the rotor's state, The signature signals are! sampled and accepted or rejected as valid based on an outlier detection criteria, Novelty detection is applied to the accepted signals. The current signature signal is compared to a range of signature signals taken when the rotor was known. to. be free of shorts, If the current signature signal strays too far from the known healthy signal, the signature signal is 'novel' and the possibility of a short is declared. The method was tested on a running test rotor with voltage excitation, A comparison of methods shows that an elliptical novelty grouping algorithm gives highly accurate results.
引用
收藏
页码:16 / 22
页数:7
相关论文
共 12 条
  • [1] [Anonymous], 1988, SELF ORG ASS MEMORY
  • [2] LOCALIZATION OF WINDING SHORTS USING FUZZIFIED NEURAL NETWORKS
    ELSHARKAWI, MA
    MARKS, RJ
    OH, S
    HUANG, SJ
    KERSZENBAUM, I
    RODRIGUEZ, A
    [J]. IEEE TRANSACTIONS ON ENERGY CONVERSION, 1995, 10 (01) : 140 - 146
  • [3] Haykin S., 1994, NEURAL NETWORKS COMP
  • [4] ROBUST CLUSTERING WITH APPLICATIONS IN COMPUTER VISION
    JOLION, JM
    MEER, P
    BATAOUCHE, S
    [J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 1991, 13 (08) : 791 - 802
  • [5] DIAGNOSING DYNAMIC FAULTS USING MODULAR NEURAL NETS
    LEONARD, JA
    KRAMER, MA
    [J]. IEEE EXPERT-INTELLIGENT SYSTEMS & THEIR APPLICATIONS, 1993, 8 (02): : 44 - 53
  • [6] Papoulis A, 1991, PROBABILITY RANDOM V
  • [7] Statistical independence and novelty detection with information preserving nonlinear maps
    Parra, L
    Deco, G
    Miesbach, S
    [J]. NEURAL COMPUTATION, 1996, 8 (02) : 260 - 269
  • [8] A PROBABILISTIC RESOURCE ALLOCATING NETWORK FOR NOVELTY DETECTION
    ROBERTS, S
    TARASSENKO, L
    [J]. NEURAL COMPUTATION, 1994, 6 (02) : 270 - 284
  • [9] Scharf L. L., 1991, Statistical signal processing: Detection, estimation
  • [10] PROBABILISTIC NEURAL NETWORKS
    SPECHT, DF
    [J]. NEURAL NETWORKS, 1990, 3 (01) : 109 - 118