Open AccessParameter Anomaly Identification Model About Supervisory Control And Data Acquisition
Author(s) -
Guo Ping
Publication year - 2021
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1848/1/012056
Subject(s) - identification (biology) , wind power , computer science , premise , control (management) , state (computer science) , basis (linear algebra) , index (typography) , anomaly (physics) , anomaly detection , control engineering , reliability engineering , control theory (sociology) , engineering , data mining , artificial intelligence , mathematics , algorithm , linguistics , philosophy , botany , geometry , world wide web , electrical engineering , biology , physics , condensed matter physics
With the rapid progress of sensor technology, state monitoring of wind turbines is more comprehensive, the amount and type of the sensor used will be more, the state parameters of wind turbines will be more. According to the status indicators to parameter index of target parameters selector model is established in this paper, and the number of input parameters are reduced on the basis of the guarantee accuracy. The two sub-models constitute the abnormal identification model of the working condition index. Finally, the model is analyzed by an example to verify the accuracy and effectiveness of the model. The research in this paper on abnormal discrimination of working condition parameters and evaluation methods of wind turbines is an important premise and basis for making scientific and reasonable operation and maintenance decisions of wind farms, and it has important academic significance.