1
|
Guo Y, Wang L, Li Y, Luo J, Wang K, Billings S, Guo L. Neural activity inspired asymmetric basis function TV-NARX model for the identification of time-varying dynamic systems. Neurocomputing 2019. [DOI: 10.1016/j.neucom.2019.04.045] [Citation(s) in RCA: 9] [Impact Index Per Article: 1.8] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/28/2022]
|
2
|
Diagnosis of Inter-Turn Short Circuit of Synchronous Generator Rotor Winding Based on Volterra Kernel Identification. ENERGIES 2018. [DOI: 10.3390/en11102524] [Citation(s) in RCA: 19] [Impact Index Per Article: 3.2] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 11/16/2022]
Abstract
The inter-turn short circuit is a common fault in the synchronous generator. This fault is not easily detected at early stage. However, with the development of the fault, it will pose a threat to the safe operation of the generator. To detect the inter-turn short circuit of rotor winding, the feasibility of identifying the stator branch characteristics of synchronous generator during inter-turn short circuit was analyzed. In this paper, an on-line fault identification method based on Volterra kernel identification is presented. This method uses the stator branch voltage and stator unbalance branch current collected from the generator as input and output signals of the series model. Recursive batch least squares method is applied to calculate the three kernels of Volterra series. When the generator is in normal state or fault state, the Volterra kernel will change accordingly. Through the identification of the time-domain kernel of the nonlinear transfer model, the inter-turn short circuit fault of the synchronous generator is diagnosed. The correctness and effectiveness of this method is verified by using the data of fault experimental synchronous generator.
Collapse
|