CAJ | 학술논문

分析了传统电力系统保护方法存在的缺点，介绍了基于BP神经网络的智能化保护方法原理。为验证该方法的有效性和正确性，基于PSCAD，EMTDc构建了电力系统仿真模型，分别以两相电流有效值和三相电流最大值作为神经网络的输入，进行了仿真研究和对比分析。结果表明：基于BP神经网络的智能保护方法用于舰船电力系统故障定位准确可行，三相电流最大值作为智能保护的输入信号更有优势。
분석료전통전력계통보호방법존재적결점，개소료기우BP신경망락적지능화보호방법원리。위험증해방법적유효성화정학성，기우PSCAD，EMTDc구건료전력계통방진모형，분별이량상전류유효치화삼상전류최대치작위신경망락적수입，진행료방진연구화대비분석。결과표명：기우BP신경망락적지능보호방법용우함선전력계통고장정위준학가행，삼상전류최대치작위지능보호적수입신호경유우세。
Analyzes the shortcomings of traditional power system protection method and introduces the principle ofintelligent protection method based on BP neural network. In order to verify the validity and correctness of the method, constructs the power system simulation model based on the PSCAD/EMTDC, and with two phase current RMS and three phase current maximum value as neural network input respectively, eonducts a simulation study and comparative analysis. The result shows that the intelligent protection method based on BP neural network for ship power system fault locating is accurate and feasible, and the maximum three-phase current input signals as the input signal of intelligent protection have more advantages.