【摘要】 人工神经网络(ANN)由于其高度的非线性映射能力在电力系统模式识别及非线性优化领域有着广泛深入的应用研究。本文将Super SAB神经网络算法应用于主变压器溶解气体故障诊断(DGA),通过与带动量因子的标准BP算法、Bold Driver算法比较,验证Super SAB算法在故障模式识别中具有更好的学习效率与泛化能力,故障诊断的准确度高于传统分析方法,表明其在变电设备状态诊断中具有良好的应用前景。更多还原

【Abstract】 This paper presents an evolutionary artificial neural network (ANN) programming based on Super SAB algorithm, which in our view will improve diagnostic accuracy of conventional dissolved gas analysis (DGA) methodologies. Our comparative analysis shows that Super SAB algorithm provides both higher learning efficiency and stronger generalization capacity versus standard BP and Bold-Driver algorithm we once used in DGA. When Super SAB was applied to transformer DGA, the fault diagnosis accuracy was evidently enhanced compared to other conventional methods. Therefore, this algorithm possesses a promising future in the diagnostic field for power transformers equipments.更多还原