基于改进学习矢量量化神经网络输电线路故障识别技术

针对输电线路距离长、覆盖范围广,易受到自然环境和人为因素的影响,对输电线路故障分类和识别非常困难.在输电线路故障分类中将经验小波变换与改进的学习矢量量化神经网络相结合,使用经验小波变换提取输电线路的故障特征,并使用改进的学习矢量量化神经网络识别故障特征.通过对不同故障类型、故障位置、过渡电阻和初始故障角度进行仿真,验证该模型的准确性和有效性.仿真结果表明,该方法在故障分类中具有一定的优势,不受上述因素的影响,具有良好的鲁棒性和故障分类性能.该研究为中国输电线故障识别技术的发展提供一定的参考.

Key technology of transmission line fault classification based on big data technology

In view of the long distance and wide coverage of the transmission circuit, it is easy to be affected by the natural environment and human factors, which makes the operation and maintenance of the transmission line difficult.In this paper, the empirical wavelet transform and the improved learning vector quantization neural network are combined in the transmission line fault classification,the empirical wavelet transform is used to extract the fault features of transmission lines, and the improved learning vector quantization neural network is used to identify the fault features.Through the simulation of different fault types, fault location, transition resistance and initial fault angle, the accuracy and effectiveness of the model are verified.The simulation results show that this method has some advantages in fault classification, not affected by the above factors, and has good robustness and fault classification performance.It can be seen that this study has certain reference and reference significance for the development of transmission line fault classification in China.