10kV电网小电流接地系统单相接地故障选线方法的研究

发布时间：2018-04-20 21:05

本文选题：小电流接地系统 + 故障选线　；参考：《中国矿业大学》2014年硕士论文

【摘要】：小电流接地系统单相接地故障选线一直是配电网中的重点和难点。当前，虽然各种选线装置层出不穷，但是选线效果甚微。究其原因，主要是单一的选线方法有其局限性，难以满足复杂多变工况下的选线要求，选线精度较低。因此，融合多种选线原理进行选线是未来发展的趋势。本文就是结合神经网络算法和D-S证据理论融合多种故障选线原理，对小电流接地系统单相接地故障选线进行深入的研究，，以提高配电网故障选线的精度，改善供电质量。首先，本文介绍了小电流接地系统单相接地故障选线这一领域在国内外的研究现状，介绍了当前主流的选线原理与选线方法，并进行了相应的Matlab/Simulink仿真模型的搭建，同时在模型的基础上进行基于传统故障选线方法的仿真，为文中后半部分的选线原理的融合打下扎实的理论基础。同时，大量的仿真数据可以为日后的融合验证提供数据保障。其次，本文根据稳态及暂态特征量的特点，构造故障测度函数，以处理仿真得到的各项数据，作为融合算法的输入值。接着，简单介绍了BP神经网络、基于遗传算法优化的BP神经网络以及D-S证据理论，将小电流接地系统故障选线同上述智能算法进行结合，使智能算法与实际问题相结合来解决这一难题。最后，利用具体算例来详细介绍本文所提出的基于遗传算法优化的BP神经网络以及D-S证据理论双融合算法，通过仿真实例来介绍该方法的优越性和选线的高精度。验证结果说明,该算法相比其他选线方法更有优势。
[Abstract]:Single-phase grounding fault line selection in low-current grounding system has always been the focus and difficulty in distribution network. At present, although a variety of line selection devices emerge in endlessly, but the effect of line selection is very little. The main reason is that the single route selection method has its limitations, it is difficult to meet the requirements of complex and changeable working conditions, and the accuracy of line selection is low. Therefore, it is the trend of future development to combine various principles of line selection. Combined with neural network algorithm and D-S evidence theory, this paper studies the single-phase grounding fault line selection of small current grounding system in order to improve the accuracy of fault line selection and improve the quality of power supply. Firstly, this paper introduces the research status of single-phase grounding fault line selection in small current grounding system at home and abroad, introduces the current mainstream line selection principle and method, and builds the corresponding Matlab/Simulink simulation model. At the same time, the simulation based on the traditional fault line selection method is carried out on the basis of the model, which lays a solid theoretical foundation for the fusion of the line selection principle in the second half of the paper. At the same time, a lot of simulation data can provide data guarantee for future fusion verification. Secondly, according to the characteristics of steady-state and transient characteristic variables, the fault measure function is constructed to process the simulated data as the input value of the fusion algorithm. Then, the BP neural network, based on BP neural network optimized by genetic algorithm and D-S evidence theory, is introduced briefly. The fault line selection of small current grounding system is combined with the intelligent algorithm mentioned above. The intelligent algorithm is combined with the practical problem to solve this problem. Finally, the BP neural network based on genetic algorithm optimization and the double fusion algorithm of D-S evidence theory proposed in this paper are introduced in detail by a concrete example. The superiority of the method and the high accuracy of line selection are introduced by a simulation example. The results show that the algorithm has more advantages than other routing methods.
【学位授予单位】：中国矿业大学
【学位级别】：硕士
【学位授予年份】：2014
【分类号】：TM862

【参考文献】