青藏铁路变电站接地网设计规则的提取

为了获得建立青藏铁路变电站接地网设计专家系统所需的模糊规则,提出神经网络和遗传算法相结合的方法自动生成模糊规则.首先建立了用于青藏线接地网接地电阻求解的遗传优化神经网络,从而可以快速得到所需的大量样本数据,然后利用遗传算法优化计算得到了用于青藏线接地网设计的模糊规则.通过仿真对比计算表明,采用此方法得到的模糊规则可以为接地网设计专家系统的建立打下了基础.

Automatically Produce Fuzzy Rules in Qinghai-Tibet Railway Grounding Grid Design

To obtain the fuzzy rules of expert design system for Qinghai-Tibet Railway grounding grid, a new method based on artificial neural network(ANN) and genetic algorithm (GA) is introduced. To obtain enough and effective data, the system model of BP ANN to calculate the grounding resistance is discussed. To improve the precision of this model, the GA is used to optimize the weight of BP ANN. According to the sample data obtained from the BP ANN model, the fuzzy rules for grounding grid design in Qinghai-Tibet Railway Substation can be acquired by the GA optimization. Compared with the simulative calculation results, the results show that the fuzzy rules obtained by this method are reliable and fit for grounding grid design. This method is helpful reference to electrical design and engineering of Qinghai-Tibet Railway.