论文部分内容阅读
提出了一个层次化与模块化相结合的具有冗余神经元的神经网络 (NN)模型系统 ,该系统充分利用了神经网络在模式识别、非线性拟合及联想记忆等方面的优势 ,其模块化结构与生物神经网络功能区域结构相一致 ,信息处理机制符合生物神经网络分类和逐步推理的规律。该系统可实现高基金项目 :国家自然科学基金资助项目 ( 598770 1 6)。压 (超高压 )架空输电线路故障测距所需的复杂信息处理要求 ,可避免常规测距方法中出现伪根、迭代不收敛、及消除对端系统运行方式和助增电流影响导致测距误差大等不足。大量的电势暂态程度 (EMTP)仿真测试表明 :该方法的故障测距精度高、综合性能好、适应性强。
A neural network (NN) model system with redundant neurons, which is a combination of hierarchical and modular, is proposed. This system takes full advantage of the advantages of neural networks in pattern recognition, nonlinear fitting and associative memory. The module The structure of the structure is consistent with the structure of the functional area of the biological neural network, and the information processing mechanism accords with the law of classification and step-by-step reasoning of the biological neural network. The system can achieve high fund project: National Natural Science Foundation of China (5987701 6). Complicated information processing requirements for fault location of overhead (EHV) overhead transmission lines can avoid pseudo-roots in conventional ranging methods, non-convergence of iterations, and elimination of the influence of the running mode and boosting current of the opposite end system on the ranging error Big enough. A large number of potential transient state (EMTP) simulation tests show that this method has the advantages of high fault location accuracy, good overall performance and strong adaptability.