论文部分内容阅读
为有效克服变压器不完备故障样本数据对故障诊断结果的影响,文中构建了一种基于粗糙集的人工鱼群极限学习机变压器故障诊断方法,该方法首先运用粗糙集对决策表中的16个条件属性进行约简;其次,根据最简规则表对训练样本进行编码,利用已编码的训练样本对极限学习机进行训练,并运用人工鱼群优化方法对极限学习机的权值及阈值进行优化;最后,利用训练好的极限学习机方法对编码好的样本进行故障诊断。该方法将粗糙集在不完整数据方面所具有的优良特性与极限学习机优良的泛化能力有机融合,以有效提高故障诊断精度。经实例对比分析表明,所构建方法具有更高的诊断准确率,从而验证了该方法的有效性。
In order to effectively overcome the influence of fault incomplete transformer sample data on the fault diagnosis results, a fault diagnosis method of artificial fish limit learning machine transformer based on rough set is proposed in this paper. The method firstly uses 16 conditions Secondly, according to the simplest rule table, the training samples are coded, and the training samples are used to train the extreme learning machine. The artificial fish swarm optimization method is used to optimize the weights and thresholds of the extreme learning machine. Finally, the well-trained limit learning machine method is used to diagnose the coded samples. This method combines the excellent features of rough set in incomplete data with the excellent generalization ability of extreme learning machine to effectively improve the fault diagnosis accuracy. The comparative analysis of examples shows that the proposed method has a higher diagnostic accuracy, which verifies the effectiveness of the method.