基于正态云模型&改进贝叶斯分类器的变压器故障诊断

在基于油色谱数据的变压器故障诊断中,一般数据挖掘方法存在数值区域划分过硬,且未考虑边界元素隶属的随机性和模糊性的问题。针对该问题,文章应用正态云模型对油色谱数据集进行预处理,同时云模型对数据集的精简也提高了关联规则挖掘的效率。为了解决朴素贝叶斯分类器中对各属性独立的假设不符合实际情况这一问题,文章引入关联规则森林表示法和属性联合概率算法,改进了朴素贝叶斯分类器,建立了基于正态云模型与改进贝叶斯分类器的变压器故障诊断模型,通过与其他模型的对比及实例验证,证明了该方法的有效性。

Transformer Fault Diagnosis Based on Normal Cloud Model & Improved Bayesian Model

In order to solve the problem of data mining in diagnosing transformer fault based on oil chromatographic data,that data of dissolved gas-in-oil is divided without considering the randomness and fuzziness,so the normal cloud model is applied.The efficiency of mining association rules is also improved through normal cloud model.For the assumption in Naive Bayes classifier is not conformed to the actual situation,an association rule forest and a method of the joint probability calculated are applied to improve Naive Bayes classifier,and the transformer fault diagnosis model based on normal cloud model and improved Bayesian classifier is built as a result.The new Bayes classifier is proved to be practical in the diagnosis of transformer by comparing with other classifier and testing examples.