\r李永丽，吴玲玲，卢 扬，孙广宇\r
\r
AuthorsHTML:\r李永丽，吴玲玲，卢 扬，孙广宇\r
\r
AuthorsListE:\rLi Yongli，Wu Lingling，Lu Yang，Sun Guangyu\r
\r
AuthorsHTMLE:\rLi Yongli，Wu Lingling，Lu Yang，Sun Guangyu\r
\r
Unit:\r智能电网教育部重点实验室(天津大学)，天津 300072\r
\r
Unit_EngLish:\rKey laboratory of Smart Grid of Ministry of Education(Tianjin University)，Tianjin 300072，China\r
\r
Abstract_Chinese:\r\r\r通过监测断路器分合闸线圈电流识别断路器状态是断路器故障诊断重要方法．但是，由于断路器动作频率不高，分合闸线圈电流的数据样本较小．为了在数据样本较小的前提下对断路器进行快速准确的故障诊断，提出了一种基于改进的贝叶斯分类算法的断路器故障诊断方法．针对原始的贝叶斯算法只适用于处理离散型变量的分类问题、应用范畴较为局限的特点，利用入侵杂草优化算法合理选取标准状态，并以此为基础引入基于标准状态概率分配的连续变量离散化方法对特征量进行离散化，对原始的贝叶斯算法进行了改进．研究表明，改进的贝叶斯分类算法将贝叶斯的应用范畴扩展至连续变量的分类问题，提高了故障诊断的准确率．通过仿真分析验证改进的贝叶斯分类算法在不同训练样本数量的情况下故障诊断的准确性，并与原始的贝叶斯算法和支持向量机进行比较．仿真结果表明在训练样本数量为\r\r10\r\r的情况下，原始贝叶斯算法、支持向量机和改进贝叶斯算法的故障诊断准确率分别为\r\r45.05\r\r%\r、\r\r83.15\r\r%\r、\r\r92.25\r\r%\r\r，改进的贝叶斯算法故障诊断准确率明显高于支持向量机，说明改进的贝叶斯算法诊断效果更好；改进的贝叶斯算法故障诊断准确率明显高于原始贝叶斯算法，说明入侵杂草优化算法的优化及基于标准状态概率分配的连续变量离散化方法在提高小样本状态下故障诊断准确率方面有良好的效果；改进的贝叶斯算法故障诊断准确率最高，这表明本文所提改进贝叶斯算法能够在样本数据较小的前提下快速准确地对断路器进行故障诊断\r\r.\r\r\r\r\r\r\r\r\r\r\r\r\r
\r
Abstract_English:\r\rTo diagnose faults in a circuit breaker\r，\rit is important to determine the status of the circuit breaker by monitoring the current through the circuit breaker’s opening and closing coils\r．\rHowever\r，\rconsidering the low operating frequency of circuit breakers\r，\rfew data samples of the currents of these opening and closing coils are available\r．\rTo quickly and accurately diagnose faults in a circuit breaker despite the availability of few data samples\r，\rwe propose an improved Bayesian algorithm\r．\rThe conventional Bayesian algorithm is only applicable to classification problems about discrete variables\r，\rso we introduce an invasive-weeds optimization algorithm to select the standard state\r，\rand on this basis\r，\rwe use a discretization method based on the standard state probability to discretize the continuous variables\r．\rThe study results reveal that the proposed improved Bayesian algorithm extends the range of categories to which the Bayesian algorithm can be applied to the classification of continuous variables and improves the accuracy of fault diagnosis\r．\rWe performed a simulation analysis of different training samples to verify the accuracy of the improved Bayesian algorithm for fault diagnosis and compared the results obtained with those obtained using the conventional Bayesian algorithm and a support vector machine\r(\rSVM\r)\r．\rFor 10 training samples\r，\rthe fault diagnosis accuracies of the conventional Bayesian algorithm\r，\rSVM\r，\rand the improved Bayesian algorithm were 45.05\r%\r，\r83.15\r%\r，\rand 92.25\r%\r，\rrespectively\r．\rThe accuracy rate of the improved Bayesian algorithm was greater than that of the SVM\r，\rwhich indicates that the diagnostic effect of the improved Bayesian algorithm is better than that of the SVM\r．\rThe accuracy rate of the improved Bayesian algorithm was also higher than that of the conventional Bayesian algorithm\r，\rwhich indicates that the optimization obtained by the invasive-weed optimization algorithm and the discretization method based on the standard state probability distribution were effective in improving the fault diagnosis accuracy using a small sample size\r．\rBecause the improved Bayesian algorithm proposed in this paper had the highest fault diagnosis accuracy\r，\rwe conclude that it can be used to quickly and accurately diagnose faults in circuit breakers using only a small data sample set\r．\r\r
\r
Keyword_Chinese:断路器；故障诊断；贝叶斯分类器；离散化；小样本\r

Keywords_English:circuit breaker；fault diagnosis；Bayesian classifier；discretization；small sample\r


PDF全文下载地址:http://xbzrb.tju.edu.cn/#/digest?ArticleID=6463