| 264 | 6 | 664 |
| 下载次数 | 被引频次 | 阅读次数 |
研究变压器故障的诊断问题,根据变压器绝缘油中的特征气体含量与变压器故障类型的对应关系,提出一种基于受限玻尔兹曼机(Restricted Boltzmann Machine,RBM)模型的故障诊断方法。首先根据故障变压器绝缘油中的五种特征气体含量计算三比值数据,并在三比值数据中增加高斯噪声;然后利用RBM对数据进行无监督式训练与特征提取,利用反馈神经网络(Back Propagation,BP)对数据进行有监督式的训练并判断故障类型。仿真结果验证该算法的有效性。
Abstract：This paper considered the transformer fault diagnosis by using the restricted boltzmann machine(RBM).Firstly,Three ratios were calculated by transformer fault characteristic gas data and the Gaussian noise were imported into three ratios data.Secondly,the RBM was used for unsupervised training and getting feature.Then the Back Propagation(BP)was used for supervised training and getting transformer fault.Simulation examples show the effectiveness of the presented approach.
[1]刘勇辉.基于DGA的变压器故障诊断[J].高电压技术,2005,31(6):87-88.Liu Yonghui.Power Transformer fault diagnosis based-on dissolved gas analysis[J].High Voltage Engineering,2005,31(6):87-88.
[2]杜文霞,句希源,吕锋.基于模糊聚类算法的变压器故障诊断研究[J].变压器,2009,46(8):65-69.Du Wenxia,Ju Xiyuan,Lu Feng.Research on transformer fault diagnosis based on fuzzy clustering algorithm[J].Transformer,2009,46(8):65-69.
[3]郭创新,朱承治,张琳,等.应用多分类多核学习支持向量机的变压器故障诊断方法[J].中国电机工程学报,2010,30(13):130-136.Guo Chuangxin,Zhu Chengzhi,Zhang Lin,et al.A fault diagnosis method for power transformer based on multiclass multiple-kernel learning support vector machine[J].Proceedings of the CSEE,2010,30(13):130-136.
[4]符杨,田振宁,江玉蓉,等.加权模糊核聚类法在电力变压器故障诊断中的应用[J].高电压技术,2010,36(2):371-374.Fu Yang,Tian Zhenning,Jiang Yurong,et al.Power transformer fault diagnosis using weighted Fuzzy kernel clustering[J].High Voltage Engineering,2010,36(2):371-374.
[5]付强,陈特放,朱佼佼.采用自组织RBF网络算法的变压器故障诊断[J].高电压技术,2012,38(6):1368-1375.Fu Qiang,Chen Tefang,Zhu Jiaojiao.Transformer fault diagnosis using self-adaptive RBF neural network algorithm[J].High Voltage Engineering,2012,38(6):1368-1375.
[6]李霜,王朗珠,张为,等.基于DGA的改进BP神经网络的变压器故障诊断方法[J].变压器,2010,47(12):61-65.Li Shuang,Wang Langzhu,Zhang Wei,et al.Fault diagnosis method of transformer based on improved BP neural network of DGA[J].Transformer,2010,47(12):61-65.
[7]王晓霞,王涛.基于BP神经网络的变压器故障诊断[J].华东电力,2008,36(2):112-116.Wang Xiaoxia,Wang Tao.Transformer fault diagnosis based on BP networks[J].East China Electric Power,2008,36(2):112-116.
[8]潘翀,陈伟根,云玉新,等.基于遗传算法进化小波神经网络的电力变压器故障诊断[J].电力系统自动化,2007,31(13):88-92.Pan Zhong,Chen Weigen,Yun yuxin,et al.Fault diagnosis of power transformers based on genetic algorithm evolving wavelet neural network[J].Automation of Electric Power Systems,2007,31(13):88-92.
[9]Tang W H,Goulermas J Y,Wu Q H.A probabilistic classifier for tr-ansformer dissolved gas analysis with a particle swarm optimizer[J].IEEE Transactions on Power Delivery,2008,23(2):751-759.
[10]宋绍民,王耀南,孙炜,等.基于免疫聚类算法的变压器DGA数据故障诊断方法[J].变压器,2008,45(8):70-72.Song Shaomin,Wang Yaonan,Sun Wei,et al.Fault diagnosis method with transformer DGA data based on immune recognition algorithm[J].Transformer,2008,45(8):70-72.
[11]Hinton G E,Salakhutdinov R R,Reducing the dimensionality of data with neural networks[J].Science,2006,313(5786),504-507.
[12]Garrison W.Cottrell.New life for neural networks[J].Science,2006.313:454-455.
[13]Roux N L,Bengio Y.Representational power of restricted boltzmann machines and deep belief networks[J].Neural Computation,2008,20(6):1631–1649.
[14]Salakhutdinov R,Larochelle H.Efficient learning of deep Boltzmann machines[J].Journal of Machine Learning Research:Proceedings Track,2010,9(1):693-700.
[15]Jaitly N,Hinton G E.Learning a better representation of speech sound waves using restricted Boltzmann machines[C].Proc of the2011IEEE Int Conf on Acoustics.Speech and Signal Processing,2011:5884-5887.
[16]Dahl G,Yu Dong,Deng Li,et al.Context-dependent pretrained deep neural networks for large vocabulary speech recongnition[J].IEEE Trans on Audio,Speech and Language Processing.2012,20(1):30-42.
[17]耿基明,郭晓峰.应用变压器油色谱分析判断变压器故障[J].变压器,2006,43(11):44-47.Geng Jiming,Guo Xiaofeng.Diagnosis of Transformer Faults by Chromatogr aphic Analysis of Transformer oil[J].Transformer,2006,43(11):44-47.
[18]Hinton G E.Training products of experts by minimizing contrastive divergence[J].Neural Computation,2002,14(8):1771?1800.
[19]尚勇,闫春江,严璋.基于信息融合的大型油浸电力变压器故障诊断[J].中国电机工程学报,2002,22(7):50-55.Shang Yong,Yan Chunjiang,Yan Zhang.Synthetic Insulation Fault Diagnostic Model of Oil-immersed Power Transformers Utilizing Information Fusion[J].Proceedings of the CSEE,2002,22(7):50-55.
[20]Schulz H,Müller A,Behnke S.Investigating Convergence of Restricted Boltzmann Machine Learning[C].//NIPS 2010 Workshop on Deep Learning and Unsupervised Feature Learning,2010:1-9.
[21]Duval M,dePabla A.Interpretation of gas-in-oil analysis using new IEC publication 60599and IEC TC 10databases[J].IEEE on Electrical Insulation Magazine,2001,17:31-41.
基本信息:
DOI：10.16441/j.cnki.hdxb.20150437
中图分类号:TM41
引用信息:
[1]王鲁昆,赵晓颖,张健,等.带高斯噪声的受限玻尔兹曼机在变压器故障诊断中的应用[J],2018,48(06):114-119.DOI:10.16441/j.cnki.hdxb.20150437.
基金信息:
山东省高等学校科技计划项目(J17KB167);; 泰安市科技发展计划项目(2017GX0014);; 山东科技大学人才引进科研启动基金项目(2017RCJJ077)资助~~