正文:
4 现场诊断实例
某变电站1号主变发生故障,由色谱分析测得H
2、CH
4、C
2H
6、C
2H
4、C
2H
2 的气体浓度(×10
-6)分别是188,236,18.1,237,31.8,现分别计算出比值R
1,R
2,R
3作为ANFIS的输入,计算输出是第9类故障,即电弧放电兼过热。改良电协研法得出比值编码为122,诊断结果为电弧放电兼过热。实际现场调查结果C相线圈分接头引线对压铁马蹄口放电,低压B相尾部烧焦。
5 结论
将ANFIS用于变压器故障诊断,通过训练样本数据获得模糊规则,克服了模糊系统过于依赖专家知识和经验的局限性
[12];使用Fletcher-Reeves共轭梯度法改进ANFIS原始的学习算法,由于FR算法是全局收敛的,因此可以有效的克服BP算法容易陷入局部最优的缺点,加快收敛速度;识别的结果证明这种方法用于变压器故障诊断是可行的,而且ANFIS是一个自适应系统,可以迅速跟踪输入输出的样本数据调整自身参数,因此能够进一步用来研究变压器故障在线诊断技术。
参考文献:
[1] 董明,赵文彬,严璋.油气分析诊断变压器故障方法的改进[J].高电压技术,2002,28(4):6-8.DONG Ming, ZHAO Wen-bin, YAN Zhang. An improved method for transformer fault diagnosis based on DGA[J]. HighVoltage Engineering, 2002, 28(4): 6-8.
[2] 许坤,周建华,茹秋实,等.变压器油中溶解气体在线监测技术发展与展望[J].高电压技术,2005,31(8):30-32.XU Kun, ZHOU Jian-hua, RU Qiu-shi, et al. Development and prospect of transformer oil dissolved gas on-line monitoring tech-nology[J]. High Voltage Engineering, 2005, 31(8): 30-32.
[3] 王雪梅,李文申,严璋. BP网络在电力变压器故障诊断中的应用[J].高电压技术,2005, 31(7):12-14.WANG Xue-mei, LI Wen-shen, YAN Zhang. Application study of BP network used in the fault diagnosis of power transformer[J]. High Voltage Engineering, 2005,31(7):12-14.
[4] 刘一,倪远平.三比值灰关联度分析的变压器故障诊断法[J].高电压技术,2002,28(10):16-17.LIU Yi, NI Yuan-ping. A transformer faults diagnosis method based on the grey corelation theory[J]. High Voltage Engineering, 2002, 28(10): 16-17.
[5] 梁永春,李彦明.改进型组合RBF神经网络的变压器故障诊断[J].高电压技术,2005,31(9):31-33.LIANG Yong-chun, LI Yan-ming. Application of modified combinatorial radial basis function neural network in fault diagnosisof power transformer[J]. High Voltage Engineering, 2005, 31(9): 31-33.
[6] 钱政,严璋,罗承沐.范例推理与模糊数学的变压器故障诊断方法[J].高电压技术, 2001, 27(6): 1-5.QIAN Zheng, YAN Zhang, LUO Cheng-mu. Fault diagnosismethod of power transformer by integrating case-based reasoning with fuzzy theory and neural network[J]. High Voltage Engineering, 2001, 27(6): 1-5.
[7] 吴晓莉,林哲辉(Wu Xiaoli, Lin Zhehui). MATLAB辅助模糊系统设计(Design of fuzzy system using MATLAB)[M].西安:西安电子科技大学出版社(Xi’an: XidianUniv. Press), 2002. 130-150.
[8] Jyh-Shing Roger Jang, Chuen-Tsai Sun. Neuro-fuzzymodeling and control [J]. Proc. of the IEEE, 1995, 83(3):378-406.
[9] Jhy-Shing R. Jang, Anfis: Adaptive–Network-Based Fuzzy Inference System, IEEE Transactions on Systems, Man and Cybernetics, Vol.23, No. 3, 665-685, 1993.
[10] DEMUTH H,BEALE M,HAGAN M.Neural network toolbox for use with MATLAB user’s guide[M].USA,MA:The MathWorks Inc,2005.
[11] JIANG M,GIELEN G,ZHANG B,et al.Fast learning algorithms for feedforward neural networks[J].Applied Intelligence,2003,18(1):37-54.
[12] Serge Guillaume. Designing fuzzy inference systems from data: An interpretability-oriented review [J]. IEEE Trans.on Fuzzy Systems, 2001, 9(3): 426-442.
3/3 首页 上一页 1 2 3