应用RBF网络和D-S证据推理的模拟电路诊断

Abstract
Figure/Table
References
Related Citation (15)

Download: PDF (280 KB) HTML (1 KB)
Export: BibTeX | EndNote (RIS)

Abstract In order to solve the possible problems in neural-network based analog fault diagnosis including lack of fault information, slow training speed and difficult converge, a novel data-fusion based fault diagnosis approach for analog circuits is presented by using radial basis function (RBF) networks and D-S evidential reasoning. The manifold transducer information and symptoms were utilized in diagnosis. The map from symptom space to fault pattern space was constructed by the separate RBF network for each kind of symptom information. The output results of every RBF network were then aggregated using the D-S evidential reasoning algorithm. Fault location was accomplished based on the synthesis decision regulation. The experimental results show that the proposed approach can effectively combine the evidences to produce a more accurate diagnosis and has the capability to diagnose catastrophic and parametric faults of analog circuits with tolerance.

Key words： Fault diagnosis data fusion RBF network evidential reasoning analog circuit

Received: 20 January 2009 Published: 17 February 2014

PACS:

TM131

Fund:This work is supported by National Natural Science Foundation of China under Grant (60673084) and Hunan Provincial Natural Science Foundation of China (06JJ4075, 04JJ6034).

	Service

	E-mail this article
	Add to my bookshelf
	Add to citation manager
	E-mail Alert
	RSS
	Articles by authors
	Peng Minfang
	Shen Meie
	He Yigang
	Sun Yichuang

Cite this article:

Peng Minfang,Shen Meie,He Yigang等. Analog Circuit Diagnosis Using RBF Network and D-S Evidential Reasoning[J]. Transactions of China Electrotechnical Society, 2009, 24(8): 6-13.

URL:

http://dgjsxb.ces-transaction.com/EN/ OR http://dgjsxb.ces-transaction.com/EN/Y2009/V24/I8/6

[1] Czaja Z. Using a square-wave signal for fault diagnosis of analog parts of mixed-signal electronic embedded systems[J]. IEEE Transactions on Instrumentation and Measurement, 2008, 57(8): 1589-1595.
[2] Aminian M, Aminian F. A modular fault-diagnostic system for analog electronic circuits using neural networks with wavelet transform as a preprocessor[J]. IEEE Transactions on Instrumentation and Measurement, 2007, 56(5): 1546-1554.
[3] Wang Peng, Yang Shiyuan. A new diagnosis approach for handling tolerance in analog and mixed-signal circuits by using fuzzy math[J]. IEEE Transactions on CASⅠ, 2005, 52(10): 2118-2127.
[4] Catelani M, Fort A. Soft fault detection and isolation in analog circuits: some results and a comparison between a fuzzy approach and radial basis function networks[J]. IEEE Transactions on Instrumentation and Measurement, 2002, 51(2): 196-202.
[5] Sun Yongkui, Chen Guangju, Li Hui. Fault diagnosis method for analog circuit based on testability analysis and support vector machine[J]. Chinese Journal of Scientific Instrument, 2008, 29(6): 1182-1186.
[6] Tang Jingyuan, Shi Yibing, Jiang Ding, et al. Analog circuit fault diagnosis based on SVDD and dempster- shafer theory[J]. Measurement & Control Technology, 2008, 27(9): 65-68.
[7] Zhang Bo. Discussion on several fundamental problems necessary to be solved in power electronics[J]. Transactions of China Electrotechnical Society, 2006, 21(3): 24-35.
[8] Peng Minfang, He Yigang, Shen Meie, et al. Tolerance-circuit fault screen diagnosis based on multiobjective genetic algorithm[J]. Transactions of China Electrotechnical Society, 2006, 21(3): 118-122.
[9] Peng Minfang, He Yigang, Wang Yaonan, et al. Synthetic intelligence based fault diagnosis of analog circuits[J]. Proceedings of the CSEE, 2006, 26(3): 19-24.
[10] Zhu Daqi, Yu Shenglin. Data fusion algorithm based on D-S evidential theory and its application for circuit fault diagnosis[J]. Acta Electronica Sinica, 2002, 30(2): 221-223.
[11] Wang Cheng, Chen Guangju, Xie Yongle. Fault diagnosis based on radial basis function neural network in analog and mixed-signal circuits[J]. Journal of Circuits and Systems, 2007, 12(2): 65-68.
[12] Luo Zhizeng, Ye Ming. Fusion of dependency information using dempster-shafer evidential reasoning[J]. Journal of Electronics and Information Technology, 2001, 23(1): 970-974.
[13] Gao Weixin Luo Xianjue. A new distribution substation planning algorithm based on hopfield neural network[J]. Transactions of China Electrotechnical Society, 2005, 20(5): 58-64.
[14] Narendra K G, Sood V K, Khorasani K, et al. Application of a radial basis function (RBF) neural network for fault diagnosis in a HVDC system[J]. IEEE Transactions on Power Systems, 1998, 13(1): 177-183.
[15] Mahanty R N, Dutta Gupta P B. Application of RBF neural network to fault classification and location in transmission line[J]. IEE Proc. Gener. Transm. Distrib., 2004, 151(2): 201-212.
[16] Gao Huanwen, Wang Hui. Computer aided analyse and design for analog circuits—application of PSPICE[M]. Beijing: Tsinghua University Press, 2003.
Peng Minfang female, received the PhD degrees in electrical engineering from Hunan University, China, in 2006. She works as a professor at the college of electrical and information engineering in Hunan University. Her research interests are in test and diagnosis of analog circuits, fault diagnosis of power system equipments, intelligent information processing and application of electromagnetic field theory.
Shen Meie female, received the MS degree in automation from Huazhong University of Science and Technology in 1989. She works as an associate professor at the college of computer science in Beijing University of Information Science and Technology. Her research interests are in computer aided model, test and diagnosis of analog circuits.
应用RBF网络和D-S证据推理的模拟电路诊断
彭敏放¹ 沈美娥² 何怡刚¹ 孙义闯³
(1. 湖南大学电气与信息工程学院长沙 410082 2. 北京信息科技大学计算机学院北京 100101 3. Department of ECEE, University of Herdfordshire Hatfield ALl0 9AB UK)
摘要提出了一种基于径向基函数网络与证据推理的模拟电路融合诊断方法, 以解决模拟电路诊断中由于故障信息缺乏所致的诊断准确性问题, 并提高其训练速度。采集多类电路信息, 对应于每类特征参量构造一个径向基函数网络, 由这多个彼此独立的径向基函数网络来完成故障的初级诊断。再用初级诊断中各子网络的输出结果构造证据体, 通过证据融合推理分析, 得出最终的故障定位结果。模拟实验结果表明, 所提方法对于电路的硬故障与元件参数偏移较小的软故障诊断均有效, 其充分挖掘了多类测试信号中的故障信息, 提高了诊断结果的准确率。
关键词：故障定位数据融合径向基函数网络证据推理模拟电路
中图分类号: TM131
正泰杯第三届全国电气工程师论文大赛征文通知
2009年电气时代杂志社将举办第三届全国电气工程师论文大赛。本届大赛由浙江正泰电器股份有限公司独家赞助, 《电气应用》编辑部承办, 同时得到了中国电机工程学会、中国建筑学会建筑电气分会、北京电力设计院和业内知名专家的大力支持。现将征文内容和具体要求介绍如下。
一、征文内容
(1)电力电气(绿色电力、继电保护、变压器、开关设备、配电自动化及城市电网改造)。
(2)建筑电气(供配电、照明、防雷接地、智能建筑、电气安全、标准讨论、电能质量及方案设计)。
(3)石化电气(节能降耗新技术、电气安全<防雷、防爆>、供配电、UPS技术及应用、电能质量、电气控制、电气设备改造及电气管理)。
(4)工业电气(电气传动、工业控制与检测、现场总线、工业用电管理及电机起动与保护)。
(5)理论前沿(直流输电、柔性输电、电气仿真技术研究、超导技术及智能电器)。
二、征文要求
(1)来稿注明“电气工程师论文大赛”字样。每篇文章署名作者不能超过4位。
(2)稿件未在全国公开发行的刊物上发表过, 未参评过前两届电气工程师论文大赛。
(3)稿件要求论点鲜明, 内容新颖实用, 数据可靠, 条理清晰, 文字简洁通顺, 图文清晰, 突出实用性。字数控制在5000字以内(包括插图、表格等)。
(4)稿件首页包括：题目、200字以内的中、英文摘要和3～5条关键词, 中图分类号。如来稿属于基金项目(写明基金编号)、国家攻关项目等, 请在首页的最底一行注明。