基于粗糙集理论和生命初态信息的继电器寿命预测方法

摘要
图/表
参考文献
相关文章 (15)

全文: PDF (357 KB)
输出: BibTeX | EndNote (RIS)

摘要工作寿命是表征产品可靠性的重要特征量。对于继电器这类长寿命产品,以寿命为指标进行产品筛选的方法目前还未得到深入研究。近来通过对继电器寿命试验数据进行分析发现：继电器个体的寿命与其生命初期的性态有关,初期性态较好的个体其寿命也较长,反之则寿命较短。本文基于这一发现提出了继电器的个体寿命预测与筛选方法,即首先通过寿命试验获取一组样本在生命初期的性能参数值与寿命值,然后利用粗糙集理论中的属性约简提取一组与寿命相关的性能参数,并建立一组寿命决策规则。此后对于任一同型产品,只要测出其生命初态信息即可根据这组规则预测其寿命,进而完成以寿命为指标的继电器产品筛选。本文最后进行了实例分析,结果表明了该方法的有效性。

	服务

	把本文推荐给朋友
	加入我的书架
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章
	李玲玲
	张士暖
	李志刚
	贺鹏举

关键词 ：继电器, 生命初期特征, 寿命预测, 产品筛选, 粗糙集理论

Abstract：Working life is an important feature of product reliability. However the product screening method using life as the sole index hasn’t been thoroughly studied for long life products such as relays. After the life test data of relays was analyzed,a fact was found recently that there are some relations between relay’s initial working state and its working life, i.e., better performance of the initial state, longer life expectancy of the individual relay, and vice versa. Based on the fact, a method of the individual relay’s life predicting and screening was presented. Firstly, obtained the initial state performance parameters values and life values of the sample relays through life test. Secondly, extracted a set of parameters associated with life based on the method of attribute reduction from the rough set theory, then established a set of life decision rules based on the extracted parameters. After that, for any one of the relay whose model same as the samples, its life could be predicted only according to its initial state information and the rules, then the screening using life as the sole index could be achieved. At last, the availability of the above method was proved by a practical example of relay.

Key words： Relay initial state information life prediction product screening rough set theory

收稿日期: 2014-07-28 出版日期: 2016-10-13

PACS:

TM581.3

基金资助:国家自然科学基金（61072100、51377044）,河北省自然科学基金（E2014202230）和河北省高校创新团队领军人才培育计划（LJRC003）资助项目

通讯作者: 李志刚男,1958年生,博士,教授,博士生导师,研究方向为电子电器、电器可靠性及其检测技术。E-mail: zgli@hebut.edu.cn（通信作者）

作者简介: 李玲玲女,1968年生,博士,教授,博士生导师,研究方向为电器可靠性、电力系统及其自动化。E-mail: lilingling@hebut.edu.cn

引用本文:

李玲玲, 张士暖, 李志刚, 贺鹏举. 基于粗糙集理论和生命初态信息的继电器寿命预测方法[J]. 电工技术学报, 2016, 31(18): 46-53. Li Lingling, Zhang Shinuan, Li Zhigang, He Pengju. The Life Prediction Method of Relay Based on Rough Set Theory and Relay’s Initial Life Information. Transactions of China Electrotechnical Society, 2016, 31(18): 46-53.

链接本文:

https://dgjsxb.ces-transaction.com/CN/Y2016/V31/I18/46

[1] 张又衡. 车辆继电器寿命综合实验台[D]. 长春: 吉林大学, 2007.
[2] 张菲菲, 李志刚. 基于BP神经网络的继电器剩余寿命预测[J]. 低压电器, 2012(1): 11-14. Zhang Feifei, Li Zhigang. Remaining lifetime prediction of relay based on BP neural network[J]. Low Voltage Apparatus, 2012(1): 11-14.
[3] 李华, 孙东旺, 贺鹏举, 等. 基于超程时间回归模型的继电器寿命预测方法[J]. 电工技术学报, 2013, 28(S2): 414-417. Li Hua, Sun Dongwang, He Pengju, et al. The method of relay life prediction based on the regression model of super-path time[J]. Transactions of China Electrotech- nical Society, 2013, 28(S2): 414-417.
[4] Ye Xuerong, Yu Qiong, Zhai Guofu. Reliability assessment for electromagnetic relay based on time parameters degradation[C]//2010 11th International Conference on Electronic Packaging Technology & High Density Packaging, Xi’an, 2010: 1269-1272.
[5] Yu Qiong, Qi Ming, Wang Shujuan, et al. Research on life prediction based on wavelet transform and ARMA model for space relay[C]//4th IEEE Conference on Industrial Electronics and Applications, Xi’an, 2009: 1275-1280.
[6] 任立. 航天继电器可靠性寿命试验分析系统的研究[D]. 哈尔滨: 哈尔滨工业大学, 2009.
[7] 王淑娟, 余琼, 翟国富. 电磁继电器接触失效机理判别方法[J]. 电工技术学报, 2010, 25(8): 38-44. Wang Shujuan, Yu Qiong, Zhai Guofu. Discrimination method of contact failure mechanisms for electro- magnetic apparatus[J]. Transactions of China Electro- technical Society, 2010, 25(8): 38-44.
[8] 冯兴杰, 潘文欣, 卢楠. 基于小波包的RBF神经网络网络流量混沌预测[J]. 计算机工程与设计, 2012, 33(5): 1681-1686. Feng Xingjie, Pan Wenxin, Lu nan. Research on chaotic prediction method of network traffic based on wavelet packet[J]. Computer Engineering and Design, 2012, 33(5): 1681-1686.
[9] Liu Guilong. Rough set theory based on two universal sets and its applications[J]. Knowledge-Based Systems, 2010, 23(2): 110-115.
[10] 高爽, 冬雷, 高阳, 等. 基于粗糙集理论的中长期风速预测[J]. 中国电机工程学报, 2012, 32(1):32-37. Gao Shuang, Dong Lei, Gao Yang, et al. Mid-long term wind speed prediction based on rough set theory[J]. Proceedings of the CSEE, 2012, 32(1): 32-37.
[11] Yanyan Yang, Degang Chen, Ze Dong. Novel algo- rithms of attribute reduction with variable precision rough set model[J]. Neurocomputing, 2014, 139(2): 336-344.
[12] Kai Zheng, Jie Hu, Zhenfei Zhan. An enhancement for heuristic attribute reduction algorithm in rough set[J]. Expert Systems with Applications, 2014, 41(15): 6748-6754.
[13] 高晓红. 基于分类质量的决策系统属性约简新算法[J]. 计算机与现代化, 2010(1): 19-22. Gao Xiaohong. Novel attribute reduction algorithm of decision system based on classification quality[J]. Computer and Modernization, 2010(1): 19-22.
[14] Jing Tian, Quan Wang, Yu Bing. A rough set algo- rithm for attribute reduction via mutual information and conditional entropy[C]//Fuzzy Systems and Know- ledge Discovery(FSKD), Shenyang, 2013: 567-571.
[15] Wang Yun, Wu Zhiqiang. Generating algorithm of approximate decision rules and its application[C]// Granular Computing(GrC), San Jose, CA, 2010: 830- 833.
[16] Qiong Wu, Xin Pan. A novel remote sensing classify- cation rule extraction method based on discrete rough set[C]//Fuzzy Systems and Knowledge Discovery (FSKD), Shanghai, 2011: 330-334.
[17] 杨传振, 朱玉全, 陈耿. 一种基于粗糙集属性约简的多分类器集成方法[J]. 计算机应用研究, 2012, 29(5): 1648-1650. Yang Chuanzhen, Zhu Yuquan, Chen Geng. New classifier ensemble method based on rough set attribute reduction[J]. Application Research of Computers, 2012, 29(5): 1648-1650.
[18] 龙丹丽, 黎静华, 韦化. 粗糙集法解多环境因素影响的母线负荷预测问题[J]. 电网技术, 2013, 37(5): 1335-1340. Long Danli, Li Jinghua, Wei Hua. Solution of multi environmental factor-influenced bus load forecasting by rough set method[J]. Power System Technology, 2012, 37(5): 1335-1340.