当前位置:主页 > 科技论文 > 电力论文 >

信息融合技术在发电机组故障诊断中的应用

发布时间:2018-05-03 00:11

  本文选题:发电机组 + 信息融合 ; 参考:《华东理工大学》2014年硕士论文


【摘要】:随着现代社会用电量的急剧增加,为居民和企业提供持续不间断的供电已变得愈发重要,其直接关系到国民经济的健康发展。近些年来新能源技术开始慢慢发展,但这些能源提供的电能都是零散的,小范围的,且技术还不够成熟,因此传统的能源发电,比如火力发电,仍处于主导地位。如何提前对这些发电机组进行有效的故障诊断以保障其正常运行被提上日程。由于发电机组故障机理日趋复杂化和多样化,传统的故障诊断方法己不能满足现代化设备的需要,本文就是在这样的背景下,开展了信息融合技术在发电机组故障诊断中的应用研究。 针对信息融合技术中的D-S证据理论在证据存在高冲突情况下无法获取准确的诊断结果的问题,本文提出了两种修改组合规则的方法对传统的D-S证据理论进行了改进。一种是认为冲突信息是部分可用的,其可利用的程度取决于证据的支持权和证据的平均支持度的乘积,并通过实际的数值算例来验证了该方法的有效性。其二是认为即使证据之间有冲突但也是完全可用的,把证据冲突概率按各个命题的均比支持度加权进行分配,并将其应用到发电机组的故障诊断中,取得了良好的融合结果。
[Abstract]:With the rapid increase of electricity consumption in modern society, it has become more and more important for the residents and enterprises to supply continuous and continuous power supply. It is directly related to the healthy development of the national economy. In recent years new energy technology has begun to develop slowly, but the energy provided by these energy sources is scattered, small, and the technology is not mature enough. Therefore, the technology is not mature enough. Therefore, the technology is not mature enough. Therefore, the technology is not mature enough, therefore, the transmission of energy is not mature enough. Energy generation, such as thermal power generation, is still in the leading position. How to make effective fault diagnosis of these generators in advance to ensure its normal operation is put on the agenda. Because of the increasingly complex and diversified fault mechanism of the generator set, the traditional fault diagnosis method can not meet the needs of modern equipment. This paper is this paper In this context, the application of information fusion technology in fault diagnosis of generating units is studied.
In view of the problem that D-S evidence theory in information fusion technology can not obtain accurate diagnosis results in the case of high conflict of evidence, this paper proposes two methods of modifying combination rules to improve the traditional D-S evidence theory. One is that the conflict information is partially available, and the extent to which it can be used depends on the evidence. The product of the support weight and the average support of evidence is verified by a practical numerical example. Secondly, it is considered that even if there is a conflict between the evidence but also completely available, the probability of the conflict of evidence is weighted by the average of the propositions than the support degree, and is applied to the fault diagnosis of the generator set. Good fusion results have been achieved.

【学位授予单位】:华东理工大学
【学位级别】:硕士
【学位授予年份】:2014
【分类号】:TM31;TP202

【参考文献】

相关期刊论文 前10条

1 王璇,,李春升,周荫清;多传感器信息融合技术[J];北京航空航天大学学报;1994年04期

2 陈俊任,王保强,刘心田;多传感器数据融合技术与应用[J];成都信息工程学院学报;2005年05期

3 谢春丽,夏虹,刘永阔;多传感器数据融合技术在故障诊断中的应用[J];传感器技术;2004年04期

4 安治永;李应红;苏长兵;;航空电子设备故障诊断技术研究综述[J];电光与控制;2006年03期

5 董彦佼;韩元杰;刘洁莉;;D-S证据理论在多传感器目标识别中的改进[J];弹箭与制导学报;2009年04期

6 刘海燕;赵宗贵;刘熹;;D-S证据理论中冲突证据的合成方法[J];电子科技大学学报;2008年05期

7 王俊松;李建林;;D-S证据理论改进方案综述[J];信息化研究;2011年06期

8 孙全,叶秀清,顾伟康;一种新的基于证据理论的合成公式[J];电子学报;2000年08期

9 易正俊,黄瀚敏,黄席樾;基于Dempster-shafer理论的多个神经网络分类器融合算法[J];重庆大学学报(自然科学版);2002年07期

10 谭逢友;卢宏伟;刘成俊;何玉林;任蜀焱;;信息融合技术在机械故障诊断中的应用[J];重庆大学学报(自然科学版);2006年01期



本文编号:1836065

资料下载
论文发表

本文链接:https://www.wllwen.com/kejilunwen/dianlilw/1836065.html


Copyright(c)文论论文网All Rights Reserved | 网站地图 |

版权申明:资料由用户73515***提供,本站仅收录摘要或目录,作者需要删除请E-mail邮箱bigeng88@qq.com