论文部分内容阅读
为充分利用在故障诊断进程中积累的成功经验和数据,提出了基于粗糙集,近邻算法等理论的实例推理模型,利用粗糙集理论软件rosetta完成对条件属性冗余信息的属性约简,对实例进行权重的确定,再利用近邻算法在故障库中搜索相似实例,从而避免了传统近邻算法计算量大的弊端,在UG软件平台基础上利用UG二次开发工具UG/OPEN设计出友好的人机交互界面诊断系统,减少了故障诊断的时间,提高了生产效率。
In order to make full use of the successful experience and data accumulated in the process of fault diagnosis, an example reasoning model based on rough sets and neighbors algorithm is put forward. Rough set theory software rosetta is used to reduce the attribute information of conditional attributes redundant information. Then the nearest neighbor algorithm is used to search for similar instances in the fault database, which avoids the disadvantages of large amount of computation in the traditional neighbor algorithm. Based on the UG software platform, the UG secondary development tool UG / OPEN is used to design a friendly man-machine Interface diagnostic system, reducing the time to troubleshoot, improve production efficiency.