微型电脑应用

提前感知光纤链路健康程度是泛网智能变电站时钟系统质量监管模块设计中的重要的内容，为此基于一种数据挖掘算法进行质量监管模块设计与实现。该模块包括三部分：先是对变电站运行大数据和设备台账信息等历史数据信息进行处理，包括标准化处理、降维处理和离散处理；然后利用遗传算法提取数据特征；最后利用数据挖掘算法中的k-means算法进行光纤链路异常状况判断。结果表明所研究方法的漏报率和误报率都低于三种前人研究的方法，说明该模块的设计是有效的，为泛网智能变电站时钟系统完善提供了参考和借鉴。

Sensing the health degree of optical fiber link in advance is an important content in the design of quality supervision module of pan network intelligent substation clock system. Therefore, a module is designed and implemented based on a data mining algorithm. The module design includes three parts. Firstly, the historical data such as substation operation big data and equipment account information are processed, including standardization processing, dimension reduction processing and discrete processing. Then, the genetic algorithm is used to extract data features. Finally, the k-means algorithm of data mining algorithm is used to judge the abnormal condition of optical fiber link. The results show that under the application of the research method, the false alarm rate and false alarm rate are lower than the three previous research methods, which shows that the design of the module is effective, and provides reference for the improvement of Pan network intelligent substation clock system.