基于数据挖掘的集中监控设备典型缺陷预测方法

为改善传统方法对监控设备典型缺陷分析结果的不理想,提出了基于数据挖掘技术的集中监控设备缺陷预测方法。预测集中监控设备在未来时间内的相关监控数据,并将其与历史典型缺陷发生期间内的监控数据相似度进行比较,以量化指标的形式对集中监控设备的典型缺陷进行预测。实验结果表明,利用所提方法对实际发生的油温异常典型缺陷进行预测,计算出的相似度指标形成了一个峰值,而缺陷未发生时的相似度指标较低,证明本文方法能够较好地体现缺陷发生的可能性,整体应用性较高。

Research on Typical Defect Prediction Method of Centralized Monitoring Equipment Based on Data Mining

In order to improve the traditional method to analyze the typical defect analysis results of monitoring equipment, this paper proposes a method based on data mining technology to predict the defects of centralized monitoring equipment. It predicts the relevant monitoring data of the centralized monitoring equipment in the future time, and compares it with the similarity of the monitoring data during the historical typical defect occurrence period, and predicts the typical defects of the centralized monitoring equipment in the form of quantitative indicators. The experimental results show that the proposed method can predict the typical oil temperature anomalies, and the calculated similarity index forms a peak, while the similarity index is lower when the defect does not occur, which proves that the method can be better. Reflecting the possibility of defects, the overall application is higher.