基于垂直数据格式的企业隐患预警方法研究
发布时间：2019-05-11 01:51
【摘要】：企业在事故隐患排查治理过程中积累了大量隐患数据,为挖掘其潜在价值,实现事故隐患预警预控,针对隐患类型多、数量大的特点,应用垂直数据格式挖掘算法对高维隐患数据进行关联规则挖掘,并利用Kulc和不平衡比(IR)减小隐患出现频率差异对规则的影响;在此基础上,设计基于关联规则的隐患预警评估模型,并对预警信息进行可视化处理,最终构建完整的企业隐患预警方法。以130家机械制造企业的53 029条隐患数据为例,验证所建预警方法的可行性。结果表明,该方法对事故隐患预警的准确率为80.62%。
[Abstract]:Enterprises have accumulated a large number of hidden danger data in the process of accident hidden danger investigation and treatment. In order to excavate its potential value and realize the early warning and pre-control of accident hidden danger, in view of the characteristics of many types and large quantities of hidden dangers, The vertical data format mining algorithm is used to mine the association rules of high dimensional hidden danger data, and Kulc and imbalance ratio (IR) are used to reduce the influence of hidden trouble frequency difference on the rules. On this basis, a hidden danger early warning evaluation model based on association rules is designed, and the early warning information is visually processed, and finally a complete enterprise hidden danger early warning method is constructed. Taking 53 029 hidden danger data from 130 mechanical manufacturing enterprises as an example, the feasibility of the established early warning method is verified. The results show that the accuracy of this method is 80.62%.
【作者单位】： 中国地质大学(北京)工程技术学院;国网吉林电力科学研究院;
【基金】：国家科技支撑计划项目(2015BAK16B03) 国家重点研发计划项目(2016YCF0801906)
【分类号】：X928;TP311.13
[Abstract]:Enterprises have accumulated a large number of hidden danger data in the process of accident hidden danger investigation and treatment. In order to excavate its potential value and realize the early warning and pre-control of accident hidden danger, in view of the characteristics of many types and large quantities of hidden dangers, The vertical data format mining algorithm is used to mine the association rules of high dimensional hidden danger data, and Kulc and imbalance ratio (IR) are used to reduce the influence of hidden trouble frequency difference on the rules. On this basis, a hidden danger early warning evaluation model based on association rules is designed, and the early warning information is visually processed, and finally a complete enterprise hidden danger early warning method is constructed. Taking 53 029 hidden danger data from 130 mechanical manufacturing enterprises as an example, the feasibility of the established early warning method is verified. The results show that the accuracy of this method is 80.62%.
【作者单位】： 中国地质大学(北京)工程技术学院;国网吉林电力科学研究院;
【基金】：国家科技支撑计划项目(2015BAK16B03) 国家重点研发计划项目(2016YCF0801906)
【分类号】：X928;TP311.13
【参考文献】
相关期刊论文 前9条
1 欧阳秋梅;吴超;黄浪;;大数据应用于安全科学领域的基础原理研究[J];中国安全科学学报;2016年11期
2 胡建华;习智琴;周科平;;深部采空区尺寸效应的危险度正态云辨识模型[J];中国安全科学学报;2016年10期
3 王玲;李树林;吴璐璐;;基于定量关联规则树的分类及回归预测算法[J];工程科学学报;2016年06期
4 谭章禄;王泽;陈晓;;基于LDA的煤矿安全隐患主题发现研究[J];中国安全科学学报;2016年06期
5 杨丹;宋英华;洪志坤;吕伟;王U，
本文编号：2474159
本文链接：https://www.wllwen.com/kejilunwen/ruanjiangongchenglunwen/2474159.html
