支持向量机多重分类救生舱环境评价研究  

Study on dynamic environment assessment for coal refuge chamber based on support vector machine multi-classification

作　　者：姚舜才[1,2] 朱红青[1] 沈静[1] 和超楠[1] 

机构地区：[1]中国矿业大学〈北京〉资源与安全工程学院,北京100083 [2]中北大学信息与通信工程学院,山西太原030051

出　　处：《中国安全生产科学技术》2013年第4期44-50,共7页Journal of Safety Science and Technology

基　　金：国家自然科学基金资助项目(51074168);中央高校基本科研业务费专项资金(青年科研专项)资助项目(2010QZ03)

摘　　要：针对矿用救生舱舱内环境动态评价的问题,采用支持向量机多重分类机制进行评价研究。确定了舱内环境评价的等级指标;将环境评价问题处理为分类和分级两部分,分别给出了相应的函数。使用粒子群优化算法进行了参数优化;制订了具体的评价方案,得出了动态评价结果。经现场试验证明,该环境评价方法可以对救生舱舱内环境进行有效、实时的动态评价,算法收敛速度较快,为救生舱舱内环境调控提供了可靠的理论基础和充分的现场数据。Aiming at the problem of dynamic environment assessment in coal mine refuge chamber, support vector machine multi-classification was adopted to assess research. The classification targets of inner environment were de- fined. Environment assessment of refuge chamber was divided into two parts, which were classification and grading The corresponding functions were given. The parameters were optimized by using particle swarm organization, for- mulates specific assessment scheme, and final dynamic assessment results were obtained. It was proved that the as- sessment scheme can assess inner environment of coal mine refuge chamber in real time and effectively by experiments, which are accomplished in a practical chamber. Furthermore, the convergence speed of assessment algorithm was improved. It provided reliable theoretical basis and adequate data.

关 键 词：矿用救生舱 支持向量机 多重分类 动态环境评价 

分 类 号：TP272[自动化与计算机技术—检测技术与自动化装置]