基于粗糙集理论通风系统可靠性神经网络仿真  

Study on ventilation system reliability ANN based on rough sets theory

作　　者：王洪德[1] 马云东[2] 陈长华[2] 

机构地区：[1]辽宁工程技术大学计算中心,辽宁阜新123000 [2]辽宁工程技术大学资源与环境工程学院,辽宁阜新123000

出　　处：《辽宁工程技术大学学报（自然科学版）》2003年第4期445-447,共3页Journal of Liaoning Technical University (Natural Science)

基　　金：辽宁省教育厅A类计划项目(202183383)

摘　　要：提出了一种基于粗糙集理论的矿井通风系统可靠性神经网络仿真结构设计模型。通过对属性和属性值的约简,剔除系统中不必要的影响因素指标,以达到对系统可靠性特征参数优化的目的;同时克服了神经网络规模过于庞大及分类识别速度慢等缺点,取得了减少分类过程中模式匹配搜索量的良好效果。该方法对复杂系统可靠性工程的深入研究及应用具有一定的参考价值。New structure design ideas about mining ventilation reliability ANN imitation are put forward in this paper. In order to optimize the reliability characteristic factors of the system, the unnecessary influencing factors of it are eliminated by mean of the reduction of the attribute and its value. At the same time, the disadvantage of the ANN scale too large and the speed of classifiable identification too slow and so on are overcome too. So the fine effects to reduce the pattern match search time in the course of classification. This method has a definite reference value for the further research into the complex system reliability.

关 键 词：粗糙集理论 通风系统 可靠性 神经网络 计算机仿真 属性约简 不可分辨关系 

分 类 号：TD724[矿业工程—矿井通风与安全] TP18[自动化与计算机技术—控制理论与控制工程]