系统故障演化过程中关键事件的确定方法研究  

Research on the determination method of key events in process system fault evolution

作　　者：李莎莎 崔铁军 LI Shasha;CUI Tiejun(School of Environmental and Chemical Engineering,Shenyang Ligong University,Shenyang 110159,China)

机构地区：[1]沈阳理工大学环境与化学工程学院,沈阳110159

出　　处：《安全与环境学报》2024年第5期1716-1722,共7页Journal of Safety and Environment

基　　金：国家自然科学基金项目(52004120)。

摘　　要：为研究系统故障演化过程中关键事件的确定方法,提出了一种基于核局部保持投影(Kernel Locality Preserving Projections,KLPP)的关键事件确定方法。首先论述了系统故障演化过程、关键事件和因素空间,随后提出了关键事件确定方法,最后进行了实例分析。研究认为系统故障演化过程具有复杂的结构和层次,经历事件是演化测量得到的对象,其中具有决定作用的就是关键事件。关键事件是描述演化过程的基础,可通过因素空间中的对象分布进行确定。通过KLPP方法对对象分布特征进行研究,实现近邻对象分析,得到特征对象。这些特征对象对应的经历事件即为关键事件。按照测量时刻升序排列特征对象即为所求,最终作为描述演化过程的空间故障网络的节点。实例分析得到了预期结果,并说明了方法的特点和研究意义。The purpose of this paper is to study a method for determining key events in the system fault evolution process,and to analyze the objects measured at various times during this process.A basic data matrix is established consisting of two dimensions:factors and objects.The set of neighboring objects of each particular object needs to be considered to determine a characteristic object.The event that occurs when the characteristic object is measured and can be defined as the key event.With this consideration in mind,a key event determination method based on Kernel Local Preserving Projections(KLPP)is proposed.The system fault evolution process,key events,and factor space are then discussed,after which a key event determination method is proposed.Finally,an example is analyzed.This research shows that the system fault evolution process has a complex structure and hierarchy:the experienced event is the object of evolution measurement,while the key event is the decisive one.Key events are the basis for describing a process of evolution and can be determined by a distribution of objects in the factor space.Through the KLPP method,the distribution characteristics of objects can be studied,as well as the characteristic objects obtained by analyzing the nearest neighboring objects.The experienced events corresponding to these characteristic objects are defined as key events.The requirement is to arrange the characteristic objects in ascending order based on measurement time,serving as nodes for a space fault network that describes the evolution process.The use of electrical systems as an example is influenced by six factors.The evolution process measures 100 objects and a process of algorithm analysis obtained 16 characteristic values and characteristic object sets.The key events of the evolution process are then obtained by arranging the characteristic objects in the corresponding measurement order.Finally,the research significance and characteristics of this method are presented.

关 键 词：安全科学技术基础学科 系统故障 演化过程 关键事件 特征对象 核局部保持投影(KLPP) 

分 类 号：X913[环境科学与工程—安全科学]