大数据结构化与数据驱动的复杂系统维修决策

Complex System Maintenance Decisions Based on Big Data Structuration and Data-driven

现代大型机电系统组成结构越来越复杂、智能化程度越来越高,然而系统维修工作却越来越困难;另外,尽管快速发展的信息技术使得系统内部的各种流数据得到了有效的保存,但却缺乏对这类大数据的有效利用、实现复杂系统的维修控制与决策.为此,提出了大数据结构化与数据驱动的复杂系统维修决策方法.大数据结构化使用了层次分析法(Analytic hierarchy process, AHP)的思想,依次建立系统维修的各个层级模型;基于模型抽象出支持系统维修的数据变量、提炼出各层级变量的表达函数;研究进一步实现了维护决策的数据驱动技术,在模型和函数之上定义了数据状态块矩阵,通过设计矩阵的特殊运算算法完成维修决策的数据驱动.最后,使用一个具体的例子来说明提出方法的可用性,结果证明提出的方法是可行的,符合设备维修决策建设目标,即维修方法经济、高效与实用.

Modern large-scale electromechanical systems are the structure more and more complex, the intelligence higher and higher, but the system maintenance work has become more and more difficult. In addition, although the rapid development of information technology has effectively saved all kinds of stream datum in the system, it lacks the effective use of such large data and realizes the maintenance control and decision-making of complex systems. So, a complex system maintenance decision based on the large data structuration and data driven is proposed. Using the analytic hierarchy process(AHP) idea in the big data structuration, the hierarchical model is established in turn for supporting the system maintenance. Data variables are abstracted based on the model, and the expression functions of each level variable are extracted. Further, the maintenance decision based on the data driven technology is realized, the data block matrix over model and function is defined in this research, special operation algorithms on the matrix are developed to carry out the maintenance decision of data driven technology. Finally, a specific example is given to illustrate the availability of the proposed method, and the results show that the proposed method is feasible. With the goal of building equipment maintenance decision, the maintenance method is economical, efficient and practical.