Study On The Application Of Data Mining In The Reliability Evaluation Of Structures

This paper mainly studies several factors that affect the reliability of established structures .The theory of Data Mining is introduced into this paper as a new method to study the evaluation of established structures. New information is ultimately mined from "Data Sea" filed up in existed structures. According to the Chinese Structure Code and engineering experience, the factors affecting the reliability of structures are properly qualified as input parameters. This paper mainly researches with engineering structural examples on the theories of neural networks and fuzzy cluster, which belong to the field of Data Mining.Traditional reliability evaluation of structures and the theory of Data mining are combined together in harmony, which strengthens each other. Not only the traditional reliability evaluation of structures is enriched, the application of the theory of Data mining is also extended. Blank of the application of Data mining theory in civil engineering is filled by the methods put forward in this paper. The problem of immediate on-the-spot reliability evaluation of structures that's has been puzzling people in this field is effectively solved.Comparisons are made between the traditional methods of reliability evaluation of established structures and the method put forward in this paper.According to the analysis of these two methods, it is found that the method put forward in this paper is practicable, reliable and effective. Meanwhile, the weaknesses of the traditional reliability evaluation of structures, that is, long period of evaluation, huge and tedious calculation and arbitral judgments, are avoided with the introduction of the new methods in this paper. For the reason above, the above methods deserve to be extended into engineering application with furthering research.