![]() A rule is a classical IF-THEN condition, where the IF-part are humanly readable boolean conditions of variables fulfilling the conclusion. Once the simulation runs have been separated into two groups, our proprietary rule mining technique can extract rules. For the latter case, the categorization by deformation behavior is used by clustering of simulation results with similar distributions of plastic strain. This criterion may be in general a boolean condition, such as a response with specified bounds or the affiliation to a specific deformation mode. As an alternative to common statistical postprocessing, this paper proposes the usage of data-mining methods from the field of knowledge discovery in databases to condensate important effects and give insight into their origins.īefore application of mining techniques, one has to separate the data into two groups regarding a criterion. Efficiently and systematically extracting knowledge from design of experiments studies in the field of vehicle crash simulation is increasingly challenging due to the number and size of the simulation models and the complexity of the occurring mechanisms. ![]()
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |