Simulation Credibility Evaluation Based on Multi-source Data Fusion
Real-world system experiment data, similar system running data, empirical data or domain knowledge of SME (subject matter expert) can serve as observed data in credibility evaluation. It is of great significance to study how to incorporate multi-source observed data to evaluate the validity of the model. Generally, data fusion methods are categorized into original data fusion, feature level fusion, and decision level fusion. In this paper, we firstly discuss the hierarchy of multiple source data fusion in credibility evaluation. Then, a Bayesian feature fusion method and a MADM-based (multiple attribute decision making) decision fusion approach are proposed for credibility evaluation. The proposed methods are available under different data scenarios. Furthermore, two case studies are provided to examine the effectiveness of credibility evaluation methods with data fusion.
KeywordsMulti-source data fusion Credibility evaluation Bayesian feature fusion Model validation
The paper was supported by the National Natural Science Foundation of China (Grant No. 61374164 and 61627810).
- 4.Wang, Z.Q., Fu, Y., Yang, R.Y.: Model validation of dynamic engineering models under uncertainty. In: Proceedings of the ASME 2016 International Design Engineering Technical Conferences and Computers and Information in Engineering Conference, IDETC/CIE (2016)Google Scholar
- 12.McNab, I.R.: Pulsed power options for large EM launchers. In: 2014 17th International Symposium on Electromagnetic Launch Technology (2014)Google Scholar
- 15.Zhou, Y.C.: Transformation methods and assistant tools from data consistency analysis result to simulation credibility. Master dissertation, Harbin Institute of Technology, China (2014)Google Scholar