A heterogeneous GRA-CBR-based multi-attribute emergency decision-making model considering weight optimization with dual information correlation

The emergency response in an engineering operating entails a heterogeneous multi-attribute emergency decision-making (HMAEDM) problem containing crisp, interval, linguistic variables, etc. which is a dynamic process due to the continuous changes of engineering environment. However, few of researches on engineering emergency decision involved with heterogeneous multi attributes, and the static and non-inferential analytical methods ignored the linkage of the dual information between objective characteristics and preference information, which failed to effectively quantify the attribute weights and the similarity between cases and thus are difficult to make a valid decision for the dynamic decision-making environment. Based on case-based reasoning (CBR), a novel emergency decision model embedding with the grey relational analysis (GRA) and grey wolf optimization (GWO) algorithms, is proposed to help engineering emergency decision. Specially, the global indicator is derived by grey incidence degree for the similarity measure between heterogeneous multi-attribute cases from the perspective of system space, along with the GWO-based relative entropy method considering dual information correlation is designed for more reasonable weight allocation. Hence, the proposed model can exploit previous experiences and retrieve the optimal alternative for the future engineering emergency with heterogeneous multi attributes by imitating human thinking process. Finally, a real case in a water transfer project and comparison with three popular methods are conducted to demonstrate the applicability and effectiveness of the proposed model.