Interval-Valued Intuitionistic Uncertain Linguistic Multi-attribute Decision-Making Method for Plant Location Selection with Partitioned Hamy Mean

Plant location selection (PLS) is a typical and complex multi-attribute group decision-making (MAGDM) problem, which requires consideration of several alternatives and multiple attributes. However, existing research results on PLS lack sufficient consideration of complex relationship patterns between attributes, which often leads to inaccurate decision results. Thus, in this paper, a new MAGDM technique is proposed to solve the problem of PLS, in which complex interrelationship structures exist between multi-inputs and attribute values are represented as interval-valued intuitionistic uncertain linguistic variables (IVIULVs). First, to solve the shortcomings of the existing operations, some new operational rules are redefined for IVIULVs based on linguistic scale functions and Archimedean T-conorms and T-norms. These new rules of operation hold the closedness, and are flexible for semantic transformation processing. Then, to more accurately reflect the partition structure and the complex interrelationship pattern among multi-input arguments, we extend the traditional Hamy mean and propose the partitioned Hamy mean (PHAM), which can eliminate the impact of unrelated attributes on the results and meet the semantic conversion needs of different decision makers. Furthermore, we develop two new fuzzy linguistic aggregation operators: interval-valued intuitionistic uncertain linguistic PHAM (IVIULPHAM) and its weighted version (IVIULWPHAM). Finally, a novel MAGDM technique (IVIUL-MAGDM) based on the IVIULWPHAM operator is proposed to solve the problem of PLS. Several examples of PLS are also illustrated to show the validity and advantages of the IVIUL-MAGDM method by comparing with the other existing MAGDM methods.