AI-driven circular plastic recycling model based on q-Fractional fuzzy Z-information

Abstract

This study focuses on creating an AI-based circular plastic recycling decision-making framework to enhance the sustainability and operational efficiency of plastic waste management systems in a decision-making environment with unknown decision conditions. The proposed recycling facility utilizes artificial intelligence to improve plastic sorting, processing, and resource recovery; and minimize environmental impacts. In order to select the optimal recycling strategies, a multi-criteria decision making (MCDM) framework is presented that is based on the recently developed q-Fractional Fuzzy Z-Numbers (q-FFZNs). To achieve more realistically realistic decision analysis, the proposed model introduces Sugeno-Weber aggregation operators to take into account uncertainty and the reliability of expert evaluations simultaneously. The potential applicability of the proposed framework is illustrated by a case study on an AI based circular plastics recycling plant, where recycling alternatives are assessed based on economic, environmental, energy consumption and process efficiency. For further comparison, the ranking performance of the proposed approach is validated by comparing it with WASPAS method. The outcomes show that the proposed approach based on the q-FFZN framework offers stable and stable rankings and is suitable for dealing with uncertain information and information based on reliability, which helps to find the best recycling strategy. The detailed framework proposed in this work is an efficient decision support tool for sustainable plastic recycling and can be extended to other complex industrial decision-making problems with uncertain information.