Optimisation method of product family supplier selection based on data mining under carbon neutral policy

Abstract

The carbon neutral policy restrains the carbon emissions of product family manufacturers, which incurs additional costs for manufacturers. In previous studies of product family supplier selection, the dilemma of carbon neutrality faced by manufacturers was rarely researched. Therefore, this study puts forward an intelligent optimisation method for product family supplier selection under carbon neutral constraints, which assists manufacturers in satisfying carbon neutrality constraints while minimising total production costs. Firstly, the data representation models of product family are constructed by using information ontology technology, and then the candidate suppliers that meet the manufacturer’s performance requirements are mined by semantic similarity. Secondly, by calculating the configuration cost and carbon footprint of the product family, the configuration cost-carbon neutral cost model (CC-CNC model) of the manufacturer is established with the goal of minimising the manufacturer’s total cost, and then the genetic algorithm is employed to solve the model, thus the optimal supplier selection scheme is mined. The feasibility of the proposed method is demonstrated by supplier selection for water-cooled fan product family, which guides the manufacturer to minimise the cost by selecting the best supplier scheme and taking reasonable carbon neutral measures, contributing to the manufacturer’s low-carbon production and economic benefits.

KEYWORDS:

• Supplier selection
• product family
• carbon neutrality
• cost minimisation
• optimisation model

Disclosure statement

No potential conflict of interest was reported by the authors.

Additional information

Funding

This work was supported by Doctoral Special Project of Nanyang Normal University (grant number 2024ZX030), National Natural Science Foundation of China (grant number 51475459), Key Scientific and Technological Project of Henan Province (grant number 232102211047), and Key Scientific and Technological Project of Henan Province (grant number 242300420439).