Answers are grounded in this paper and cite their sources.
To address the challenge of reducing carbon emissions in the automotive industry, new energy vehicles (NEVs) have emerged, leading to an increase in the number of discarded vehicles. Utilising internet technology for recycling not only helps manage discarded vehicles and enhance enterprise efficiency but also meets government environmental requirements. Therefore, this study explores the impact of government intervention on the green supply chain of dual recycling channels for NEVs and proposes an Improved Multi-Objective Deep Reinforcement Learning Algorithm (IMDRL) to handle complex recycling issues. The study's conclusions include: (1) The combination of multiple recycling channels can reduce costs and carbon emissions while improving the return on investment in big data. (2) The IMDRL algorithm can dynamically adjust remanufacturing supply chain strategies to achieve optimal solutions. (3) Government subsidies significantly enhance the efficiency of multi-cycle multi-objective optimisation. The contributions of the study include: (1) Establishing models for online, offline, joint, and government intervention recycling, providing insights for efficient multi-channel recycling. (2) Proposing the IMDRL algorithm, which integrates fuzzy optimisation, Multi-Objective Deep Learning Algorithm, and heuristic Hybrid Algorithm (HA), to more accurately predict and solve multi-objective problems. (3) Providing management theories for government support in establishing NEVs remanufacturing supply chains.
No takes yet. Share an insight, caveat, or question.
Wang et al. (2024) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: