Green Supply Chain Optimization Based on BP Neural Network

Area of Science:

• Artificial Intelligence
• Supply Chain Management
• Operations Research

Background:

• The Back Propagation Neural Network (BPNN) offers unique learning, generalization, and non-linear capabilities applicable to prediction tasks.
• Optimizing green supply chains is crucial for improving enterprise economic and environmental performance.
• Intelligent logistics robots can enhance green supply chain operations.

Purpose of the Study:

• To apply the BPNN algorithm for optimizing green supply chains assisted by intelligent logistics robots.
• To develop a systematic approach for selecting suppliers within a green supply chain framework.
• To evaluate the effectiveness of the BPNN model in a practical supply chain selection scenario.

Main Methods:

• Establishment of a supplier evaluation index system with 4 first-level indicators (operational, economic, green, social) and 14 secondary indicators.
• Modeling the evaluation indicator system using the BPNN algorithm.
• Simulation and analysis of a green supply chain enterprise's partner selection in Xi'an using the BPNN model.

Main Results:

• The BPNN model successfully processed input parameters and influencing factors to optimize the green supply chain.
• Supplier selection simulation yielded output scores for five alternative enterprises: 0.77, 0.75, 0.68, 0.72, and 0.65.
• The highest-scoring enterprise was selected as the primary cooperative partner, and the second highest as an alternate.

Conclusions:

• The proposed BPNN-based green supply chain model is scientifically sound and effective, validated through simulation.
• The model provides a scientific and effective method for optimizing green supply chains.
• The study offers significant reference value for future green supply chain optimization initiatives.