Dual carbon oriented optimization method for manufacturing industry chain based on BP neural network and clonal selection algorithm

Abstract

Global economic growth and increasing carbon emissions pose significant challenges to managing and optimizing industry chains. Against the backdrop of carbon peak and carbon neutrality goals, manufacturing enterprises forgo economic efficiency to achieve low-carbon goals. Therefore, balancing the economic efficiency and carbon emissions of the entire industrial chain has become a vital issue for manufacturing enterprises. Based on the existing research, "a dual carbon industrial chain" is proposed in this study to reveal the characteristics of the industrial chain under the dual carbon goals. A collaborative optimization model under the "dual carbon industrial chain" was constructed by combining complex networks, back-propagation (BP) neural networks, and clonal selection algorithm to optimize the economic efficiency and carbon emissions of the entire industrial chain. Using a chip industry chain as an example, an optimization solution from the perspective of the overall industry chain is proposed. The results show that the proposed method can optimize the economic benefits and carbon emissions of the entire industrial chain, which has specific theoretical and practical significance for developing modern industrial chains with a dual carbon background.