Risk Assessment Method for New Energy Vehicle Supply Chain Based on Hierarchical Holographic Model and Matter Element Extension Model

New energy vehicles provide new solutions for low-carbon emissions. With the continuous expansion of the new energy vehicle industry, a more scientific supply chain management system is needed to effectively identify and evaluate risks. This study proposes a more scientific and comprehensive risk assessment method for the supply chain system of new energy vehicles based on a hierarchical holographic model and matter element extension model. The results showed that the proposed algorithm improved the classification performance of risk factors by 1.2%, 1.3%, and 1.5% compared to the clustering performance of the nearest frequency amount clustering, particle swarm optimization, and selforganizing mapping algorithms. In terms of noise processing effectiveness, the Rand index has improved by an average of 55% and 41% compared to the kernel density threshold algorithm and spectral clustering algorithm, with smaller fluctuations and significant differences (P<0.05). The accuracy, recall, and F-measure were 9.4%, 8.5%, and 9.6% higher than traditional spectral clustering algorithms, with smaller fluctuations and significant differences (P<0.05). While reducing the risk handling time by 21%, the effect has improved by 6%, and the fluctuations during the risk handling process were smaller than those of the self-exploration model. Therefore, the proposed algorithm can cope with many uncertain factors in the complex supply chain management system, ensuring the sustainability and stability of the development of the new energy vehicle industry supply chain.