<p>As the demand for natural gas supply chain security increases, the optimization of inspection efficiency in natural gas stations is increasingly critical to ensure the safe operation of equipment. This study identifies key issues, including the disregard for equipment priority differences and inadequate coordination of multiple objectives in traditional inspection path planning. By integrating digitalization and artificial intelligence technologies, and considering both inspection costs and priority satisfaction, a priority satisfaction function is constructed, and a multi-objective optimization model is proposed to minimize inspection costs and maximize priority satisfaction. A hybrid genetic-simulated annealing algorithm (GA-SA) is designed to solve this model. A case study was conducted to validate the model and algorithm’s effectiveness in reducing inspection costs and enhancing priority satisfaction. The study demonstrated that, compared to experience-based manual planning methods, the proposed model reduced inspection costs by approximately 20.70% and increased priority satisfaction by about 5.33%. These improvements are practically significant for the natural gas industry: the 20.70% cost reduction directly alleviates operational burdens, while the 5.33% enhancement in priority satisfaction strengthens coverage of high-risk equipment, aligning with the industry’s dual goals of economic efficiency and safety. A sensitivity analysis of key parameters (including β, ω₁, D_max, and α) is conducted to provide practical parameter setting guidelines, enhancing the model’s applicability. Based on the research findings, a dynamic inspection path management strategy based on artificial intelligence is proposed, which provides intelligent decision support that balances both economic and safety considerations for the natural gas industry. This strategy also offers theoretical insights for multi-objective path optimization problems in complex scenarios.</p>