To address the issues of semantic heterogeneity among multi-source data and the difficulty in reusing operational maintenance knowledge in intelligent operations and maintenance for gas plants and stations, this paper proposes a method for constructing an ontology model tailored to intelligent O&M in gas plant and station environments. First, by integrating the operational workflows of gas plants and stations, we systematically identify and map the concepts and interrelationships across key knowledge dimensions, including equipment assets, process systems, maintenance tasks, and fault diagnosis. Second, employing a four-stage modeling approach—requirements analysis, concept extraction, hierarchical structuring, and rule definition—we develop an intelligent O&M ontology model for gas plants and stations using the OWL language, and implement its formalized representation and consistency validation through the Protégé tool. Finally, the ontology is integrated into an intelligent O&M prototype system, and its applicability is validated through a fault-diagnosis scenario involving pressure-regulating equipment at a typical plant or station. The results demonstrate that this ontology model enables semantic fusion of multi-source O&M data, achieving a fault-diagnosis accuracy that exceeds traditional experience-based methods by more than 34%, thereby providing robust knowledge support and decision-making assistance for intelligent O&M in gas plants and stations.