Abstract: An intelligent identification technology was proposed for the intelligent monitoring of damage in petrochemical pressure equipment. The proposed method primarily included the following key aspects. A custom sample expansion method was developed based on GB/T 30579-2022 Damage Modes Identification for Pressure Equipments and API 571-2020 Corrosion and Materials. 8 000 samples were selected from 20 kinds of damage textual descriptions, which were combined with more than 4 000 inspection and testing engineering case samples to form a mechanistic dataset of over 12 000 equipment damage identification samples. This dataset was used to construct a mechanistic model and conduct mechanism-based damage identification. Based on operational data from over 11 000 engineering inspection cases, a data-driven sample set for damage identification was constructed. This dataset was used to develop an operational big data model and perform data-based damage identification. The mechanistic model and the operational big data model were integrated to develop an intelligent damage identification model for pressure equipment. The results show that the intelligent damage identification model achieved an overall identification accuracy of 0.89 for 20 types of damage, including corrosion thinning, environmental cracking, mechanical damage, and material degradation. The model achieved identification accuracies of 0.95, 0.94, 0.90, and 0.94 for chloride stress corrosion cracking, atmospheric corrosion (without insulation layer), naphthenic acid corrosion, and hydrogen embrittlement, respectively. The model, integrated with operational data retrieved from real-time databases (e.g., DCS/LIMS) of petrochemical plants, enables intelligent monitoring of damage in pressure equipment.