Prediction of corrosion rate and characterisation of influencing factors in process pipelines based on data mining

Reliably predicting and characterising corrosion is a fundamental requirement for effective corrosion control in petrochemical plants, particularly for process pipelines that frequently experience corrosion leaks due to corrosive environmental influences. Traditional corrosion monitoring and detection methods have certain limitations in terms of timeliness and scope when identifying pipeline corrosion conditions. This paper proposes a data mining-based approach for predicting the corrosion state of process pipelines in petrochemical plants and further characterises the correlation relationships of key influencing factors. By analysing the characteristics of multi-source corrosion-related data from different types of petrochemical process pipelines and performing data preprocessing, a corrosion rate prediction model was established using genetic algorithm-optimised Gradient Boosting Regression Tree. The model achieved an RMSE of 0.0125, MAE of 0.0090 and R ² of 0.940. Subsequently, through the Spearman correlation coefficient method and Apriori association rule mining algorithm, pressure, chloride ion concentration, temperature, flow rate, sulphide ion concentration and iron ion concentration were identified as key factors influencing the corrosion rate. Based on the proposed association rule construction method, quantitative patterns were revealed, such as a significant increase in corrosion rate (>0.3 mm/a) when the sulphide ion concentration exceeds 120 mg/L, the flow rate exceeds 80 m ³ /h or the pressure exceeds 0.8 MPa. This paper provides a scientific basis and guidance for identifying potential safety hazards and implementing precise corrosion control in petrochemical plants.