压力容器2025，Vol.42Issue(2)：80-86,7.DOI:10.3969/j.issn.1001-4837.2025.02.010
大型原油储罐底板腐蚀速率预测方法研究
Research on prediction method of corrosion rate of floor of large crude oil storage tank
摘要
Abstract
In view of the difficulty of quantitatively predicting the corrosion rate of the bottom plate of large crude oil storage tanks,when the tank was not opened,the main factors affecting or characterizing the corrosion of the bottom plate were screened by collecting the design and construction,inspection and operation sampling data of a large number of 5×104～1.5×105 m3 large crude oil storage tanks in China.Based on random forest(RF)combined with particle swarm optimization(PSO),the corrosion rate prediction model of crude oil storage tank floor was established.The results show that the error between the predicted corrosion rate of tank floor and the measured corrosion rate of tank floor is small,and the error between the predicted value and the measured value of 93.3%is less than 0.1 mm/a,which has a high accuracy with mean absolute error(MAE)of 0.021 mm/a,root mean square error(RMSE)of 0.038 mm/a and the correlation(R2)of 0.942.The research can provide technical support for making maintenance cycle and corrosion protection decision of large crude oil storage tank.关键词
原油储罐/随机森林/粒子群优化/机器学习Key words
crude oil storage tank/random forest/particle swarm optimization/machine learning分类
机械工程引用本文复制引用
程伟,陈炜,袁文彬,李志远,巫红军,吴祥..大型原油储罐底板腐蚀速率预测方法研究[J].压力容器,2025,42(2):80-86,7.基金项目
国家重点研发计划项目(2024YFC3014204) （2024YFC3014204）
