基于粒子群优化和最小二乘支持向量机的储罐腐蚀速率预测  

Corrosion Rate Prediction of Storage Tank Based on Particle Swarm Optimization and Least Squares Support Vector Machine

作　　者：王明慧 党鹏飞 杨铮鑫 龚博 WANG Minghui;DANG Pengfei;YANG Zhengxin;GONG Bo(School of Mechanical and Power Engineering,Shenyang University of Chemical Technology,Shenyang 110142,China;Second Oil Mine Geological Team of Sixth Oil Production Plant,Petrochina Daqing Oilfield,Daqing 163400,China)

机构地区：[1]沈阳化工大学机械与动力工程学院,沈阳110142 [2]中国石油大庆油田采油六厂第二油矿地质队,大庆163400

出　　处：《腐蚀与防护》2024年第8期71-76,共6页Corrosion & Protection

基　　金：国家自然科学基金(12002219);辽宁省教育厅一般项目(LQ2019008)。

摘　　要：利用粒子群优化(PSO)算法的全局寻优能力,对最小二乘支持向量机(LSSVM)的正则化参数和核参数进行优化,提出了基于PSO-LSSVM的大型储罐腐蚀速率的预测方法。采用该方法对储罐腐蚀速率进行预测,并利用实测数据对模型的预测精度进行验证。结果表明:使用PSOLSSVM获得的腐蚀速率预测结果与实际腐蚀速率较为吻合,罐顶、第一层罐壁、罐底预测结果的平均绝对百分误差分别为2.265%、3.077%、1.18%,均方根误差分别为0.010%、0.012%、0.011%,决定系数分别为0.973、0.982、0.976。该方法可以对储罐内腐蚀速率进行有效的预测。A prediction method for corrosion rate of large storage tanks was proposed based on particle swarm optimization(PSO)algorithm and least squares support vector machine(LSSVM),which utilize the global optimization capability of PSO algorithm to optimize the regularization parameters and kernel parameters of LSSVM.The corrosion rates of storage tanks were predicted by the method,and the prediction accuracy of the model was verified by measured data.The results show that the predicted corrosion rates obtained using PSO-LSSVM were in good agreement with the actual corrosion rates.The mean absolute percentage errors of the predicted results of the tank top,the first tank wall and the tank bottom were 2.265%,3.077%and 1.18%,the root mean square errors were 0.010%,0.012%and 0.011%,and the corresponding coefficient of determination were 0.973,0.982 and 0.976,respectively.So this method can effectively predict the corrosion rates of storage tanks.

关 键 词：粒子群优化(PSO) 最小二乘支持向量机(LSSVM) 腐蚀速率预测 

分 类 号：TE988[石油与天然气工程—石油机械设备]