基于ALPO的碳钢大气腐蚀速率预测研究  

Research on Prediction of Atmospheric Corrosion Rate of Carbon Steel Based on ALPO

作　　者：杨彪 闫莹[2] 刘振栋 YANG Biao;YAN Ying;LIU Zhendong(Industrial School of Shen’an Cyber Security,Shanghai Technical Institute of Electronics&Information,Shanghai 201411,China;School of Resources and Environmental Engineering,East China University of Science and Technology,Shanghai 200237,China;School of Computer and Information Engineering,Shanghai Polytechnic University,Shanghai 201209,China)

机构地区：[1]上海电子信息职业技术学院,申安网络安全产业学院,上海201411 [2]华东理工大学,资源与环境工程学院,上海200237 [3]上海第二工业大学,计算机与信息工程学院,上海201209

出　　处：《微型电脑应用》2025年第2期265-268,272,共5页Microcomputer Applications

摘　　要：针对大气环境下碳钢材料腐蚀速率预测模型的构建问题,提出一种结合自适应变异粒子群优化(AMPSO)和最小二乘支持向量机(LSSVM)的自适应最小二乘支持向量机粒子优化(ALPO)模型。利用AMPSO对LSSVM的核心参数进行优化,克服LSSVM参数选取的随机性,以提高大气环境下碳钢材料腐蚀速率预测的准确性。基于伊比利亚美洲腐蚀图(MICAT)碳钢腐蚀速率数据集,对比ALPO与传统模型的预测效果。结果显示,ALPO相对于LSSVM将平均绝对误差(MAE)、平均绝对百分比误差(MAPE)、均方根误差(RMSE)分别降低了40.04个百分点、38.01个百分点、42.83个百分点,表明所提模型对于碳钢大气腐蚀率的预测更为精准,可行性更高,为碳钢大气腐蚀速率预测模型的构建提供了一种新的方法。An adaptive least squares support vector machine particle optimization(ALPO)model that integrates adaptive mutation particle swarm optimization(AMPSO)and least squares support vector machine(LSSVM)is proposed in this paper to address the issue of predicting carbon steel corrosion rates in atmospheric environments.AMPSO is utilized to optimize the core parameters of LSSVM,overcome the randomness of parameter selection,and improve the prediction accuracy of carbon steel corrosion rates.The predictive performance of the ALPO model and traditional models is evaluated based on the iberoamerican corrosion map project(MICAT)carbon steel corrosion rate dataset.The results show that ALPO reduces the mean absolute error(MAE)mean absolute percentage error(MAPE)and root mean square error(RMSE)by 40.04 percentage points,38.01 percentage points and 42.83 percentage points,respectively,compared to the LSSVM model.This indicates that the ALPO model provides more accurate and feasible predictions for atmospheric corrosion rates of carbon steel,and offers a new method for constructing prediction model for carbon steel atmospheric corrosion rates.

关 键 词：碳钢 大气腐蚀 粒子群优化 支持向量回归 腐蚀速率预测 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]