基于IPSO-GEV优化的腐蚀油气管道剩余寿命预测  

Residual Life Prediction of Corroded Oil and Gas Pipelines Based on IPSO-GEV Optimization

作　　者：张新生[1] 西忠山 ZHANG Xin-sheng;XI Zhong-shan(School of Management, Xi'an University of Architecture and Technology, Xi * an 710055, China)

机构地区：[1]西安建筑科技大学管理学院

出　　处：《材料保护》2019年第4期42-48,167,共8页Materials Protection

基　　金：国家自然科学基金(41877527);陕西省自然科学基金(2018S34)资助

摘　　要：针对埋地管道腐蚀的随机性及极值类型选择不当而引起的拟合误差等问题,构建了基于IPSO(免疫粒子群优化算法)-GEV(广义极值分布)优化的油气管道最大腐蚀深度预测模型。首先,采用GEV分布拟合极值数据,利用1PSO优化GEV分布函数的参数并确定极值分布类型,以此确定整条管道的最大腐蚀深度;然后,建立基于可靠性理论的腐蚀裕量模型,来预测管道的剩余寿命;最后,以国内两条腐蚀管道为例验证模型的预测精度。实例结果表明:经IPSO-GEV优化的管道最大腐蚀深度预测模型不受限于数据的具体分布,且预测模型的预测精度较高,管道的剩余寿命预测合理。In view of the complexity of the buried pipeline environment and the fitting error caused by the improper selection of the extreme value distribution model, the prediction model of the maximum corrosion depth of the oil and gas pipeline based on the immune particle swarm optimization(IPSO)-generalized extreme value(GEV) ditribution optimization was constructed. First, the GEV distribution was used to fit the extreme value, and the IPSO was used to optimize the parameters of the GEV distribution function and determine the type of the extreme value distribution, which further determined the maximum corrosion depth of the whole pipeline. Then, a residual wall thickness model based on reliability theory was established to predict the remaining life of pipelines. Finally, the prediction accuracy of the model was verified by taking two corrosion pipelines in China as examples. Results showed that after IPSO-GEV distribution optimization, the prediction model of the maximum corrosion depth of the pipeline could be not limited by the specific distribution of the data, and the prediction accuracy of the prediction model was relatively high. Moreover, the prediction of the remaining life of the pipeline was reasonable.

关 键 词：油气输送管道 GEV分布 最大腐蚀深度 免疫粒子群优化算法 可靠度 剩余寿命预测 

分 类 号：U177[交通运输工程] X937[环境科学与工程—安全科学]