基于径向基函数神经网络预测模型评价油气水集输管道的均匀腐蚀缺陷  

Evaluation of Uniform Corrosion Defects of Oil-Gas-Water Gathering Pipeline Based on Radial Basis Function Artificial Neural Network Prediction Model

作　　者：曾维国[1] 李曙华 李岩 范峥[4] ZENG Weiguo;LI Shuhua;LI Yan;FAN Zheng(China Special Equipment Inspection and Research Institute.Beijing 100029,China;Gas Field Development Office,Changqing Oilfield Company of PetroChina,Xi'an 710021,China;Oil Field Development Office,Changqing Oilfield Company of PetroChina,Xi’an 710018,China;College of Chemistry and Chemical Engineering,Xi'an Shiyou University,Xi’an 710065,China)

机构地区：[1]中国特种设备检测研究院,北京100029 [2]中国石油长庆油田分公司气田开发事业部,西安710021 [3]中国石油长庆油田分公司油田开发事业部,西安710018 [4]西安石油大学化学化工学院,西安710065

出　　处：《腐蚀与防护》2020年第10期50-56,共7页Corrosion & Protection

基　　金：中国国家留学基金(201908610135);陕西省科学技术研究与发展计划(2016GY-150)。

摘　　要：利用多相动态腐蚀检测装置测定不同工况下油气水集输管道的均匀腐蚀速率,以此结果为样本建立径向基函数人工神经网络预测模型,并对管道均匀腐蚀缺陷进行评价。结果表明:当以硫化氢含量、二氧化碳含量、水含量、钙离子含量、镁离子含量、氯离子含量、温度、压力、流速等为输入信号,以管道均匀腐蚀速率为输出信号时,9-29-1型径向基函数人工神经网络结构合理且准确度良好,经过4450次迭代后,预测模型的均方误差为0.0009,小于允许收敛误差限0.0010,在训练阶段、验证阶段与测试阶段线性拟合的决定系数分别为0.993、0.973、0.969,预测值和期望值具有较高相关性,同时还依据该模型找出了9段存在均匀腐蚀风险的管道。The uniform corrosion rates of oil-gas-water gathering pipeline under different working conditions were measured by a multiphase dynamic corrosion detection device.A radial basis function artificial neural network prediction model was established using the data from above mentioned experiment as samples.The average corrosion defects of the pipeline were also evaluated.The results show that 9-29-1 radial basis artificial neural network had a reasonable structure and good accuracy when hydrogen sulfide content,carbon dioxide content,water content,calcium ion content,magnesium ion content,chloride ion content,temperature,pressure and flow rate were used as input signals and uniform corrosion rate was used as output signal.A mean square error of 0.0009 lower than the specific convergence tolerance of 0.0010 was obtained after 4450 iterations.The coefficients of determination of linear fitting in training,verification and testing stages were 0.993,0.973 and 0.969,respectively,demonstrating high relevance between the predicted values and the desired values.Meanwhile,according to the model,9 sections of pipelines with uniform corrosion risk were found.

关 键 词：油气水集输管道 径向基函数 人工神经网络 预测 均匀腐蚀 评价 

分 类 号：TG172.8[金属学及工艺—金属表面处理]