论文部分内容阅读
根据气田现场工况的调研情况,应用动电位极化法测量了典型气田环境中316L不锈钢的临界点蚀温度(CPT),并利用人工神经网络(ANN)技术对CPT进行了预测。结果表明,CPT随Cl-浓度升高而降低,p H值对CPT影响很小。建立的ANN模型对316L不锈钢的CPT具有良好的预测能力,可实现对气田各作业区复杂耦合环境下CPT的预测。ANN模型的预测结果表明,Cl-浓度和p H值对CPT的影响无交互作用,Cl-浓度是影响CPT的主要因素,因此Cl-将是气田防腐蚀工程的重点控制因素。
According to the investigation of gas field conditions, the critical pitting temperature (CPT) of 316L stainless steel in a typical gas field environment was measured by potentiodynamic polarization. The artificial neural network (ANN) was used to predict the CPT. The results showed that CPT decreased with increasing Cl- concentration, and p H value had little effect on CPT. The established ANN model has good predictive ability for 316L stainless steel CPT, which can predict the CPT in complex coupling environment of each operation area of gas field. The prediction results of ANN model show that there is no interaction between the concentration of CP and the value of p H on the CPT. The concentration of Cl- is the main factor affecting CPT. Therefore, Cl- will be the key control factor in the anti-corrosion project.