论文部分内容阅读
通过模糊聚类确定了影响碳钢腐蚀速率的主要土壤因素,对14个腐蚀站点土壤的理化性质以及碳钢的年腐蚀数据进行分析,构建了碳钢年土壤腐蚀预测模型,利用该模型在BP人工神经网络中进行学习、训练、模拟,并将预测结果与现场碳钢埋片腐蚀实验结果对比。结果表明:含水量、pH值、Cl-含量、SO42-、电导率、可溶盐总量6种土壤环境参数为影响14个腐蚀站点土壤中碳钢腐蚀的主要因素;运用BP人工神经网络可以建立起稳定性好的土壤腐蚀预测模型,较好地预测了我国典型地区碳钢在土壤中的腐蚀速率。
The main soil factors influencing the corrosion rate of carbon steel were determined by fuzzy clustering. The physicochemical properties of soil at 14 sites and the annual corrosion data of carbon steel were analyzed. The soil erosion prediction model of carbon steel was constructed. By using this model, Artificial neural network to learn, train, simulate and compare the prediction results with the corrosion results of on-site carbon steel buried pieces. The results showed that six soil environmental parameters including water content, pH value, Cl-content, SO42-, conductivity and total soluble salt content were the main factors affecting the corrosion of carbon steel in 14 corroded sites. Using BP artificial neural network The establishment of a good stability of the soil erosion prediction model, a good prediction of the corrosion rate of carbon steel in the soil in typical areas of our country.