采用非线性动力学系统的BP数据网络进行管材涂层腐蚀性能预测。首先采用增重法获取9种腐蚀工况下的增重数据，将获取的数据用于构建 BP 神经网络模型，通过传输和反演操作设置拓扑结构为6×15×1的 BP神经网络，然后基于90组实验数据用于验证和评价BP神经网络预测模型，最后通过对优选出的涂层进行 Ni-Cr 系涂层的机理分析，从而解决生物质电站锅炉“四管”的腐蚀问题，研发的抗腐蚀涂层具有较好的经济性和实用性。
BP neural network that belongs to nonlinear dynamics system was used to predict corrosion property of pipe coatings in this experiment.Firstly desiccant method was adopted to obtain the weight data of 9 corrosion con-ditions,then the data was used to build BP neural network model.The BP neural network model with the topological structure of 6×15×1 was set up through transmission and inverse operation.Based on the experimental data,90 groups of them were used to verify and evaluate the BP neural network model.At last,the mechanism of the best Ni-Cr coating was analyzed,so as to solve the corrosion problems of“four tubes”in biomass power plant boiler.And the corrosion resistance coating devised in this research is more economical and practical.
参考文献
- 下载量()
- 访问量()
- 您的评分：
-
10%
-
20%
-
30%
-
40%
-
50%