利用人工神经网络所具有的高度非线性映射功能，对现役长输油气腐蚀管道失效压力进行预测，并综合分析了管径、壁厚、屈服强度、环向腐蚀速率、径向腐蚀速率、缺陷长度及蚀坑深度对腐蚀管道失效压力的影响。为了验证人工神经网络具有很好的通用性，通过选择6种不同管径的腐蚀管道样本训练集交叉对网络进行训练，并利用训练好的网络进行预测。结果表明，人工神经网络在满足工程需要的前提下，是一个比较准确、方便的数学模型。
The failure pressure of long-distance gas pipeline was predicted based on nonlinear mapping function of artificial neural network. The effects of pipe diameter, pipe wall thickness, material yield strength, radial corrosion rate, longitudinal corrosion rate, defect length and pit depth on the pipeline failure were analyzed comprehensively. In order to illustrate the generality of neural network, the network was trained using sample training set from six corroded pipelines with different diameters. The result showed that the neural network can be a more accurate and convenient method to predict pipeline failure.
参考文献
| [1] | |
| [2] | |
| [3] |
- 下载量()
- 访问量()
- 您的评分：
-
10%
-
20%
-
30%
-
40%
-
50%