建立人工神经网络，并利用4个实海暴露点8年累积的腐蚀数据对其进行训练。在训练成功以后，应用其对合金的16年腐蚀行为进行预测。预测结果与实际结果的误差在20%以内，远比传统的函数回归方法小。尤其对于规律性差，无法成功进行函数回归的腐蚀数据，应用人工襁网络预测却能得到较为准确的结果。
Set up an artificial neural net and train it with the data provided by four seawater corrosion experiment stations. After the succession of training , the net can predict any kind of metals corrosion status on 16years and the comparative error is not beyond 20 percent. Compare with the way of function regression, this result is more accurate. The net can also trained with the anomaly data that can not regress to any function and the net can make an accurate prediction.
参考文献
| [1] |
上一张
下一张
上一张
下一张
计量
- 下载量()
- 访问量()
文章评分
- 您的评分：
-
10%
-
20%
-
30%
-
40%
-
50%