| 灰铸铁石墨形态的神经网络识别研究 |
| |
| 引用本文： | 江虹,曾立波,张泽兰,胡继明. 灰铸铁石墨形态的神经网络识别研究[J]. 武汉大学学报(理学版), 2000, 46(3): 385-388 |
| |
| 作者姓名： | 江虹 曾立波 张泽兰 胡继明 |
| |
| 作者单位： | 武汉大学,分析测试科学系,武汉,430072 |
| |
| 基金项目： | 国家科技部科研基金资助项目(JG-99-9) |
| |
| 摘 要： | 在分析分形维、纹理粗细度及二维回归系数共同组成的纹理特征基础上，本文运用人工神经网络方法实现了对灰铸铁石墨形态的识别．相对于传统方法，该方法识别速度快、重现性强、数据更为客观准确，避免了由于主观判断所引起的人为误差．在识别过程中，本文使用了一种确定隐层节点数的新方法，结果显示良好，对于人工神经网络中隐层节点数确定难的问题具有很好的实用参考价值．
|
| 关 键 词： | 灰铸铁 石墨形态；分形维；粗细度；回归系数 BP网络 |
| 文章编号： | 0253-9888(2000)03-0385-04 |
| 修稿时间： | 2000-01-12 |
Recognizing Graphite Morphology of Gray Cast Iron by ANN |
| |
| JIANG Hong,ZENG Li-bo,ZHANG Ze-lan,HU Ji-ming. Recognizing Graphite Morphology of Gray Cast Iron by ANN[J]. JOurnal of Wuhan University:Natural Science Edition, 2000, 46(3): 385-388 |
| |
| Authors: | JIANG Hong ZENG Li-bo ZHANG Ze-lan HU Ji-ming |
| |
| Affiliation: | JIANG Hong,ZENG Li-bo,ZHANG Ze-lan,HU Ji-ming;(Department of Analysis-Measurement Science, Wuhan University, Wuhan 430072,China) |
| |
| Abstract: | On the base of feature vector composed of fractal parameter, roughness parameter and regression, we complete the classification of the gray cast iron's graphite morphology by ANN. Compared with the traditional method, it works much quicker, and is with better repeatability, more objective and veracious results. Furthermore, we apply a new method to decide the hidden node's number of ANN, which shows valuable to such a difficulty in ANN structure decision. Result shows available. |
| |
| Keywords: | gray east iron graphite morphology fractal roughness regression BP network |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
|
