利用正交试验法获得的TC4钛合金微弧氧化实验数据建立了基于4-11-1(即4个输入神经元,11个隐含层节点,1个输出神经元)结构的BP神经网络预测膜层厚度的模型,并引入遗传算法(GA)对其权值和阈值进行优化.以微弧氧化工艺参数中的电流密度、脉冲频率、占空比和氧化时间作为网络的输入向量,氧化膜层厚度作为网络的输出向量,对比和分析了BP与GA-BP模型的预测结果.与BP网络模型相比,GA-BP网络模型稳定性能较好,并能高精度预测膜层的厚度,GA-BP网络模型预测值的平均误差为0.015,最大误差仅为0.036,而BP模型预测结果的平均误差为0.064,最大误差为0.099.
参考文献
| [1] | 王丽,付文,陈砺.等离子体电解氧化技术及机理研究进展[J].电镀与涂饰,2012(04):48-52. |
| [2] | A. L. Yerokhin;X. Nie;A. Leyland;A. Matthews;S. J. Dowey .Plasma electrolysis for surface engineering[J].Surface & Coatings Technology,1999(2/3):73-93. |
| [3] | 王凤彪,狄士春.医用钛合金微弧氧化膜的制备及其生物相容性研究[J].电镀与涂饰,2011(06):25-28. |
| [4] | 钟涛生,蒋百灵,李均明.微弧氧化技术的特点、应用前景及其研究方向[J].电镀与涂饰,2005(06):47-50. |
| [5] | 李克杰,李全安.合金微弧氧化技术研究及应用进展[J].稀有金属材料与工程,2007(z3):199-203. |
| [6] | Tsunekawa, S.;Aoki, Y.;Habazaki, H. .Two-step plasma electrolytic oxidation of Ti-15V-3Al-3Cr-3Sn for wear-resistant and adhesive coating[J].Surface & Coatings Technology,2011(19):4732-4740. |
| [7] | Khorasanian, M.;Dehghan, A.;Shariat, M.H.;Bahrololoom, M.E.;Javadpour, S. .Microstructure and wear resistance of oxide coatings on Ti-6Al-4V produced by plasma electrolytic oxidation in an inexpensive electrolyte[J].Surface & Coatings Technology,2011(6):1495-1502. |
| [8] | Minghui Chen;Wenbo Li;Mingli Shen;Shenglong Zhu;Fuhui Wang .Glass-ceramic coatings on titanium alloys for high temperatureoxidation protection: Oxidation kinetics and microstructure[J].Corrosion Science: The Journal on Environmental Degradation of Materials and its Control,2013(Sep.):178-186. |
| [9] | TAN G P;WANG D F;LI Q .Vehicle interior sound quality prediction based on back propagation neural network[J].Procedia Environmental Sciences,2011,11(Part A):471-477. |
| [10] | Gianluca Buffa;Livan Fratini;Fabrizio Micari .Mechanical and microstructural properties prediction by artificial neural networks in FSW processes of dual phase titanium alloys[J].Journal of manufacturing processes,2012(3):289-296. |
| [11] | 严浙平,李滋,陈涛,赵玉飞,杜朋洁.基于GA-BP神经网络的UUV航向容错控制[J].传感技术学报,2013(09):1236-1242. |
| [12] | LIU K;GUO W Y;SHEN X L et al.Research on the forecast model of electricity power industry loan based on GA-BP neural network[J].Energy Procedia,2012,14:1918-1924. |
| [13] | 田亮,罗宇,王阳.基于遗传算法优化BP神经网络的TIG焊缝尺寸预测模型[J].上海交通大学学报,2013(11):1690-1696,1701. |
| [14] | 傅荟璇;赵红.MATLAB神经网络应用设计[M].北京:机械工业出版社,2010:83-91. |
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%