XING Chong*,WANG Kunhao.Prediction of Hardness of Hard Anodic Oxidation Film Based on BP and RBF Neural Network[J].Plating & Finishing,2021,(7):25-29.[doi:10.3969/j.issn.1001-3849.2021.07.005]
基于BP和RBF神经网络预测硬质阳极氧化膜的硬度
- Title:
- Prediction of Hardness of Hard Anodic Oxidation Film Based on BP and RBF Neural Network
- 文献标志码:
- A
- 摘要:
- 通过两种不同方式分别构建NEWRB函数RBF神经网络和K-均值聚类RBF神经网络，同时构建BP神经网络。采用正交实验数据对不同神经网络进行训练，然后用训练完成的不同神经网络预测硬质阳极氧化膜的硬度，并将预测结果与实测值进行对比。结果表明：与BP神经网络相比，NEWRB函数RBF神经网络和K-均值聚类RBF神经网络的平均相对误差和最大相对误差均较低。通过两种不同方式构建的RBF神经网络都具有较高的预测精度，并且K-均值聚类RBF神经网络具有更高的预测精度，更适用于预测硬质阳极氧化膜的硬度。
- Abstract:
- NEWRB function RBF neural network and K-mean clustering RBF neural network were established in two different ways, and BP neural network was also established. Different neural networks were trained using orthogonal experimental data, and then the trained different neural networks were used to predict the hardness of hard anodic oxidation film, and the predicted value was compared with the measured value. The results showed that compared with BP neural network, the average relative error and maximum relative error of NEWRB function RBF neural network and K-mean clustering RBF neural network were lower. The RBF neural network established by two different methods has higher prediction accuracy, and the K-mean clustering RBF neural network has much higher prediction accuracy, which was more suitable for predicting the hardness of hard anodic oxidation film.
参考文献/References:
[1] 张欢. 氧化时间对2A12铝合金硬质阳极氧化膜性能的影响[J]. 航空制造技术,2014,466(22):148-150.
Zhang H. Influence of oxidation time on property of hard anodic oxidation film on 2A12 aluminum alloy[J]. Aeronautical Manufacturing Technology,2014,466(22):148-150(in Chinese).
[2] 时春燕. 挤压成型2A12铝合金硬质阳极氧化膜的制备工艺及性能研究[D]. 南昌:南昌航空大学,2018.
[3] Kong D J,Wang J C,Liu H. Friction and wear performances of 7475 aluminium alloy after anodic oxidation[J]. Rare Metal Materials and Engineering,2016,45(5):1122-1127(in Chinese).
[4] 石绪忠,刘晓鹤,余向飞,等. 6061铝合金硬质阳极氧化的影响因素研究[J]. 材料开发与应用,2018,33(4):53-58.
Shi X Z,Liu X H,Yu X F,et al. Study on the influence factors of hard anodic oxidation of 6061 aluminum alloy[J]. Development and Application of Materials,2018,33(4):53-58(in Chinese).
[5] 于金金, 吕一兵. 一种求解非线性极大极小问题的神经网络方法[J]. 长江大学学报(自科版), 2019, 16(4):67-70.
Yu J J,Lyu Y B. A neural network method for solving nonlinear minimax problems[J]. Journal of Yangtze University(Natural Science Edition),2019,16(4):67-70(in Chinese).
[6] Moustris K,Tsiros I X,Tseliou A,et al. Development and application of artificial neural network models to estimate values of a complex human thermal comfort index associated with urban heat and cool island patterns using air temperature data from a standard meteorological station[J]. International Journal of Biometeorology,2018(62):1265-1274.
[7] Peurifoy J,Shen Y C,Jing L,et al. Nanophotonic particle simulation and inverse design using artificial neural networks[J]. Science Advances, 2018, 4(6):4206-4213.
[8] 王嵘冰,徐红艳,李波,等. BP神经网络隐含层节点数确定方法研究[J]. 计算机技术与发展, 2018, 28(4):31-35.
Wang R B,Xu H Y,Li B,et al. Research on method of determining hidden layer nodes in BP neural network[J]. Computer Technology and Development, 2018, 28(4):31-35(in Chinese).
[9] Kai C,Qin X T. Virtual reality research of the dynamic characteristics of soft soil under metro vibration loads based on BP neural networks[J]. Neural Computing and Applications, 2017, 29(5):1233-1242.
[10] 王晓雷,李栋豪,郑晓婉,等. 基于RBF神经网络的跌倒检测算法研究[J]. 电子测量与仪器学报,2019,33(11):185-191.
Wang X L,Li D H,Zheng X W,et al. Research on fall detection algorithm based on RBF neural network[J]. Journal of Electronic Measurement and Instrument,2019,33(11):185-191(in Chinese).
[11] 王敏,周树道,刘展华,等. 卷积神经网络识别地基云图的数据库建立及处理方法[J]. 信息技术与网络安全,2020, 39(3):56-61.
Wang M,Zhou S D,Liu Z H,et al. Establishment and processing of Ground-based cloud image database for CNN[J]. Information Techology and Network Security, 2020,39(3):56-61(in Chinese).
[12] 雷升锴,刘红阳,何嘉,等. 动态K-均值聚类算法在RBF神经网络中心选取中的应用[J]. 信息系统工程,2011(6):83-85.
Lei S K,Liu H Y,He J,et al. Application of dynamic K-means clustering algorithm in RBF neural network center selection[J]. Information System Engineering,2011(6):83-85(in Chinese).
相似文献/References:
[1]张士宪,赵晓萍,李 慧,等.Mo基MoSi2复合材料的力学和抗热震性能研究[J].电镀与精饰,2018,(12):11.[doi:10.3969/j.issn.1001?3849.2018.12.003]
ZHANG Shixian,ZHAO Xiaoping,LI Hui,et al.Study on Mechanical Properties and Thermal Shock Resistance of Mo-MoSi2 Composite Materials[J].Plating & Finishing,2018,(7):11.[doi:10.3969/j.issn.1001?3849.2018.12.003]
[2]贾启华,许晓娟*.沉积时间对镁合金化学镀镍的影响[J].电镀与精饰,2019,(12):1.[doi:10.3969/j.issn.1001-3849.2019.12.001]
JIA Qihua,XU Xiaojuan*.Effect of Deposition Time on Direct Electroless Plating of Magnesium Alloys[J].Plating & Finishing,2019,(7):1.[doi:10.3969/j.issn.1001-3849.2019.12.001]
[3]谭宇硕*,容旭巍,韩 瀚,等.45钢杆件化学镀Ni-Co-P及Ni-W-P镀层的性能比较[J].电镀与精饰,2020,(9):1.
TAN Yushuo*,RONG Xuwei,HAN Han.Comparison of Properties of Ni-Co-P Coating and Ni-W-P Coating Prepared by Electroless Plating on Surface of 45 Steel Rod-Shaped Parts[J].Plating & Finishing,2020,(7):1.
[4]高 辉,刘伟杰*.2A12铝合金电沉积Ni-Co-MoS2复合镀层的耐磨性能研究[J].电镀与精饰,2020,(10):1.[doi:10.3969/j.issn.1001-3849.2020.10.0010]
GAO Hui,LIU Weijie*.Research on Wear Resistance of Ni-Co-MoS2 Composite Coating Electrodeposited on 2A12 Aluminium Alloy[J].Plating & Finishing,2020,(7):1.[doi:10.3969/j.issn.1001-3849.2020.10.0010]
[5]丁小艳,程俊,丁德林.基于神经网络和遗传算法的电沉积Ni-TiB2复合镀层工艺参数优化[J].电镀与精饰,2020,(11):20.[doi:10.3969/j.issn.1001-3849.2020.11.0050]
DING Xiaoyan,CHENG Jun,DING Delin.Optimization of Process Parameters of Electrodepositing Ni-TiB2 Composite Coating based on Neural Network and Genetic Algorithm[J].Plating & Finishing,2020,(7):20.[doi:10.3969/j.issn.1001-3849.2020.11.0050]
[6]刘建祥*,浦建堂,周 磊,等.有机磺酸盐添加剂对电镀硬铬性能的影响[J].电镀与精饰,2021,(6):6.[doi:10.3969/j.issn.1001-3849.2021.06.002]
LIU Jianxiang*,PU Jiantang,ZHOU Lei,et al.Effect of Organic Sulfonate Additives on Properties of Hard Chromium Electroplating[J].Plating & Finishing,2021,(7):6.[doi:10.3969/j.issn.1001-3849.2021.06.002]
[7]杨惠良*.硫酸盐镀液中紫铜电沉积Ni-Co/WC复合镀层的工艺条件优化[J].电镀与精饰,2021,(6):30.[doi:10.3969/j.issn.1001-3849.2021.06.007]
YANG Huiliang*.Optimization of Process Conditions for Electrodeposition of Ni-Co/WC Composite Coatings on Red Copper from Sulfate Bath[J].Plating & Finishing,2021,(7):30.[doi:10.3969/j.issn.1001-3849.2021.06.007]
[8]索 帅*,李 文,杜宝帅,等.无氰电刷镀银镀层性能研究[J].电镀与精饰,2022,(2):7.[doi:10.3969/j.issn.1001-3849.2022.02.002]
SUO Shuai*,LI Wen,DU Baoshuai,et al.Study on Properties of Cyanide-Free Silver Coating by Electro-Brush Plating[J].Plating & Finishing,2022,(7):7.[doi:10.3969/j.issn.1001-3849.2022.02.002]
[9]张 勇,刘桂珍,宋影伟*.AZ91镁合金表面纳米化学复合镀研究[J].电镀与精饰,2022,(5):8.[doi:10.3969/j.issn.1001-3849.2022.05.002]
ZHANG Yong,LIU Guizhen,SONG Yingwei*.Study on Nanometer Electroless Composite Plating on AZ91 Mg Alloy[J].Plating & Finishing,2022,(7):8.[doi:10.3969/j.issn.1001-3849.2022.05.002]
[10]邱小云,王冀恒. 铝合金阳极氧化膜沸水-稀土盐双重封闭及力学性能研究 [J].电镀与精饰,2022,(7):30.[doi:10.3969/j.issn.1001-3849.2022.07.006]
QIU Xiaoyun,WANG Jiheng.Dual Sealing of Anodic Oxidation Film on Aluminum Alloy with Boiling Water and Rare Earth Salt and Mechanical Properties[J].Plating & Finishing,2022,(7):30.[doi:10.3969/j.issn.1001-3849.2022.07.006]
[11]李 倩*,周艳丽,杨 鹏.电压对铝锂合金硬质阳极氧化膜性能的影响[J].电镀与精饰,2023,(8):13.[doi:10.3969/j.issn.1001-3849.2023.08.003]
Li Qian*,Zhou Yanli,Yang Peng.Effect of voltage on the properties of hard anodized films on aluminum-lithium alloy[J].Plating & Finishing,2023,(7):13.[doi:10.3969/j.issn.1001-3849.2023.08.003]
备注/Memo
收稿日期： 2020-11-24；修回日期： 2020-12-22
*通信作者： 邢翀，changchun_00@163.com
基金项目： 吉林省科技厅自然科学基金（20190201191JC），吉林省教育厅科学技术研究基金（JJKH20210787KJ）