[1]李学威,王兆浩.doi: 10.3969/j.issn.1001-3849.2025.08.012基于改进PSO-BP神经网络的Ni-TiC复合镀层工艺参数优化方法[J].电镀与精饰,2025,(08):76-82.
　Li Xuewei*,Wang Zhaohao.Optimization method for process parameters of Ni-TiC composite coating based on improved PSO-BP neural network[J].Plating & Finishing,2025,(08):76-82.
点击复制

doi: 10.3969/j.issn.1001-3849.2025.08.012基于改进PSO-BP神经网络的Ni-TiC复合镀层工艺参数优化方法()

《电镀与精饰》[ISSN:1001-3849/CN:12-1096/TG]

卷:
期数:
2025年08
页码:
76-82
栏目:
出版日期:
2025-08-31

文章信息/Info

Title:
Optimization method for process parameters of Ni-TiC composite coating based on improved PSO-BP neural network
作者:
李学威1; 王兆浩2
复合镀层工艺参数优化方法李学威1,王兆浩2(1. 周口职业技术学院 信息工程学院,河南 周口 466000 ;2. 山西师范大学 数学与计算机科学学院,山西 太原 030002)
Author(s):
Li Xuewei1*;  Wang Zhaohao2
(1. School of Information and Engineering, Zhoukou Vocational and Technical College, Zhoukou 466000, China; 2. School of Mathematics and Computer Science, Shanxi Normal University, Taiyuan 030002, China)
关键词:
改进PSO算法; BP神经网络; Ni-TiC复合镀层; 工艺参数优化; 正交实验; 脉冲负荷电沉积方法
Keywords:
improving PSO algorithm;  BP neural network;  Ni-TiC composite coating;  process parameter optimization;  orthogonal experiment;  pulse load electrodeposition method
分类号:
TQ050.9
文献标志码:
A
摘要:
在Ni-TiC复合镀层的制备过程中，由于受到参数非线性波动以及多参数间复杂作用关系的影响，其镀层制备效果不佳。为达到理想的镀层效果，本次借助脉冲负荷电沉积法制备Ni-TiC复合镀层环境，开展基于改进粒子群优化—反向传播(Particle Swarm Optimization Backpropagation，PSO-BP)神经网络的Ni-TiC复合镀层工艺参数优化方法研究。先对Ni-TiC复合镀层工艺进行分析，探讨TiC粒子浓度、电流密度以及pH值三种工艺参数的影响，然后以此为基础，设计正交试验，开展对Ni-TiC复合镀层工艺参数的初步优化，最后以得到的正交试验结果为输入，采用BP神经网络完成Ni-TiC复合镀层工艺参数优化模型的构建与训练设计，应用改进PSO算法完成BP神经网络模型参数寻优，实现Ni-TiC复合镀层工艺参数优化。实验结果表明：应用该方法，可以实现Ni-TiC复合镀层的制备工艺参数优化，采用优化后的工艺制备的复合镀层的耐腐蚀能力更强。
Abstract:
In the preparation process of Ni-TiC composite coating, the coating preparation effect is poor due to the influence of nonlinear parameter fluctuations and complex interaction relationships between multiple parameters. In order to achieve the desired coating effect, a study was conducted on the process parameter optimization method of Ni TiC composite coating based on improved particle swarm optimization backpropagation neural network (PSO-BPNN) using pulse load electrodeposition method to prepare Ni TiC composite coating environment. Firstly, the process of Ni-TiC composite coating was analyzed to explore the effects of three process parameters: TiC particle concentration, current density, and pH value. Based on this, an orthogonal experiment was designed to carry out preliminary optimization of process parameters of Ni-TiC composite coating. Finally, taking the obtained orthogonal experimental results as input, a BP neural network was used to construct and train an optimization model for the process parameters of Ni-TiC composite coating. The improved PSO algorithm was applied to optimize the BP neural network model parameters, and the process parameters of Ni-TiC composite coating were optimized. The experimental results show that the application of this method can optimize the preparation process parameters of Ni-TiC composite coatings, and the composite coatings prepared using the optimized process have stronger corrosion resistance

参考文献/References:

[1].肖绮, 陈蔚清, 陈杨连, 等. 电流密度对Ni-W-Ti3C2Tx复合镀层耐腐蚀性能的影响[J]. 稀有金属, 2022, 46(10): 1298-1305.
[2].付传起, 黄亚忠, 李省君, 等. Ni-P/Ni-Zn-P三层复合镀层的制备与耐腐蚀性能研究[J]. 表面技术, 2021, 50(12): 400-407.
[3].郭明忠. Ni-P/纳米TiO2复合镀层制备及热处理性能研究[J]. 热加工工艺, 2023, 52(20): 112-114.
[4].任鑫, 张雨辰, 田佳茹, 等. 不同方式电沉积Ni-纳米TiC复合镀层的微观结构与性能[J]. 复合材料学报, 2022, 39(8): 4093-4101.
[5].张伟, 李本刚, 龙雄云, 等. 脉冲电沉积制备NiW-Si3N4/MWCNTs复合镀层及其性能研究[J]. 特种油气藏, 2021, 28(4): 158-163.
[6].孙垂康, 贾卫平, 周绍安, 等. 超声辅助脉冲电沉积Ni-TiN复合镀层的结合力和耐蚀性[J]. 材料保护, 2021, 54(4): 80-85.
[7].张璐, 余云丹, 卫国英. 电流密度对电沉积钴-铁-二氧化锆复合镀层性能的影响[J]. 电镀与涂饰, 2023, 42(9): 1-6.
[8].肖金涛, 鞠鹏飞, 臧旭升, 等. 铝合金表面润滑耐蚀复合镀层的制备及性能分析[J]. 中国表面工程, 2021, 34(4): 38-45.
[9].朱云娜, 高利霞, 熊彤彤, 等. 化学镀工艺制备高耐腐蚀性能的Ni-Co-B-Pr复合镀层[J]. 材料导报, 2021, 35(4): 4159-4164.
[10].任鑫, 王港, 孙涛, 等. 纳米TiC浓度对双脉冲电沉积Ni-TiC复合镀层结构及性能的影响[J]. 材料热处理学报, 2024, 45(4): 167-173.
[11].单凤君, 王双红. 工艺参数对锌镍合金镀层组织及性能的影响[J]. 电镀与涂饰, 2021, 40(11): 829-833.
[12].杨凯, 崔凡, 封小松, 等. 工艺参数对异种纯铝镀层铝合金回填式搅拌摩擦点焊接头组织性能的影响研究[J]. 热加工工艺, 2023, 52(21): 93-98.
[13].陈树梁, 徐雷, 胡元昊, 等. 铝合金预拉伸板残余应力数值模拟方法研究[J]. 计算机仿真, 2023, 40(2): 292-296, 516.
[14].郭富钰, 于金库, 肖静静, 等. FeCoNiCr高熵合金涂层的制备及工艺参数优化(英文)[J]. 稀有金属材料与工程, 2021, 50(7): 2337-2342.
[15].文思倩, 闫焉服, 周慧, 等. 电镀参数对电沉积Sn-Ag-Cu合金镀层的影响[J]. 稀有金属与硬质合金, 2024, 52(1): 63-68, 80.
[16].Chen L Y, Yu T B, Chen X, et al. Process optimization, microstructure and microhardness of coaxial laser cladding TiC reinforced Ni-based composite coatings[J]. Optics & Laser Technology, 2022, 152: 108-129.
[17].Mo T, Che J Q, Bai W Q, et al. Ni/TiC composite electrodeposition on the surface of Ni-based superalloy[J]. Surface & Coatings Technology, 2021, 424: 1-14.
[18].Unal E, Yasar A, Karahan I H. Estimation of microhardness and crystal grain size values of electrodeposited Ni-B/TiC nanocomposite coatings by artificial neural networks (ANN) method[J]. Journal of Alloys and Compounds, 2023, 966: 171-187.
[19].邱有春, 赵立平. 基于改进神经网络的机身镀层抗冲击性能预测[J]. 兵器材料科学与工程, 2022, 45(5): 148-153.

相似文献/References:

[1]雷翔霄?,徐立娟,唐春霞.基于神经网络PID算法的镀液温度控制系统[J].电镀与精饰,2020,(8):39.[doi:10.3969/j.issn.1001-3849.2020.08.0080]
　LEI Xiangxiao,XU Lijuan,et al.Bath Temperature Control System Based on Neural Network PID[J].Plating & Finishing,2020,(08):39.[doi:10.3969/j.issn.1001-3849.2020.08.0080]
[2]邢 翀*,王坤昊.基于BP和RBF神经网络预测硬质阳极氧化膜的硬度[J].电镀与精饰,2021,(7):25.[doi:10.3969/j.issn.1001-3849.2021.07.005]
　XING Chong*,WANG Kunhao.Prediction of Hardness of Hard Anodic Oxidation Film Based on BP and RBF Neural Network[J].Plating & Finishing,2021,(08):25.[doi:10.3969/j.issn.1001-3849.2021.07.005]
[3]覃树宏,梁 锦.doi: 10.3969/j.issn.1001-3849.2026.01.015面向Ni-SiC纳米镀层耐磨性能预测的GA-BP神经网络模型[J].电镀与精饰,2026,(01):116.
　QIN Shuhong,LIANG Jin.Predicted GA-BP neural network model for wear resistance of Ni-SiC nano coatings[J].Plating & Finishing,2026,(08):116.

更新日期/Last Update: 2025-08-11