基于RBF-BP算法的Ni-SiC镀层性能预测研究  

Prediction of corrosion resistance of Ni-SiC composite coatings based on RBF-BP algorithm

作　　者：马春阳[1] 左韩睿 夏法锋[1] 李超宇 李强[1] MA Chunyang;ZUO Hanrui;XIA Fafeng;LI Chaoyu;LI Qiang(College of Mechanical Science and Engineering,Northeast Petroleum University,Daqing 163318,China)

机构地区：[1]东北石油大学机械科学与工程学院,黑龙江大庆163318

出　　处：《兵器材料科学与工程》2021年第3期39-44,共6页Ordnance Material Science and Engineering

基　　金：国家自然科学基金(51974089)。

摘　　要：采用磁场辅助喷射电沉积技术,在不同工艺条件下制备Ni-SiC复合镀层,通过构建4×4×4×7×10×1的RBF-BP复合神经网络模型预测Ni-SiC复合镀层耐蚀性。结果表明:RBF-BP复合神经网络的预测值与真实值拟合度为0.974 97,高于单神经网络,表明复合神经网络能准确预测不同工艺参数下制备的Ni-SiC复合镀层耐蚀性。经复合神经网络预测,当电流密度为4 A/dm^(2)、喷射速度为6 m/s、SiC粒子浓度为8 g/L、磁场强度为0.8 T时复合镀层腐蚀失重最低,复合镀层的耐蚀性最好。通过镀层表征研究分析可知,该条件下镀层晶粒显著细化,镀层表面较平滑,SiC纳米粒子复合量高且分布均匀。Composite coatings were prepared by magnetic field assisted jet electrodeposition under different Ni-SiC conditions.Corrosion resistance of composite coatings was predicted by constructing RBF-BP composite neural network model 4×4×4×7×10×1. The results show that the fitting degree between the predicted value and the true value of the RBF-BP composite neural network is 0.974 97,higher than that of single neural network. Experimental results show that the composite neural network can accurately predict the corrosion resistance of Ni-SiC composite coatings prepared under different process parameters. The corrosion weight loss of the composite coating is the lowest at the current density of 4 A/dm^(2),the jet speed of 6 m/s,the SiC particle concentration of 8 g/L,and the magnetic field intensity of 0.8 T,illustrating the superior corrosion resistance. According to the analysis of the coating characterization,the grain size of the coating has been significantly refined,and its surface is smoother with a large amount of uniform SiC nanoparticles.

关 键 词：RBF-BP复合神经网络模型 NI-SIC复合镀层 耐蚀性 

分 类 号：TH117.1[机械工程—机械设计及理论]