摘要
在高速钢(W18Cr4V基体上)表面,运用脉冲电沉积技术制取Co-WC镀层。建立T-S模糊神经网络模型预测镀层磨损量。利用SEM以及XRD研究镀层形貌及物相组成。试验表明:T-S模型的模糊神经网络能较好的预测Co-WC复合镀层磨损量。当WC粒子含量30 g/L、施镀温度50℃、电流密度3.5 A·dm~(-2)、pH值5、搅拌速率500 r·min~(-1),稀土CeO_2含量10 g/L,Co-WC复合镀层表面平整,晶粒细化,改善了Co-WC复合镀层的性能。
Co-WC coating was prepared on the surface of high speed steel(W18Cr4V substrate) by pulse electrodeposition technology. A T-S fuzzy neural network model was established to predict the wear of coating. The morphology and phase composition of the coatings were studied by SEM and XRD. The experiments showed that the fuzzy neural network of T-S model well predicted the wear rate of Co-WC composite coating. When WC particle content was 30 g/L, the temperature was 50 ℃, the current density was 3.5 A·dm~(-2), pH was 5, the stirring rate was 500 r·min~(-1), the content of rare earth CeO_2 was 10 g/L, prepared Co-WC composite coating surface was smooth, the grain was fine, which improved the performance of Co-WC composite coating.
引文
[1]李恒嵬.模糊神经网络研究现状综述[J].辽宁科技学院学报,2010,12(2):15-17.
[2]程立新,杨杰辉.电镀Ni-PTFE复合镀层研究[J].电镀与环保,1997,17(5):8-9.
[3]Takaya M,Matsunaga M,Otaka T.Trivalent Chromium Composite Coatings[J].Plating Surface Finishing,1987,74(9):70.
[4]班国东,刘朝辉,叶圣天,等.碳纤维复合吸波涂层材料的性能影响研究[J].当代化工,2017,43(3):449-453.
[5]张芳,荆天辅,乔桂英,等.脉冲电沉积钴镍合金及其生长形态研究[J].电沉积与涂饰,2001,20(4):1-3.
[6]张欢,郭忠诚,朱晓云.(Ni-W-P)-Si C复合镀层的脉冲电沉积及其耐蚀性[J].电镀与精饰,2004,26(2):4-7.
[7]尚丽娟.我国应用稀土改性金属表面的现状[J].稀有金属,1995(3):132-135.
[8]张乃尧,阎平凡.神经网络与模糊控制[M].北京:清华大学出版社,2005.
[9]宋彬彬.模糊神经网络的发展与应用[J].煤炭技术,2012(07):15-19.
[10]王小川,史峰,郁磊,李洋.神经网络43个案例分析[M].北京:北京航空航天大学出版社,2013.