论文部分内容阅读
采用脉冲电沉积法在45#钢表面制备Ni-SiC镀层。建立RBF神经网络模型预测镀层磨损量,利用扫描电镜(SEM)及X线衍射仪(XRD)研究镀层表面形貌及物相组成。结果表明:采用RBF神经网络预测误差最大值与最小值,分别为2.94%和1.45%;当电流密度为2A/dm2、SiC粒子的质量浓度为7g/L、镀液温度为50℃,Ni-SiC镀层表面较为平整,犁沟较浅;Ni-SiC镀层中存在Ni、SiC两相。
The Ni-SiC coating was prepared on the surface of 45 steel by pulse electrodeposition. The RBF neural network model was established to predict the coating wear. The surface morphology and phase composition of the coating were studied by scanning electron microscopy (SEM) and X-ray diffraction (XRD). The results show that the maximum and minimum error of prediction by RBF neural network are 2.94% and 1.45%, respectively. When the current density is 2 A / dm2, the mass concentration of SiC particles is 7 g / L, the bath temperature is 50 ℃, SiC coating surface is relatively flat, furrow shallow; Ni-SiC coating in the presence of Ni, SiC two-phase.