基于MPA-ANN的冷喷增材制造沉积建模与预测

Deposition modeling and prediction in cold spray additive manufacturing based on MPA-ANN

针对冷喷增材制造(CSAM)过程中沉积形貌的几何描述与模拟,提出一种基于海洋捕食者算法(MPA)的人工神经网络(ANN)预测模型,以实现CSAM加工沉积层轮廓的几何控制。首先,构建双坐标系,描述喷枪与零件的三维特征,综合分析粒径分布和射流分布等因素对沉积形态的影响,建立沉积剖面分布模型;其次,应用灰色关联度模型对输入层参数进行关键影响因子筛选,以详细轮廓点为输入变量,采用MPA优化ANN模型的关键参数,构建基于海洋捕食者算法的人工神经网络(MPA-ANN)模型;最后,将所提模型的预测结果与FNN、Gauss、PSO-ANN和BP模型进行对比,得到其平均绝对误差为0.0143 mm,相关系数为0.9986,相关数据均优于其他模型,结果表明基于MPA-ANN的冷喷涂沉积建模与预测具有更好的稳定性和预测精度。

Aiming at the geometric description and simulation of deposition morphology during Cold Spraying Additive Manufacturing(CSAM),an Artificial Neural Network(ANN)prediction model based on Marine Predators Algorithm(MPA)was proposed to realize the geometric control of the deposition layer’s profile for CSAM machining.A double coordinate system was constructed,the three-dimensional characteristics of the gun and the part were described,the influence of particle size distribution and jet distribution on the deposition morphology was comprehensively analyzed,and the deposition profile distribution model was established.The gray correlation degree model was applied to screen the key influencing factors of the input layer parameters,and with the detailed contour points as input variables.The key parameters of the ANN model were optimized by the Marine Predator Algorithm so that an ANN model based on MPA(MPA-ANN)was constructed.By comparing the prediction results of the proposed model with those of the FNN,Gauss,PSO-ANN and BP models,the average absolute error was 0.0143mm and the correlation coefficient was 0.9986,which were better than other models,and the results showed that the cold spray deposition modeling and prediction based on MPA-ANN had better stability and prediction accuracy.