摘要
为进一步研究熔融沉积成型(FDM)3D打印制件力学性能与工艺参数之间的关系,试验以聚乳酸(PLA)为材料,参考正交试验和神经网络模型设计原则,利用遗传算法(GA)对反向传播(BP)神经网络初始值进行优化,建立GA-BP神经网络模型,以分层厚度、填充密度、喷嘴温度、填充速度以及外壳厚度为输入层参数,拉伸强度为输出层参数进行训练和预测,并分析其预测精度。通过对GA-BP和BP神经网络模型的预测结果进行对比发现,GA-BP神经网络模型预测值与测试实际值更为接近,误差平均值为2.27%,而BP神经网络模型预测误差平均值为4.10%,且GA-BP神经网络模型评价指标值均优于BP神经网络模型,故GA-BP神经网络模型预测精度更高,可为提升FDM 3D打印制件力学性能,优化成型工艺,指导工业生产提供参考。
In order to further study the relationship between the mechanical properties and process parameters of fused deposition modeling(FDM)3 D printed sample,GA-BP neural network model was established by using PLA as the material in the experiment,referring to the principles of orthogonal experiment and of model designs for neural network and optimizing the initial value of BP neural network by genetic algorithm.The input layer parameters,such as,the layer thickness,filling rate,printing temperature,filling speed and contour thickness and the tensile strength as the output layer parameters was used for training and prediction by GA-BP neural network model and the prediction accuracy of the model was analyzed.By comparing the prediction results of GA-BP and BP neural network model,it is found that the prediction value of GA-BP neural network model is closer to the test value,2.27%for GA-BP neural network model and 4.10%for BP neural network model in the average error of prediction.GA-BP neural network model are better than BP neural network model for the evaluation index values.Therefore,GA-BP neural network model is better for the prediction accuracy and may be used to improve the mechanical properties of FDM 3 D printing sample,to optimize the forming process and to provide reference for guiding industrial production.
作者
白鹤
赵明侠
袁一如
刘亚明
何石磊
庞瑞
郭晓东
BAI He;ZHAO Mingxia;YUAN Yiru;LIU Yaming;HE Shilei;PANG Rui;GUO Xiaodong(College of Mechatronics and Informatics,Baoji Vocational&Technical College,Baoji 721013,China;Welded Pipe Research Institute of Baoji Petroleum Steel Pipe Co.,Ltd.,Baoji 721008,China;National Petroleum and Gas Tubular Goods Engineering Technology Research Center,Baoji 721008,China;Baoji Steel Pipe Factory School,Baoji 721008,China;Xi'an Meicheng Intelligent Technology Co.,Ltd,Xi'an 710077,China)
出处
《塑料工业》
CAS
CSCD
北大核心
2022年第9期192-197,共6页
China Plastics Industry
基金
陕西省教育科学“十四五”规划2021年度课题(SGH21Y0574)
宝鸡职业技术学院2020年度院级课题(2020130Y)。
