Study on the Effectiveness of Machine Learning Algorithms for Process Parameter Prediction in 3D Printing Process of Variable-component Composites

被引：0
作者：
Niu, Jingyi [1 ,2 ,3 ]
Lu, Siwei [1 ,2 ,3 ]
Zhang, Beining [1 ,2 ,3 ]
Yang, Chuncheng [4 ]
Li, Dichen [1 ,2 ,3 ]
机构：
[1] State Key Laboratory for Manufacturing System Engineering, Xi’an Jiaotong University, Xi’an
[2] School of Mechanical Engineering, Xi’an Jiaotong University, Xi’an
[3] National Medical Products Administration (NMPA), Key Laboratory for Research and Evaluation of Additive Manufacturing Medical Devices, Xi’an Jiaotong University, Xi’an
[4] Shaanxi Jugao-IM Technology Co., Ltd., Xi’an
来源：
Jixie Gongcheng Xuebao/Journal of Mechanical Engineering | 2024年 / 60卷 / 21期
关键词：
additive manufacturing; machine learning; prediction of process parameters; variable component composites;
D O I：
10.3901/JME.2024.21.263
中图分类号：
学科分类号：
摘要：
3D printing of variable-component composites is a cutting-edge direction in the development of additive manufacturing, which is an important technology to realise gradient material structure. Online regulation of process parameters to adapt to the material component changes during 3D printing is a difficult problem in manufacturing variable-component composites. Combining machine learning algorithms with 3D printing process, and on the basis of small-sample training in additive manufacturing, establishing an algorithmic model of the relationship between process parameters and extruded volume, so as to explore the effectiveness of machine learning algorithms to regulate the process parameters of variable-component composites 3D printing. The screw extrusion 3D printing equipment is used to collect experimental data for different material components. Five machine learning algorithms, SVR support vector regression, BP neural network, RF random forest, RBF neural network and Kriging model, were used to predict the extrusion volume, which is used to adjust the process parameters according to different material components. From the results, it can be seen that when extrusion volume prediction is performed, the training sample size should be more than 30 groups in order to ensure the prediction results. Moreover, SVR algorithm is the most suitable for the small sample size prediction situation among the five machine learning algorithms, and it has the highest extrusion volume prediction accuracy. 3D printing experiments of variable-component composites are carried out, and the process parameters are adjusted according to the material components during the printing process. The sample pieces are printed with good quality, which verifies the effectiveness of the SVR algorithm to regulate the process parameters. © 2024 Chinese Mechanical Engineering Society. All rights reserved.
引用
收藏
页码：263 / 274
页数：11
相关论文
共 14 条
  • [1] SWAMINATHAN K, SACHIN H, RAJANNA T., Buckling analysis of functionally graded materials by dynamic approach[J], Materials Today：Proceedings, 45, pp. 172-178, (2021)
  • [2] MA Wenjing, Preparation and application development of functionally graded materials[J], New Technology & New Products of China, 7, (2015)
  • [3] LI Dichen, LU Zhongliang, TIAN Xiaoyong, Et al., Additive manufacturing—revolutionary technology for leading aerospace manufacturing[J], Acta Aeronaut Astronautica Sinica, 43, 4, (2022)
  • [4] LI X Y, ZHANG M N, ZHOU M X, Et al., Qualify assessment for extrusion-based additive manufacturing with 3D scan and machine learning[J], Journal of Manufacturing Processes, 90, pp. 274-285, (2023)
  • [5] TIAN X, GU D，, Et al., Roadmap for additive manufacturing ： Toward intellectualization and industrialization[J], Chinese Journal of Mechanical Engineering：Additive Manufacturing Frontiers, 1, 1, (2022)
  • [6] SHARMA R, RAJ PAUL A, MUKHERJEE M, Et al., Forecasting of process parameters using machine learning techniques for wire arc additive manufacturing process[J], Materials Today：Proceedings, 80, pp. 248-253, (2023)
  • [7] PHADKE N, RAJ R, KUMAR SRIVASTAVA A, Et al., Modeling and parametric optimization of laser powder bed fusion 3D printing technique using artificial neural network for enhancing dimensional accuracy[J], Materials Today：Proceedings, 56, pp. 873-878, (2022)
  • [8] SONG C, LIU L, YANG Y, Et al., Prediction on geometrical characteristics of laser energy deposition based on regression equation and neural network[J], IFAC-PapersOnLine, 53, 5, pp. 89-96, (2020)
  • [9] ZHU X, JIANG F，, GUO C，, Et al., Prediction of melt pool shape in additive manufacturing based on machine learning methods[J], Optics & Laser Technology, 159, (2023)
  • [10] ALHADDAD W，, HE M, HALABI Y, Et al., Optimizing the material and printing parameters of the additively manufactured fiber-reinforced polymer composites using an artificial neural network model and artificial bee colony algorithm[J], Structures, 46, pp. 1781-1795, (2022)
12