Back Propagation Neural Network Based Electrohydrodynamic Printing Accuracy Prediction Study
Conference: MEMAT 2022 - 2nd International Conference on Mechanical Engineering, Intelligent Manufacturing and Automation Technology
01/07/2022 - 01/09/2022 at Guilin, China
Proceedings: MEMAT 2022
Pages: 4Language: englishTyp: PDF
Authors:
Yang, Jingwen; Chen, Xiaoyong; Zhang, Junhua (College of Mechanical and Electrical Engineering, Guilin University of Electronic Technology, Guilin, Guangxi, China)
Yang, Xu (College of Mechanical and Electrical Engineering, Xidian University, Xi 'an, Shaanxi, China)
Abstract:
Electrohydrodynamic technology is a new type of micro and nano additive manufacturing technology for manufacturing fields such as flexible displays, wearable electronics and bio-medicine. However, the complex mechanism of e-jet forming makes it difficult to establish an accurate relational model. In this paper, a combination of finite element models and BP neural network algorithms is proposed to establish a predictive model for e-jet accuracy. By comparing the results with those of the response surface method, the error of the BP neural network prediction model is smaller than that of the response surface model, while the negative correlation coefficient is larger. This indicates that the BP neural network model has higher prediction accuracy than the response surface model and can be used to optimize the parameters of e-jet printing.