杨静文,陈小勇,张军华.基于机器学习的电喷印精度预测方法研究[J].包装工程,2022,43(13):203-208.
YANG Jing-wen,CHEN Xiao-yong,ZHANG Jun-hua.Machine Learning Based E-jet Printing Accuracy Prediction Method[J].Packaging Engineering,2022,43(13):203-208. |
| 基于机器学习的电喷印精度预测方法研究 |
| Machine Learning Based E-jet Printing Accuracy Prediction Method |
| |
| DOI：10.19554/j.cnki.1001-3563.2022.13.026 |
| 中文关键词: 机器学习 电流体微纳打印 射流精度 预测模型 |
| 英文关键词: machine learning electrofluidic micro-nano printing jet accuracy prediction model |
| 基金项目:广西自然科学基金(22GXNSFAA035616);广西制造系统和先进制造技术重点实验室基金(2006540007Z) |
|
| 摘要点击次数: |
| 全文下载次数: |
| 中文摘要: |
| 目的 节省电流体喷射打印精度预测的时间和解决电流体工艺参数的选择问题，达到提高电流体打印的质量和效率的目的。方法 为了对电流体喷射打印精度进行预测，提出有限元模型与机器学习相结合的方法。基于线性回归、支持向量回归和神经网络等机器学习算法建立4种参数与射流直径的关系模型。结果 算法结果表明:支持向量回归和神经网络预测模型的决定系数R2能达到0.9以上，表示模型可信度高;支持向量回归和神经网络预测模型指标都比线性回归预测模型的小。结论 机器学习算法可对电喷印打印精度进行有效预测，预测效率提高了十几倍，节省了精度预测的时间。 |
| 英文摘要: |
| The work aims to save time in predicting the accuracy of E-jet printing, solve the problems in selection of electrofluidic process parameters, and improve the design quality and efficiency of electrofluidic printing. A combination of finite element models and machine learning was proposed to predict the accuracy of E-jet printing. Based on machine learning algorithms such as linear regression, support vector regression and neural networks, a model on relationship between four parameters and jet diameter was established. The algorithm results showed that the determination coefficient R2 of the support vector regression and neural network prediction models could reach above 0.9, indicating that the models were highly credible; RMSE and MAE, which were indicators of model error, were both smaller than those of the linear regression prediction models. Machine learning algorithms enable effective prediction of E-jet printing accuracy, increasing prediction efficiency by more than a factor of ten and saving time on accuracy prediction. |
|
查看全文
查看/发表评论 下载PDF阅读器 |
| 关闭 |
渝公网安备 50010702501716号