| 刘清涛,王子俊,张玉隆,张义超,赵斌,尹恩怀,吕景祥.融合自注意力与残差神经网络的3D打印激光在机测量误差修正方法[J].电子测量与仪器学报,2024,38(4):27-36 |
| 融合自注意力与残差神经网络的3D打印激光在机测量误差修正方法 |
| Method for correcting laser in-machine measurement errors integratingself-attention and residual neural network in 3D printing |
| |
| DOI： |
| 中文关键词: 3D打印 激光在机测量 残差神经网络 自注意力机制 误差修正 |
| 英文关键词:3D printing laser on-machine measurement residual neural network self-attention mechanism error correction |
| 基金项目:国家重点研发计划项目(2022YFB4602800)、西安市科技计划重点产业链关键核心技术攻关项目(23LLRH0079)资助 |
|
|
| Author | Institution |
| Liu Qingtao | Key Laboratory of Road Construction Technology and Equipment of MoE, Chang′an University, Xi′an 710064, China |
| Wang Zijun | Key Laboratory of Road Construction Technology and Equipment of MoE, Chang′an University, Xi′an 710064, China |
| Zhang Yulong | Key Laboratory of Road Construction Technology and Equipment of MoE, Chang′an University, Xi′an 710064, China |
| Zhang Yichao | Key Laboratory of Road Construction Technology and Equipment of MoE, Chang′an University, Xi′an 710064, China |
| Zhao Bin | Key Laboratory of Road Construction Technology and Equipment of MoE, Chang′an University, Xi′an 710064, China |
| Yin Enhuai | Xi′an Ruite 3D Technology Co., Ltd., Xi′an 710061, China |
| Lyu Jingxiang | Key Laboratory of Road Construction Technology and Equipment of MoE, Chang′an University, Xi′an 710064, China |
|
| 摘要点击次数: 111 |
| 全文下载次数: 2988 |
| 中文摘要: |
| 激光测量能够实现高效地非接触实时测量，被广泛应用于3D打印领域，但激光测量容易受测量条件、外部环境等多种因素的干扰，这些因素错综复杂，难以量化分析。为此，结合直射式激光三角测量原理，在分析测量精度影响因素的基础上，提出了一种基于融合自注意力和残差神经网络的3D打印在机测量误差修正方法。首先，将影响测量精度的因素作为输入变量，采集激光测量值，得到样本数据集；然后利用残差网络提取出样本数据的深层次特征，并引入自注意力机制建立影响因素之间的联系,得到带权重的提取特征；再通过全连接网络对带权重特征进行学习，得到测量误差的预测值，基于该预测值完成对测量误差的修正。自主搭建了一套激光在机测量系统，采用红、绿、紫3种同材质彩色卡纸进行实验验证。结果表明，所提的方法与卷积神经网络和自注意力神经网络相比，均方误差、均方根误差和平均绝对误差均最小，稳定性最好，修正结果最接近真实值；对激光测量结果进行校正后，使其误差由原来的 ±28 μm减小到 ±9 μm以下，显著提高了3D打印激光在机测量的精度和稳定性。 |
| 英文摘要: |
| Laser measurement enables efficient non-contact real-time measurement and finds extensive application in the field of 3D printing. However, laser measurement is susceptible to interference from various factors such as measurement condition and the external environment, which are complex and difficult to quantify and analyze. Therefore, based on the principle of direct laser triangulation and an analysis of the factors affecting measurement accuracy, this paper proposes a 3D printing in-machine measurement error correction method integrating self-attention and residual neural network (SRNN). Firstly, the factors that affect measurement accuracy are used as input variables to collect laser measurement values and obtain a sample dataset. Then, residual network is employed to extract deep-level features from the sample data, and a self-attention mechanism is introduced to establish connections between influencing factors, resulting in weighted extracted features. Subsequently, the weighted features are learned through a fully connected network to obtain the predicted values of measurement errors. Based on this predicted value, the measurement errors are corrected. A laser in-machine measurement system is built, and experimental verification is conducted using three types of color cards (red, green, and purple) made of the same material. The results show that, compared to convolutional neural network (CNN) and self-attention neural network (SelfNN), the method proposed in this paper achieves the smallest mean squared error (MSE), root mean squared error (RMSE), and mean absolute error (MAE), exhibits the best stability, and yields correction results that are closest to the ground truth. After the laser measurement result is calibrated, the error is reduced from the original ±28 μm to below ±9 μm, significantly enhancing the accuracy and stability of 3D printing laser in-machine measurement. |
| 查看全文 查看/发表评论 下载PDF阅读器 |
|
|
|
