arXiv 2103.115882021-03-22cond-mat.mtrl-scics.LGeess.SPstat.ML

使用CNN进行焊丝进给laser增材制造的综合工艺-熔池关系建模

Comprehensive process-molten pool relations modeling using CNN for wire-feed laser additive manufacturing

Colorado School of Mines（科罗拉多矿业学院）

Noopur Jamnikar, Sen Liu, Craig Brice, Xiaoli Zhang

备注：: 23 pages

摘要：

走丝激光增材制造（WLAM）由于其高自动化水平，高沉积速率和良好的打印零件质量而获得广泛关注。减少材料质量不确定性的过程中监测和反馈控制正处于早期开发阶段。机器学习有望通过在工艺设置输入和材料质量结果之间建立工艺-结构-属性联系，加快增材制造中新工艺和属性设计的采用。熔池尺寸信息和温度是实现高质量构建的指标，其可以通过工艺参数直接控制。为了现场质量控制的目的，应该基于来自过程（特别是熔池）的感测信息来实时控制过程参数。因此，熔池-过程关系具有初步的重要性。本文分析了实验收集的原位传感数据从熔池下的一组控制的工艺参数在WLAM系统。给出了熔池稳态和瞬态随独立工艺参数变化的规律。提出了一种多模态卷积神经网络（CNN）架构，用于直接从可测量的熔池传感器数据预测控制参数，以实现所需的几何和微观结构特性。丢弃和正则化应用于CNN架构以避免过拟合问题。结果强调，与基于图像的单模态CNN方法相比，接收温度分布作为从图像数据提取的特征的外部特征的多模态CNN具有改进的预测性能。

英文摘要：

Wire-feed laser additive manufacturing (WLAM) is gaining wide interest due to its high level of automation, high deposition rates, and good quality of printed parts. In-process monitoring and feedback controls that would reduce the uncertainty in the quality of the material are in the early stages of development. Machine learning promises the ability to accelerate the adoption of new processes and property design in additive manufacturing by making process-structure-property connections between process setting inputs and material quality outcomes. The molten pool dimensional information and temperature are the indicators for achieving the high quality of the build, which can be directly controlled by processing parameters. For the purpose of in situ quality control, the process parameters should be controlled in real-time based on sensed information from the process, in particular the molten pool. Thus, the molten pool-process relations are of preliminary importance. This paper analyzes experimentally collected in situ sensing data from the molten pool under a set of controlled process parameters in a WLAM system. The variations in the steady-state and transient state of the molten pool are presented with respect to the change of independent process parameters. A multi-modality convolutional neural network (CNN) architecture is proposed for predicting the control parameter directly from the measurable molten pool sensor data for achieving desired geometric and microstructural properties. Dropout and regularization are applied to the CNN architecture to avoid the problem of overfitting. The results highlighted that the multi-modal CNN, which receives temperature profile as an external feature to the features extracted from the image data, has improved prediction performance compared to the image-based uni-modality CNN approach.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

摘要：

英文摘要：

相关论文