基于熔池热历史的陶瓷增强金属基复材激光定向能量沉积质量实时监测方法  

Real-time quality monitoring method of ceramic reinforced metal matrix composites fabricated by laser directed energy deposition based on melt pool thermal history

作　　者：陈颖 黄海鸿[1,2] 徐鸿蒙 刘志峰 CHEN Ying;HUANG Haihong;XU Hongmeng;LIU Zhifeng(School of Mechanical Engineering,Hefei University of Technology,Hefei 230009,China;Key Laboratory of Green Design and Manufacturing of Mechanical Industry,Hefei University of Technology,Hefei 230009,China)

机构地区：[1]合肥工业大学机械工程学院,安徽合肥230009 [2]机械工业绿色设计与制造重点实验室,安徽合肥230009

出　　处：《计算机集成制造系统》2024年第11期3943-3953,共11页Computer Integrated Manufacturing Systems

基　　金：国家自然科学基金资助项目(U20A20295)。

摘　　要：针对激光定向能量沉积(L-DED)制备陶瓷增强金属基复合材料(CRMMC)过程中成形质量不稳定的问题,提出一种基于熔池热历史的CRMMC质量监测方法。为实现在CPU硬件上的实时监测,构建了单路结构的轻量级全深度可分离卷积神经网络模型(FD-Net)。输入9个不同激光能量制备不同状态的CRMMC成形质量,使用红外热像仪同步采集熔池红外图像作为数据集训练和测试FD-Net,并与当前先进的轻量级卷积神经网络(CNN)模型进行性能对比。结果表明:FD-Net在Inter-CPU上以7.90ms/帧的推理时间实现了高精度监测,显著低于其他CNN模型,证明所提方法可在工业微型计算机上实现CRMMC质量状态的实时监测。0x09In the preparation of Ceramic Reinforced Metal Matrix Composites(CRMMC)by Laser Directed Energy Deposition(L-DED),the degree of segregation and dissolution of the ceramic particles is determined by the melt pool thermal history,which can lead to unstable forming quality.A method for monitoring the quality of CRMMC deposition layer based on the melt pool thermal history was proposed.To realize the real-time monitoring of the CPU hardware with poor parallel computing capability,the lightweight Fully Depth-separable convolutional neural Network(FD-Net)with a single-path structure was constructed.Nine different laser energies were input to prepare different states of CRMMC.The corresponding infrared images of the melt pool were synchronously captured by an infrared thermal camera as the dataset for training and testing the FD-Net model,and the Performance comparisons were conducted between FD-Net and other state-of-the-art lightweight CNN models.The results indicated that FD-Net could achieve an inference time of 7.9 ms/frame on the Inter-CPU,which was significantly lower than other CNN models.It was proved that FD-Net could realize real-time monitoring of CRMMC quality status on industrial microcomputers.

关 键 词：熔池热历史 卷积神经网络 陶瓷增强金属基复材 激光定向能量沉积 红外图像 

分 类 号：TB333[一般工业技术—材料科学与工程] TP391.41[自动化与计算机技术—计算机应用技术]