{"title":"机器学习预测 LPBF 快速成型制造中的飞溅行为","authors":"","doi":"10.1016/j.mtla.2024.102268","DOIUrl":null,"url":null,"abstract":"<div><div>The adoption of additive manufacturing (AM) technologies, particularly Laser Powder Bed Fusion (LPBF), has been rapidly increasing in industries requiring high precision and complex geometries. Despite its advantages, LPBF faces challenges related to defects that affect material quality, with spatter formation being a significant concern. Spatters – tiny particles ejected during the printing process – can adversely affect the final product’s integrity by altering surface roughness and contributing to defects. This study introduces a comprehensive approach to predict the ejection velocity and direction of spatter particles using a suite of machine learning (ML) algorithms, including Random Forest, Gaussian Process Regression, Support Vector Machine, Regularized Linear Regressions, Gradient Boosting Trees, and Neural Networks. Our analysis reveals that the Neural Network model outperforms others, achieving prediction accuracies of 97.58% for spatter velocity and 88.22% for ejection direction, thus offering a substantial improvement in understanding and controlling spatter-related defects in LPBF processes. The practical implications of these predictions are profound, enabling manufacturers to adjust AM parameters in real time to minimize defects and enhance product quality. This study not only fills a gap in the current literature by providing a detailed comparative analysis of multiple ML algorithms for spatter ejection prediction but also paves the way for future research into real-time monitoring and control systems in AM.</div></div>","PeriodicalId":47623,"journal":{"name":"Materialia","volume":null,"pages":null},"PeriodicalIF":3.0000,"publicationDate":"2024-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Machine learning predictions of spatter behavior in LPBF additive manufacturing\",\"authors\":\"\",\"doi\":\"10.1016/j.mtla.2024.102268\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><div>The adoption of additive manufacturing (AM) technologies, particularly Laser Powder Bed Fusion (LPBF), has been rapidly increasing in industries requiring high precision and complex geometries. Despite its advantages, LPBF faces challenges related to defects that affect material quality, with spatter formation being a significant concern. Spatters – tiny particles ejected during the printing process – can adversely affect the final product’s integrity by altering surface roughness and contributing to defects. This study introduces a comprehensive approach to predict the ejection velocity and direction of spatter particles using a suite of machine learning (ML) algorithms, including Random Forest, Gaussian Process Regression, Support Vector Machine, Regularized Linear Regressions, Gradient Boosting Trees, and Neural Networks. Our analysis reveals that the Neural Network model outperforms others, achieving prediction accuracies of 97.58% for spatter velocity and 88.22% for ejection direction, thus offering a substantial improvement in understanding and controlling spatter-related defects in LPBF processes. The practical implications of these predictions are profound, enabling manufacturers to adjust AM parameters in real time to minimize defects and enhance product quality. This study not only fills a gap in the current literature by providing a detailed comparative analysis of multiple ML algorithms for spatter ejection prediction but also paves the way for future research into real-time monitoring and control systems in AM.</div></div>\",\"PeriodicalId\":47623,\"journal\":{\"name\":\"Materialia\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":3.0000,\"publicationDate\":\"2024-10-24\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Materialia\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S2589152924002655\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"MATERIALS SCIENCE, MULTIDISCIPLINARY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Materialia","FirstCategoryId":"1085","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S2589152924002655","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"MATERIALS SCIENCE, MULTIDISCIPLINARY","Score":null,"Total":0}
引用次数: 0
摘要
在要求高精度和复杂几何形状的行业中,增材制造(AM)技术,尤其是激光粉末床熔融(LPBF)技术的应用迅速增加。尽管 LPBF 具有诸多优势,但它也面临着与影响材料质量的缺陷有关的挑战,其中飞溅物的形成是一个重大问题。飞溅物--印刷过程中喷射出的微小颗粒--会改变表面粗糙度并导致缺陷,从而对最终产品的完整性产生不利影响。本研究介绍了一种综合方法,利用一套机器学习(ML)算法,包括随机森林、高斯过程回归、支持向量机、正则化线性回归、梯度提升树和神经网络,预测飞溅颗粒的喷射速度和方向。我们的分析表明,神经网络模型优于其他模型,对飞溅速度的预测准确率达到 97.58%,对喷射方向的预测准确率达到 88.22%,从而大大提高了对 LPBF 工艺中飞溅相关缺陷的理解和控制能力。这些预测具有深远的实际意义,使制造商能够实时调整 AM 参数,从而最大限度地减少缺陷,提高产品质量。本研究通过对用于飞溅喷射预测的多种 ML 算法进行详细比较分析,不仅填补了现有文献的空白,还为未来 AM 实时监测和控制系统的研究铺平了道路。
Machine learning predictions of spatter behavior in LPBF additive manufacturing
The adoption of additive manufacturing (AM) technologies, particularly Laser Powder Bed Fusion (LPBF), has been rapidly increasing in industries requiring high precision and complex geometries. Despite its advantages, LPBF faces challenges related to defects that affect material quality, with spatter formation being a significant concern. Spatters – tiny particles ejected during the printing process – can adversely affect the final product’s integrity by altering surface roughness and contributing to defects. This study introduces a comprehensive approach to predict the ejection velocity and direction of spatter particles using a suite of machine learning (ML) algorithms, including Random Forest, Gaussian Process Regression, Support Vector Machine, Regularized Linear Regressions, Gradient Boosting Trees, and Neural Networks. Our analysis reveals that the Neural Network model outperforms others, achieving prediction accuracies of 97.58% for spatter velocity and 88.22% for ejection direction, thus offering a substantial improvement in understanding and controlling spatter-related defects in LPBF processes. The practical implications of these predictions are profound, enabling manufacturers to adjust AM parameters in real time to minimize defects and enhance product quality. This study not only fills a gap in the current literature by providing a detailed comparative analysis of multiple ML algorithms for spatter ejection prediction but also paves the way for future research into real-time monitoring and control systems in AM.