Search

Abstract In additive manufacturing (AM), process defects such as keyhole pores are difficult to anticipate, affecting the quality and integrity of the AM-produced materials. Hence, considerable efforts have aimed to predict these process defects by training machine learning (ML) models using passive measurements such as acoustic emissions. This work considered a dataset in which keyhole pores of a laser powder bed fusion (LPBF) experiment were identified using X-ray radiography and then registered both in space and time to acoustic measurements recorded during the LPBF experiment. Due to AM’s intrinsic process controls, where a pore-forming event is relatively rare, the acoustic datasets collected during monitoring include more non-pores than pores. In other words, the dataset for ML model development is imbalanced. Moreover, this imbalanced and sparse data phenomenon remains ubiquitous across many AM monitoring schemes since training data is nontrivial to collect. Hence, we propose a machine learning approach to improve this dataset imbalance and enhance the prediction accuracy of pore-labeled data. Specifically, we investigate how data augmentation helps predict pores and non-pores better. This imbalance is improved using recent advances in data augmentation called Mixup, a weak-supervised learning method. Convolutional neural networks (CNNs) are trained on original and augmented datasets, and an appreciable increase in performance is reported when testing on five different experimental trials. When ML models are trained on original and augmented datasets, they achieve an accuracy of 95% and 99% on test datasets, respectively. We also provide information on how dataset size affects model performance. Lastly, we investigate the optimal Mixup parameters for augmentation in the context of CNN performance.

X-rays are used for imaging and sterilisation of bone but cause damage due to ionising radiation. Here, the authors study the degradation of collagen caused by photon-electron excitations and show that damage is initiated from onset which has implications for X-ray imaging and the levels of safe exposure.

Metal lattices are an important class of cellular materials that offer great advantages by providing high-strength and lightweight structures as compared to bulk materials. Progress in additive manufacturing techniques has led to increased complexity in design and shape of produced objects and is greatly beneficial for the development of metallic lattice structures. However additive manufacturing of lattices suffers from unpredictable defect creation that can compromise its mechanical integrity. Although post-build inspection techniques can provide quality assurance of the process, accurate assessment can be technically challenging, time consuming and costly. In this work, we investigate the use of high-speed measurements of thermal emission from the melt pool to identify defective individual struts formed with a missing bottom half in an otherwise fully built lattice structure produced with laser powder bed fusion. Surprisingly, results indicate lower photodiode signal, suggesting colder melt pool surface temperature, when printing struts with missing bottom half as compared to nominal struts. Additional thermographic imaging and multi-physics simulations reveal that the low photodiode signal is accompanied by presence of hot spatters carrying heat away from detection and continuous avalanche of powder on the melt pool. Based on these observations, a method was developed to identify defective individual struts with missing bottom half in full built lattices. This prediction approach provides valuable insights about part quality which are important for process qualification and illustrates the utility of melt pool thermal emission monitoring for identifying specific defects introduced by laser powder bed fusion.

Holotomography, a phase-sensitive synchrotron-based (µCT) modality, is a quantitative 3D imaging method. By exploiting partial spatial X-ray coherence, bones can be imaged volumetrically with high resolution coupled with impressive density sensitivity. This tomographic method reveals the main characteristics of the important tissue compartments in forming bones, including the rapidly changing soft tissue and the partially or fully mineralized bone regions, while revealing subtle density differences in 3D. Here, we show typical results observed within the growing femur bone midshafts of healthy mice that are 1, 3, 7, 10, and 14 days old (postpartum). Our results make use of partially coherent synchrotron radiation employing inline Fresnel propagation in multiple tomographic datasets obtained in the imaging beamline ID19 of the European Synchrotron Radiation Facility. The exquisite detail creates maps of the juxtaposed soft, partially mineralized and highly mineralized bone revealing the environment in which bone cells create and shape the matrix. This high-resolution 3D data can be used to create detailed computational models to study the dynamic processes involved in bone tissue formation and adaptation. Such data can enhance our understanding of the important biomechanical interactions directing maturation and shaping of the bone micro- and macro-geometries.