Open Access

The formation of defects such as keyhole pores is a major challenge for the production of metal parts by Laser Powder Bed Fusion (LPBF). The LPBF process is characterized by a large number of influencing factors which can be hard to quantify. Machine Learning (ML) is a prominent tool to predict the outcome of complex processes on the basis of different sensor data. In this study, a ML model for defect prediction is created using thermographic image features as input data. As a reference, the porosity information calculated from an x-ray Micro Computed Tomography (µCT) scan of the produced specimen is used. Physical knowledge about the keyhole pore formation is incorporated into the model to increase the prediction accuracy. From the prediction result, the quality of the input data is evaluated and future demands on in-situ monitoring of LPBF processes are formulated.

For the wide acceptance of the use of additive manufacturing (AM), it is required to provide reliable testing methods to ensure the safety of the additively manufactured parts. A possible solution could be the deployment of in-situ monitoring during the build process. However, for laser powder bed fusion using metal powders (PBF-LB/M) only a few in-situ monitoring techniques are commercially available (optical tomography, melt pool monitoring), which have not been researched to an extent that allows to guarantee the adherence to strict quality and safety standards. In this contribution, we present results of a study of PBF-LB/M printed parts made of the nickel-based superalloy Haynes 282. The formation of defects was provoked by local variations of the process parameters and monitored by thermography, optical tomography and melt pool monitoring. Afterwards, the defects were characterized by computed tomography (CT) to identify the detection limits of the used in-situ techniques.

The formation of flaws such as internal porosity in parts produced by Metal-based Powder Bed Fusion with Laser Beam (PBF-LB/M) significantly hinders its broader industrial application, as porosity can potentially lead to part failure. Addressing this issue, this study explores the efficacy of in-situ thermography, particularly short-wave infrared thermography, for detecting and predicting porosity during manufacturing. This technique is capable of monitoring the part’s thermal history which is closely connected to the flaw formation process. Recent advancements in Machine Learning (ML) have been increasingly leveraged for porosity prediction in PBF-LB/M. However, previous research primarily focused on global rather than localized porosity prediction which simplified the complex prediction task. Thereby, the opportunity to correlate the predicted flaw position with expected part strain to judge the severity of the flaw for part performance is neglected. This study aims to bridge this gap by studying the potential of SWIR thermography for predicting local porosity levels using regression models. The models are trained on data from two identical HAYNES®282® specimens. We compare the effectiveness of feature-based and raw data-based models in predicting different porosity types and examine the importance of input data in porosity prediction. We show that models trained on SWIR thermogram data can identify systematic trends in local flaw formation. This is demonstrated for forced flaw formation using process parameter shifts and, moreover, for randomly formed flaws in the specimen bulk. Furthermore, we identify features of high importance for the prediction of lack-of-fusion and keyhole porosity from SWIR monitoring data.

In this study, we present an enhanced deep learning framework for the prediction of porosity based on thermographic in-situ monitoring data of laser powder bed fusion processes. The manufacturing of two cuboid specimens from Haynes 282 (Ni-based alloy) powder was monitored by a short-wave infrared camera. We use thermogram feature data and x-ray computed tomography data to train a convolutional neural network classifier. The classifier is used to perform a multi-class prediction of the spatially resolved porosity level in small sub-volumes of the specimen bulk.

Since laser powder bed fusion (PBF-LB/M) is prone to the formation of defects during the building process, a fundamental requirement for widespread application is to find ways to assure safety and reliability of the additively manufactured parts. A possible solution for this problem lies in the usage of in-situ thermographic monitoring for defect detection. In this contribution we investigate possibilities and limitations of the VIS/NIR wavelength range for defect detection. A VIS/NIR camera can be based on conventional silicon-based sensors which typically have much higher spatial and temporal resolution in the same price range but are more limited in the detectable temperature range than infrared sensors designed for longer wavelengths. To investigate the influence, we compared the thermographic signatures during the creation of artificially provoked defects by local parameter variations in test specimens made of a nickel alloy (UNS N07208) for two different wavelength ranges (~980 nm and ~1600 nm).