Search for: All records

Abstract While the complexity of laser powder bed fusion (LPBF) processes facilitates customized and metal-based functional parts to be built, existing process monitoring techniques have limitations. Therefore, the need for intricate process monitoring has grown. Non-uniform emission readings are correlated with overheating. Therefore, process monitoring of areas experiencing excess thermal emission during print to track potential overheating is needed. A process monitoring technique using deep neural network-long short-term memory (DNN-LSTM) deep learning (DL) models for emission tracking has been developed. The DNN component harnesses process parameters, while the LSTM harnesses the time-series emission structure on multiple sets of prints in parallel. Moreover, trust and interpretation of the opaque methodology are needed to make the process widely applicable. Existing explainable artificial intelligence (XAI) methods are inoperative with the model developed. We overcome this gap by developing an attribution-based XAI-enabled DNN-LSTM for predicting, explaining, and evaluating layer-wise emission prediction. Interpretation from attribution-based methods, namely, Shapley additive explanations, integrated gradient explanations, and local interpretable model-agnostic explanations, reveal an estimate of how each physics variable (process parameters, layer number, layer-wise average emission readings) impacts each future layer-wise average emission behavior as decided by the DL model. Finally, existing evaluation metrics of XAI are mostly domain-focused. We overcome this gap by establishing evaluation criteria appropriate for understanding the trust of the explanations in the context of thermal emission prediction for LPBF. 

Abstract Deep learning has impacted defect prediction in additive manufacturing (AM), which is important to ensure process stability and part quality. However, its success depends on extensive training, requiring large, homogeneous datasets—remaining a challenge for the AM industry, particularly for small- and medium-sized enterprises (SMEs). The unique and varied characteristics of AM parts, along with the limited resources of SMEs, hamper data collection, posing difficulties in the independent training of deep learning models. Addressing these concerns requires enabling knowledge sharing from the similarities in the physics of the AM process and defect formation mechanisms while carefully handling privacy concerns. Federated learning (FL) offers a solution to allow collaborative model training across multiple entities without sharing local data. This article introduces an FL framework to predict section-wise heat emission during laser powder bed fusion (LPBF), a vital process signature. It incorporates a customized long short-term memory (LSTM) model for each client, capturing the dynamic AM process's time-series properties without sharing sensitive information. Three advanced FL algorithms are integrated—federated averaging (FedAvg), FedProx, and FedAvgM—to aggregate model weights rather than raw datasets. Experiments demonstrate that the FL framework ensures convergence and maintains prediction performance comparable to individually trained models. This work demonstrates the potential of FL-enabled AM modeling and prediction where SMEs can improve their product quality without compromising data privacy. 

Abstract Powder bed fusion (PBF) is an additive manufacturing process in which laser heat liquefies blown powder particles on top of a powder bed, and cooling solidifies the melted powder particles. During this process, the laser beam heat interacts with the powder causing thermal emission and affecting the melt pool. This paper aims to predict heat emission in PBF by harnessing the strengths of recurrent neural networks. Long short-term memory (LSTM) networks are developed to learn from sequential data (emission readings), while the learning is guided by process physics including laser power, laser speed, layer number, and scanning patterns. To reduce the computational efforts on model training, the LSTM models are integrated with a new approach for down-sampling the pyrometry raw data and extracting useful statistical features from raw data. The structure and hyperparameters of the LSTM model reflect several iterations of tuning based on the training on the pyrometer readings data. Results reveal useful knowledge on how raw pyrometer data should be processed to work the best with LSTM, how physics features are informative in predicting overheating, and the effectiveness of physics-guided LSTM in emission prediction. 

Abstract Factory in a box (FiB) is an emerging technology that meets the dynamic and diverse market demand by carrying a factory module on vehicles to perform on-site production near customers’ locations. It is suitable for meeting time-sensitive demands, such as the outbreak of disasters or epidemics/pandemics. Compared to traditional manufacturing, FiB poses a new challenge of frequently reconfiguring supply chain networks since the final production location changes as the vehicle carrying the factory travels. Supply chain network reconfiguration involves decisions regarding whether suppliers or manufacturers can be retained in the supply chain or replaced. Such a supply chain reconfiguration problem is coupled with manufacturing process planning, which assigns tasks to each manufacturer that impacts material flow in the supply chain network. Considering the supply chain reconfigurability, this article develops a new mathematical model based on nonlinear integer programming to optimize supply chain reconfiguration and assembly planning jointly. An evolutionary algorithm (EA) is developed and customized to the joint optimization of process planning and supplier/manufacturer selection. The performance of EA is verified with a nonlinear solver for a relaxed version of the problem. A case study on producing a medical product demonstrates the methodology in guiding supply chain reconfiguration and process planning as the final production site relocates in response to local demands. The methodology can be potentially generalized to supply chain and service process planning for a mobile hospital offering on-site medical services. 

Physics-informed machine learning is emerging through vast methodologies and in various applications. This paper discovers physics-based custom loss functions as an implementable solution to additive manufacturing (AM). Specifically, laser metal deposition (LMD) is an AM process where a laser beam melts deposited powder, and the dissolved particles fuse to produce metal components. Porosity, or small cavities that form in this printed structure, is generally considered one of the most destructive defects in metal AM. Traditionally, computer tomography scans measure porosity. While this is useful for understanding the nature of pore formation and its characteristics, purely physics-driven models lack real-time prediction ability. Meanwhile, a purely deep learning approach to porosity prediction leaves valuable physics knowledge behind. In this paper, a hybrid model that uses both empirical and simulated LMD data is created to show how various physics-informed loss functions impact the accuracy, precision, and recall of a baseline deep learning model for porosity prediction. In particular, some versions of the physics-informed model can improve the precision of the baseline deep learning-only model (albeit at the expense of overall accuracy).