An official website of the United States government
Abstract The temperature history of an additively manufactured part plays a critical role in determining process–structure–property relationships in fusion-based additive manufacturing (AM) processes. Therefore, fast thermal simulation methods are needed for a variety of AM tasks, from temperature history prediction for part design and process planning to in situ temperature monitoring and control during manufacturing. However, conventional numerical simulation methods fall short in satisfying the strict requirements of time efficiency in these applications due to the large space and time scales of the required multiscale simulation. While data-driven surrogate models are of interest for their rapid computation capabilities, the performance of these models relies on the size and quality of the training data, which is often prohibitively expensive to create. Physics-informed neural networks (PINNs) mitigate the need for large datasets by imposing physical principles during the training process. This work investigates the use of a PINN to predict the time-varying temperature distribution in a part during manufacturing with laser powder bed fusion (L-PBF). Notably, the use of the PINN in this study enables the model to be trained solely on randomly synthesized data. These training data are both inexpensive to obtain, and the presence of stochasticity in the dataset improves the generalizability of the trained model. Results show that the PINN model achieves higher accuracy than a comparable artificial neural network trained on labeled data. Further, the PINN model trained in this work maintains high accuracy in predicting temperature for laser path scanning strategies unseen in the training data.
more »
« less
Capturing Local Temperature Evolution During Additive Manufacturing Through Fourier Neural Operators
High-fidelity, data-driven models that can quickly simulate thermal behavior during additive manufacturing (AM) are crucial for improving the performance of AM technologies in multiple areas, such as part design, process planning, monitoring, and control. However, the complexities of part geometries make it challenging for current models to maintain high accuracy across a wide range of geometries. Additionally, many models report a low mean square error (MSE) across the entire domain (part). However, in each time step, most areas of the domain do not experience significant changes in temperature, except for the heat-affected zones near recent depositions. Therefore, the MSE-based fidelity measurement of the models may be overestimated. This paper presents a data-driven model that uses Fourier Neural Operator to capture the local temperature evolution during the additive manufacturing process. In addition, the authors propose to evaluate the model using the R2 metric, which provides a relative measure of the model’s performance compared to using mean temperature as a prediction. The model was tested on numerical simulations based on the Discontinuous Galerkin Finite Element Method for the Direct Energy Deposition process, and the results demonstrate that the model achieves high fidelity as measured by R2 and maintains generalizability to geometries that were not included in the training process.
more »
« less
- Award ID(s):
- 2309250
- PAR ID:
- 10496761
- Publisher / Repository:
- American Society of Mechanical Engineers
- Date Published:
- Journal Name:
- ASME 2023 International Design Engineering Technical Conferences and Computers and Information in Engineering Conference
- ISBN:
- 978-0-7918-8729-5
- Format(s):
- Medium: X
- Location:
- Boston, Massachusetts, USA
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Understanding thermal stress evolution in metal additive manufacturing (AM) is crucial for producing high-quality components. Recent advancements in machine learning (ML) have shown great potential for modeling complex multiphysics problems in metal AM. While physics-based simulations face the challenge of high computational costs, conventional data-driven ML models require large, labeled training datasets to achieve accurate predictions. Unfortunately, generating large datasets for ML model training through time-consuming experiments or high-fidelity simulations is highly expensive in metal AM. To address these challenges, this study introduces a physics-informed neural network (PINN) framework that incorporates governing physical laws into deep neural networks (NNs) to predict temperature and thermal stress evolution during the laser metal deposition (LMD) process. The study also discusses enhanced accuracy and efficiency of the PINN model when supplemented with small simulation data. Furthermore, it highlights the PINN transferability, enabling fast predictions with a set of new process parameters using a pre-trained PINN model as an online soft sensor, significantly reducing computation time compared to physics-based numerical models while maintaining accuracy.more » « less
-
Abstract Designing for manufacturing poses significant challenges in part due to the computation bottleneck of Computer-Aided Manufacturing (CAM) simulations. Although deep learning as an alternative offers fast inference, its performance is dependently bounded by the need for abundant training data. Representation learning, particularly through pre-training, offers promise for few-shot learning, aiding in manufacturability tasks where data can be limited. This work introduces VIRL, a Volume-Informed Representation Learning approach to pre-train a 3D geometric encoder. The pretrained model is evaluated across four manufacturability indicators obtained from CAM simulations: subtractive machining (SM) time, additive manufacturing (AM) time, residual von Mises stress, and blade collisions during Laser Power Bed Fusion process. Across all case studies, the model pre-trained by VIRL shows substantial enhancements in generalizability, as measured by R2 regression results, with improved performance on limited data and superior predictive accuracy with larger datasets. Regarding deployment strategy, case-specific phenomenon exists where finetuning VIRL-pretrained models adversely affects AM tasks with limited data but benefits SM time prediction. Moreover, the efficacy of Low-rank adaptation (LoRA), which balances between probing and finetuning, is explored. LoRA shows stable performance akin to probing with limited data, while achieving a higher upper bound than probing as data size increases, without the computational costs of finetuning. Furthermore, static normalization of manufacturing indicators consistently performs well across tasks, while dynamic normalization enhances performance when a reliable task dependent input is available.more » « less
-
A Data-Driven Approach for Process Optimization of Metallic Additive Manufacturing Under UncertaintyThe presence of various uncertainty sources in metal-based additive manufacturing (AM) process prevents producing AM products with consistently high quality. Using electron beam melting (EBM) of Ti-6Al-4V as an example, this paper presents a data-driven framework for process parameters optimization using physics-informed computer simulation models. The goal is to identify a robust manufacturing condition that allows us to constantly obtain equiaxed materials microstructures under uncertainty. To overcome the computational challenge in the robust design optimization under uncertainty, a two-level data-driven surrogate model is constructed based on the simulation data of a validated high-fidelity multiphysics AM simulation model. The robust design result, indicating a combination of low preheating temperature, low beam power, and intermediate scanning speed, was acquired enabling the repetitive production of equiaxed structure products as demonstrated by physics-based simulations. Global sensitivity analysis at the optimal design point indicates that among the studied six noise factors, specific heat capacity and grain growth activation energy have the largest impact on the microstructure variation. Through this exemplar process optimization, the current study also demonstrates the promising potential of the presented approach in facilitating other complicate AM process optimizations, such as robust designs in terms of porosity control or direct mechanical property control.more » « less
-
Design for manufacturing provides engineers with a structure for accommodating the limitations of traditional manufacturing processes. However, little emphasis is typically given to the capabilities of processes that enable novel design geometries, which are often a point of focus when designing products to be made with additive manufacturing (AM) technologies. In addition, limited research has been conducted to understand how knowledge of both the capabilities (i.e., opportunistic) and limitations (i.e., restrictive aspects) of AM affects design outcomes. This study aims to address this gap by investigating the effect of no, restrictive, and both, opportunistic and restrictive (dual) design for additive manufacturing (DfAM) education on engineering students’ creative process. Based on the componential model of creativity [1], these effects were measured through changes in (1) motivation and interest in AM, (2) DfAM self-efficacy, and (3) the emphasis given to DfAM in the design process. These metrics were chosen as they represent the cognitive components of ‘task-motivation’ and ‘domain relevant skills’, which in turn influence the learning and usage of domain knowledge in creative production. The results of the study show that while the short (45 minute) DfAM intervention did not significantly change student motivation and interest towards AM, students showed high levels of motivation and interest towards AM, before the intervention. Teaching students different aspects of DfAM also resulted in an increase in their self-efficacy in the respective topics. However, despite showing a greater increase in self-efficacy in their respective areas of training, the students did not show differences in the emphasis they gave to these DfAM concepts, in the design process. Further, students from all three education groups showed higher use of restrictive concepts, in comparison to opportunistic DfAM.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- https://doi.org/10.1115/DETC2023-117055
