Powder Bed Fusion (PBF) is a type of Additive Manufacturing (AM) technology that builds parts in a layer-by-layer fashion out of a bed of metal powder via the selective melting action of a laser or electron beam heat source. The technology has become widespread, however the demand is growing for closed loop process monitoring and control in PBF systems to replace the open loop architectures that exist today. This paper demonstrates the simulated efficacy of applying closed-loop state estimation to the problem of monitoring temperature fields within parts during the PBF build process. A simplified LTI model of PBF thermal physics with the properties of stability, controllability and observability is presented. An Ensemble Kalman Filter is applied to the model. The accuracy of this filters’ predictions are assessed in simulation studies of the temperature evolution of various test parts when subjected to simulated laser heat input. The significant result of this study is that the filter supplied predictions that were about 2.5x more accurate than the open loop model in these simulation studies.
more »
« less
This content will become publicly available on January 1, 2025
Physics-Guided Long Short-Term Memory Networks for Emission Prediction in Laser Powder Bed Fusion
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.
more » « less- Award ID(s):
- 2152908
- NSF-PAR ID:
- 10519853
- Publisher / Repository:
- ASME
- Date Published:
- Journal Name:
- Journal of Manufacturing Science and Engineering
- Volume:
- 146
- Issue:
- 1
- ISSN:
- 1087-1357
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Abstract Powder bed fusion (PBF) is an additive manufacturing (AM) process that builds parts in a layer-by-layer fashion out of a bed of metal powder via the selective melting action of a laser or electron beam heat source. Despite its transformational manufacturing capabilities, PBF is currently controlled in the open loop and there is significant demand to apply closed-loop process monitoring and control to the thermal management problem. This paper introduces a controls theoretic analysis of the controllability and observability of temperature states in PBF. The main contributions of the paper are proofs that certain configurations of PBF are classically controllable and observable, but that these configurations are not strongly structurally controllable and observable. These results are complemented by case studies, demonstrating the energy requirement of state estimation under various, industry relevant PBF configurations. These fundamental characterizations of controllability and observability provide a basis for realizing closed-loop PBF temperature estimation.more » « less
-
Powder Bed Fusion (PBF) is a type of additive manufacturing process that builds parts out of metal powder in a layerwise fashion. Quality control (QC) remains an unsolved problem for PBF. Data-driven models of PBF are expensive to train and maintain, in terms of materials and machine time, because they are sensitive to changes in processing conditions.The length and time scale discrepancies of the process make physics-based modeling impractical to implement. We propose monitoring PBF with an Ensemble Kalman Filter (EnKF). The EnKF combines the computational efficiency of datadriven models with the flexibility of physics-based models, while mitigating the flaws of either method. We validate EnKF performance for linear process models, using finite element method data in place of measured experimental data. We show that the EnKF can reduce the error signal 2-norm and 1-norm relative to the open loop model by as much as 75%.more » « less
-
more » « less
This study investigated the influence of diverse laser processing parameters on the thermophysical properties of Ti-6Al-4V and AlSi10Mg alloys manufactured via laser powder bed fusion. During fabrication, the laser power (50 W, 75 W, 100 W) and laser scanning speed (0.2 m/s, 0.4 m/s, 0.6 m/s) were adjusted while keeping other processing parameters constant. Besides laser processing parameters, this study also explored the impact of test temperatures on the thermophysical properties of the alloys. It was found that the thermophysical properties of L-PBF Ti-6Al-4V alloy samples were sensitive to laser processing parameters, while L-PBF AlSi10Mg alloy showed less sensitivity. In general, for the L-PBF Ti-6Al-4V alloy, as the laser power increased and laser scan speed decreased, both thermal diffusivity and conductivity increased. Both L-PBF Ti-6Al-4V and L-PBF AlSi10Mg alloys demonstrated similar dependence on test temperatures, with thermal diffusivity and conductivity increasing as the test temperature rose. The CALPHAD software Thermo-Calc (2023b), applied in Scheil Solidification Mode, was utilized to calculate the quantity of solution atoms, thus enhancing our understanding of observed thermal conductivity variations. A detailed analysis revealed how variations in laser processing parameters and test temperatures significantly influence the alloy’s resulting density, specific heat, thermal diffusivity, and thermal conductivity. This research not only highlights the importance of processing parameters but also enriches comprehension of the mechanisms influencing these effects in the domain of laser powder bed fusion.
-
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
