Data-driven prediction of the high-dimensional thermal history in directed energy deposition processes via recurrent neural networks

Mozaffar, Mojtaba; Paul, Arindam; Al-Bahrani, Reda; Wolff, Sarah; Choudhary, Alok; Agrawal, Ankit; Ehmann, Kornel F.; Cao, Jian

doi:10.1016/j.mfglet.2018.10.002

Cited by 135 publications

(61 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example, recurrent neural networks are designed to work with sequence data (also known as temporal or time-series data) of varying lengths, with most popular applications in speech recognition [89] natural language processing, [90] as well as some recent applications in materials informatics. [91,92] A relatively new class of deep learning is called geometric deep learning which is capable of dealing with non-Euclidean data, such as graphs with nodes and edges, where standard deep learning kernels like convolution are not well-defined. Due to its ability to work with graph data, it has found applications in quantum chemistry, [93,94] in particular for analyzing data from molecular dynamics simulations.…”

Section: Other Types Of Deep Learning Networkmentioning

confidence: 99%

Deep materials informatics: Applications of deep learning in materials science

2019

Self Cite

View full text Add to dashboard Cite

show abstract

Section: Other Types Of Deep Learning Networkmentioning

confidence: 99%

Deep materials informatics: Applications of deep learning in materials science

2019

Self Cite

View full text Add to dashboard Cite

show abstract

“…There has been some limited work on the application of ML techniques for AM processes. Mozaffar et al [44] proposed a data-driven approach to predict the thermal behavior in a directed energy deposition process for various geometries using recurrent neural networks. The proposed approach mapped the position of a point on the printing surface, the time of deposition, the distance of the closest cooling surface, and laser parameters with the thermal output.…”

Section: Related Workmentioning

confidence: 99%

A Real-Time Iterative Machine Learning Approach for Temperature Profile Prediction in Additive Manufacturing Processes

Paul¹,

Mozaffar²,

Yang³

et al. 2019

2019 IEEE International Conference on Data Science and Advanced Analytics (DSAA)

Self Cite

View full text Add to dashboard Cite

Additive Manufacturing (AM) is a manufacturing paradigm that builds three-dimensional objects from a computeraided design model by successively adding material layer by layer. AM has become very popular in the past decade due to its utility for fast prototyping such as 3D printing as well as manufacturing functional parts with complex geometries using processes such as laser metal deposition that would be difficult to create using traditional machining. As the process for creating an intricate part for an expensive metal such as Titanium is prohibitive with respect to cost, computational models are used to simulate the behavior of AM processes before the experimental run. However, as the simulations are computationally costly and timeconsuming for predicting multiscale multi-physics phenomena in AM, physics-informed data-driven machine-learning systems for predicting the behavior of AM processes are immensely beneficial. Such models accelerate not only multiscale simulation tools but also empower real-time control systems using in-situ data. In this paper, we design and develop essential components of a scientific framework for developing a data-driven model-based real-time control system. Finite element methods are employed for solving time-dependent heat equations and developing the database. The proposed framework uses extremely randomized trees -an ensemble of bagged decision trees as the regression algorithm iteratively using temperatures of prior voxels and laser information as inputs to predict temperatures of subsequent voxels. The models achieve mean absolute percentage errors below 1% for predicting temperature profiles for AM processes. The code is made available for the research community at https://github.com/paularindam/ml-iter-additive.

show abstract

“…In recent years, there have been multiple efforts focusing on creating surrogate models to cope with the computational cost of the HFMs for AM [ 5 , 9 , 10 , 11 , 12 , 13 , 14 ]. In general, the data acquired from the high fidelity simulations or experiments are used for training the surrogate models (see Figure 1 ).…”

Section: Introductionmentioning

confidence: 99%

Feature Engineering for Surrogate Models of Consolidation Degree in Additive Manufacturing

Roy

Wodo

2021

Materials

View full text Add to dashboard Cite

Surrogate models (SM) serve as a proxy to the physics- and experiment-based models to significantly lower the cost of prediction while providing high accuracy. Building an SM for additive manufacturing (AM) process suffers from high dimensionality of inputs when part geometry or tool-path is considered in addition to the high cost of generating data from either physics-based models or experiments. This paper engineers features for a surrogate model to predict the consolidation degree in the fused filament fabrication process. Our features are informed by the physics of the underlying thermal processes and capture the characteristics of the part’s geometry and the deposition process. Our model is learned from medium-size data generated using a physics-based thermal model coupled with the polymer healing theory to determine the consolidation degree. Our results demonstrate high accuracy (>90%) of consolidation degree prediction at a low computational cost (four orders of magnitude faster than the numerical model).

show abstract

Data-driven prediction of the high-dimensional thermal history in directed energy deposition processes via recurrent neural networks

Cited by 135 publications

References 19 publications

Deep materials informatics: Applications of deep learning in materials science

Deep materials informatics: Applications of deep learning in materials science

A Real-Time Iterative Machine Learning Approach for Temperature Profile Prediction in Additive Manufacturing Processes

Feature Engineering for Surrogate Models of Consolidation Degree in Additive Manufacturing

Contact Info

Product

Resources

About