2020
DOI: 10.1016/j.procir.2020.03.108
|View full text |Cite
|
Sign up to set email alerts
|

Convolutional Neural Network for geometric deviation prediction in Additive Manufacturing

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
6
0

Year Published

2021
2021
2024
2024

Publication Types

Select...
7
2
1

Relationship

0
10

Authors

Journals

citations
Cited by 38 publications
(6 citation statements)
references
References 10 publications
0
6
0
Order By: Relevance
“…In laser powder-directed energy deposition (LP-DED), three classic geometries, namely a plane wall, L-shaped wall, and rectangular box, are included in finite element analysis with thermal-mechanical modeling to generate training datasets; then, an ANN is applied to build up a model to predict residual stresses [116], as shown in Figure 13. In addition to the ANN model, a convolution neural network is also applied to predict geometric deviation before deposition to avoid defects [117]. The gray-box model approach is also included in the shot-peening process.…”
Section: Machine Learning Methodsmentioning
confidence: 99%
“…In laser powder-directed energy deposition (LP-DED), three classic geometries, namely a plane wall, L-shaped wall, and rectangular box, are included in finite element analysis with thermal-mechanical modeling to generate training datasets; then, an ANN is applied to build up a model to predict residual stresses [116], as shown in Figure 13. In addition to the ANN model, a convolution neural network is also applied to predict geometric deviation before deposition to avoid defects [117]. The gray-box model approach is also included in the shot-peening process.…”
Section: Machine Learning Methodsmentioning
confidence: 99%
“…In the study of additive manufacturing (AM) product quality prediction, reducing the time and cost of process design is key to achieving rapid prototyping. To avoid conducting large numbers of simulation experiments, small sample simulation results are used to train ML models for quickly predicting the inherent strain [40] or geometric deviation [41] of AM products. Additionally, ML can be used in the manufacturing phase, for instance, to predict the quality of surface roughness [42], tensile strength [43], porosity [44,45], and microstructural defects [46] based on digital images or machine sensors.…”
Section: Quality Prediction Based On Machine Learning Techniquesmentioning
confidence: 99%
“…Neurons in a fully connected layer have full connections to all activations in the previous layer. Their activations can hence be computed with a matrix multiplication followed by a bias offset [68].…”
Section: A Fcdnn Structurementioning
confidence: 99%