Deep Learning for Distortion Prediction in Laser-Based Additive Manufacturing using Big Data

Francis, Jack; Bian, Linkan

doi:10.1016/j.mfglet.2019.02.001

Cited by 156 publications

(52 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this regard, ML models are capable of identifying the occurrence of geometric defect, quantifying the geometric deviation, and providing guidance of geometric error 9 compensation. For instance, Francis et al [20] developed a geometric error compensation framework for L-PBF process using convolutional neural network (CNN) ML model, shown in Figure 5. Using thermal history and some processing parameters as input and distortion as output, the trained ML model is capable of predicting distortion which is then imported reversely to the CAD model to achieve error compensation.…”

Section: Geometric Deviation Controlmentioning

confidence: 99%

See 1 more Smart Citation

Machine Learning in Additive Manufacturing: A Review

Meng

McWilliams

Jarosinski³

et al. 2020

JOM

268

View full text Add to dashboard Cite

In this review article, the latest applications of machine learning (ML) in additive manufacturing (AM) field are reviewed. These applications, such as parameter optimization and anomaly detection, are classified into different types of ML tasks, including regression, classification, and clustering. The performance of various ML algorithms in these types of AM tasks are compared and evaluated. Finally, several future research directions are suggested.

show abstract

Section: Geometric Deviation Controlmentioning

confidence: 99%

“…CAMP-BD represents Convolutional and artificial neural network for Additive Manufacturing Prediction using Big Data. Reprinted with permission from reference[20].…”

mentioning

confidence: 99%

Machine Learning in Additive Manufacturing: A Review

Meng

McWilliams

Jarosinski³

et al. 2020

JOM

268

View full text Add to dashboard Cite

show abstract

“…A Proposed Framework of the Industry 4.0 Impact on the Additive Manufacturing Business Models Industry 4.0 promises major improvements to the current production processes and it is essential for additive manufacturing to be an integral part of Industry 4.0. Many areas with a high potential, such as big data could have vast influence on the shape of new business models [98], but only a few studies address it. For instance, Jack Francis and Linkan Bian [98] propose a model using cloud-computing, connected, manufacturing environment of Industry 4.0 by wisely using Big Data to obtain an increased geometrical accuracy for parts fabricated using laser-based additive manufacturing [98].…”

Section: Business Models and Additive Manufacturingmentioning

confidence: 99%

“…Many areas with a high potential, such as big data could have vast influence on the shape of new business models [98], but only a few studies address it. For instance, Jack Francis and Linkan Bian [98] propose a model using cloud-computing, connected, manufacturing environment of Industry 4.0 by wisely using Big Data to obtain an increased geometrical accuracy for parts fabricated using laser-based additive manufacturing [98]. By combining product design and additive manufacturing, manufacturing costs can be calculated by evaluating more product model features with big data [99].…”

Section: Business Models and Additive Manufacturingmentioning

confidence: 99%

Impact Assessment of Additive Manufacturing on Sustainable Business Models in Industry 4.0 Context

et al. 2020

View full text Add to dashboard Cite

Additive manufacturing has the potential to make a longstanding impact on the manufacturing world and is a core element of the Fourth Industrial Revolution. Additive manufacturing signifies a new disruptive path on how we will produce parts and products. Several studies suggest this technology could foster sustainability into manufacturing systems based on its potential of optimizing material consumption, creating new shapes, customizing designs and shortening production times that, all combined, will greatly transform some of the existing business models. Although it requires reaching a certain level of design maturity to completely insert this technology in an industrial setting, additive manufacturing has the potential to favorably impact the manufacturing sector by reducing costs in production, logistics, inventories, and in the development and industrialization of a new product. The transformation of the industry and the acceleration of the adopting rate of new technologies is driving organizational strategy. Thus, through the lenses of Industry 4.0 and its technological concepts, this paper aims to contribute to the knowledge about the impacts of additive manufacturing technology on sustainable business models. This aim is accomplished through a proposed framework, as well as the models and scales that can be used to determine these impacts. The effects are assessed by taking into account the social, environmental and economic impacts of additive manufacturing on business models and for all these three dimensions a balanced scorecard structure is proposed.

show abstract

“…Therefore, the predictive models used for both inner-and outer-loop control are previously trained, offline, data-driven AI/ML models. The major output of the loop-based monitoring functions, therefore, are the information models needed as inputs to those AI/ML models [12][13][14][15][16][17].…”

Section: Am Process Control Architecturementioning

confidence: 99%

A New Architectural Approach to Monitoring and Controlling AM Processes

Adnan

Jones

et al. 2020

Applied Sciences

View full text Add to dashboard Cite

The abilities to both monitor and control additive manufacturing (AM) processes in real-time are necessary before the routine production of quality AM parts will be possible. Currently, neither ability exist! The major reason is that AM processes are different from traditional manufacturing processes in many ways and so are the sensors and the monitoring data collected from them. In traditional manufacturing, that data is mostly numeric in nature. To that numeric data, AM monitoring data add large volumes of a variety of in situ, high-speed, image data. Collecting, fusing, and analyzing all that AM data and making the necessary control decisions is not possible using traditional, rigid, hierarchical-control architectures. Therefore, researchers are proposing to use real-time, machine-learning algorithms to analyze the data and to execute the other control functions. This paper identifies those control functions and proposes a new architecture to integrate them. This paper also shows an example of using that architecture to analyze the melt-pool, shape analysis using a clustering method.

show abstract

Deep Learning for Distortion Prediction in Laser-Based Additive Manufacturing using Big Data

Cited by 156 publications

References 11 publications

Machine Learning in Additive Manufacturing: A Review

Machine Learning in Additive Manufacturing: A Review

Impact Assessment of Additive Manufacturing on Sustainable Business Models in Industry 4.0 Context

A New Architectural Approach to Monitoring and Controlling AM Processes

Contact Info

Product

Resources

About