Machine Learning Models in Additive Manufacturing (3D Printing): A Comprehensive Review

Machine Learning Models in Additive Manufacturing (3D Printing): A Comprehensive Review

Additive manufacturing, also known as 3D printing, is a rapidly evolving field that involves the layer-by-layer fabrication of objects controlled by a computer-aided design (CAD) model. As this technology advances, the amount of data generated during the manufacturing process is growing exponentially. This has led to the integration of machine learning (ML), a subset of artificial intelligence (AI), into additive manufacturing research (1).

solidprofessor.com

Applications of Machine Learning in Additive Manufacturing

Machine learning models have found numerous applications in additive manufacturing, such as parameter optimization and anomaly detection. These applications can be classified into different types of ML tasks, including regression, classification, and clustering (1).

Parameter Optimization

One of the major challenges in additive manufacturing is the inconsistency in the quality of printed products, which is highly dependent on numerous processing parameters, such as printing speed and layer thickness. Machine learning models can help address this challenge by making predictions and determining the optimal processing parameters in an efficient way (1).

Anomaly Detection

Another application of machine learning in additive manufacturing is anomaly detection. With the help of in situ monitoring systems, machine learning models can deal with in situ data for defect detection in real time (1).

Machine Learning Techniques in Additive Manufacturing

Machine learning techniques have become more prevalent in manufacturing to develop items and products with reduced labor cost, time, and effort. The integration of ML and optimization techniques has further boosted the necessity and interest in enhancing product quality (2).

Design, Processes, and Production Control

The current state of ML techniques focuses on modern manufacturing methods, particularly additive manufacturing. The various categories, especially focusing on design, processes, and production control of additive manufacturing, are described in the form of a state-of-the-art review (2).

mdpi.com

Future Directions

The research community is exploring new and innovative approaches to integrate ML and AI methods into additive manufacturing. ML algorithms, applications, and platforms are helping AM practitioners improve product quality, optimize the manufacturing process, and reduce costs (1).

In conclusion, the integration of machine learning models into additive manufacturing is a promising area of research that offers numerous opportunities for improving the efficiency and effectiveness of manufacturing processes. However, it also presents several challenges, particularly in terms of handling the large amounts of data generated during the manufacturing process. As this field continues to evolve, further research and development are needed to fully realize the potential of machine learning in additive manufacturing.

Learn more:

1. link.springer.com

2. link.springer.com

3. ieeexplore.ieee.org

4. link.springer.com

5. link.springer.com

6. mdpi.com

7. anl.gov

8. gu.berkeley.edu

要查看或添加评论,请登录

社区洞察

其他会员也浏览了