40th International Conference on Production Engineering of Serbia
ICPES 2025
Nis, Serbia, 18-19th september 2025
DIGITALISATION AND SENSING IN ADDITIVE MANUFACTURING: DATA COLLECTION FOR PRODUCT(ION) OPTIMISATION
Vojislav PETROVIC-FILIPOVIC
DOI: 10.46793/ICPES25.023PF
Additive Manufacturing (AM) has evolved into a robust industrial production technology, but its inherent process complexity poses significant challenges to ensuring consistent part quality and repeatability. Traditional quality control methods often take place in the post-process phase, being time-consuming and costly. This paper argues that the future of AM lies in the adoption of real-time, in-situ monitoring and closed-loop control systems and offers several examples to fundament this claim. The AM systems leverage a network of sensors to collect vast amounts of data during the build process, enabling immediate analysis and corrective measures to prevent defect propagation. The methodology of this data-driven approach is explored, distinguishing between different in-situ monitoring solutions (optical, acoustic, and infrared sensors) and their practical implementation. A robust data management pipeline, incorporating advanced data reduction and AI/ML models, is essential to make this approach viable. The paper is discussed through four key research projects—CUSTODIAN, QuaL-DED, WAVETAILOR, and crystAIr—to illustrate these concepts in practice. These projects collectively demonstrate the importance of sensor fusion, AI-driven models and digital twins in establishing a self-optimising ecosystem that can significantly reduce scrap, accelerate development, and pave the way for a zero-defect manufacturing paradigm in AM. The conclusion is that digitalisation in AM is a critical shift that will secure the technology’s future in advanced industrial production.
Additive manufacturing, digital technologies, monitoring, sensors
[1] Market Growth Reports, Laser Market Size & Growth, and Industry Analysis, Aug 2025.
[2] Gibson, I. Additive Manufacturing Technologies, Springer, 2014.
[3] Vincent, J., et al. 3D Printing in Orthopedics: A Review of the Current State and Future Perspectives, Journal of Orthopaedic Case Reports, 2018.
[4] FormNext Trends, FormNext, 2025.
[6] Grasso, M., et al. Laser Powder Bed Fusion Process Monitoring: A Review on Sensors and Systems, Journal of Manufacturing Science and Engineering, 2021.
[7] Shevchik, S. A., et al. Acoustic emission for process monitoring of additive manufacturing, Additive Manufacturing, 2019.
[8] Tapia, G., et al. In-Situ Monitoring of Laser-Based Additive Manufacturing, Journal of Advanced Manufacturing Technology, 2019.
[9] Lidong L, Alexander C.A., Additive Manufacturing and Big Data. December 2016. International Journal of Mathematical Engineering and Management Sciences 1(3):107-121
[10] Petrovic-Filipovic V. et al. Monitoring concept for powder flow monitoring in Laser-Directed Energy Deposition (L-DED) process based on flexible piezoelectric sensors, Materials Open Research, 2022
[11] Montero et al. Inspection of Powder Flow During LMD Deposition by High-Speed Imaging. December 2016. Physics Procedia 83:1319-1328
[12]. CUSTODIAN project official webpage: www.shapeyourlaser.eu
[13] Pallas A et al. A convolutional approach to quality monitoring for laser manufacturing. Journal of Intelligent Manufacturing 31 (3-4). 2020
[14] QuaL-DED Projekt, Project Database: https://projekte.ffg.at/projekt/3701237
[15] WAVETAILOR official project webpage: http://wavetailor.eu
[16] Giuliani F, Petrovic-Filipovic V. et al. Combining Machine Learning, Embedded Sensor Networks and Additive Burner Design for Combustor Structural Health Monitoring. Journal of Engineering for Gas Turbines and Power, Vol 147 (3). 2025
[17] High Temperature Pressure Sensor CP5X, Datasheet: https://www.piezocryst.com/en/product/CP5x1