Applications of Machine Learning in Process Monitoring and Controls of L-PBF Additive Manufacturing: A Review

Abstract

One of the main issues hindering the adoption of parts produced using laser powder bed fusion (L-PBF) in safety-critical applications is the inconsistencies in quality levels. Furthermore, the complicated nature of the L-PBF process makes optimizing process parameters to reduce these defects experimentally challenging and computationally expensive. To address this issue, sensor-based monitoring of the L-PBF process has gained increasing attention in recent years. Moreover, integrating machine learning (ML) techniques to analyze the collected sensor data has significantly improved the defect detection process aiming to apply online control. This article provides a comprehensive review of the latest applications of ML for in situ monitoring and control of the L-PBF process. First, the main L-PBF process signatures are described, and the suitable sensor and specifications that can monitor each signature are reviewed. Next, the most common ML learning approaches and algorithms employed in L-PBFs are summarized. Then, an extensive comparison of the different ML algorithms used for defect detection in the L-PBF process is presented. The article then describes the ultimate goal of applying ML algorithms for in situ sensors, which is closing the loop and taking online corrective actions. Finally, some current challenges and ideas for future work are also described to provide a perspective on the future directions for research dealing with using ML applications for defect detection and control for the L-PBF processes.

Classification of Metal Additive Manufacturing Technologies

“…The LP-DED process is illustrated in Figure 4. The laser beam in the building chamber uses a lens to focus on the building platform, and a powder nozzle simultaneously injects metal powder [24]. The metal powder flows directly on the substrate forming a melting pool after each layer, while the laser source and building platform move simultaneously [25].…”

A Review of Non-Destructive Testing (NDT) Techniques for Defect Detection: Application to Fusion Welding and Future Wire Arc Additive Manufacturing Processes

“…Here, some very interesting approaches similar to the process of LPBF (Laser Powder Bed Fusion) have already been made and could also be transferred/applied to WAAM. For further studies on this topic, we would like to refer the reader to the following non-exhaustive bibliography [ 89 , 90 , 91 , 92 , 93 ].…”

Thermal design considerations for a L-PBF built metal component: effects of Inter-Layer Cooling Time, Preheating Temperature and Gas Flow

“…-L-PBF technique is suitable for many materials, especially for engineering metal alloys such as nickel-based ones [12]; -L-PBF can be conducted at a much higher speed, over 1 m/s, with a lower material cost; -in L-PBF, lower heat induces lower distortions, allowing higher dimensional resolution and precision for the final part. [13] All these advantages facilitate significant investments in developing industrial applications where the printed parts were increasingly larger and more complex and had to meet more stringent quality and functional requirements. Moreover, the ability to manufacture lightweight metal components while maintaining the mechanical and performance required allows the proliferation of L-PBF in the aerospace and aviation industry [13,14].…”