A Review of <i>In Situ</i> Defect Detection and Monitoring Technologies in Selective Laser Melting

Peng, Xing; An, Huijun; Dong, Guangxi

doi:10.1089/3dp.2021.0114

Cited by 11 publications

(5 citation statements)

References 145 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…On the first look, making a prototype or a few pieces by hand may be more cost-effective. However, as hundreds or thousands of components are produced, the requirement for postprocessing automation in AM becomes increasingly urgent [80,87,114]. To overcome these challenges, researchers and the industry have developed new algorithms and technologies to simplify surface post-processing, such as machine learning approaches that automate key elements of the process, lowering the time and resources necessary.…”

Section: Challenges and Future Prospectsmentioning

confidence: 99%

Untapped Opportunities in Additive Manufacturing with Metals: From New and Graded Materials to Post-Processing

Mosallanejad,

Ghanavati,

Behjat

et al. 2024

Metals

View full text Add to dashboard Cite

Metal additive manufacturing (AM) is an innovative manufacturing method with numerous metallurgical benefits, including fine and hierarchical microstructures and enhanced mechanical properties, thanks to the utilization of a local heat source and the rapid solidification nature of the process. High levels of productivity, together with the ability to produce complex geometries and large components, have added to the versatile applicability of metal AM with applications already implemented in various sectors such as medicine, transportation, and aerospace. To further enhance the potential benefits of AM in the context of small- to medium-scale bulk production, metallurgical complexities should be determined and investigated. Hence, this review paper focuses on three significant metallurgical aspects of metal AM processes: in situ alloying, functionally graded materials, and surface treatments for AM parts. The current text is expected to offer insights for future research works on metal AM to expand its potential applications in various advanced manufacturing sectors.

show abstract

Section: Challenges and Future Prospectsmentioning

confidence: 99%

Untapped Opportunities in Additive Manufacturing with Metals: From New and Graded Materials to Post-Processing

Mosallanejad,

Ghanavati,

Behjat

et al. 2024

Metals

View full text Add to dashboard Cite

show abstract

“…Interestingly, the research results of Oshiro et al [36] just illustrated and verified this application issue. In the study of Peng et al [37], various types of in situ monitoring and defect detection methods (e.g., RFs) and their applications are reviewed for the SLS processes.…”

Section: Random Forestmentioning

confidence: 99%

Oversampling Application of Identifying 3D Selective Laser Sintering Yield by Hybrid Mathematical Classification Models

et al. 2023

View full text Add to dashboard Cite

Selective laser sintering (SLS) is one of the most popular 3D molding technologies; however, the manufacturing steps of SLS machines are cumbersome, and the most important step is focused on molding testing because it requires a lot of direct labor and material costs. This research establishes advanced hybrid mathematical classification models, including random forest (RF), support vector machine (SVM), and artificial neural network (ANN), for effectively identifying the SLS yield of the sintering results from three sintered objects (boxes, cylinders, and flats) to achieve the key purpose of reducing the number of model verification and machine parameter adjustments, thereby saving a lot of manufacturing time and costs. In the experimental process, performance evaluation indicators, such as classification accuracy (CA), area under the ROC curve (AUC), and F1-score, are used to measure the proposed models’ experience with practical industry data. In the experimental results, the ANN gets the highest 0.6168 of CA, and it is found that each machine reduces the average sintering time by four hours when compared with the original manufacturing process. Moreover, we employ an oversampling method to expand the sample data to overcome the existing problems of class imbalance in the dataset collected. An important finding is that the RF algorithm is more suitable for predicting the sintering failure of objects, and its average sintering times per machine are 1.7, which is lower than the 1.95 times of ANN and 2.25 times of SVM. Conclusively, this research yields some valuable empirical conclusions and core research findings. In terms of research contributions, the research results can be provided to relevant academic circles and industry requirements for referential use in follow-up studies or industrial applications.

show abstract

“…The powder exhibits different states during the process of heating, melting, and solidification, which tend to release complex acoustic, optical, and thermal signals. Therefore, it is of great significance to monitor the complex signals of different powder states and realize the online adjustment of the parameters in the printing process for improving the quality of the printing parts (Aminzadeh and Kurfess, 2019;Peng et al, 2022).…”

Section: Introductionmentioning

confidence: 99%

Collaborative control for in situ monitoring of molten pool in selective laser melting

et al. 2023

View full text Add to dashboard Cite

In situ monitoring during the selective laser melting (SLM) process is a promising solution to mitigate defects and improve the quality of as-built parts. However, the existing monitoring platform lacks collaborative control of the process monitoring components, and as a result, it cannot realize a real-time and accurate signal acquisition at a close distance and multiple angles during the whole printing process. In this paper, driven by multiple motors, an off-axis monitoring platform is constructed that enables movement in conjunction with the scraper and laser beam. A fuzzy control-based velocity optimization is proposed to avoid the shock effect on the imaging quality of the CMOS camera and the collision of the scraper and laser. The error between the current location and target location of the molten pool is utilized as the input of the fuzzy controller. Then, the parameters of the PI controller of the stepping motor are dynamically adjusted. ADAMS and SIMULINK co-simulation are conducted to verify the feasibility of the fuzzy algorithm. Finally, the experiment of collaborative motion and the responses of each module are conducted. The results show that with the proposed collaborative platform, the response speed of the system is improved by about 49.6%, and the initial speed of the motor is decreased by about 12.6%, thus avoiding excessive acceleration of the motor. The response time of each motor is ahead of schedule by about 31.8%, which meets the requirements of motion response for SLM process monitoring.

show abstract

A Review of In Situ Defect Detection and Monitoring Technologies in Selective Laser Melting

Cited by 11 publications

References 145 publications

Untapped Opportunities in Additive Manufacturing with Metals: From New and Graded Materials to Post-Processing

Untapped Opportunities in Additive Manufacturing with Metals: From New and Graded Materials to Post-Processing

Oversampling Application of Identifying 3D Selective Laser Sintering Yield by Hybrid Mathematical Classification Models

Collaborative control for in situ monitoring of molten pool in selective laser melting

Contact Info

Product

Resources

About