Anomaly detection in laser powder bed fusion using machine learning: A review

Sahar, Tayyaba; Rauf, Muhammad; Murtaza, Ahmar; Khan, Liaqat Ali; Ayub, Hasan; Jameel, Syed Muslim; Ahad, Inam Ul

doi:10.1016/j.rineng.2022.100803

Cited by 23 publications

(7 citation statements)

References 55 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A digital twin is explored in [8] with the goal of detecting anomalies based on data from the machine learning algorithms, digital twin and Industry 4.0 technology. Anomaly detection is also explored in [9] by doing a review of the current techniques used in metal additive manufacturing.…”

Section: Related Work a Industry 40mentioning

confidence: 99%

Anomaly Detection in Smart Industrial Machinery Through Hidden Markov Models and Autoencoders

Sorostinean,

Burghelea,

Gellert

2024

IEEE Access

View full text Add to dashboard Cite

This study addresses the need to develop a sustainable manufacturing process in industrial factories, as the industry desires to remain competitive while it is challenged to adopt eco-friendly practices. A Machine Learning-based software is proposed to deal with the environmental issues, aiming to facilitate the monitoring and analysis of industrial machinery, more exactly of CNC woodworking machines. The focus is on two aspects that determine the environmental impact: energy consumption and toxic emissions, which are used to determine the operating modes of the machines and to detect potential working anomalies. This software consists of a pipeline with two main components: the first one aims to categorize the operating modes of the used machines through time series clustering methods, such as Hidden Markov Models. The second component employs Hidden Markov Models again alongside deep learning based Autoencoders, in order to identify huge deviations within the environmental data. For evaluation, a dataset was collected as a time series from a CNC woodworking machine and then the preprocessed data was further analyzed using the implemented software. The experiments have shown that for anomaly detection in machine operating modes, the Hidden Markov Model outperforms the Autoencoder and state-of-the-art models in terms of efficiency and robustness.

show abstract

Section: Related Work a Industry 40mentioning

confidence: 99%

Anomaly Detection in Smart Industrial Machinery Through Hidden Markov Models and Autoencoders

Sorostinean,

Burghelea,

Gellert

2024

IEEE Access

View full text Add to dashboard Cite

show abstract

“…In addition, a novel PBF 3D printing system by integrating machine learning and artificial intelligence techniques can automatically detect and predict potential printing problems, and achieve automatic optimization of printing parameters to enhance print quality. 90,94 Bevans et al 103 fused multiple real-time sensor data in laser powder bed fusion (LPBF) 3D printing for shapeindependent real-time detection of multi-scale defects, and by acquiring heterogeneous sensor data from an infrared camera, a splash imaging camera, and an optical powder bed imaging camera, were able to extract the underlying spectrograms to be used as inputs for a simple machine learning model. The method adjusts the laser parameters in real-time according to the shape and temperature of the melt pool during the printing process to prevent the formation of defects.…”

Section: Powder Bed Fusionmentioning

confidence: 99%

Section: Materials Jettingmentioning

confidence: 99%

Advances in 3D printing for polymer composites: A review

Ma,

Zhang,

Ruan

et al. 2024

InfoMat

View full text Add to dashboard Cite

The potential of three‐dimensional (3D) printing technology in the fabrication of advanced polymer composites is becoming increasingly evident. This review discusses the latest research developments and applications of 3D printing in polymer composites. First, it focuses on the optimization of 3D printing technology, that is, by upgrading the equipment or components or adjusting the printing parameters, to make them more adaptable to the processing characteristics of polymer composites and to improve the comprehensive performance of the products. Second, it focuses on the 3D printable novel consumables for polymer composites, which mainly include the new printing filaments, printing inks, photosensitive resins, and printing powders, introducing the unique properties of the new consumables and different ways to apply them to 3D printing. Finally, the applications of 3D printing technology in the preparation of functional polymer composites (such as thermal conductivity, electromagnetic interference shielding, biomedicine, self‐healing, and environmental responsiveness) are explored, with a focus on the distribution of the functional fillers and the influence of the topological shapes on the properties and functional characteristics of the 3D printed products. The aim of this review is to deepen the understanding of the convergence between 3D printing technology and polymer composites and to anticipate future trends and applications.image

show abstract

“…This will establish the safety factor of such failures. Currently, the determination of the nonconformance of an AM build is to capture in situ monitoring data and attempt to characterize the build to other successful and unsuccessful ones [22]. Virtual testing of each specific DTI should be far more reliable than correlations.…”

Section: Digital Twin Certified and Additive Manufacturing (Am)mentioning

confidence: 99%

Digital Twin Certified: Employing Virtual Testing of Digital Twins in Manufacturing to Ensure Quality Products

Grieves

2023

Machines

View full text Add to dashboard Cite

Quality products are a main focus for manufacturers. Product users only determine a product to be a quality product if it performs in operation to the user’s perceived standard. Product manufactures need to take a product lifecycle quality (PLQ) perspective of quality and not simply focus on manufacturing quality control, which is more accurately specification control. Manufacturing is the key phase where products take their physical form. There are increasing costs and decreasing risks of different physical quality strategies. The information provided using digital twins and virtual testing promises to be both low risk and cost and has the potential to predict what the customer will experience in operation by testing products passively with data and actively with simulation to destruction. Digital Twin Certified (DTC) is proposed as the methodology for accomplishing this. DTC will be especially important for the adoption of additive manufacturing.

show abstract

Anomaly detection in laser powder bed fusion using machine learning: A review

Cited by 23 publications

References 55 publications

Anomaly Detection in Smart Industrial Machinery Through Hidden Markov Models and Autoencoders

Anomaly Detection in Smart Industrial Machinery Through Hidden Markov Models and Autoencoders

Advances in 3D printing for polymer composites: A review

Digital Twin Certified: Employing Virtual Testing of Digital Twins in Manufacturing to Ensure Quality Products

Contact Info

Product

Resources

About