Detecting Attacks in CyberManufacturing Systems: Additive Manufacturing Example

Wu, Min; Zhou, Heguang; Lin, Longwang Lucas; Silva, Bruno; Song, Zhengyi; Cheung, Jackie Chi Kit; Moon, Young B.

doi:10.1051/matecconf/201710806005

Cited by 18 publications

(6 citation statements)

References 5 publications

(10 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Previous work has focused on the use of classification techniques in additive manufacturing processes. Wu et al [17,18] applied random forest, k-nearest neighbor, and anomaly detection techniques to detect defects caused by a cyberattack on an FDM printer during part fabrication. Amini and Chang [19] used classification techniques to reduce defects in metal parts manufacturing processes using selective laser melting (SLM) printers.…”

Section: Introductionmentioning

confidence: 99%

Decision Tree Methods for Predicting Surface Roughness in Fused Deposition Modeling Parts

Barrios

Romero

2019

Materials

View full text Add to dashboard Cite

3D printing using fused deposition modeling (FDM) includes a multitude of control parameters. It is difficult to predict a priori what surface finish will be achieved when certain values are set for these parameters. The objective of this work is to compare the models generated by decision tree algorithms (C4.5, random forest, and random tree) and to analyze which makes the best prediction of the surface roughness in polyethylene terephthalate glycol (PETG) parts printed in 3D using the FDM technique. The models have been created using a dataset of 27 instances with the following attributes: layer height, extrusion temperature, print speed, print acceleration, and flow rate. In addition, a dataset has been created to evaluate the models, consisting of 15 additional instances. The models generated by the random tree algorithm achieve the best results for predicting the surface roughness in FDM parts.

show abstract

Section: Introductionmentioning

confidence: 99%

Decision Tree Methods for Predicting Surface Roughness in Fused Deposition Modeling Parts

Barrios

Romero

2019

Materials

View full text Add to dashboard Cite

show abstract

“…To detect infill defect in 3D printing, in connection with their previous work (Wu et al, 2016); therefore, this study uses three ML algorithms, that is, (random forest, K-nearest neighbour and anomaly detection) to classify, cluster and detect anomalies on different kind of infills. The findings compare the accuracies between simulated 3D printing process images and the actual 3D printing process images (Wu et al, 2017b).…”

Section: Recent Applications Of Machine Learning With Big Data In Addmentioning

confidence: 99%

“…Wu et al (2017b) described cyber-manufacturing system as the goal of future of manufacturing and a platform where several physical components are connected and integrated together within an environment through computational processes. Wu et al (2017b) describes "additive manufacturing as a type of system that is vulnerable to malicious attacks which as a result could lead to defective interior infills without affecting the exterior or the final part". Their study uses a visionbased system to detect intentional attacks within the additive manufacturing production using ML techniques.…”

Section: Recent Applications Of Machine Learning With Big Data In Addmentioning

confidence: 99%

A Survey on Recent Applications of Machine Learning with Big Data in Additive Manufacturing Industry

Alabi¹,

Botef²

2018

American Journal of Engineering and Applied Sciences

View full text Add to dashboard Cite

Additive Manufacturing (AM) which is also known as 3D printing technology; is recognized as a new paradigm for manufacturing industry. Additive manufacturing is rapidly expanding across different sectors such as healthcare, electronics, automotive, science and engineering, education, dental, etc. Machine Learning and Big Data are both emerging technologies which are becoming popular and gaining more attention from the industries and academic. Machine Learning is a growing field of Artificial Intelligence (AI) that allows systems to learn from data, identify patterns and make decisions with very little human involvement. On the other hand, Big Data is referred to as datasets whose size is more than the capacity of what a conventional database software tools can capture, store, manage and analyze. Lately, Machine Learning techniques and Big Data Analytics are being applied to various applications of additive manufacturing to monitor building process and enhance decisions making using data generated through different sensors or cameras. This paper explores recent applications of Machine Learning with Big Data in the field of additive manufacturing, for instance, application of machine learning in detecting defect or anomaly during build process in additive manufacturing/3D printing machine.

show abstract

“…In the FDM process, SVM was used to classify good and defective parts from the images taken by a digital camera at present checkpoints [113]. To detect various kinds of malicious infills, layer-wise images were processed by the K-nearest neighbour (KNN), RF and unsupervised ML methods, where unsupervised ML methods offered the highest classification accuracy [114,115].…”

Section: J O U R N a L P R E -P R O O Fmentioning

confidence: 99%