An Online Side Channel Monitoring Approach for Cyber-Physical Attack Detection of Additive Manufacturing

2020 ◽  
Author(s):  
Chenang Liu ◽  
Chen Kan ◽  
Wenmeng Tian
Keyword(s):  
Additive Manufacturing ◽  
Process Monitoring ◽  
Attack Detection ◽  
Monitoring Methods ◽  
Fused Filament Fabrication ◽  
Geometric Dimensioning And Tolerancing ◽  
Part Geometry ◽  
Physical Attack ◽  
Side Channels ◽  
Process Product

Abstract Due to its predominant flexibility in fabricating complex geometries, additive manufacturing (AM) has gain increasing popularity in various mission critical applications, such as aerospace, health care, military, and transportation. The layerby-layer manner of AM fabrication significantly expands the vulnerability space of AM cyber-physical systems, leading to potentially altered AM parts with compromised mechanical properties and functionalities. Moreover, internal alterations of the build are very difficult to detect based on traditional geometric dimensioning and tolerancing (GD&T) features. Therefore, how to achieve effective monitoring and attack detection is a very important problem for broader adoption of AM technology. To address this issue, this paper proposes to utilize side channels for process authentication. An online feature extraction approach is developed based on autoencoder to detect unintended process/product alterations caused by cyber-physical attacks. Both supervised and unsupervised monitoring schemes are implemented based on the extracted features. To validate the effectiveness of the proposed method, two real-world case studies are conducted on a fused filament fabrication (FFF) platform equipped with two accelerometers for process monitoring. Two different types of attacks are implemented. The results demonstrate that the proposed method outperforms conventional process monitoring methods, and can effectively detect part geometry and layer thickness alterations in real time.

Accelerated Geometry Accuracy Optimization of Additive Manufacturing Parts

2017 ◽  
Author(s):  
Amir M. Aboutaleb ◽  
Linkan Bian ◽  
Prahalad K. Rao ◽  
Mark A. Tschopp
Keyword(s):  
Additive Manufacturing ◽  
Optimization Problem ◽  
Principal Component ◽  
Geometric Features ◽  
Simulation Studies ◽  
Fused Filament Fabrication ◽  
Efficient Manner ◽  
Geometric Dimensioning And Tolerancing ◽  
Novel Approach

Despite recent advances in improving mechanical properties of parts fabricated by Additive Manufacturing (AM) systems, optimizing geometry accuracy of AM parts is still a major challenge for pushing this cutting-edge technology into the mainstream. This work proposes a novel approach for improving geometry accuracy of AM parts in a systematic and efficient manner. Initial experimental data show that different part geometric features are not necessary positively correlated. Hence, it may not be possible to optimize them simultaneously. The proposed methodology formulates the geometry accuracy optimization problem as a multi-objective optimization problem. The developed method targeted minimizing deviations within part’s major Geometric Dimensioning and Tolerancing (GD&T) features (i.e., Flatness, Circularity, Cylindricity, Concentricity and Thickness). First, principal component analysis (PCA) is applied to extract key components within multi-geometric features of parts. Then, experiments are sequentially designed in an accelerated and integrated framework to achieve sets of process parameters resulting in acceptable level of deviations within principal components of multi-geometric features of parts. The efficiency of proposed method is validated using simulation studies coupled with a real world case study for geometry accuracy optimization of parts fabricated by fused filament fabrication (FFF) system. The results show that optimal designs are achieved by fewer numbers of experiments compared with existing methods.

scholarly journals Design of Shape Memory Thermoplastic Material Systems for FDM-Type Additive Manufacturing

Materials ◽  
2021 ◽  
Vol 14 (15) ◽  
pp. 4254
Author(s):  
Paulina A. Quiñonez ◽  
Leticia Ugarte-Sanchez ◽  
Diego Bermudez ◽  
Paulina Chinolla ◽  
Rhyan Dueck ◽  
...  
Keyword(s):  
Additive Manufacturing ◽  
Shape Memory ◽  
Thermomechanical Processing ◽  
Material Selection ◽  
Shape Memory Polymer ◽  
Fused Filament Fabrication ◽  
Materials Development ◽  
Thermoplastic Material ◽  
Polymer Systems ◽  
Injection Molded

The work presented here describes a paradigm for the design of materials for additive manufacturing platforms based on taking advantage of unique physical properties imparted upon the material by the fabrication process. We sought to further investigate past work with binary shape memory polymer blends, which indicated that phase texturization caused by the fused filament fabrication (FFF) process enhanced shape memory properties. In this work, two multi-constituent shape memory polymer systems were developed where the miscibility parameter was the guide in material selection. A comparison with injection molded specimens was also carried out to further investigate the ability of the FFF process to enable enhanced shape memory characteristics as compared to other manufacturing methods. It was found that blend combinations with more closely matching miscibility parameters were more apt at yielding reliable shape memory polymer systems. However, when miscibility parameters differed, a pathway towards the creation of shape memory polymer systems capable of maintaining more than one temporary shape at a time was potentially realized. Additional aspects related to impact modifying of rigid thermoplastics as well as thermomechanical processing on induced crystallinity are also explored. Overall, this work serves as another example in the advancement of additive manufacturing via materials development.

Fused Filament Fabrication 3D Printed Polylactic Acid Electroosmotic Pumps

Lab on a Chip ◽  
2021 ◽  
Author(s):  
Liang Wu ◽  
Stephen Beirne ◽  
Joan-Marc Cabot Canyelles ◽  
Brett Paull ◽  
Gordon G. Wallace ◽  
...  
Keyword(s):  
Additive Manufacturing ◽  
3D Printing ◽  
Polylactic Acid ◽  
Fused Filament Fabrication ◽  
Flexible Approach ◽  
Electroosmotic Pump ◽  
3D Printed ◽  
Electroosmotic Pumps

Additive manufacturing (3D printing) offers a flexible approach for the production of bespoke microfluidic structures such as the electroosmotic pump. Here a readily accessible fused filament fabrication (FFF) 3D printing...

scholarly journals GEOMETRICAL BENCHMARKING OF LASER POWDER BED FUSION SYSTEMS BASED ON DESIGNER NEEDS

2021 ◽  
Vol 1 ◽  
pp. 1657-1666
Author(s):  
Joaquin Montero ◽  
Sebastian Weber ◽  
Christoph Petroll ◽  
Stefan Brenner ◽  
Matthias Bleckmann ◽  
...  
Keyword(s):  
Additive Manufacturing ◽  
Use Case ◽  
Powder Bed Fusion ◽  
Design For Additive Manufacturing ◽  
Laser Powder Bed Fusion ◽  
Measuring Systems ◽  
Powder Bed ◽  
Geometric Dimensioning And Tolerancing ◽  
Uncertainty Map ◽  
New System

AbstractCommercially available metal Laser Powder Bed Fusion (L-PBF) systems are steadily evolving. Thus, design limitations narrow and the diversity of achievable geometries widens. This progress leads researchers to create innovative benchmarks to understand the new system capabilities. Thereby, designers can update their knowledge base in design for additive manufacturing (DfAM). To date, there are plenty of geometrical benchmarks that seek to develop generic test artefacts. Still, they are often complex to measure, and the information they deliver may not be relevant to some designers. This article proposes a geometrical benchmarking approach for metal L-PBF systems based on the designer needs. Furthermore, Geometric Dimensioning and Tolerancing (GD&T) characteristics enhance the approach. A practical use-case is presented, consisting of developing, manufacturing, and measuring a meaningful and straightforward geometric test artefact. Moreover, optical measuring systems are used to create a tailored uncertainty map for benchmarking two different L-PBF systems.

The influence of infill density gradient on the mechanical properties of PLA optimized structures by additive manufacturing

2021 ◽  
pp. 146442072110071
Author(s):  
AIL Pais ◽  
C Silva ◽  
MC Marques ◽  
JL Alves ◽  
J Belinha
Keyword(s):  
Finite Element Method ◽  
Finite Element ◽  
Additive Manufacturing ◽  
Structural Optimization ◽  
Meshless Method ◽  
Load Case ◽  
Fused Filament Fabrication ◽  
Ductile Metals ◽  
Four Point Bending ◽  
Bending Load

The aim of this work is the development of a novel framework for structural optimization using bio-inspired remodelling algorithm adapted to additive manufacturing. The fact that polylactic acid (PLA, E = 3145 MPa (Young’s modulus) according to the supplier for parts obtained by injection) shows a similar parameterized behavior with ductile metals, in the sense that both materials are characterized by a bi-linear elastic-plastic law, allows to simulate and prototype parts to be further constructed in ductile metals at a lower cost and then be produced with more expensive fabrication processes. Moreover, cellular materials allow for a significant weight reduction and therefore reduction of production costs. Structural optimization algorithms based on biological phenomena were used to determine the density distribution of the infill density of the specimens. Several simple structures were submitted to distinct complex load cases and analyzed using the mentioned optimization algorithms combined with the finite element method and a meshless method. The surface was divided according to similar density and then converted to stereolitography files and infilled with the gyroid structure at the desired density determined before, using open-source slicing software. Smoothing functions were used to smooth the density field obtained with the remodeling algorithms. The samples were printed with fused filament fabrication technology and submitted to mechanical flexural tests similar to the ones analyzed analytically, namely three- and four-point bending tests. Thus, the factors of analysis were the smoothing parameter and the remodeling method, and the responses evaluated were stiffness, specific stiffness, maximum force, and mass. The experimental results correlated (obtaining accuracy of 35% for the three-point bending load case and 5% for the four-point bending load case) to the numerical results in terms of flexural stiffness and it was found that the complexity of the load case is relevant for the efficiency of the functional gradient. The fused filament fabrication process is still not accurate enough to be able to experimentally compare the results based of finite element method and meshless method analyses.

scholarly journals Cyber—Physical Attack Detection in Water Distribution Systems with Temporal Graph Convolutional Neural Networks

Water ◽  
2021 ◽  
Vol 13 (9) ◽  
pp. 1247
Author(s):  
Lydia Tsiami ◽  
Christos Makropoulos
Keyword(s):  
Neural Networks ◽  
Distribution System ◽  
Distribution Systems ◽  
Water Distribution ◽  
Attack Detection ◽  
Convolutional Network ◽  
Irreversible Damage ◽  
Physical Attack ◽  
Temporal Graph ◽  
Graph Neural Networks

Prompt detection of cyber–physical attacks (CPAs) on a water distribution system (WDS) is critical to avoid irreversible damage to the network infrastructure and disruption of water services. However, the complex interdependencies of the water network’s components make CPA detection challenging. To better capture the spatiotemporal dimensions of these interdependencies, we represented the WDS as a mathematical graph and approached the problem by utilizing graph neural networks. We presented an online, one-stage, prediction-based algorithm that implements the temporal graph convolutional network and makes use of the Mahalanobis distance. The algorithm exhibited strong detection performance and was capable of localizing the targeted network components for several benchmark attacks. We suggested that an important property of the proposed algorithm was its explainability, which allowed the extraction of useful information about how the model works and as such it is a step towards the creation of trustworthy AI algorithms for water applications. Additional insights into metrics commonly used to rank algorithm performance were also presented and discussed.

scholarly journals Monitoring of Flotation Systems by Use of Multivariate Froth Image Analysis

Minerals ◽  
2021 ◽  
Vol 11 (7) ◽  
pp. 683
Author(s):  
Chris Aldrich ◽  
Xiu Liu
Keyword(s):  
Image Analysis ◽  
Process Monitoring ◽  
Chemical Species ◽  
Platinum Metal ◽  
Local Binary Patterns ◽  
Monitoring Methods ◽  
Multivariate Statistical ◽  
Statistical Process ◽  
Froth Stability ◽  
Froth Image

Froth image analysis has been considered widely in the identification of operational regimes in flotation circuits, the characterisation of froths in terms of bubble size distributions, froth stability and local froth velocity patterns, or as a basis for the development of inferential online sensors for chemical species in the froth. Relatively few studies have considered flotation froth image analysis in unsupervised process monitoring applications. In this study, it is shown that froth image analysis can be combined with traditional multivariate statistical process monitoring methods for reliable monitoring of industrial platinum metal group flotation plants. This can be accomplished with well-established methods of multivariate image analysis, such as the Haralick feature set derived from grey level co-occurrence matrices and local binary patterns that were considered in this investigation.

Sign in / Sign up

Export Citation Format

Share Document