scholarly journals Deep learning-based automated characterization of crosscut tests for coatings via image segmentation

Author(s):  
Gaoyuan Zhang ◽  
Christian Schmitz ◽  
Matthias Fimmers ◽  
Christoph Quix ◽  
Sayed Hoseini

AbstractA manual scratch test to measure the scratch resistance of coatings applied to a certain substrate is usually used to test the adhesion of a coating. Despite its significant amount of subjectivity, the crosscut test is widely considered to be the most practical measuring method for adhesion strength with a good reliability. Intelligent software tools help to improve and optimize systems combining chemistry, engineering based on high-throughput formulation screening (HTFS) technologies and machine learning algorithms to open up novel solutions in material sciences. Nevertheless, automated testing often misses the link to quality control by the human eye that is sensitive in spotting and evaluating defects as it is the case in the crosscut test. In this paper, we present a method for the automated and objective characterization of coatings to drive and support Chemistry 4.0 solutions via semantic image segmentation using deep convolutional networks. The algorithm evaluated the adhesion strength based on the images of the crosscuts recognizing the delaminated area and the results were compared with the traditional classification rated by the human expert.

2015 ◽  
Vol 1111 ◽  
pp. 1-6 ◽  
Author(s):  
Elena Simona Dogar Cutean ◽  
Ion Mitelea ◽  
Viorel Aurel Şerban ◽  
Cosmin Codrean

Scratch test is one of widely used, fast, and effective methods to obtain the critical loads that are related to adhesion properties of coatings. The determination of adhesion and the scratch resistance is essential for the mechanical characterization of surface layers for research and industry. To evaluate the performance of coatings the scratch test with a Rockwell-C diamond stylus as indenter is a commonly used test for the characterization of hard coatings on predominant metallic substrates due to its comparatively robust experimental setup, the easy use and the representative results. This is the only technique capable of imaging such interface defects which are due to the stressin duced by the scratch experiment.This paper aims to characterize the adhesion and scratch resistance using Millennium200 - Technical Tribo equipment of Ti layer deposited on steel surfaces by means of TIG/WIG welding technique. Ensuring appropriate functional properties of WIG welding coatings (Ti) requires a good compatibility with the substrate material (S235). For this reason was used to deposit titanium WIG welding an intermediary layer of copper, obtained in the same experimental conditions. The optimal selection of the coating material takes into consideration the metallurgical, mechanical and process technology compatibility. The mechanical properties of coatings must match the substrate. From this point of view, maintaining a high corrosion resistance is mainly conditioned by achieving a good adhesion and a microstructure free of internal cracks or other defects.


2018 ◽  
Vol 784 ◽  
pp. 135-140
Author(s):  
Lukáš Václavek ◽  
Jan Tomaštík ◽  
Libor Nožka ◽  
Radim Čtvrtlík

Hafnium oxide (HfO2) is a material characterized by a good mechanical, thermal and chemical stability and is used as a material in a variety of technological applications in optics and electronics. In this work the influence of annealing temperature on the mechanical structural properties of amorphous HfO2 thin film was explored. Films were deposited by electron beam evaporation and annealed in the temperature range from 200 °C to 500 °C in vacuum. Mechanical properties such as hardness and elastic modulus were determined using nanoindentation, while cohesive-adhesive properties of the film using a scratch test. Surface morphology was determined using a confocal microscope and structure using XRD. The transformation of amorphous phase of the films to the nanocrystalline monoclinic phase was observed after vacuum annealing at 500 °C. This crystallization leads to increase in hardness on one hand but also to growth of brittleness and in turn to decrease in scratch resistance on the other hand.


2003 ◽  
Vol 766 ◽  
Author(s):  
A. Sekiguchi ◽  
J. Koike ◽  
K. Ueoka ◽  
J. Ye ◽  
H. Okamura ◽  
...  

AbstractAdhesion strength in sputter-deposited Cu thin films on various types of barrier layers was investigated by scratch test. The barrier layers were Ta1-xNx with varied nitrogen concentration of 0, 0.2, 0.3, and 0.5. Microstructure observation by TEM indicated that each layer consists of mixed phases of β;-Ta, bcc-TaN0.1, hexagonal-TaN, and fcc-TaN, depending on the nitrogen concentration. A sulfur- containing amorphous phase was also present discontinuously at the Cu/barrier interfaces in all samples. Scratch test showed that delamination occurred at the Cu/barrier interface and that the overall adhesion strength increased with increasing the nitrogen concentration. A good correlation was found between the measured adhesion strength and the composing phases in the barrier layer.


Algorithms ◽  
2021 ◽  
Vol 14 (5) ◽  
pp. 144
Author(s):  
Yuexing Han ◽  
Xiaolong Li ◽  
Bing Wang ◽  
Lu Wang

Image segmentation plays an important role in the field of image processing, helping to understand images and recognize objects. However, most existing methods are often unable to effectively explore the spatial information in 3D image segmentation, and they neglect the information from the contours and boundaries of the observed objects. In addition, shape boundaries can help to locate the positions of the observed objects, but most of the existing loss functions neglect the information from the boundaries. To overcome these shortcomings, this paper presents a new cascaded 2.5D fully convolutional networks (FCNs) learning framework to segment 3D medical images. A new boundary loss that incorporates distance, area, and boundary information is also proposed for the cascaded FCNs to learning more boundary and contour features from the 3D medical images. Moreover, an effective post-processing method is developed to further improve the segmentation accuracy. We verified the proposed method on LITS and 3DIRCADb datasets that include the liver and tumors. The experimental results show that the performance of the proposed method is better than existing methods with a Dice Per Case score of 74.5% for tumor segmentation, indicating the effectiveness of the proposed method.


2011 ◽  
Vol 685 ◽  
pp. 367-370 ◽  
Author(s):  
Min Qi ◽  
Da Yi Yang ◽  
Jing Ying Zhang ◽  
Hong Jun Ai

In order to improve the osteoblast growth and bacteria resistance, Zn-containing hydroxyapatite (Zn-HA) and titanium oxide (TiO2) composite coatings were prepared to improve binding between coating and Ti substrate. TiO2 film was prepared on the surface of Ti by micro-arc oxidation (MAO) and Zn-HA coating was deposited on TiO2 using sol–gel technique. Phase structure, composition and microstructure of the surface coatings were analyzed by X-ray diffraction (XRD) and Energy Dispersive Spectrometer (EDS), respectively. The adhesion strength between the coatings with different Zn content was measured by tensile testing. The results showed that there was no significant influence of Zn content on adhesion strength between coating and Ti substrate.


2004 ◽  
Vol 126 (2) ◽  
pp. 372-379 ◽  
Author(s):  
J. L. Bucaille ◽  
E. Felder ◽  
G. Hochstetter

An experimental and numerical study of the scratch test on polymers near their surface is presented. The elastoplastic response of three polymers is compared during scratch tests at large deformations: polycarbonate, a thermosetting polymer and a sol-gel hard coating composed of a hybrid matrix (thermosetting polymer-mineral) reinforced with oxide nanoparticles. The experiments were performed using a nanoindenter with a conical diamond tip having an included angle of 30 deg and a spherical radius of 600 nm. The observations obtained revealed that thermosetting polymers have a larger elastic recovery and a higher hardness than polycarbonate. The origin of this difference in scratch resistance was investigated with numerical modelling of the scratch test in three dimensions. Starting from results obtained by Bucaille (J. Mat. Sci., 37, pp. 3999–4011, 2002) using an inverse analysis of the indentation test, the mechanical behavior of polymers is modeled with Young’s modulus for the elastic part and with the G’sell-Jonas’ law with an exponential strain hardening for the viscoplastic part. The strain hardening coefficient is the main characteristic parameter differentiating the three studied polymers. Its value is equal to 0.5, 4.5, and 35, for polycarbonate, the thermosetting polymer and the reinforced thermosetting polymer, respectively. Firstly, simulations reveals that plastic strains are higher in scratch tests than in indentation tests, and that the magnitude of the plastic strains decreases as the strain hardening increases. For scratching on polycarbonate and for a penetration depth of 0.5 μm of the indenter mentioned above, the representative strain is equal to 124%. Secondly, in agreement with experimental results, numerical modeling shows that an increase in the strain hardening coefficient reduces the penetration depth of the indenter into the material and decreases the depth of the residual groove, which means an improvement in the scratch resistance.


2018 ◽  
Vol 925 ◽  
pp. 318-325
Author(s):  
Rohollah Ghasemi ◽  
Anders E.W. Jarfors

The present study focuses on scratch behaviour of a conventional pearlitic and a number of solid solution strengthened ferritic Compacted Graphite Iron (CGI) alloys. This was done by employing a single-pass microscratch test using a sphero-conical diamond indenter under different constant normal loads conditions. Matrix solution hardening was made by alloying with different content of Si alloy; (3.66, 4.09 and 4.59 wt%. Si) which are named as low-Si, medium-Si and high-Si ferritic CGI alloys, respectively. A good correlation between the tensile and scratch test results was observed explaining the influence of CGI’s matrix characteristics on scratch behaviour both for pearlitic and fully ferritic solution strengthened ones. Both the scratch depth and scratch width showed strong tendency to increase with increasing the normal load, however the pearlitic one showed more profound deformation compared to the solution strengthened CGI alloys. Among the investigated alloys, the maximum and minimum scratch resistance was observed for high-Si ferritic CGI and pearlitic alloys, respectively. It was confirmed by the scratched surfaces analysed using Scanning Electron Microscopy (SEM) as well. In addition, the indenter’s depth of penetration value (scratch depth) was found as a suitable measure to ascertain the scratch resistance of CGI alloys.Keywords: Silicon solution strengthening, CGI, Abrasion, Scratch testing, Scratch resistance


Sign in / Sign up

Export Citation Format

Share Document