Application of CNN networks for an automatic determination of critical loads in scratch tests on a-C:H:W coatings

Lenz, Bastian; Hasselbruch, Henning; Grossmann, Holger; Mehner, A.

doi:10.1016/j.surfcoat.2020.125764

Cited by 26 publications

(13 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…According to the aforementioned points, we concluded that a model based on the convolutional neural networks was most suitable for developing the quality assessment module, as its combined feature extraction and classification into a single trainable model with a manageable number of tunable parameters [ 26 , 27 , 28 ]. Ensuring a substantial amount of data, the model was expected to be invulnerable regarding its classification capabilities due to the input’s data variations.…”

Section: Approachmentioning

confidence: 99%

Deep Quality Assessment of a Solar Reflector Based on Synthetic Data: Detecting Surficial Defects from Manufacturing and Use Phase

Papacharalampopoulos

Tzimanis

Sabatakakis

et al. 2020

Sensors

View full text Add to dashboard Cite

Vision technologies are used in both industrial and smart city applications in order to provide advanced value products due to embedded self-monitoring and assessment services. In addition, for the full utilization of the obtained data, deep learning is now suggested for use. To this end, the current work presents the implementation of image recognition techniques alongside the original the quality assessment of a Parabolic Trough Collector (PTC) reflector surface to locate and identify surface irregularities by classifying images as either acceptable or non-acceptable. The method consists of a three-step solution that promotes an affordable implementation in a relatively small time period. More specifically, a 3D Computer Aided Design (CAD) of the PTC was used for the pre-training of neural networks, while an aluminum reflector surface was used to verify algorithm performance. The results are promising, as this method proved applicable in cases where the actual part was manufactured in small batches or under the concept of customized manufacturing. Consequently, the algorithm is capable of being trained with a limited number of data.

show abstract

Section: Approachmentioning

confidence: 99%

Deep Quality Assessment of a Solar Reflector Based on Synthetic Data: Detecting Surficial Defects from Manufacturing and Use Phase

Papacharalampopoulos

Tzimanis

Sabatakakis

et al. 2020

Sensors

View full text Add to dashboard Cite

show abstract

“…Several cracks appeared with the normal load increases. When the normal load is large enough to damage the TiN films, a large number of transverse cracks and more serious delamination occurred in the scratch [28][29]. Combined with the optical images and the acoustic signals in Figure4, three critical loads Lc1, Lc2, and Lc3 respectively correspond to the three failure mechanisms of the TiN films.…”

mentioning

confidence: 94%

Friction reduction mechanisms of TiN film sliding in graphene aqueous dispersion

Wang

et al. 2022

Lubrication Science

View full text Add to dashboard Cite

The lamellar structure and weak interlayer shear force of graphene endow itself potential application value in lubrication fields, while its lubrication performance has been vastly investigated in various fields. However, there are few studies on the composite tribological performance of graphene and ceramic films. In this study, a solid-liquid lubricating system which TiN film slides in graphene aqueous dispersion is developed, aiming to achieve low friction of the TiN ceramic film in macroscale contact. Two kinds of TiN films were obtained by multi-arc ion plating and magnetron sputtering respectively. The tribological test show that the friction coefficient of the TiN film drops when adding graphene aqueous dispersion and varies with the concentrations of graphene. The results indicate that the graphene might act in two ways to achieve low friction of TiN film, which are liquid lubricating effect of solvents and the formation of smooth sliding interface promoted by graphene.

show abstract

“…It is very suitable for cutting and crushing applications owing to its high abrasion resistance and high toughness. In addition, its hardness up to 62 ± 2 HRC makes it attractive to use (Lenz et al , 2020). Some manufacturing methods are needed to make these hard materials suitable for the place of use (Chen et al , 2020).…”

Section: Introductionmentioning

confidence: 99%

An investigation on cutting of the cold work steel X153CrMoV12 by WEDM

Ceritbinmez

2021

AEAT

View full text Add to dashboard Cite

Purpose Wire electric discharge machining (WEDM) is a non-conventional machining process, which is used for cutting parts of civil and military aircraft, rotorcraft, satellites and spacecraft. The cold work steel X153CrMoV12 is used in molds that are needed to produce plastic and metal parts used in these areas. It is only possible to produce parts with precise dimensions and quality with the use of mold steels with sensitive surfaces. The purpose of this study is to analyze X153CrMoV12 material by cutting it with WEDM method in precise dimensions. Design/methodology/approach The effects of varying cutting parameters on the size of the finished product, surface roughness (SR) and surface hardness were determined by making rough in one pass and precision cuts in different passes. Nikon SMZ745T, Mitutoyo micrometer, Mitutoyo SJ-210 and Insize ISHL-P100 were used for macro-analysis, dimensional control, SR and surface hardness, respectively, to determine the cut qualities. Findings According to the hardness measurement results obtained from the steel surface before cutting and from the cut surfaces after cutting, there was no significant change in the surface hardness owing to the use of heat-treated steel. Increasing the wire tension as a result of the increase in the number of cutting passes and the decrease in the amount of rough stock left for the final cut increased the cut quality. Cutting precision has increased by preventing vibration of the wire with zero upper and lower water pressure required for slag cleaning. Originality/value There are many studies on WEDM in the literature, but there is no similar study emphasizing the importance of the processing parameters such as the number of cutting passes and rough stock amount. In this study, cold work steel with a hardness of 56–60 HRC was machined as rough cut in one pass, rough and fine cut in double pass, double fine cut after one roughing in three passes. As a result of the cuts, 3 µm measurement precision and 0.998 Ra SR were obtained as well as there was no hardness change in the cut surfaces.

show abstract

Application of CNN networks for an automatic determination of critical loads in scratch tests on a-C:H:W coatings

Cited by 26 publications

References 10 publications

Deep Quality Assessment of a Solar Reflector Based on Synthetic Data: Detecting Surficial Defects from Manufacturing and Use Phase

Deep Quality Assessment of a Solar Reflector Based on Synthetic Data: Detecting Surficial Defects from Manufacturing and Use Phase

Friction reduction mechanisms of TiN film sliding in graphene aqueous dispersion

An investigation on cutting of the cold work steel X153CrMoV12 by WEDM

Contact Info

Product

Resources

About