Automated evaluation of Rockwell adhesion tests for PVD coatings using convolutional neural networks

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

doi:10.1016/j.surfcoat.2020.125365

Cited by 24 publications

(9 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The Rockwell adhesion test, defined by the VDI 3198 guidelines (VDI: Verein Deutscher Ingenieure), is a well-established method for adhesion testing. 31,32) In addition, a change in the plasma state owing to the application of a magnetic field was observed. The plasma at the exit of the anode was observed using a fiber scope (DEPSTECH, DS450).…”

Section: Experimental Methodsmentioning

confidence: 97%

DC vacuum arc deposition system with an anode generating magnetic field for preparation of TiN films

Kito

Saiki

Homma

et al. 2023

Jpn. J. Appl. Phys.

View full text Add to dashboard Cite

In this study, a coiled anode that generates a magnetic field using a direct current (DC) arc was designed and employed in a cathodic vacuum-arc deposition system. Its performance was evaluated by the formation of TiN films with and without a magnetic field. When the magnetic field was applied by the coiled anode, the deposition rate was approximately 1.5 times faster than that without the magnetic field. In addition, a reduction in the number of droplets with films of the same thickness was expected. Furthermore, the hardness of the film was improved by approximately 10% with the magnetic field of the coiled anode, resulting in a very hard film of 43.7 GPa. These results suggest that the coiled anode is effective in reducing the number of droplets and is promising for the formation of super-hard films, which are preferred for cutting tools.

show abstract

Section: Experimental Methodsmentioning

confidence: 97%

DC vacuum arc deposition system with an anode generating magnetic field for preparation of TiN films

Kito

Saiki

Homma

et al. 2023

Jpn. J. Appl. Phys.

View full text Add to dashboard Cite

show abstract

“…In the classification of brain tumors, Toğaçar et al [17] used AlexNet and VGG16. Lenz et al [18] has used the deep learning models of AlexNet, GoogLeNet, and inception model for the determination of the adhesion strength, and it was noticed that the classification of the implemented models indicates 85 to 90% of accuracy as compared to the assessment done by the human being. Rehman et al [19] has used the VGG16, AlexNet, and GoogLeNet model with transfer learning for the classification of brain tumors and has attained an accuracy of 98.69% with the VGG16 model.…”

Section: Related Workmentioning

confidence: 99%

A Deep Learning-Based Approach in Classification and Validation of Tomato Leaf Disease

Wagle¹

2021

View full text Add to dashboard Cite

Deep learning models are playing a vital role in classification goals that can have propitious results. In the past few years, many models are being used for this purpose of plant disease classification. This work has assisted in the process of identification and classification of a plant leaf disease. In this paper, the Tomato plant leaf images are taken from the PlantVillage Database consisting of one healthy and eight disease classes. The disease classes are selected based on the occurrence of the disease in India. The deep learning models of AlexNet, VGG16, GoogLeNet, MobileNetv2, and SqueezeNet are used in this work for the classification of Tomato plant leaf as healthy or diseased and further which disease class it belongs to. The models used here are all the pre-trained models, so transfer learning is used to fit the total number of classes that need to be classified by the network model. VGG16 model outperformed giving 99.17% accuracy compared to AlexNet, GoogLeNet, MobileNetv2, and SqueezeNet. The work concludes with the model’s validation results on the set of images captured at Krishi Vigyan Kendra Narayangaon (KVKN), India.

show abstract

“…The user can also adapt the classifying layers to the needs of the model being created. This method, called transfer learning, is often used in steels and metal alloys [75,[77][78][79][80]. Numerous models are available, including AlexNet [81], GoogLeNet, VGGNet, and ResNet, which can be used with this technique.…”

Section: Deep Neural Networkmentioning

confidence: 99%

“…Lenz et al [77] applied transfer learning to the automatic evaluation of the adhesion of a coating applied to a steel substrate using the PVD method. The classifier selected one of the six adhesion classes based on the impression image after the standard Rockwell hardness test with a visible network of cracks and peeling of the coating.…”

Section: Deep Neural Networkmentioning

confidence: 99%

Practical Aspects of the Design and Use of the Artificial Neural Networks in Materials Engineering

Sitek

Trzaska

2021

Metals

View full text Add to dashboard Cite

Artificial neural networks are an effective and frequently used modelling method in regression and classification tasks in the area of steels and metal alloys. New publications show examples of the use of artificial neural networks in this area, which appear regularly. The paper presents an overview of these publications. Attention was paid to critical issues related to the design of artificial neural networks. There have been presented our suggestions regarding the individual stages of creating and evaluating neural models. Among other things, attention was paid to the vital role of the dataset, which is used to train and test the neural network and its relationship to the artificial neural network topology. Examples of approaches to designing neural networks by other researchers in this area are presented.

show abstract

Automated evaluation of Rockwell adhesion tests for PVD coatings using convolutional neural networks

Cited by 24 publications

References 12 publications

DC vacuum arc deposition system with an anode generating magnetic field for preparation of TiN films

DC vacuum arc deposition system with an anode generating magnetic field for preparation of TiN films

A Deep Learning-Based Approach in Classification and Validation of Tomato Leaf Disease

Practical Aspects of the Design and Use of the Artificial Neural Networks in Materials Engineering

Contact Info

Product

Resources

About