Analysis of the Region of Interest According to CNN Structure in Hierarchical Pattern Surface Inspection Using CAM

Moon, In Yong; Lee, Ho Won; Kim, Se Jong; Oh, Youngseok; Jung, Jaimyun; Kang, Seong-Hoon

doi:10.3390/ma14092095

Cited by 10 publications

(4 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Multiple channel surfaces, contrary micro-pits, and complicated processing forms have been shown to have a beneficial influence on bone cell behavior. Additionally, EDM machining produced channel forms with an average surface roughness of 0.1-10 µm (for Ti6Al4V alloy) [48] and 2.5-10 µm (for aluminum alloy) [49] in channel forms. In this work, a high level of surface quality was attained by reducing the Cp-Ti alloy's surface roughness in consideration of the high accuracy required for micromachining.…”

Section: The Topographies Of Surface Patterned Cp-ti Alloymentioning

confidence: 99%

Surface properties of micro surface patterned Cp-Ti alloy via electrical discharge machining

BALTA

2023

J Adv Manuf Eng

View full text Add to dashboard Cite

The process of machining micro surface patterns on a workpiece to improve various performance aspects of engineering materials, including wear resistance, corrosion resistance, and biocompatibility, has been a hot topic of research in recent years. Due to the restricted machinability of titanium and its alloys, it is very challenging to process micro surface patterns with exact surface geometries using traditional machining methods. Consequently, non-traditional processing techniques, such as laser, electro-erosion, and chemical etching, may overcome these obstacles. In the present study, electrical discharge machining (EDM) is used to form micro surface patterns on Cp-Ti alloy samples. First, graphite electrodes with several channels were manufactured, and then square-shaped surface patterns were processed onto Cp-Ti samples using EDM. To evaluate the machining performance of the process and surface features of the obtained micro surface patterns, the surface morphology and topography of the processed samples were investigated by scanning electron microscopy (SEM) and three-dimensional (3D) optical profilometry, respectively. The average widths of the square-shaped surface patterns along the X and Y axes were 663.7±8 µm and 609.5±4 µm, respectively. For micro surface designs with square geometry, dimensional consistency was obtained with exceedingly small amounts of variation. However, a limited number of microcracks were observed due to rapid cooling during the processing of the surface patterns. The 3D surface topographies revealed that square-shaped micro surface patterns were successfully processed on the samples, indicating that micro surface patterns can be processed on Cp-Ti samples by using the proposed methodology, which has the potential for obtaining tailor-designed surface features, particularly for biomedical and tribological applications.

show abstract

Section: The Topographies Of Surface Patterned Cp-ti Alloymentioning

confidence: 99%

Surface properties of micro surface patterned Cp-Ti alloy via electrical discharge machining

BALTA

2023

J Adv Manuf Eng

View full text Add to dashboard Cite

show abstract

“…The ANN model is an AI algorithm, and it has shown an excellent performance when solving nonlinear and complex problems [21][22][23]. Figure 1 shows the ANN structure used in this study.…”

Section: Ann Modelmentioning

confidence: 99%

Predicting High Temperature Flow Stress of Nickel Alloy A230 Based on an Artificial Neural Network

Moon

Jeong

Lee

et al. 2022

Metals

Self Cite

View full text Add to dashboard Cite

The high-temperature deformation behavior of metals and alloys undergoes complex mechanisms depending on the deformation conditions. The microstructure and mechanical properties after deformation are important factors that determine the strength and durability of the final product. Therefore, many studies to predict the microstructure and mechanical properties have been conducted. In this regard, numerous mathematical approaches for predicting microstructure and flow stress have been proposed over the past half century. Accordingly, many advances have been made in the field of material science. Nevertheless, there are limitations in the mathematical modeling method as there is a complex relationship between the deformation conditions and the mechanical properties. Therefore, in this study, flow stress prediction was performed by applying conventional constitutive equation and artificial intelligence technology, which is known to be effective in modeling complex relationships. As a result, it was confirmed that the flow stresses modeled by the artificial neural network showed a higher accuracy than the flow stresses modeled by the conventional Arrhenius hyperbolic sine equation.

show abstract

“…Recently, research on the prediction and detection of structural damage using deep learning technology has been actively conducted. Moon et al 18 used a class activation map (CAM) to study the relationship between the gray image of a press-formed electric discharge machined aluminum plate and the presence or absence of manufacturing defects. 18 The developed CAM classified the presence or absence of defects with an accuracy of 93.7%.…”

Section: Introductionmentioning

confidence: 99%

“…Moon et al 18 used a class activation map (CAM) to study the relationship between the gray image of a press-formed electric discharge machined aluminum plate and the presence or absence of manufacturing defects. 18 The developed CAM classified the presence or absence of defects with an accuracy of 93.7%. The validity was confirmed by outputting the CAM image, indicating the area with the greatest influence on the judgment.…”

Section: Introductionmentioning

confidence: 99%

Initial structural damage detection approach via FE-based data augmentation and class activation map

Jeong

Kim

Cho

et al. 2023

Structural Health Monitoring

View full text Add to dashboard Cite

Damage is generally initiated locally and spread to the entire structure. To avoid the destruction of the entire structure, it is crucial to detect and act on damage at an early stage through the real-time monitoring of the entire structure. However, the attachment of the many sensors to obtain sufficient detection resolution could change the structural dynamic characteristics of the structure. To compensate for these shortcomings, research has been conducted on digital image correlation (DIC) as a non-contact method of displacement/strain measurement. In addition, the real-time monitoring of a structure using DIC equipment is relatively straightforward. The final goal of this study is to predict the location of damage using the displacement of the structure surface which can be via DIC. This paper introduces a method for monitoring damage locations using a class activation map (CAM) network. The feasibility of the proposed process using the finite element method for an example considering the experimental situation was confirmed. To generate training data, the finite element method was used to obtain the displacement and strain of a target structure. Herein, sub-structuring approach with data augmentation using Gaussian integration point interpolation were employed to obtain the benign performance of the proposed approach. Thus, the proposed CAM network could classify the presence or absence of damage by considering strain fields. Moreover, the relevant result of the CAM network is a CAM image, which indicates the location of the damage. Finally, this CAM network was applied to a tensile specimen example and show good performance in the classification and detection of damage locations.

show abstract

Analysis of the Region of Interest According to CNN Structure in Hierarchical Pattern Surface Inspection Using CAM

Cited by 10 publications

References 32 publications

Surface properties of micro surface patterned Cp-Ti alloy via electrical discharge machining

Surface properties of micro surface patterned Cp-Ti alloy via electrical discharge machining

Predicting High Temperature Flow Stress of Nickel Alloy A230 Based on an Artificial Neural Network

Initial structural damage detection approach via FE-based data augmentation and class activation map

Contact Info

Product

Resources

About