แจ้งเอกสารไม่ครบถ้วน, ไม่ตรงกับชื่อเรื่อง หรือมีข้อผิดพลาดเกี่ยวกับเอกสาร ติดต่อที่นี่ ==>
หากไม่มีอีเมลผู้รับให้กรอก thailis-noc@uni.net.th
หากไม่มีอีเมลผู้รับให้กรอก thailis-noc@uni.net.th
Saprangsit Mruetusatorn. Powder metallurgy microstructure classification using image processing and deep learning techniques. (). King Mongkut's University of Technology North Bangkok. Central Library. : , 2022.
Powder metallurgy microstructure classification using image processing and deep learning techniques
Name: Khattipong Usamran
Organization :
Thai-Nichi Institute of Technology
Email :
us.khattipong_st@tni.ac.th
Name: Saprangsit Mruetusatorn
Organization :
Thai-Nichi Institute of Technology
Email :
saprangsit@tni.ac.th
LCSH:
Powder metallurgy
LCSH:
Materials
-- Classification
LCSH:
Image processing
LCSH:
Materials science
-- Data processing
Abstract:
Evaluation of the fusion characteristic of the sintering neck is important to indicate the quality of metal workpieces forming with powder metallurgy. The quality is analyzed by microstructure images after forming. Currently, quality evaluation is primarily performed by experts without a clear standard; as a result, the goal of this study aims to present the application of image processing and deep learning based on the CNN (Convolution neural network) to develop a model to evaluate sintering neck using the characteristics of pores in microstructure images. Images evaluated by three metallurgical experts were utilized in a prototype for creating the deep learning model. The research measured the results of accuracy and time used in creating the model using five different algorithms. As the result, the accuracy range of 94-98% was obtained, except for the model generated by GoogLeNet which was unable to classify image types of pores, and ResNet-50 spent the shortest time constructing the deep learning model among all four models
King Mongkut's University of Technology North Bangkok. Central Library
Address:
BANGKOK
Email:
library@kmutnb.ac.th
Created:
2022
Modified:
2025-08-22
Issued:
2025-08-22
บทความ/Article
application/pdf
BibliograpyCitation :
In Electrical Engineering Academic Association (Thailand) and Rajamangala University of Technology Isan Khon Kaen Campus. Faculty of Engineering. The 2022 International Electrical Engineering Congress (iEECON 2022) (P01653). Khon Kaen : Rajamangala University of Technology Isan, 2022
eng
©copyrights King Mongkut's University of Technology North Bangkok
RightsAccess:
ใช้เวลา
0.024703 วินาที
Khattipong Usamran
| Title | Contributor | Type |
|---|---|---|
| Powder metallurgy microstructure classification using image processing and deep learning techniques
มหาวิทยาลัยเทคโนโลยีพระจอมเกล้าพระนครเหนือ Khattipong Usamran;Saprangsit Mruetusatorn | บทความ/Article |
Saprangsit Mruetusatorn
| Title | Contributor | Type |
|---|---|---|
| Powder metallurgy microstructure classification using image processing and deep learning techniques
มหาวิทยาลัยเทคโนโลยีพระจอมเกล้าพระนครเหนือ Khattipong Usamran;Saprangsit Mruetusatorn | บทความ/Article |