Method for Detecting Tiny Defects on Machined Surfaces of Mechanical Parts Based on Object Recognition

In response to the high missed detection rates and low efficiency of traditional methods in detecting tiny defects on the machining surfaces of mechanical parts, this study proposes an efficient defect detection method based on deep learning. Initially, referencing the network architectures of Resne...

Full description

Saved in:
Bibliographic Details
Main Authors: Haotian Li, Zhen Wang, Lipeng Qiu, Xichu Wei
Format: Article
Language:English
Published: MDPI AG 2025-02-01
Series:Applied Sciences
Subjects:
Online Access:https://www.mdpi.com/2076-3417/15/5/2484
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850228277364391936
author Haotian Li
Zhen Wang
Lipeng Qiu
Xichu Wei
author_facet Haotian Li
Zhen Wang
Lipeng Qiu
Xichu Wei
author_sort Haotian Li
collection DOAJ
description In response to the high missed detection rates and low efficiency of traditional methods in detecting tiny defects on the machining surfaces of mechanical parts, this study proposes an efficient defect detection method based on deep learning. Initially, referencing the network architectures of Resnet and Yolo, an image detection network was designed featuring a shared encoder, a classification decoder, and a localization decoder. The shared encoder is used to extract a unified feature representation; the classification decoder accomplishes efficient data classification; and the localization decoder achieves precise defect localization. Furthermore, upon acquiring high-resolution images of the machining surfaces with dimensional features, this study introduces a real-time sliding window method to perform segmented detection and classification of these images, transforming most of the target detection tasks into image classification problems, thereby further enhancing the efficiency and accuracy of defect detection and target localization. Practical results demonstrate that this method outperforms traditional approaches in terms of missed detection rates and detection efficiency, effectively addressing the challenge of detecting complex machining surface defects, and providing a high-precision, high-efficiency defect detection solution for the mechanical part machining field.
format Article
id doaj-art-aec0032de30441db893628341dd4e87f
institution OA Journals
issn 2076-3417
language English
publishDate 2025-02-01
publisher MDPI AG
record_format Article
series Applied Sciences
spelling doaj-art-aec0032de30441db893628341dd4e87f2025-08-20T02:04:34ZengMDPI AGApplied Sciences2076-34172025-02-01155248410.3390/app15052484Method for Detecting Tiny Defects on Machined Surfaces of Mechanical Parts Based on Object RecognitionHaotian Li0Zhen Wang1Lipeng Qiu2Xichu Wei3School of Mechanical Engineering, Dalian University, Dalian 116022, ChinaSchool of Mechanical Engineering, Dalian University, Dalian 116022, ChinaSchool of Mechanical Engineering, Dalian University, Dalian 116022, ChinaSchool of Mechanical Engineering, Dalian University, Dalian 116022, ChinaIn response to the high missed detection rates and low efficiency of traditional methods in detecting tiny defects on the machining surfaces of mechanical parts, this study proposes an efficient defect detection method based on deep learning. Initially, referencing the network architectures of Resnet and Yolo, an image detection network was designed featuring a shared encoder, a classification decoder, and a localization decoder. The shared encoder is used to extract a unified feature representation; the classification decoder accomplishes efficient data classification; and the localization decoder achieves precise defect localization. Furthermore, upon acquiring high-resolution images of the machining surfaces with dimensional features, this study introduces a real-time sliding window method to perform segmented detection and classification of these images, transforming most of the target detection tasks into image classification problems, thereby further enhancing the efficiency and accuracy of defect detection and target localization. Practical results demonstrate that this method outperforms traditional approaches in terms of missed detection rates and detection efficiency, effectively addressing the challenge of detecting complex machining surface defects, and providing a high-precision, high-efficiency defect detection solution for the mechanical part machining field.https://www.mdpi.com/2076-3417/15/5/2484deep learningtiny-defect detectionimage detection network
spellingShingle Haotian Li
Zhen Wang
Lipeng Qiu
Xichu Wei
Method for Detecting Tiny Defects on Machined Surfaces of Mechanical Parts Based on Object Recognition
Applied Sciences
deep learning
tiny-defect detection
image detection network
title Method for Detecting Tiny Defects on Machined Surfaces of Mechanical Parts Based on Object Recognition
title_full Method for Detecting Tiny Defects on Machined Surfaces of Mechanical Parts Based on Object Recognition
title_fullStr Method for Detecting Tiny Defects on Machined Surfaces of Mechanical Parts Based on Object Recognition
title_full_unstemmed Method for Detecting Tiny Defects on Machined Surfaces of Mechanical Parts Based on Object Recognition
title_short Method for Detecting Tiny Defects on Machined Surfaces of Mechanical Parts Based on Object Recognition
title_sort method for detecting tiny defects on machined surfaces of mechanical parts based on object recognition
topic deep learning
tiny-defect detection
image detection network
url https://www.mdpi.com/2076-3417/15/5/2484
work_keys_str_mv AT haotianli methodfordetectingtinydefectsonmachinedsurfacesofmechanicalpartsbasedonobjectrecognition
AT zhenwang methodfordetectingtinydefectsonmachinedsurfacesofmechanicalpartsbasedonobjectrecognition
AT lipengqiu methodfordetectingtinydefectsonmachinedsurfacesofmechanicalpartsbasedonobjectrecognition
AT xichuwei methodfordetectingtinydefectsonmachinedsurfacesofmechanicalpartsbasedonobjectrecognition