PSO-Optimized Deep Learning for Ultra-Precise Corrosion Detection on HDD Read/Write Heads

This paper presents a novel deep learning approach for automated detection and counting of corrosion pits on Hard Disk Drive (HDD) read/write heads using Scanning Electron Microscopy (SEM) images. A U-Net model optimized via Particle Swarm Optimization (PSO) is developed to enhance segmentation perf...

Full description

Saved in:
Bibliographic Details
Main Authors: Chaiwat Punyammaree, Somyot Kaitwanidvilai
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/11050437/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850107854523990016
author Chaiwat Punyammaree
Somyot Kaitwanidvilai
author_facet Chaiwat Punyammaree
Somyot Kaitwanidvilai
author_sort Chaiwat Punyammaree
collection DOAJ
description This paper presents a novel deep learning approach for automated detection and counting of corrosion pits on Hard Disk Drive (HDD) read/write heads using Scanning Electron Microscopy (SEM) images. A U-Net model optimized via Particle Swarm Optimization (PSO) is developed to enhance segmentation performance by automatically tuning hyperparameters. The methodology includes optimized SEM image acquisition, preprocessing (patch-based subdivision and expert annotation), PSO-driven hyperparameter selection, and post-processing with thresholding and connected component analysis for pit counting. Experimental results demonstrate that the PSO-optimized U-Net significantly outperforms standard U-Net, SegNet, and LinkNet models, achieving an F1-score of 79.60%, an IoU of 86.51%, and an accuracy of 99.77%. Additionally, the proposed method achieves 86.9% counting accuracy, surpassing human experts (72.7%) while processing images 15 times faster (180 seconds vs. 2700 seconds per image). These findings highlight the potential of PSO-optimized deep learning for improving HDD quality control by providing an accurate, efficient, and standardized solution for corrosion pit detection, ultimately reducing the risk of HDD failure and data loss.
format Article
id doaj-art-b977fa504de643fc8326ea2fc18e2736
institution OA Journals
issn 2169-3536
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-b977fa504de643fc8326ea2fc18e27362025-08-20T02:38:29ZengIEEEIEEE Access2169-35362025-01-011311062311063510.1109/ACCESS.2025.358260211050437PSO-Optimized Deep Learning for Ultra-Precise Corrosion Detection on HDD Read/Write HeadsChaiwat Punyammaree0https://orcid.org/0009-0008-7209-2246Somyot Kaitwanidvilai1https://orcid.org/0009-0005-3255-3851School of Engineering, King Mongkut’s Institute of Technology Ladkrabang, Bangkok, ThailandSchool of Engineering, King Mongkut’s Institute of Technology Ladkrabang, Bangkok, ThailandThis paper presents a novel deep learning approach for automated detection and counting of corrosion pits on Hard Disk Drive (HDD) read/write heads using Scanning Electron Microscopy (SEM) images. A U-Net model optimized via Particle Swarm Optimization (PSO) is developed to enhance segmentation performance by automatically tuning hyperparameters. The methodology includes optimized SEM image acquisition, preprocessing (patch-based subdivision and expert annotation), PSO-driven hyperparameter selection, and post-processing with thresholding and connected component analysis for pit counting. Experimental results demonstrate that the PSO-optimized U-Net significantly outperforms standard U-Net, SegNet, and LinkNet models, achieving an F1-score of 79.60%, an IoU of 86.51%, and an accuracy of 99.77%. Additionally, the proposed method achieves 86.9% counting accuracy, surpassing human experts (72.7%) while processing images 15 times faster (180 seconds vs. 2700 seconds per image). These findings highlight the potential of PSO-optimized deep learning for improving HDD quality control by providing an accurate, efficient, and standardized solution for corrosion pit detection, ultimately reducing the risk of HDD failure and data loss.https://ieeexplore.ieee.org/document/11050437/Hard disk drivecorrosion pitsparticle swarm optimizationimage segmentationU-Net
spellingShingle Chaiwat Punyammaree
Somyot Kaitwanidvilai
PSO-Optimized Deep Learning for Ultra-Precise Corrosion Detection on HDD Read/Write Heads
IEEE Access
Hard disk drive
corrosion pits
particle swarm optimization
image segmentation
U-Net
title PSO-Optimized Deep Learning for Ultra-Precise Corrosion Detection on HDD Read/Write Heads
title_full PSO-Optimized Deep Learning for Ultra-Precise Corrosion Detection on HDD Read/Write Heads
title_fullStr PSO-Optimized Deep Learning for Ultra-Precise Corrosion Detection on HDD Read/Write Heads
title_full_unstemmed PSO-Optimized Deep Learning for Ultra-Precise Corrosion Detection on HDD Read/Write Heads
title_short PSO-Optimized Deep Learning for Ultra-Precise Corrosion Detection on HDD Read/Write Heads
title_sort pso optimized deep learning for ultra precise corrosion detection on hdd read write heads
topic Hard disk drive
corrosion pits
particle swarm optimization
image segmentation
U-Net
url https://ieeexplore.ieee.org/document/11050437/
work_keys_str_mv AT chaiwatpunyammaree psooptimizeddeeplearningforultraprecisecorrosiondetectiononhddreadwriteheads
AT somyotkaitwanidvilai psooptimizeddeeplearningforultraprecisecorrosiondetectiononhddreadwriteheads