Multi-Modal Dynamic Fusion for Defect Detection in Electronic Products: A Novel Approach Based on Energy and Deep Learning

As electronic products continue to evolve in complexity, maintaining stringent quality standards during manufacturing presents mounting challenges. Conventional defect detection approaches, which typically depend on a single modality, often fall short in both efficiency and reliability. To address t...

Full description

Saved in:
Bibliographic Details
Main Authors: Yulin Liu, Yang Gao
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/11062584/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850112411360559104
author Yulin Liu
Yang Gao
author_facet Yulin Liu
Yang Gao
author_sort Yulin Liu
collection DOAJ
description As electronic products continue to evolve in complexity, maintaining stringent quality standards during manufacturing presents mounting challenges. Conventional defect detection approaches, which typically depend on a single modality, often fall short in both efficiency and reliability. To address these shortcomings, this study introduces a dynamic multi-modal fusion framework that leverages data from sensors, visual imagery, and component attributes to enhance detection performance. Specifically, Transformer architectures are employed for sensor data analysis, Convolutional Neural Networks (CNNs) are applied to process image data, and Multi-Layer Perceptrons (MLPs) are used to represent part-level features. A distinguishing element of this approach is an energy-based late-stage fusion mechanism that adaptively modulates each modality’s influence according to its uncertainty level. Empirical evaluations demonstrate that the proposed model achieves superior results across multiple performance metrics—including accuracy, precision, recall, and F1 score—compared to conventional and unimodal systems. These findings underscore the model’s potential in advancing practical defect detection and quality assurance in manufacturing environments.
format Article
id doaj-art-1527e778cd1841a1bbe5a5be5af24491
institution OA Journals
issn 2169-3536
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-1527e778cd1841a1bbe5a5be5af244912025-08-20T02:37:23ZengIEEEIEEE Access2169-35362025-01-011311856511857310.1109/ACCESS.2025.358455111062584Multi-Modal Dynamic Fusion for Defect Detection in Electronic Products: A Novel Approach Based on Energy and Deep LearningYulin Liu0https://orcid.org/0009-0008-7862-5840Yang Gao1College of Economics and Management, Business Administration, University of Electronic Science and Technology (UESTC), Chengdu, Sichuan, ChinaCollege of Information and Communication Engineering, Electronics and Information, University of Electronic Science and Technology (UESTC), Chengdu, Sichuan, ChinaAs electronic products continue to evolve in complexity, maintaining stringent quality standards during manufacturing presents mounting challenges. Conventional defect detection approaches, which typically depend on a single modality, often fall short in both efficiency and reliability. To address these shortcomings, this study introduces a dynamic multi-modal fusion framework that leverages data from sensors, visual imagery, and component attributes to enhance detection performance. Specifically, Transformer architectures are employed for sensor data analysis, Convolutional Neural Networks (CNNs) are applied to process image data, and Multi-Layer Perceptrons (MLPs) are used to represent part-level features. A distinguishing element of this approach is an energy-based late-stage fusion mechanism that adaptively modulates each modality’s influence according to its uncertainty level. Empirical evaluations demonstrate that the proposed model achieves superior results across multiple performance metrics—including accuracy, precision, recall, and F1 score—compared to conventional and unimodal systems. These findings underscore the model’s potential in advancing practical defect detection and quality assurance in manufacturing environments.https://ieeexplore.ieee.org/document/11062584/Multi-modal fusiondefect detectiontransformerconvolutional neural networksquality control
spellingShingle Yulin Liu
Yang Gao
Multi-Modal Dynamic Fusion for Defect Detection in Electronic Products: A Novel Approach Based on Energy and Deep Learning
IEEE Access
Multi-modal fusion
defect detection
transformer
convolutional neural networks
quality control
title Multi-Modal Dynamic Fusion for Defect Detection in Electronic Products: A Novel Approach Based on Energy and Deep Learning
title_full Multi-Modal Dynamic Fusion for Defect Detection in Electronic Products: A Novel Approach Based on Energy and Deep Learning
title_fullStr Multi-Modal Dynamic Fusion for Defect Detection in Electronic Products: A Novel Approach Based on Energy and Deep Learning
title_full_unstemmed Multi-Modal Dynamic Fusion for Defect Detection in Electronic Products: A Novel Approach Based on Energy and Deep Learning
title_short Multi-Modal Dynamic Fusion for Defect Detection in Electronic Products: A Novel Approach Based on Energy and Deep Learning
title_sort multi modal dynamic fusion for defect detection in electronic products a novel approach based on energy and deep learning
topic Multi-modal fusion
defect detection
transformer
convolutional neural networks
quality control
url https://ieeexplore.ieee.org/document/11062584/
work_keys_str_mv AT yulinliu multimodaldynamicfusionfordefectdetectioninelectronicproductsanovelapproachbasedonenergyanddeeplearning
AT yanggao multimodaldynamicfusionfordefectdetectioninelectronicproductsanovelapproachbasedonenergyanddeeplearning