A comprehensive overview and comparative analysis on deep learning models: CNN, RNN, LSTM, GRU

FM Shiri, T Perumal, N Mustapha… - arxiv preprint arxiv …, 2023‏ - arxiv.org
Deep learning (DL) has emerged as a powerful subset of machine learning (ML) and
artificial intelligence (AI), outperforming traditional ML methods, especially in handling …

DenseSPH-YOLOv5: An automated damage detection model based on DenseNet and Swin-Transformer prediction head-enabled YOLOv5 with attention mechanism

AM Roy, J Bhaduri - Advanced Engineering Informatics, 2023‏ - Elsevier
Objective. Computer vision-based up-to-date accurate damage classification and
localization are of decisive importance for infrastructure monitoring, safety, and the …

Surface defect detection and classification of steel using an efficient Swin Transformer

W Zhu, H Zhang, C Zhang, X Zhu, Z Guan… - Advanced Engineering …, 2023‏ - Elsevier
Detecting steel-surface defects is a crucial phase in steel manufacturing; however,
accurately completing the detection task is challenging. The Swin Transformer, a self …

Survey on AI applications for product quality control and predictive maintenance in industry 4.0

TV Andrianandrianina Johanesa, L Equeter… - Electronics, 2024‏ - mdpi.com
Recent technological advancements such as IoT and Big Data have granted industries
extensive access to data, opening up new opportunities for integrating artificial intelligence …

Surface defect detection of aeroengine blades based on cross-layer semantic guidance

K Song, X Sun, S Ma, Y Yan - IEEE Transactions on …, 2023‏ - ieeexplore.ieee.org
In the production process of aeroengine blades (AEBs), the surface defect detection of
blades is substantial. Currently, most blade detection methods are aimed at large blades …

STFE-Net: a multi-stage approach to enhance statistical texture feature for defect detection on metal surfaces

H Zhong, D Fu, L **ao, F Zhao, J Liu, Y Hu… - Advanced Engineering …, 2024‏ - Elsevier
Statistical texture features are essential for metal surface defect detection. However, low
contrast and cluttered backgrounds exacerbate the intrinsic blurriness and variability of …

Efficient multi-branch dynamic fusion network for super-resolution of industrial component image

G Wang, M Chen, YC Lin, X Tan, C Zhang, W Yao… - Displays, 2024‏ - Elsevier
This work aims to promote the application of a high-performance super-resolution (SR)
method in industry. Considering the lack of industrial datasets to evaluate performance, an …

GDALR: Global Dual Attention and Local Representations in transformer for surface defect detection

X Zhou, S Zhou, Y Zhang, Z Ren, Z Jiang, H Luo - Measurement, 2024‏ - Elsevier
Automated surface detection has gradually emerged as a promising and crucial inspection
method in the industrial sector, greatly enhancing production quality and efficiency …

From anomaly detection to defect classification

J Klarák, R Andok, P Malík, I Kuric, M Ritomský… - Sensors, 2024‏ - mdpi.com
This paper proposes a new approach to defect detection system design focused on exact
damaged areas demonstrated through visual data containing gear wheel images. The main …

Automatic augmentation and segmentation system for three-dimensional point cloud of pavement potholes by fusion convolution and transformer

J Dong, N Wang, H Fang, H Lu, D Ma, H Hu - Advanced Engineering …, 2024‏ - Elsevier
The regular three-dimensional (3D) detection of potholes is essential for the assessment of
pavement conditions. However, some problems associated with the segmentation of …