2022 International Conference on Emerging Smart Computing and Informatics (ESCI) 2022
DOI: 10.1109/esci53509.2022.9758280
|View full text |Cite
|
Sign up to set email alerts
|

Deep Learning-Based Predictive Model for Defect Detection and Classification in Industry 4.0

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
3
0

Year Published

2023
2023
2024
2024

Publication Types

Select...
6
1
1

Relationship

2
6

Authors

Journals

citations
Cited by 9 publications
(4 citation statements)
references
References 22 publications
0
3
0
Order By: Relevance
“…The selection of the network’s hyperparameters seems critical and is determined by the activity where the CNN is utilized. The hyperparameter for the CNN learning model includes “Batch size, Number of epochs, Pooling size, Number of Filters, and Kernel size.” The learning algorithm controls the gradient descent method’s performance, and the speed determines how much updating the earlier weights affects the updating of subsequent weights [ 28 ].…”
Section: Methodsmentioning
confidence: 99%
“…The selection of the network’s hyperparameters seems critical and is determined by the activity where the CNN is utilized. The hyperparameter for the CNN learning model includes “Batch size, Number of epochs, Pooling size, Number of Filters, and Kernel size.” The learning algorithm controls the gradient descent method’s performance, and the speed determines how much updating the earlier weights affects the updating of subsequent weights [ 28 ].…”
Section: Methodsmentioning
confidence: 99%
“…Koscielny et al [1] employed fuzzy neural networks to perform fault detection based on the temperatures and residue in the evaporation units in a sugar factory. Based on the VGG-16 model, Lilhore et al [34] proposed a fault detection system that can automatically detect whether a machine is damaged and aid factories in estimating the lifespan of product components. In more recent years, Wen et al [35] and Chen et al [36] developed fault detection systems by combining different convolutional neural networks (CNNs) with deep neural networks (DNNs).…”
Section: Related Workmentioning
confidence: 99%
“…The detection layer contains a deep CNN model with magnitude pruning and quantization, an internet connection is established. The remote access of deep model output is provided by the visualization layer to [30]. Comparing the edge learning servers to the most advanced cloud computing architecture, the edge learning servers reduce the workload of the network infrastructure.…”
Section: Edge Computing Platformmentioning
confidence: 99%