<p>Edge Intelligence with Light Weight CNN Model for Surface Defect Detection in Manufacturing Industry</p>
Online Publishing @ NISCAIR
View Archive InfoField | Value | |
Authentication Code |
dc |
|
Title Statement |
<p>Edge Intelligence with Light Weight CNN Model for Surface Defect Detection in Manufacturing Industry</p> |
|
Added Entry - Uncontrolled Name |
Rani, D Shobha; Institute of Aeronautical Engineering College, Hyderabad 500 043, Telangana, India Burra, Lakshmi Ramani; Prasad V. Potluri Siddhartha Institute of Technology, Vijayawada 520 007, Andhra Pradesh, India Kalyani, G ; Velagapudi Ramakrishna Siddhartha Engineering College,Vijayawada 520 007, Andhra Pradesh, India Rao, B Narendra Kumar; Sree Vidyanikethan Engineering College, Tirupati 517 102, Andhra Pradesh, India |
|
Uncontrolled Index Term |
CondenseNet, Convolutional neural networks, Deep learning, Edge device, Industrial products |
|
Summary, etc. |
<p class="Abstract">Surface defect identification is essential for maintaining and improving the quality of industrial products. However, numerous environmental factors, including reflection, radiance, light, and material, affect the defect detection process, considerably increasing the difficulty of detecting surface defects. Deep Learning, a part of Artificial intelligence, can detect surface defects in the industrial sector. However, conventional deep learning techniques are heavy in terms of expensive GPU requirements to support massive computations during the defect detection process.CondenseNetV2, a Lightweight CNN-based model, which performs well on microscopic defect inspection, and can be operated on low-frequency edge devices, was proposed in this research. It provides sufficient feature extractions with little computational overhead by reusing a set of the existing Sparse Feature Reactivation module. The training data are subjected to data augmentation techniques, and the hyper-parameters of the proposed model are fine-tuned with transfer learning. The model was tested extensively with two real datasets while running on an edge device (NVIDIA Jetson Xavier Nx SOM). The experiment results confirm that the projected model can efficiently detect the faults in the real-world environment while reliably and robustly diagnosing them.</p> |
|
Publication, Distribution, Etc. |
Journal of Scientific & Industrial Research 2023-02-09 21:08:13 |
|
Electronic Location and Access |
application/pdf http://op.niscair.res.in/index.php/JSIR/article/view/69945 |
|
Data Source Entry |
Journal of Scientific & Industrial Research; ##issue.vol## 82, ##issue.no## 02 (2023) |
|
Language Note |
en |
|