Journal of Scientific and Industrial Research

Open Access Open Access  Restricted Access Subscription Access

Hyper Parameter Optimization for Transfer Learning of ShuffleNetV2 with Edge Computing for Casting Defect Detection


Affiliations
1 Computer Science and Engineering, Institute of Aeronautical Engineering, Hyderabad, 500 043, Telangana, India
2 Computer Science and Engineering, CVR College of Engineering, Hyderabad, 501 510, Telangana, India
3 Computer Science and Engineering, Prasad V. Potluri Siddhartha Institute of Technology, Vijayawada, 520 007, Andhra Pradesh, India
4 Computer Science and Engineering, Koneru Lakshmaiah Education Foundation, Vaddeswaram, 522 302, Andhra Pradesh, India
 

A casting defect is an expendable abnormality and the most undesirable thing in the metal casting process. In Casting Defect Detection, deep learning based on Convolution Neural Network (CNN) models has been widely used, but most of these models require a lot of processing power. This work proposes a low-power ShuffleNet V2-based Transfer Learning model for defect identification with low latency, easy upgrading, increased efficiency, and an automatic visual inspection system with edge computing. Initially, various image transformation techniques were used for data augmentation on casting datasets to test the model flexibility in diverse casting. Subsequently, a pre-trained lightweight ShuffleNetV2 model is adapted, and hyperparameters are fine-tuned to optimize the model. The work results in a lightweight, adaptive, and scalable model ideal for resource-constrained edge devices. Finally, the trained model can be used as an edge device on the NVIDIA Jetson Nano-kit to speed up detection. The measures of precision, recall, accuracy, and F1 score were utilized for model evaluation. According to the statistical measures, the model accuracy is 99.58%, precision is 100%, recall is 99%, and the F1-Score is 100 %.

Keywords

Edge Computing, Industrial Internet of Things, NVIDIA Jetson Nano-Kit, ShuffleNetV2.
User
Notifications
Font Size

  • Wang T, Chen Y, Qiao M & Snoussi H, A fast and robust convolutional neural network-based defect detection model in product quality control, Int J Adv Manuf Technol, 94(8) (2018) 3465–3471.

  • Liao Z, Abdelhafeez A, Li H, Yang Y, Diaz O G & Axinte D, State-of-the-art of surface integrity in machining of metal matrix composites, Int J Mach Tools Manuf, 143 (2019) 63–91.

  • Kim D H, Kim T J, Wang X L, Kim M, Quan Y J & Oh J W, Smart machining process using machine learning:A review and perspective on machining industry, Int J Pr Eng Man-Gt, 5(4) (2018) 555–568.

  • Zhang H, Shen X, Bo A, Li Y, Zhan H & Gu Y, A multiscale evaluation of the surface integrity in boring trepanning association deep hole drilling, Int J Mach Tools Manuf, 123 (2017) 48–56.

  • Rao X, Zhang F, Lu Y, Luo X & Chen F, Surface and subsurface damage of reaction-bonded silicon carbide induced by electrical discharge diamond grinding, Int J Mach Tools Manuf, 154 (2020) 103564.

  • Zhang Z & Sun C, Multi-site structural damage identification using a multi-label classification scheme of machine learning, Measurement, 154 (2020) 107473.

  • Ravimal D, Kim H, Koh D, Hong J H & Lee S K, Image-based inspection technique of a machined metal surface for an unmanned lapping process, Int J Pr Eng Man-Gt, 7(3) (2020) 547–557.

  • Boaretto N & Centeno T M, Automated detection of welding defects in pipelines from radiographic images DWDI, Ndt & E Int, 86 (2017) 7–13.

  • Cireşan D C, Meier U, Masci J, Gambardella L M & Schmidhuber J, High-performance neural networks for visual object classification, arXiv (2011) preprint arXiv: 1102.0183.

  • Shanmugamani R, Sadique M & Ramamoorthy B, Detection and classification of surface defects of gun barrels using computer vision and machine learning, Measurement, 60 (2015) 222–230.

  • Toğaçar M, Ergen B & Cömert Z, Classification of flower species by using features extracted from the intersection of feature selection methods in convolutional neural network models, Measurement, 158 (2020) 107703.

  • Janakiramaiah B, Kalyani G & Jayalakshmi A, Automatic alert generation in a surveillance system for smart city environment using deep learning algorithm, Evol Intell, 14(2) (2021) 635–642.

  • Cheng F T, Tieng H, Yang H C, Hung M H, Lin Y C, Wei C F & Shieh Z Y, Industry 4.1 for wheel machining automation, IEEE Robot Autom Lett, 1(1) (2016) 332–339.

  • Zhou X, Li Y & Liang W, CNN-RNN based intelligent recommendation for online medical pre-diagnosis support, IEEE/ACM Trans Comput Biol Bioinform, 18(3) (2020) 912–921.

  • Ng H F, Automatic thresholding for defect detection, Pattern Recognit Let, 27(14) (2006) 1644–1649.

  • Mery D & Filbert D, Automated flaw detection in aluminum castings based on the tracking of potential defects in a radioscopic image sequence, IEEE Trans Robot Autom, 18(6) (2003) 890–901

  • Bai X, Fang Y, Lin W, Wang L & Ju B F, Saliency-based defect detection in industrial images by using phase spectrum, IEEE Trans Industr Inform, 10(4) (2014) 2135–2145.

  • Duan L, Yang K & Ruan L, Research on automatic recognition of casting defects based on deep learning, IEEE Access, 9 (2020) 12209–12216.

  • Lin J, Yao Y, Ma L & Wang Y, Detection of a casting defect tracked by deep convolution neural network, Int J Adv Manuf Technol, 97(1) (2018) 573–581.

  • Ferguson M, Ak R, Lee Y T T & Law K H, Automatic localization of casting defects with convolutional neural networks, IEEE Int Conf Big Data, (2017) 1726–1735.

  • Ren Z, Fang F, Yan N & Wu Y, State of the art in defect detection based on machine vision, Int J Pr Eng Man-Gt 9(2) (2022) 661–691.

  • Benbarrad T, Salhaoui M, Kenitar S B & Arioua M, Intelligent machine vision model for defective product inspection based on machine learning, J Sens Actuator Netw, 10(1) (2021).

  • Li E, Zeng L, Zhou Z & Chen X, Edge AI: On-demand accelerating deep neural network inference via edge computing, IEEE Trans Wirel Commun, 19(1) (2019) 447–457.

  • Lin Y C, Chen W H & Kuo C H, Implementation of pavement defect detection system on edge computing platform, Appl Sci, 11(8) (2021) 3725.

  • Shi W, Sun H, Cao J, Zhang Q & Liu W, Edge computing—an emerging computing model for the internet of everything era, J Comput Sci Res Dev, 54(5) (2017) 907.

  • Subramanian M, Narasimha Prasad Lv, Janakiramaiah B, Mohan Babu A & Satishkumar Ve, Hyperparameter optimization for transfer learning of VGG16 for disease identification in corn leaves using bayesian optimization, J Big Data, 10(3) (2022) 215–229.

  • Rajalaxmi R R, Narasimha L V, Janakiramaiah B, Pavankumar C S, Neelima N & Sathishkumar V E, Optimizing hyperparameters and performance analysis of LSTM model in detecting fake news on social media, ACM Trans Asian Low-Resour Lang Inf Process (2022), https://doi.org/10.1145/3511897

  • Dabhi R, Casting product image data for quality inspection, https://www.kaggle.com/datasets/ravirajsinh45/real-life-industrial-dataset-of-casting-product (27 December 2022)].


Abstract Views: 50

PDF Views: 55




  • Hyper Parameter Optimization for Transfer Learning of ShuffleNetV2 with Edge Computing for Casting Defect Detection

Abstract Views: 50  |  PDF Views: 55

Authors

Narasimha Prasad L V
Computer Science and Engineering, Institute of Aeronautical Engineering, Hyderabad, 500 043, Telangana, India
Durga Bhavani Dokku
Computer Science and Engineering, CVR College of Engineering, Hyderabad, 501 510, Telangana, India
Sri Lakshmi Talasila
Computer Science and Engineering, Prasad V. Potluri Siddhartha Institute of Technology, Vijayawada, 520 007, Andhra Pradesh, India
Praveen Tumuluru
Computer Science and Engineering, Koneru Lakshmaiah Education Foundation, Vaddeswaram, 522 302, Andhra Pradesh, India

Abstract


A casting defect is an expendable abnormality and the most undesirable thing in the metal casting process. In Casting Defect Detection, deep learning based on Convolution Neural Network (CNN) models has been widely used, but most of these models require a lot of processing power. This work proposes a low-power ShuffleNet V2-based Transfer Learning model for defect identification with low latency, easy upgrading, increased efficiency, and an automatic visual inspection system with edge computing. Initially, various image transformation techniques were used for data augmentation on casting datasets to test the model flexibility in diverse casting. Subsequently, a pre-trained lightweight ShuffleNetV2 model is adapted, and hyperparameters are fine-tuned to optimize the model. The work results in a lightweight, adaptive, and scalable model ideal for resource-constrained edge devices. Finally, the trained model can be used as an edge device on the NVIDIA Jetson Nano-kit to speed up detection. The measures of precision, recall, accuracy, and F1 score were utilized for model evaluation. According to the statistical measures, the model accuracy is 99.58%, precision is 100%, recall is 99%, and the F1-Score is 100 %.

Keywords


Edge Computing, Industrial Internet of Things, NVIDIA Jetson Nano-Kit, ShuffleNetV2.

References