MEDIUM VOLTAGE INSULATOR CRACK DETECTION USING MOBILENetV2 AND TENSORFLOW

Ahmad Yani; Sofyan Sofyan; Musfirah Putri Lukman; Usman Usman; Apri Junaidi

doi:10.31963/elekterika.v22i1.5420

Authors

Ahmad Yani Politeknik Negeri Ujung Pandang
Sofyan Sofyan Politeknik Negeri Ujung Pandang
Musfirah Putri Lukman Politeknik Negeri Ujung Pandang
Usman Usman Politeknik Negeri Ujung Pandang
Apri Junaidi Universiti Teknologi Malaysia

DOI:

https://doi.org/10.31963/elekterika.v22i1.5420

Keywords:

Crack detection, medium voltage insulator, MobileNetV2, Pascal VOC, Android application

Abstract

This study discusses the detection of medium voltage insulator cracks using object detection technology. This study uses medium voltage ceramic insulator image data at the ULP Daya Waste Material Warehouse. Ceramic insulator image data is categorized into good and damaged conditions. Preprocessing involves labeling, dividing train data, validation, and testing, and exporting data to Pascal VOC format. MobileNetV2 is implemented on Google Collab to train the object detection model. The evaluation of the model accuracy is in the COCO matrix, while the performance graph shows that the model can read objects well because the reading curve is in line with the smooth curve. Furthermore, this model is applied in creating an Android application that uses the device's camera to detect objects in real-time. This application processes images, converts from YUV to RGB, and performs object detection using the trained model. The detection results are displayed with bounding boxes and labels on the camera reviewer, namely the good class with a reading value of 1.0, the damaged class with a reading value of 0.67 and the background 1.0. This application also tracks detected objects and updates the display according to the detection results.

References

1. Thanh, P.N., M.-Y. Cho, and T.N. Da, Insulator leakage current prediction using surface spark discharge data and particle swarm optimization based neural network. Electric Power Systems Research, 2021. 191: p. 106888.

2. Xing, Y., et al., Defects and failure types of solid insulation in gas‐insulated switchgear: In situ study and case analysis. High Voltage, 2022. 7(1): p. 158-164.

3. Rouhanizadeh, B. and S. Kermanshachi, Development of strategies to prevent third rail insulator failures in transit systems. Urban Rail Transit, 2021. 7: p. 58-70.

4. Jadid, R., Thermal Imaging on Ceramic and Glass Insulators against Aging . 2023, Gadjah Mada University.

5. Dewi, T.p.,Analysis of Insulation Resistance Reduction of Porcelain Pin Type Insulation of Sungkai Feeder of Bungaran Main Substation at Ampera Ulp Pt Pln (Persero) . 2021, Sriwijaya State Polytechnic.

6. Abdul Malik, A., Human Face Identification Using Yolo Frameworks With Scale Modifier Method As Real Time Preprocessing. 2023.

7. Al Choedori, M.M., Penerapan Image Processing Untuk Mendeteksi Pergerakan Ikan Koki Dengan Metode Cascade Classifier. 2021.

8. Alfarizi, D.N., et al., The Use of YOLO Method in Object Detection: A Systematic Literature Review. AI and DSS: Journal of Artificial Intelligence and Decision Support Systems, 2023. 1 (1): p. 54-63.

9. Marine, Y., Implementation of Canny Edge Detection Algorithm Using Python and Opencv. Smart Techno (Smart Technology, Informatics and Technopreneurship), 2023. 5 (1): P. 1-7.

10. Barokah Asmarahman, T., Detection and Identification of Traffic Signs Based on You Only Look Once Algorithm . 2023, Muhammadiyah University of Jakarta.

11. Li, Y., et al., YOLO-ACN: Focusing on small target and occluded object detection. IEEE access, 2020. 8: p. 227288-227303.

12. ANHAR, A. and R.A. PUTRA, Design and Implementation of Self-Checkout System in Retail Stores using Convolutional Neural Network (CNN). ELKOMIKA: Journal of Electrical EnergyEngineering, Telecommunication Engineering, & Electronic Engineering, 2023. 11(2): p . 466.

13. Darwis, M.R., Facial Expression Recognition on Video Based on Deep Learning Using Mobilenet V2 . 2022, Sultan Syarif Kasim State Islamic University, Riau.

14. Ae, N.H. and M.I. Zul, Indonesian Sign Language Translator Application to Voice Based on Android Using Tensorflow. Journal of Applied Computer, 2021. 7 (1): p. 74-83.

15. Febrywinata, E., Introduction and Classification of Fruit Types Using the CNN Method in a Simple Way Using Google Colab. Mercury: Journal of Information Systems and Informatics Engineering Research, 2024. 2 (4): p. 185-193.

16. Holide, YA, A. Krismon, and DZE Prasetya. Android-Based Kediri City Tourism Application Using Android Studio . in National Seminar on Technology & Science . 2022.

17. Putra, B., B. Nugroho, and F. Anggraeny, Use of elevators in buildings-Detection and counting of humans using Yolo-CNN. Journal of Informatics and Information Systems, 2021. 2 (1): p. 67-76.

18. Sharma, L. and M. Carpenter, Computer Vision and Internet of Things: Technologies and Applications. 2022: CRC Press.

19. Chakraborty, R., A. Ghosh, and J.K. Mandal, Machine Learning Techniques and Analytics for Cloud Security. 2021: John Wiley & Sons.

20. Kamila, NL, Understanding What Data Preprocessing Stages Are. 2023.

21. Sugandi, AN and B. Hartono. Implementation of Image Processing on Quadcopter for Human Detection Using YOLO Algorithm . in Proceeding Industrial Research Workshop and National Seminar . 2022.

22. Hayati, NJ, D. Singasatia, and MR Muttaqin, Object Tracking Using the You Only Look Once (Yolo) V8 Algorithm to Count Vehicles. Komputa: Scientific Journal of Computer and Informatics, 2023. 12 (2): p. 91-99.