Klasifikasi Kondisi Isolator Menggunakan Logistic Regression dan Support Vector Machine dengan Analisis Citra Berbasis VGG-16, VGG-19, dan Inception V3: Classification of Insulator Conditions Using Logistic Regression and Support Vector Machine with Image Analysis Based on VGG-16, VGG-19, and Inception V3

Aris Purwaningtyas; Imam Yuadi

doi:10.57152/malcom.v6i3.2652

Authors

Aris Purwaningtyas Universitas Airlangga
Imam Yuadi Universitas Airlangga

DOI:

https://doi.org/10.57152/malcom.v6i3.2652

Keywords:

Deep Learning, Isolator, Klasifikasi Citra, Logistic Regression, Pemeliharaan Prediktif, SVM, VGG

Abstract

Keandalan sistem ketenagalistrikan sangat bergantung pada kondisi isolator sebagai komponen yang mencegah kebocoran arus listrik, karena kerusakannya dapat memicu gangguan hingga pemadaman berskala luas. Meskipun inspeksi menggunakan Unmanned Aerial Vehicle (UAV) semakin banyak diterapkan, analisis visual masih dilakukan secara manual sehingga cenderung subjektif, tidak konsisten, dan memerlukan waktu yang lama. Penelitian ini mengembangkan sistem klasifikasi kondisi isolator berbasis citra menggunakan platform Orange Data Mining. Model pre-trained Deep Convolutional Neural Network (DCNN), yaitu VGG-16, VGG-19, dan Inception V3, dimanfaatkan sebagai feature extractor, sedangkan Logistic Regression dan Support Vector Machine (SVM) digunakan sebagai algoritma klasifikasi untuk membedakan isolator normal dan terkontaminasi. Dataset terdiri atas 168 citra isolator keramik dan kaca yang diperoleh melalui inspeksi lapangan menggunakan drone. Evaluasi dilakukan menggunakan 5-fold stratified cross-validation untuk menjaga distribusi kelas pada setiap fold. Hasil menunjukkan bahwa kombinasi VGG-19 dan Logistic Regression memberikan performa terbaik dengan akurasi 96,4%, AUC 0,986, dan Matthews Correlation Coefficient (MCC) 0,929, serta menurunkan false positive menjadi 3,6%. Temuan ini menunjukkan efektivitas pendekatan hybrid DCNN–machine learning untuk deteksi dini kondisi isolator secara otomatis.

Downloads

Download data is not yet available.

References

M. F. Ahmed, J. C. Mohanta, and A. Sanyal, “Inspection and identification of transmission line insulator breakdown based on Deep Learning using aerial images,” Electric Power Systems Research, vol. 211, Oct. 2022, doi: 10.1016/j.epsr.2022.108199.

J. Liu, M. M. Hu, J. Y. Dong, and X. Lu, “Summary of insulator defect detection based on Deep Learning,” Nov. 01, 2023, Elsevier Ltd. doi: 10.1016/j.epsr.2023.109688.

H. de Santos and M. Sanz-Bobi, “A machine learning approach for condition monitoring of high voltage insulators in polluted environments,” Electric Power Systems Research, vol. 220, Jul. 2023, doi: 10.1016/j.epsr.2023.109340.

A. Odo, S. McKenna, D. Flynn, and J. B. Vorstius, “Aerial Image Analysis Using Deep Learning for Electrical Overhead Line Network Asset Management,” IEEE Access, vol. 9, pp. 146281–146295, 2021, doi: 10.1109/ACCESS.2021.3123158.

D. Li, X. Wang, J. Zhang, and Z. Ji, “Automated Deep Learning system for power line inspection image analysis and processing: Architecture and design issues,” Global Energy Interconnection, vol. 6, no. 5, pp. 614–633, Oct. 2023, doi: 10.1016/j.gloei.2023.10.008.

X. Liu, X. Miao, H. Jiang, and J. Chen, “Data analysis in visual power line inspection: An in-depth review of Deep Learning for component detection and fault diagnosis,” Jan. 01, 2020, Elsevier Ltd. doi: 10.1016/j.arcontrol.2020.09.002.

L. Das, B. Gjorgiev, and G. Sansavini, “An improved anomaly detection model for automated inspection of power line insulators,” Eng. Appl. Artif. Intell., vol. 158, Oct. 2025, doi: 10.1016/j.engappai.2025.111431.

R. Rahimi Nejadbougar, E. Ghanbari Parmehr, A. Afary, and S. Mavaddati, “A new Deep Learning framework for intelligent aerial monitoring of power transmission line insulators,” Eng. Appl. Artif. Intell., vol. 161, Dec. 2025, doi: 10.1016/j.engappai.2025.112290.

L. Tan and Y. Hu, “Accurate Detection and Classification of Surface Defects in Electric Porcelain Insulators Based on Deep Learning Intelligent Algorithms,” in Procedia Computer Science, Elsevier B.V., 2025, pp. 582–588. doi: 10.1016/j.procs.2025.04.248.

B. Vigneshwaran et al., “Recognition of pollution layer location in 11 kV polymer insulators used in smart power grid using dual-input VGG Convolutional Neural Network,” Energy Reports, vol. 7, pp. 7878–7889, Nov. 2021, doi: 10.1016/j.egyr.2020.12.044.

J. Zhang, T. Xiao, M. Li, and Y. Zhou, “Deep-Learning-Based Detection of Transmission Line Insulators,” Energies (Basel)., vol. 16, no. 14, Jul. 2023, doi: 10.3390/en16145560.

A. S. Haiba and A. Eliwa Gad, “Artificial neural network analysis for Classification of defected high voltage ceramic insulators,” Sci. Rep., vol. 14, no. 1, Dec. 2024, doi: 10.1038/s41598-024-51860-8.

I. Maduako et al., “Deep Learning for component fault detection in electricity transmission lines,” J. Big Data, vol. 9, no. 1, Dec. 2022, doi: 10.1186/s40537-022-00630-2.

S. R. Shah, S. Qadri, H. Bibi, S. M. W. Shah, M. I. Sharif, and F. Marinello, “Comparing Inception V3, VGG 16, VGG 19, CNN, and ResNet 50: A Case Study on Early Detection of a Rice Disease,” Agronomy, vol. 13, no. 6, Jun. 2023, doi: 10.3390/agronomy13061633.

Y. Zhai, D. Wang, M. Zhang, J. Wang, and F. Guo, “Fault detection of insulator based on saliency and adaptive morphology,” Multimed. Tools Appl., vol. 76, no. 9, pp. 12051–12064, May 2017, doi: 10.1007/s11042-016-3981-2.

M. Mujahid, F. Rustam, R. Álvarez, J. Luis Vidal Mazón, I. de la T. Díez, and I. Ashraf, “Pneumonia Classification from X-ray Images with Inception-V3 and Convolutional Neural Network,” Diagnostics, vol. 12, no. 5, May 2022, doi: 10.3390/diagnostics12051280.

S. Kumar, S. K. Gupta, M. Kaur, and U. Gupta, “VI-NET: A hybrid deep convolutional neural network using VGG and inception V3 model for copy-move forgery Classification,” J. Vis. Commun. Image Represent., vol. 89, Nov. 2022, doi: 10.1016/j.jvcir.2022.103644.

X. Yin, Y. Zuo, and G. Fu, “Design of intelligent detection method for electricity transmission line equipment defect based on data mining algorithm,” International Journal of Thermofluids, vol. 24, Nov. 2024, doi: 10.1016/j.ijft.2024.100814.

U. Mahapatra, M. A. Rahman, M. R. Islam, M. A. Hossain, M. R. I. Sheikh, and M. J. Hossain, “Adversarial training-based robust model for transmission line’s insulator defect Classification against cyber-attacks,” Electric Power Systems Research, vol. 245, Aug. 2025, doi: 10.1016/j.epsr.2025.111585.

J. Y. Lim, K. M. Lim, C. P. Lee, and Y. X. Tan, “A review of few-shot image Classification: Approaches, datasets and research trends,” Oct. 07, 2025, Elsevier B.V. doi: 10.1016/j.neucom.2025.130774.