A New Automatic Fault Diagnosis Algorithm for Electrical Equipment Based on Infrared Thermography

Date Received: Feb 11, 2025

Date Accepted: Jun 26, 2025

Date Published: Jun 28, 2025

DOI: https://doi.org/10.31817/vjas.2025.8.2.

Views

18

Download

7

Issue: Vol. 8 No. 2 (2025): Vietnam Journal of Agricultural Sciences

Section:

ENGINEERING AND TECHNOLOGY

How to Cite:

Truong, N., Hoc, N., Duong, N., & Tien, D. (2025). A New Automatic Fault Diagnosis Algorithm for Electrical Equipment Based on Infrared Thermography. Vietnam Journal of Agricultural Sciences, 8(2), 2509–2519. https://doi.org/10.31817/vjas.2025.8.2.

A New Automatic Fault Diagnosis Algorithm for Electrical Equipment Based on Infrared Thermography

Nguyen Xuan Truong 1 , Nguyen Thai Hoc (*) 1 , Ngo Tri Duong 1   , Dao Xuan Tien 1

  • Corresponding author: [email protected]
  • 1 Faculty of Engineering, Vietnam National University of Agriculture, Hanoi 12400, Vietnam

    • Keywords

    Thermal imaging, thermal image segmentation, thermal anomalies detection, power monitoring system, electrical equipment

    Abstract


    In this paper, a novel algorithm is proposed for an Efficient Fault Diagnosis Method (EFDM) for electrical equipment in real time. A combined optical and thermal image processing system is employed to detect thermal anomalies in electrical components in real time. A video camera is initially used to monitor and identify the electrical components, while an infrared camera, aligned with the same viewpoint, is used to capture thermal images of the equipment. The EFDM is then applied to identify and locate faults in electrical components. Numerical results indicate that the proposed algorithm achieves higher accuracy in detecting thermal anomalies compared to existing methods. Evaluation across 300 scenarios shows that the proposed method achieves 97.57% accuracy in localizing abnormal electrical components and 95.30% accuracy in estimating their surface temperatures. These results demonstrate that the proposed thermal anomaly detection algorithm is effective for electrical power monitoring applications.

    Author Biographies

    Nguyen Xuan Truong, Faculty of Engineering, Vietnam National University of Agriculture, Hanoi 12400, Vietnam

    Truong Xuan Nguyen received his B.Sc and M.Sc degrees in electrical and electronic engineering from Vietnam National University of Agriculture, Vietnam in 1995 and 2002, respectively. He then received PhD degree in Electric Power Systems at the College of Energy and Electrical Engineering, Hohai University, Nanjing 210098, China in 2012. His research interests include wind power system. 
    He can be contacted at: [email protected]@vnua.edu.vn.

    Nguyen Thai Hoc, Faculty of Engineering, Vietnam National University of Agriculture, Hanoi 12400, Vietnam

    Hoc Thai Nguyen is Lecture and Researcher at Vietnam National University of Agriculture, Hanoi, Vietnam. He received his B.Sc and M.Sc degrees in electrical and electronic engineering from Vietnam National University of Agriculture, Vietnam in 2006 and 2010, respectively. He then received PhD degree in infocommunication technologies and Automation at the Budapest University of Technology and Economics (BME), Hungary in 2018. His research interests include wireless sensor networks, Internet of Robotic Things and Applications of Artificial Intelligence in Precision Agriculture. He can be contacted at email: [email protected]; [email protected].  

    Ngo Tri Duong, Faculty of Engineering, Vietnam National University of Agriculture, Hanoi 12400, Vietnam

    Duong Tri Ngo received the PhD degree in Control Engineering and Automation from Hanoi University of Science and Technology, Vietnam, in 2009. He is currently a senior lecturer at the Faculty of Engineering of VNUA. His main research interests are control systems, IoT, and AI applications for smart agriculture. He can be contacted at: [email protected].

    Dao Xuan Tien, Faculty of Engineering, Vietnam National University of Agriculture, Hanoi 12400, Vietnam

    Tien Xuan Dao received the MA degree in electrical engineering and electrical system from the Vietnam National University of Agriculture (VNUA), Vietnam, in 2010. He is currently a lecturer at the Faculty of Engineering of VNUA and a PhD candidate at Hanoi University of Science and Technology (HUST), Vietnam. His research interests include control systems, smart grids, and AI applications for smart agriculture. He can be contacted at: [email protected].

    References

    Ahmed M. M., Huda A. N. & Isa N. A. M. (2015). Recursive construction of output-context fuzzy systems for the condition monitoring of electrical hotspots based on infrared thermography. Engineering Applications of Artificial Intelligence. 39: 120-131. DOI: 10.1016/j.engappai.2014.11.010.

    Baba A. (2022). A new design of a flying robot, with advanced computer vision techniques to perform self-maintenance of smart grids. Journal of King Saud University-Computer and Information Sciences. 34: 2252-2261. DOI: 10.1016/j.jksuci.2020.07.009.

    Balakrishnan G. K., Yaw C. T., Koh S. P., Abedin T., Raj A. A., Tiong S. K. & Chen C. P. (2022). A review of infrared thermography for condition-based monitoring in electrical energy: Applications and recommendations. Energies. 15(16): 6000. DOI: 10.3390/en15166000.

    Bagavathiappan S., Lahiri B. B., Saravanan T., Philip J. & Jayakumar T. (2013). Infrared thermography for condition monitoring–a review. Infrared Physics & Technology. 60: 35-55. DOI: 10.1016/j.infrared.2013.03.006.

    Coutin M., Plumecocq W., Melis S. & Audouin L. (2012). Energy balance in a confined fire compartment to assess the heat release rate of an electrical cabinet fire. Fire Safety Journal. 52: 34-45. DOI: 10.1016/j.firesaf.2012.05.002.

    Doutorado R. (2023). Rna eduardo tese dataset. Retrieved from https://universe.roboflow.com/rna-doutorado/rna eduardo tese, aug 2023, visited on September 15, 2024.

    Doshvarpassand S., Wu C. & Wang X. (2019). An overview of corrosion defect characterization using active infrared thermography. Infrared Physics and Technology. 96: 366-389. DOI: 10.1016/j.infrared.2018.12.006.

    Fadzail N. F., Zali S. M., Khairudin, M. A. & Hanafi, N. H., (2020). Stator winding fault detection of induction generator based wind turbine using ANN. Indonesian Journal of Electrical Engineering and Computer Science. 19: 2502-4752. DOI: 10.11591/ijeecs.v19.i1.pp126-133.

    Fatima M. (2025). Intelligent active and reactive power control using multi-layer neural network based MPPT controller for grid tied solar PV system under fault conditions. Indonesian Journal of Electrical Engineering and Computer Science. 37: 2502-4752. DOI:10.11591/ijeecs.v37.i1.pp1-14.

    Huda A. & Taib S. (2013). Suitable features selection for monitoring thermal condition of electrical equipment using infrared thermography. Infrared Physics and Technology. 61: 184-191. DOI: 10.1016/j.infrared.2013.04.012.

    Jabbar F. I., Soomro D. M., Abdullah M. N., Radzi N. H. M., Baloch M. H., Rahmoon A. A. & Fakhruldeen H. F. (2023). Optimize single line to ground fault detection in distribution grid power system using artificial bee colony. Indonesian Journal of Electrical Engineering and Computer Science. 31: 2502-4752, DOI: 10.11591/ijeecs.v31.i3.pp1286-1294.

    Jadin M. S. & Taib S. (2012). Recent progress in diagnosing the reliability of electrical equipment by using infrared thermography. Infrared Physics and Technology. 55: 236-245. DOI: 10.1016/j.infrared.2012.03.002.

    Jaffery Z. A. & Dubey A. K. (2014). Design of early fault detection technique for electrical assets using infrared thermograms. International Journal of Electrical Power and Energy Systems. 63: 753-759. DOI:10.1016/ijepes.2014.6.049.

    Kregg M. A. (2004). Benefits of using infrared thermography in utility substations. Thermosense XXVI, 5405. SPIE: 249-257. DOI:10.1117/12.549848.

    Luo Q., Gao B., Woo W. L. & Yang Y. (2019). Temporal and spatial deep learning network for infrared thermal defect detection. Ndt & E International. 108: 102164. DOI:10.1016/j.ndteint.2019.102164.

    Market S. (2025). LMD-based fault detection scheme for TCSC compensated wind integrated transmission lines. Indonesian Journal of Electrical Engineering and Computer Science. 37: 2502-4752, DOI: 10.11591/ijeecs.v37.i1.pp26-34.

    Nehete L., Bankar S., Asati R. & Khadse C. (2024). Non-contact power system fault diagnosis: a machine learning approach with electromagnetic current sensing. Indonesian Journal of Electrical Engineering and Computer Science. 36(3): 1356-1364. DOI: 10.11591/ijeecs.v36.i3.pp1356-1364.

    Ostu N. (1979). A threshold selection method from grey level histograms. IEEE Trans SMC. 9: 62.

    Pandurangan K. & Nagappan K. (2024). Hybrid total variance void-based noise removal in infrared images. Indonesian Journal of Electrical Engineering and Computer Science. 36: 1365-1378. DOI: 10.11591/ijeecs.v36.i3.pp1365-1378.

    Sedighi AR., Kafiri A., Sehhati MR. & Behdad F. (2020). Life estimation of distribution transformers using thermography: A case study Measurement. 149: 106-994.

    Xia C., Ren M., Wang B., Dong M., Xu G., Xie J. & Zhang C. (2021). Infrared thermography-based diagnostics on power equipment: Stateof-the-art. High Voltage. 6: 387-407. DOI: 10.1049/hve2.12023.

    Xu X., Xu S., Jin L. & Song E. (2011). Characteristic analysis of otsu threshold and its applications. Pattern Recognition Letters. 32: 956-961.

    Ukrit K., Sansak D. & Saktanong W (2024). Safety hysteresis comparator design for transient overvoltage detection. Indonesian Journal of Electrical Engineering and Computer Science. 34(1): 2502-4752, DOI: 10.11591/ijeecs.v34.i1.pp69-80.

    Zhou D. & Xia Z. (2016). An improved otsu threshold segmentation algorithm. textslJournal of the China University of Metrology. 3: 319-323.

    Zou H. & Huang F. (2015). A novel intelligent fault diagnosis method for electrical equipment using infrared thermography. Infrared Physics and Technology. 73: 29-35. DOI: /10.1016/j.infrared.2015.08.019.