Enhancing Reliability Prediction of Power Transformers in the Petrochemical Industry Using Deep Learning Models
محورهای موضوعی : Artificial Intelligence Tools in Software and Data Engineering
Komail Pourkhaghan
1
,
Mehran Emadi
2
1 -
2 - Department of Electrical Engineering, Mo.C., Islamic Azad University, Isfahan, Iran
کلید واژه: Reliability Analysis, Power Transformers, Deep Learning, Fuzzy Clustering, Fuzzy Distance Functions, Petrochemical Industry,
چکیده مقاله :
This research uses advanced deep learning and data mining methods to analyze and improve the reliability of power transformers in the petrochemical industry. The main goal is to identify critical equipment and optimize maintenance and repair strategies by using fuzzy clustering algorithms and fuzzy distance functions. For this purpose, transformer performance data including repair costs, mean time between failures (MTBF), downtime, and criticality score were collected and, after preprocessing, were entered into unsupervised machine learning algorithms. In the analysis process, the data were categorized into five separate clusters, which increased the accuracy in identifying critical equipment. Simulation results showed that the optimal number of clusters for reliability analysis is five clusters. The model evaluation using Mean Squared Distance (MSD) and Objective Function (OBJ) metrics showed that the fuzzy clustering algorithm performed better than the traditional methods. Specifically, the OBJ value decreased by about 12% and MSD by about 10%, which is due to the use of fuzzy distance functions to more accurately represent the relationships between data. Finally, this research provides practical suggestions for improving equipment management, including focusing on preventive maintenance of critical equipment, optimizing repair schedules for old and expensive equipment, and maintaining stable performance through regular maintenance. This approach can lead to cost reduction, increased productivity, and improved reliability of power systems in the petrochemical industry.
This research uses advanced deep learning and data mining methods to analyze and improve the reliability of power transformers in the petrochemical industry. The main goal is to identify critical equipment and optimize maintenance and repair strategies by using fuzzy clustering algorithms and fuzzy distance functions. For this purpose, transformer performance data including repair costs, mean time between failures (MTBF), downtime, and criticality score were collected and, after preprocessing, were entered into unsupervised machine learning algorithms. In the analysis process, the data were categorized into five separate clusters, which increased the accuracy in identifying critical equipment. Simulation results showed that the optimal number of clusters for reliability analysis is five clusters. The model evaluation using Mean Squared Distance (MSD) and Objective Function (OBJ) metrics showed that the fuzzy clustering algorithm performed better than the traditional methods. Specifically, the OBJ value decreased by about 12% and MSD by about 10%, which is due to the use of fuzzy distance functions to more accurately represent the relationships between data. Finally, this research provides practical suggestions for improving equipment management, including focusing on preventive maintenance of critical equipment, optimizing repair schedules for old and expensive equipment, and maintaining stable performance through regular maintenance. This approach can lead to cost reduction, increased productivity, and improved reliability of power systems in the petrochemical industry.
[1] R. O. Okeke, A. I. Ibokette, O. M. Ijiga, L. A. Enyejo, G. I. Ebiega, and O. M. Olumubo, “THE RELIABILITY ASSESSMENT OF POWER TRANSFORMERS,” Engineering Science & Technology Journal, vol. 5, no. 4, pp. 1149-1172, 2024.
[2] G. lal Rajora, M. A. Sanz-Bobi, and C. M. Domingo, “Application of Machine Learning Methods for Asset Management on Power Distribution Networks,” Emerging Science Journal, vol. 6, no. 4, pp. 905-920, 2022.
[3] J. R. Geisbush, Using Reliability Centered Maintenance (RCM) Analyses toDevelop Large Diameter Water Pipeline Maintenance Strategies, Arizona State University, 2024.
[4] K. Zadiran, and M. Shcherbakov, “New Method of Degradation Process Identification for Reliability-Centered Maintenance of Energy Equipment,” Energies, vol. 16, no. 2, pp. 575, 2023.
[5] I. H. Afefy, A. Mohib, A. El-kamash, and M. Mahmoud, “A New Framework of Reliability Centered Maintenance,” Jordan Journal of Mechanical & Industrial Engineering, vol. 13, no. 3, 2019.
[6] Seyed Abolghasemi, S.S., Emadi, M. and Karimi, M., 2024. Accuracy improvement of breast tumor detection based on dimension reduction in the spatial and edge features and edge structure in the image. Majlesi Journal of Electrical Engineering, 18(1), pp.33-44.
[7] J. Geisbush, and S. T. Ariaratnam, “Reliability centered maintenance (RCM): literature review of current industry state of practice,” Journal of Quality in Maintenance Engineering, vol. 29, no. 2, pp. 313-337, 2023.
[8] B. Wang, B. Fang, Y. Wang, H. Liu, and Y. Liu, “Power system transient stability assessment based on big data and the core vector machine,” IEEE Transactions on Smart Grid, vol. 7, no. 5, pp. 2561-2570, 2016.
[9] H. Ghasemi, E. S. Farahani, M. Fotuhi-Firuzabad, P. Dehghanian, A. Ghasemi, and F. Wang, “Equipment Failure Rate in Electric Power Distribution Networks: An Overview of Concepts, Estimation, and Modeling Methods,” Engineering Failure Analysis, pp. 107034, 2023.
[10] L. Duchesne, E. Karangelos, and L. Wehenkel, “Recent developments in machine learning for energy systems reliability management,” Proceedings of the IEEE, vol. 108, no. 9, pp. 1656-1676, 2020.
[11] Yang, Hsin-Jung, Mahsa Khosravi, Benjamin Walt, Girish Krishnan, and Soumik Sarkar. "Zero-shot Sim-to-Real Transfer for Reinforcement Learning-based Visual Servoing of Soft Continuum Arms." arXiv preprint arXiv:2504.16916 (2025).
[12] Al Hamadani, Rihab Abdullah Jaber, et al. "Improvement of Network Traffic Prediction in Beyond 5G Network using Sparse Decomposition and BiLSTM Neural Network." Qubahan Academic Journal 5.2 (2025): 156-176.
[13] A. AIROBOMAN, “Reliability Assessment of Power System Network: A Detailed Review,” International Journal of Engineering Technologies IJET, vol. 7, no. 4, pp. 90-103.
[14] S. H. Hoseinie, U. Kumar, and B. Ghodrati, Reliability centered maintenance (RCM) for automated mining machinery: Luleå tekniska universitet, 2016.
[15] Karimi, Mohsen, Zahra Karimi, Mahsa Khosravi, Zeinab Delaram, Mostafa Habibi Dehsheikhim, Somayeh Arab Najafabadi, Mohammadreza Alizadeh Aliabadi, and Nakisa Tavakoli. "Feature selection methods in big medical databases: a comprehensive survey." International Journal of Theoretical & Applied Computational Intelligence (2025): 181-209."
[16] S. K. Sahu, M. Roy, S. Dutta, D. Ghosh, and D. K. Mohanta, “Machine learning based adaptive fault diagnosis considering hosting capacity amendment in active distribution network,” Electric Power Systems Research, vol. 216, pp. 109025, 2023.
[17] L. Bertling, “Reliability-centred maintenance for electric power distribution systems,” Elektrotekniska system, 2002.
[18] N. M. d. M. Torre, and A. Bonamigo, “Action research of lean 4.0 application to the maintenance of hydraulic systems in steel industry,” Journal of Quality in Maintenance Engineering, 2024.
[19] S. Bani, and H. Nwosu, “Assessing the Sustainability of an Aluminum Roofing Sheet Corrugating Machine by Reliability Centered Maintenance and Cost Reduction Technique.”
[20] T. R. Mohan, J. P. Roselyn, R. A. Uthra, D. Devaraj, and K. Umachandran, “Intelligent machine learning based total productive maintenance approach for achieving zero downtime in industrialmachinery,” Computers & Industrial Engineering, vol. 157, pp. 107267, 2021.
[21] A. Koksal, and A. Ozdemir, “Improved transformer maintenance plan for reliability centred asset management of power transmission system,” IET Generation, Transmission & Distribution, vol. 10, no. 8, pp. 1976-1983, 2016.
[22] K. Ayu, and A. Yunusa-Kaltungo, “A holistic framework for supporting maintenance and asset management life cycle decisions for power systems,” Energies, vol. 13, no. 8, pp. 1937, 2020.
[23] D. Bose, C. K. Chanda, and A. Chakrabarti, “Vulnerability assessment of a power transmission network employing complex network theory in a resilience framework,” Microsystem Technologies, vol. 26, no. 8, pp. 2443-2451, 2020.
[24] B. Li, D. Ofori-Boateng, Y. R. Gel, and J. Zhang, “A hybrid approach for transmission grid resilience assessment using reliability metrics and power system local network topology,” Sustainable and Resilient Infrastructure, vol. 6, no. 1-2, pp. 26-41, 2021.
[25] Y. Jin, H. Wu, J. Zheng, J. Zhang, and Z. Liu, “Power transformer fault diagnosis based on improved BP neural network,” Electronics, vol. 12, no. 16, pp. 3526, 2023.
[26] L. Rutkowski, M. Jaworski, and P. Duda, "Basic Concepts of Data Stream Mining," Stream Data Mining: Algorithms andTheir Probabilistic Properties, pp. 13-33: Springer, 2020.
[27] R. Gao, J. Yin, R. Liu, Y. Liu, J. Li, L. Dong, W. Ma, L. Zhang, P. Zhang, and Z. Tian, “A novel particle size distribution correction method based on image processing and deep learning for coal quality analysis using NIRS-XRF,” Talanta, vol. 285, pp. 127427, 2025.
[28] M. R. Malarvizhi, and A. S. Thanamani, “K-nearest neighbor in missing data imputation,” International Journal of Engineering Research and Development, vol. 5, no. 1, pp. 5-7,2012.
[29] M. K. Gupta, and P. Chandra, "An Empirical Evaluation of K-Means Clustering Algorithm Using Different Distance/Similarity Metrics," Proceedings of ICETIT 2019, pp. 884-892: Springer, 2020.
[30] K. R. Devi, “Evaluation of Partitional and Hierarchical Clustering Techniques,” 2019.
