Design of an Electrical Fault Diagnosis Method Incorporating Compressed Sensing and Wavelet-SVM
DOI:
https://doi.org/10.13052/dgaej2156-3306.40561Keywords:
Electrical fault diagnosis, compressed sensing, support vector machines, wavelet transform, K-nearest neighborsAbstract
The building’s electrical system is crucial, and when a defect arises, it not only necessitates power outages and maintenance, which results in financial losses, but also interferes with people’s regular output and way of life. To a certain extent, the regular operation of building electrical facilities and equipment depends heavily on the development of problem diagnosis technology in the field of building electrical. Based on this, the study suggests a fault diagnosis model for support vector machines and K closest neighbors that incorporates compressive sensing and wavelet transform. The approach improves the K-nearest neighbor algorithm while using a support vector machine as the training framework. This increases the algorithm’s operational efficiency and diagnostic accuracy while also enhancing the support vector machine’s ability to handle huge sample sizes of data. The model uses wavelet transform and compression perception for noise reduction and dimensionality reduction of the original signal. Experimental analysis of the variables influencing the wavelet transform-support vector machine algorithm’s classification accuracy led to the conclusion that 10 was the ideal k-value for the K-nearest neighbor technique. With classification accuracy of 80.2% and 81.4% for sample data amounts of 400 and 2400, respectively, it was found through comparative experiments that the wavelet transform-support vector machine algorithm outperformed the single support vector machine and the inverse propagation algorithm. This suggests that the suggested approach is more reliable and efficient at locating electrical faults in buildings because it is not impacted by variations in the sample data volume. The use of the compressed sensing and K-nearest neighbor algorithms increased the model’s accuracy to 92.5% while reducing its running time by 809.9 s when compared to the pre-improvement algorithm. This shows that the use of these algorithms improved the model’s running efficiency as well as accuracy.
Downloads
References
Anbalagan T, Nath M K, Anbalagan A. Detection of atrial fibrillation from ECG signal using efficient feature selection and classification. Circuits, Systems, and Signal Processing, 2024, 43(9): 5782–5808.
Darwish M M F, Hassan M H A, Abdel-Gawad N M K, Lehtonen M, Mansour D E A. A new technique for fault diagnosis in transformer insulating oil based on infrared spectroscopy measurements. High Voltage, 2024, 9(2): 319–335.
Danjuma M U, Yusuf B, Yusuf I. Reliability, availability, maintainability, and dependability analysis of cold standby series-parallel system. Journal of Computational and Cognitive Engineering, 2022, 1(4): 193–200.
John Y M, Sanusi A, Yusuf I, Modibbo U M. Reliability Analysis of Multi-Hardware-Software System with Failure Interaction. Journal of Computational and Cognitive Engineering, 2023, 2(1): 38–46.
Xu B, Shen J, Liu S, Su Q, Zhang J. Research and Development of Electro-hydraulic Control Valves Oriented to Industry 4. 0: A Review. Chinese Journal of Mechanical Engineering, 2020, 33(2): 13–32.
Niu G, Wang X, Golda M, Mastro S, Zhang B. An Optimized Adaptive PReLU-DBN for Rolling Element Bearing Fault Diagnosis. Neurocomputing, 2021, 445(20): 26–34.
Zhang J, Zhang Q, He X, Sun G, Zhou D. Compound-Fault Diagnosis of Rotating Machinery: A Fused Imbalance Learning Method. IEEE Transactions on Control Systems Technology, 2021, 29(4): 1462–1474.
Han Y, Ding N, Geng Z, Wang Z, Chu C. An optimized long short-term memory network-based fault diagnosis model for chemical processes. Journal of Process Control, 2020, 92(4): 161–168.
Patil P S, Patil M S, Tamhankar S. Ensembles of Ensemble Machine Learning approach for Fault detection of Bearing. Solid State Technology, 2020, 63(6): 14442–14455.
Chen J, Gao J, Jin Y, Zhu P, Zhang Q. Fault Diagnosis in Distributed Power-Generation Systems Using Wavelet Based Artificial Neural Network. European Journal of Electrical Engineering, 2021, 23(1): 53–59.
Fu J, Leng T. Fault diagnosis and location method for electrical power supply and distribution of buildings. International Journal of Simulation and Process Modelling, 2020, 15(4): 333–342.
Du T, Zhang H, Wang L. Analogue circuit fault diagnosis based on convolution neural network. Electronics Letters, 2019, 55(24): 1277–1279.
Tuerxun W, Chang X, Hongyu G, Jin Z, Zhou H. Fault Diagnosis of Wind Turbines Based on a Support Vector Machine Optimized by the Sparrow Search Algorithm. IEEE Access, 2021, 9(1): 69307–69315.
Zhang Y, Campana P E, Yang Y, Stridh B, Lundblad A, Yan J. Energy flexibility from the consumer: Integrating local electricity and heat supplies in a building. Applied Energy, 2018, 223(3): 430–442.
Wang M H, Lu S D, Liao R M. Fault Diagnosis for Power Cables Based on Convolutional Neural Network with Chaotic System and Discrete Wavelet Transform. IEEE Transactions on Power Delivery, 2021, 37(1): 582–590.
Soltani A A, Shahrtash S M. Decision tree-based method for optimum decomposition level determination in wavelet transform for noise reduction of partial discharge signals. IET Science, Measurement & Technology, 2020, 14(1): 9–16.
Ertargin M, Yildirim O, Orhan A. Mechanical and electrical faults detection in induction motor across multiple sensors with CNN-LSTM deep learning model. Electrical Engineering, 2024, 106(6): 6941–6951.
Xi Y, Chen Z, Tang X, Li Z, Zeng X. Type identification and time location of multiple power quality disturbances based on KF-ML-aided DBN. IET Generation, Transmission & Distribution, 2022, 16(8): 1552–1566.
Peng F, Mu L, Fang C. Fault diagnosis of shipboard medium-voltage alternating current power system with fault recording data-driven SE-ResNet18-1 model. IEEJ Transactions on Electrical and Electronic Engineering, 2024, 19(3): 403–413.
Kerboua A, Kelaiaia R. Fault diagnosis in an asynchronous motor using three-dimensional convolutional neural network. Arabian Journal for Science and Engineering, 2024, 49(3): 3467–3485.
Wang X, Yang B, Wang Z, Lin Q, Chen C, Guan X. A compressed sensing and CNN-based method for fault diagnosis of photovoltaic inverters in edge computing scenarios. IET renewable power generation, 2022, 16(7): 1434–1444.
Zheng S, Ding C. A group lasso based sparse KNN classifier. Pattern Recognition Letters, 2020, 131(1): 227–233.
