AbstractPower transformers are essential components in power systems used to regulate voltage, transmit electrical energy, provide isolation, and match loads. They contribute to efficient and reliable electricity transmission and distribution. However, traditional methods for diagnosing transformer ...
AbstractPower transformers are essential components in power systems used to regulate voltage, transmit electrical energy, provide isolation, and match loads. They contribute to efficient and reliable electricity transmission and distribution. However, traditional methods for diagnosing transformer faults are time-consuming, not suitable for online monitoring, and greatly affected by environmental conditions. In this experiment, we propose the use of laser-induced fluorescence (LIF) technology for transformer fault detection. LIF technology is a method for analyzing and detecting specific molecules or atoms in samples. It combines laser technology with fluorescence measurements, making it a powerful analytical tool. It achieves high sensitivity and selectivity in analyzing molecules and atoms by exciting and detecting fluorescence in the sample. This makes it an important technology in scientific research and practical applications. Furthermore, LIF technology has not been previously applied to power transformer fault diagnosis. Therefore, this experiment introduces a transformer fault diagnosis model based on the marine predators algorithm (MPA) optimized random forest (RF) algorithm and LIF spectroscopy technology. Four different oil samples were selected for experimentation: crude oil, thermally faulty oil, partially moist oil, and electrically faulty oil. First, LIF technology for collect spectral images and data from the different fault oil samples. The obtained spectral data was preprocessed using two methods, multivariate scatter correction (MSC) and standardization method (SNV). Then, principal component analysis (PCA) and kernel principal component analysis (KPCA) for reducing the dimensionality of the preprocessed spectral data. Finally, the RF model, MPA-RF model, and PSO-RF model were established; and the reduced data was input into the model for training. Through comparisons of the predictions on the test set, evaluation metrics of the algorithm (including fitting coefficient, MSE, RMSE, and RMSE), and iteration convergence curves, the best transformer fault diagnosis model was identified. The results show that the MSC-KPCA-MPA-RF model has the best matching resule, with a fitting coefficient of 0.9963 and a mean square error of 0.0047. The SNV-PCA-MPA-RF model has the worst fitting effect, with a fitting coefficient of 0.9840 and a mean square error of 0.0199. Through comparisons of the convergence of different models, the MSC-KPCA-MPA-RF model has the best convergence and is the most applicable model for transformer fault diagnosis in this experiment. This model has significant implications for ensuring the safety of the power system.
AbstractPower transformers are essential components in power systems used to regulate voltage, transmit electrical energy, provide isolation, and match loads. They contribute to efficient and reliable electricity transmission and distribution. However, traditional methods for diagnosing transformer faults are time-consuming, not suitable for online monitoring, and greatly affected by environmental conditions. In this experiment, we propose the use of laser-induced fluorescence (LIF) technology for transformer fault detection. LIF technology is a method for analyzing and detecting specific molecules or atoms in samples. It combines laser technology with fluorescence measurements, making it a powerful analytical tool. It achieves high sensitivity and selectivity in analyzing molecules and atoms by exciting and detecting fluorescence in the sample. This makes it an important technology in scientific research and practical applications. Furthermore, LIF technology has not been previously applied to power transformer fault diagnosis. Therefore, this experiment introduces a transformer fault diagnosis model based on the marine predators algorithm (MPA) optimized random forest (RF) algorithm and LIF spectroscopy technology. Four different oil samples were selected for experimentation: crude oil, thermally faulty oil, partially moist oil, and electrically faulty oil. First, LIF technology for collect spectral images and data from the different fault oil samples. The obtained spectral data was preprocessed using two methods, multivariate scatter correction (MSC) and standardization method (SNV). Then, principal component analysis (PCA) and kernel principal component analysis (KPCA) for reducing the dimensionality of the preprocessed spectral data. Finally, the RF model, MPA-RF model, and PSO-RF model were established; and the reduced data was input into the model for training. Through comparisons of the predictions on the test set, evaluation metrics of the algorithm (including fitting coefficient, MSE, RMSE, and RMSE), and iteration convergence curves, the best transformer fault diagnosis model was identified. The results show that the MSC-KPCA-MPA-RF model has the best matching resule, with a fitting coefficient of 0.9963 and a mean square error of 0.0047. The SNV-PCA-MPA-RF model has the worst fitting effect, with a fitting coefficient of 0.9840 and a mean square error of 0.0199. Through comparisons of the convergence of different models, the MSC-KPCA-MPA-RF model has the best convergence and is the most applicable model for transformer fault diagnosis in this experiment. This model has significant implications for ensuring the safety of the power system.
참고문헌 (24)
Int. Electron. Elem. Tingzhi 10.14022/j.issn1674-6236.2023.09.022 31 109 2023 Research on transformer fault diagnosis algorithm based on multidimensional parameter correlation analysis
High Volt. Appar. Jiayu 10.13296/j.1001-1609.hva.2023.03.015 59 108 2023 Transformer fault diagnosis algorithm based on mining state parameter association rules and deep learning fusion
Trans. China Electrotech. Soc. Houxian 10.19595/j.cnki.1000-6753.tces.221422 38 83 2023 Research on power transformer fault detection based on multiple eigenvalues of vibration signals
Anal. Methods Yan 10.1039/D2AY01745H 15 261 2023 Transformer fault diagnosis research based on LIF technology and IAO optimization of LightGBM
Power Syst. Prot. Control Yan 10.19783/j.cnki.pspc.220662 51 32 2023 DBN-SSAELM transformer fault diagnosis method based on dissolved gas analysis in oil
High Volt. Eng. Xingzhen 10.13336/j.1003-6520.hve.20220670 49 1 2023 Optimization method for symptoms of dissolved gases in oil for transformer fault diagnosis
Power Syst. Prot. Control Guozhi 10.19783/j.cnki.pspc.220895 51 63 2023 Transformer fault diagnosis method based on DGA and whale algorithm optimizing logit boost decision tree
J. Phys.: Conf. Ser. Lin 10.1088/1742-6596/1914/1/012045 1914 1 2021 Convolutional bi-directional long short term memory network based dynamic fault diagnosis for transformer DGA
J. Fuel Chem. Technol. Zheng 10.1016/S1872-5813(23)60338-X 51 1 2023 Research progress of biomass thermal reaction process based on Laser-induced fluorescence spectroscopy
Aesthet. Surg. J. Kachare 10.1093/asj/sjad007 43 623 2023 Response to: discussion of details in the application of laser-assisted fluorescence angiography with SPY-Q software analysis
Plasma Sources Sci. Technol. Konopliv 10.1088/1361-6595/acb00b 32 2023 Accuracy of using metastable state measurements in laser-induced fluorescence diagnostics of xenon ion velocity in Hall thrusters
Energy Peng 10.1016/j.energy.2021.122330 239 122330.1 2022 Combustion oscillation characteristics of a supersonic ethylene jet flame using high-speed planar laser-induced fluorescence and dynamic mode decomposition
Spectrosc. Spectr. Anal. Jie 10.3964/j.issn.1000-0593(2021)07-2135-07 41 2135 2021 The application of Laser-induced fluorescence technology in the measurement of nitrogen atoms in high enthalpy air
Laser J. Mengran 10.14016/j.cnki.jgzz.2022.12.082 42 82 2021 Research on genetic algorithm optimized BP network for fast identification of adulterated honey
Chin. J. Lasers Jiajian 10.3788/CJL202148.0401005 48 78 2021 Research progress of combustion diagnosis using Laser-induced fluorescence technology
Control Decis. Ying 10.13195/j.kzyjc.2022.1752 1 2023 Time series classification method based on depth residual probability random forest
Electr. Power Autom. Equip. Lingyun 10.16081/j.epae.202304021 1 2023 A short-term power load combination prediction model based on multi-dimensional meteorological information spatiotemporal fusion and MPA-VMD
Comput. Sci. Eng. Lei 10.3969/j.issn.1007-130X.2023.02.019 45 355 2023 Elite reverse golden sine ocean predator algorithm
Control Decis. Hua 10.13195/j.kzyjc.2021.1749 38 902 2023 A staged improved marine predator algorithm and its application
Res. Technol. Manage. Changyou 10.3969/j.issn.1000-7695.2022.23.024 42 199 2022 Gaussian mixture model algorithm based on improved MPA optimization
IEEE Internet Things J. Li 10.1109/JIOT.2023.3296460 1 2023 BFOD: blockchain-based privacy protection and security sharing scheme of flight operation data
ACM Trans. Multimedia Comput. Commun. Appl. Mi 10.1145/3513263 20 42 2023 Automatic assessment of depression and anxiety through encoding pupil-wave from HCI in VR scenes
※ AI-Helper는 부적절한 답변을 할 수 있습니다.