Abstract
In view of the low utilization of catenary detection data, the imperfect research on catenary performance degradation caused by the joint action of multiple parameters, and most of the data are unsupervised learning data, which is not conducive to research and analysis. A catenary performance degradation identification method based on the improved support vector data description model (ISVDD) optimized by Gath Geva (GG) clustering and particle swarm optimization (PSO) algorithm is proposed. Firstly, select the semi supervised learning data, cluster the unlabeled data with t-distributed stochastic neighbor embedding dimension reduction method and GG clustering method, reduce the original data to two-dimensional space, and get the best number of clusters. Then, a PSO optimized ISVDD catenary performance degradation model is constructed using labeled data, which contains as much normal data and as little abnormal data as possible, and the radius of the established hypersphere model is as small as possible. Finally, the distance between the clustered sample data and the spherical center of the hypersphere is calculated, and the distance and radius are compared to determine the performance degradation degree of catenary. The simulation results show that the PSO-ISVDD proposed in this paper can judge the performance degradation of catenary more accurately than SVDD and ISVDD, and the accuracy can be as high as 99.33%, which provides a powerful reference for the identification of catenary performance degradation.
Similar content being viewed by others
References
Liu, Z.-G.; Song, Y.; Han, Y.; Wang, H.-R.; Zhang, J.; Han, Z.-W.: Research progress of high speed railway catenary. J. Southwest Jiaotong Univ. 51(03), 495–518 (2016)
Feng, D.; Yu, Q.; Sun, X.; Zhu, H.; Lin, S.; Liang, J.: Risk assessment for electrified railway catenary system under comprehensive influence of geographical and meteorological factors. IEEE Trans. Transp. Electr. 7(4), 3137–3148 (2021)
Song, Y.; Li, L.: Robust adaptive contact force control of pantograph-catenary system: an accelerated output feedback approach. IEEE Trans. Industr. Electron. 68(8), 7391–7399 (2021)
Qin, X.-Y.; Shi, B.: Performance degradation analysis of high-speed railway catenary based on continuous hidden Markov model. Electrified Railway 29(S1), 51–56 (2018)
Shi, B.; Gao, S.-B.: Performance degradation analysis of high speed railway catenary based on HHT method. Electrified Railway 28(04), 26–29 (2017)
Zhai, W.-R.; Li, X.-G.; Wang, J.-G.; Ding, W.-K.: Research on performance degradation evaluation method and application of shearer. Ind. Min. Autom. 46(12), 57-63+100 (2020)
Ziwen, C.; Feng, Z.; Ying, W.; Xiaoqiang, C.: High speed railway catenary health status assessment based on improved multi class evidence body method. Measur. Control Technol. 39(09), 128–132 (2020)
Wang, B.; Hu, X.; Li, H.-R.; Sun, D.-J.: Bearing performance degradation state identification based on basic scale entropy and GG fuzzy clustering. Vib. and Impact 38(05), 190-197+221 (2019)
Zhang, L.; Huang, W.-Y.; Xiong, G.-L.; Zhou, J.-M.; Zhou, J.-H.: Performance degradation evaluation of rolling bearing based on tespar and GMM. J. Instrum. 35(08), 1772–1779 (2014)
Gao, S.-J.: Fuzzy SVDD bearing performance degradation evaluation based on GA stochastic resonance. Modular Mach. Tool Autom. Mach. Technol. 08, 53–58 (2019)
Xuyong, H.: Performance degradation evaluation of Railway Catenary Based on IK means and CHMM. Locom. Electric Drive 02, 140–145 (2021)
Sun, M.-W.; Yang, H.-Z.: Clustering multi model soft sensor modeling based on support vector data description. Control Eng. 25(07), 1184–1189 (2018)
Saeed, I.M.; Mazari, S.A.; Alaba, P., et al.: A review of gas chromatographic techniques for identification of aqueous amine degradation products in carbonated environments. Environ. Sci. Pollut. Res. 28, 6324–6348 (2021)
Karakose, E.; Gencoglu, M.T.; Karakose, M., et al.: A new arc detection method based on fuzzy logic using S-transform for pantograph–catenary systems. J. Intell. Manuf. 29, 839–856 (2018)
Mao, X.-D.; Wang, Q.-X.; Dong, W.-G.; Liang, J.-P.; Zhu, K.: Fault diagnosis of phase shifted full bridge converter based on wavelet packet neural network and data dimension reduction. Acta Sinica Sinica 04, 68–75 (2014)
Burnaev, E.V.; Bernstein, A.V.: Functional dimension reduction in predictive modeling. J. Commun. Technol. Electron. 66, 745–753 (2021)
Yang, F.; Feng, X.; Ruan, L.; Chen, J.-W.; Xia, R.; Chen, Y.-L.; Jin, Z.-H.: Correlation study of water branch and ultra-low frequency dielectric loss based on Pearson correlation coefficient method. High Volt. Electr. Appl. 50(06), 21-25+31 (2014)
Toubiana, D.; Maruenda, H.: Guidelines for correlation coefficient threshold settings in metabolite correlation networks exemplified on a potato association panel. BMC Bioinformatics 22, 116 (2021)
Xu, S.; Hua, X.-P.; Xu, J.; Xu, X.-F.; Gao, J.; An, J.: A clustering ensemble method based on t-distribution random nearest neighbor embedding. Acta Electron. Sin. 40(06), 1316–1322 (2018)
Jiang, W.; Zhou, J.-Z.; Liu, H.; Shan, Y.-H.: A multi-step progressive fault diagnosis method for rolling element bearing based on energy entropy theory and hybrid ensemble auto-encoder. ISA Trans. 87, 235–250 (2019)
Liu, Z.-G.; Nie, R.-X.; Liu, Y.: Effects of total soy saponins on free radicals in the quadriceps femoris, serum testosterone, LDH, and BUN of exhausted rats. J. Sport Health Sci. 6(03), 359–364 (2017)
Li, H.-Z.; Wang, X.; Guo, Y.: Feature extraction and classification of power grid data based on KL transform and KL divergence. Electr. Measure. Instrum. 56(06), 87–92 (2019)
Fan, H.; Li, X.-W.; Su, H.-B.; Chen, L.; Shi, Z.-Q.: Research on fault diagnosis method of circuit breaker based on principal component analysis support vector machine optimization model. High Volt. Apparat. 56(06), 143–151 (2020)
Kamrani, H.; Asli, A.Z.; Markopoulos, P.P.; Langberg, M.; Pados, D.A.; Karystinos, G.N.: Reduced-Rank L1-norm principal-component analysis with performance guarantees. IEEE Trans. Signal Process. 69, 240–255 (2021)
Wang, B.; Wang, W.; Hu, X.; Sun, D.-J.: Degradation state recognition method based on GG fuzzy clustering. J. Instrum. 39(03), 21–28 (2018)
Wang, T.; Yang, Y.; Gu, X.-P.; Zhang, X.-C.; Zhang, W.-C.: Coherent cluster recognition based on wavelet fuzzy entropy GG clustering. Power Autom. Equip. 38(07), 140–147 (2018)
Wu, M.; Xu, C.-H.; Wang, C.-S.: Prediction of comprehensive permeability state in lead zinc sintering process based on fuzzy classification variable coefficient. J. East China Univ. Sci. Technol. 07, 825-828+871 (2006)
Alam, S.; Sonbhadra, S.K.; Agarwal, S.: Sample reduction using farthest boundary point estimation (FBPE) for support vector data description (SVDD). Pattern Recognit. Lett. 131, 268–276 (2020)
Li, X.; Zhang, Y.; Han, Y., et al.: Preload state detection for precision spindle bearings based on multi-level classification. J. Mech. Sci. Technol. 34, 4393–4403 (2020)
Tang, S.; Huang, X.; Li, Q., et al.: Optimal sizing and energy management of hybrid energy storage system for high-speed railway traction substation. J. Electr. Eng. Technol. 16, 1743–1754 (2021)
Li, G.; Yinghong, Xu.; Qin, Z.: Fenchel-Lagrange duality for DC infinite programs with inequality constraints. J. Comput. Appl. Math. 391, 0377–0427 (2021)
Zhang, J.; Wang, Y.; Li, Q.; Wang, B.: Using a dynamically selective support vector data description model to discover novelties in the control system of electric arc furnace. Measur. Control 53(7–8), 1049–1058 (2020)
Funding
The funding was provided by National Natural Science Foundation of China (61572416), Hunan Province Natural Science Zhuzhou United Foundation (2020JJ6009), Postgraduate Scientific Research Innovation Project of Hunan Province (QL20210153), Key Laboratory Open Project Fund of Disaster Prevention and Mitigation for Power Grid Transmission and Transformation Equipment.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Yi, L., Sun, T., Zhao, J. et al. Identification of Catenary Performance Degradation Based on Gath Geva Clustering and Improved Support Vector Date Description. Arab J Sci Eng 47, 13765–13780 (2022). https://doi.org/10.1007/s13369-021-06393-x
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s13369-021-06393-x