Generic placeholder image

Recent Patents on Mechanical Engineering

Editor-in-Chief

ISSN (Print): 2212-7976
ISSN (Online): 1874-477X

Research Article

Abnormal Status Detection of Catenary Based on TSNE Dimensionality Reduction Method and IGWO-LSSVM Model

Author(s): Yi Lingzhi, Yu Guo*, Wang Yahui, Dong Tengfei, Yu Huang and She Haixiang

Volume 16, Issue 3, 2023

Published on: 09 June, 2023

Page: [188 - 202] Pages: 15

DOI: 10.2174/2212797616666230505151008

Price: $65

Abstract

Background: Catenary is a crucial component of an electrified railroad's traction power supply system. There is a considerable incidence of abnormal status and failures due to prolonged outside exposure. Driving safety will be directly impacted if an abnormal status or failure occurs. Currently, catenary detection vehicles are the most often utilized technique for gathering data and identifying faults based on manual experience. However, this technology cannot meet the demands of prompt detection and correction of faults in railways engineering due to its extremely low work efficiency.

Objective: Based on the above, an abnormal status detection method of catenary based on the improved gray wolf (IGWO) algorithm optimized the least squares support vector machine (LSSVM) with the t-distributed stochastic neighbor embedding (TSNE) is proposed in this paper. In order to improve the accuracy of catenary abnormal status detection and shorten the detection time.

Methods: Firstly, the TSNE dimensionality reduction technology is used to reduce the original catenary data to three-dimensional space. Then, in order to address the issue that the parameters of the LSSVM detection model are hard to determine, the improved GWO algorithm is used to optimize the penalty factor and kernel parameter in the LSSVM and establish the TSNE-IGWO-LSSVM catenary abnormal status detection model. Finally, contrasting experimental results of different detection models. The T-distributed Stochastic Domain Embedding (TSNE) is an improved nonlinear dimensionality reduction method based on the Stochastic Neighbor Embedding (SNE). TSNE no longer adopts the distance invariance in linear dimensionality reduction methods such as ISOMAP. TSNE is much better than the linear dimensionality reduction method in the reduction degree of the original dimension. The GWO algorithm, which is frequently used in engineering research, has the advantages of a simple model, great generalization capability, and good optimization performance. The premature convergence is one of the remaining flaws. By applying a good point set to initialize the gray wolf population and the nonlinear control parameters, the gray wolf algorithm is improved in this research. The IGWO algorithm effectively makes up for the problem of balancing the local exploitation and global search capabilities of GWO. Additionally, this IGWO algorithm performs the Cauchy variation operation on the current generation optimal solution to improve population diversity, enlarge the search space, and increase the likelihood of the algorithm escaping the local optimal solution in order to prevent the algorithm from failing the local optimum. The Least Squares Support Vector Machine (LSSVM) is an improved version of the Support Vector Machine (SVM), which replaces the original inequality constraint with a linear least squares criterion for the loss function. The kernel parameters of the RBF function and the penalty factor, these two parameters directly determine the detection effect of LSSVM. In this paper, the IGWO is utilized to adjust and determine the LSSVM parameters in order to enhance the detection capacity of the LSSVM model.

Results: In this paper, in order to minimize the experiment's bias, the training data and the test data are allocated in a ratio of 4:1, the training data are set to 400 groups, and the test data are set to 100 groups. After training the five models, the test data is used to validate and compare the detection capacity of the models. After each of the five detection models was tested ten times, the TSNE-IGWO-LSSVM model is compared with the IGWO-LSSVM model, the TSNE-FA-LSSVM model, the GWO-LSSVM model, and the GWO-ELM model, the results show that the TSNE-IGWO-LSSVM model has the highest average detection accuracy of 97.1% and the shortest running time of 26.9s. For the root mean squared error (RMSE) and the root mean squared error (RMSE), the TSNE-IGWO-LSSVM model is 0.17320 and 2.51% respectively, which is the best among the five models, indicating that it not only has higher detection accuracy but also better convergence of detection accuracy than the other models.

Conclusions: With the thousands of miles of catenary and the complexity of the data, it is crucial to shorten the running time in order to improve the efficiency and ease the burden of the processors. The experiments demonstrate that the TSNE-IGWO-LSSVM detection model can detect the abnormal status of catenary more accurately and quickly, providing a new method for the abnormal status detection of catenary, which has certain application value and engineering significance in the era of fully electrified railways.

Keywords: Catenary, TSNE, IGWO, LSSVM, abnormal status detection.

[1]
Song Y, Antunes P, Pombo J, Liu Z. A methodology to study high-speed pantograph-catenary interaction with realistic contact wire irregularities. Mechanism Mach Theory 2020; 152: 103940.
[http://dx.doi.org/10.1016/j.mechmachtheory.2020.103940]
[2]
Chen R, Lin Y, Jin T. High-speed railway pantograph-catenary anomaly detection method based on depth vision neural network. IEEE Trans Instrum Meas 2022; 71: 1-10.
[http://dx.doi.org/10.1109/TIM.2022.3188042]
[3]
Liu J, Xu JG, Gao LC, Liu QH. Research on defect detection of catenary dropper based on machine vision. J Railw Eng Soc 2022; 39(5): 91-7.
[4]
Zhang F, Tao K, Xie X. Research on Fault Detection Method of Catenary Equipment Based on Deep Learning. 2021; IEEE 2nd International Conference on Information Technology, Big Data and Artificial Intelligence (ICIBA) 2: 478-82.
[5]
Huang C, Zeng Y. The fault diagnosis of catenary system based on the deep learning method in the railway industry. Proceedings of the 5th International Conference on Multimedia and Image Processing 135-40.
[http://dx.doi.org/10.1145/3381271.3381293]
[6]
Fu SP. Research on the detection of electrified railway catenary based on artificial intelligence technology. Electrotechnical Application 2020; 39(9): 51-4.
[7]
Feng W, Zhang G, Yi O, et al. Fault diagnosis of oil-immersed transformer based on TSNE and IBASA- SVM. Recent Pat Mech Eng 2022; 15.
[8]
Hao L, Wu X, Li C, Zhang W. Hemispherical surface defect classification of valve core with a noval semi-supervised learning. Recent Pat Mech Eng 2022; 15(4): 364-75.
[http://dx.doi.org/10.2174/2212797615666220204112342]
[9]
Yi L, Sun T, Zhao J, Xu X, Jiang G, Liu J. Identification of catenary performance degradation based on gath geva clustering and improved support vector date description. Arab J Sci Eng 2022; 47(11): 13765-80.
[http://dx.doi.org/10.1007/s13369-021-06393-x]
[10]
Wu SJ, Feng FZ, Wu ZC, Li B. Research on fault diagnosis method of tank planetary gearbox based on VMD-DE. Shock Vib 2020; 39: 170-9.
[11]
Yi L, Zhao J, Yu W, Liu Y, Yi C, Jiang D. Catenary fault identification based on PSO-ELM. J Phys Conf Ser 2019; 1302(3): 032017.
[http://dx.doi.org/10.1088/1742-6596/1302/3/032017]
[12]
Yi L, Guo Y, Liu N, Zhao J, Li W, Sun J. Health status identification of catenary based on VMD and FA-ELM. J Algorithm Comput Technol 2021; 15.
[http://dx.doi.org/10.1177/17483026211024898]
[13]
Guan S, Huang D, Guo S, Zhao L, Chen H. An improved fault diagnosis approach using LSSVM for complex industrial systems. Machines 2022; 10(6): 443.
[http://dx.doi.org/10.3390/machines10060443]
[14]
Liu CY, Wu H, Wang LP, Zhang Z. Tool wear state identification based on PSO-optimised LS-SVM. Qinghua Daxue Xuebao Ziran Kexue Ban 2017; 57(9): 975-9.
[15]
Yi L, Jiang Z. Short-term power load forecasting based on orthogonal PCA-LPP dimension reduction and IGWO-BiLSTM. Recent Pat Mech Eng 2022; 15.
[16]
Cheng HB, He ZY, Hu HT, Mu XQ, Wang B, Sun YX. Entropy-weighted multi-information integrated assessment of the health status of high-speed rail contact networks. Tiedao Xuebao 2014; 36(3): 19-24.
[17]
Jiang W, Zhou J, Liu H, Shan Y. A multi-step progressive fault diagnosis method for rolling element bearing based on energy entropy theory and hybrid ensemble auto-encoder. ISA Trans 2019; 87: 235-50.
[http://dx.doi.org/10.1016/j.isatra.2018.11.044] [PMID: 30527670]
[18]
Hajibabaee P, Pourkamali-Anaraki F, Hariri-Ardebili MA. An Empirical Evaluation of the t-SNE Algorithm for Data Visualization in Structural Engineering. 20th IEEE International Conference on Machine Learning and Applications (ICMLA), Pasadena, CA, USA, 2021. 1674-80.
[19]
Bemani A, Xiong Q, Baghban A, Habibzadeh S, Mohammadi AH, Doranehgard MH. Modeling of cetane number of biodiesel from fatty acid methyl ester (FAME) information using GA-, PSO-, and HGAPSO- LSSVM models. Renew Energy 2020; 150: 924-34.
[http://dx.doi.org/10.1016/j.renene.2019.12.086]
[20]
Zhang Y, Li R. Short term wind energy prediction model based on data decomposition and optimized LSSVM. Sustain Energy Technol Assess 2022; 52: 102025.
[http://dx.doi.org/10.1016/j.seta.2022.102025]
[21]
Emary E, Yamany W, Hassanien AE, Snasel V. Multi-objective gray-wolf optimization for attribute reduction. Procedia Comput Sci 2015; 65: 623-32.
[http://dx.doi.org/10.1016/j.procs.2015.09.006]
[22]
Nadimi-Shahraki MH, Taghian S, Mirjalili S. An improved grey wolf optimizer for solving engineering problems. Expert Syst Appl 2021; 166: 113917.
[http://dx.doi.org/10.1016/j.eswa.2020.113917]
[23]
Hatta NM, Zain AM, Sallehuddin R, Shayfull Z, Yusoff Y. Recent studies on optimisation method of Grey Wolf Optimiser (GWO): A review (2014–2017). Artif Intell Rev 2019; 52(4): 2651-83.
[http://dx.doi.org/10.1007/s10462-018-9634-2]
[24]
Li Y, Lin X, Liu J. An improved gray wolf optimization algorithm to solve engineering problems. Sustainability 2021; 13(6): 3208.
[http://dx.doi.org/10.3390/su13063208]
[25]
Kumar A, Pant S, Ram M. System reliability optimization using gray wolf optimizer algorithm. Qual Reliab Eng Int 2017; 33(7): 1327-35.
[http://dx.doi.org/10.1002/qre.2107]
[26]
Long W, Wu TB. Improved gray wolf optimisation algorithm for coordinated exploration and development of capabilities. Control and Decision 2017; 32(10): 1749-57.
[27]
Zhao C, Wang B, Sun ZX, Wang X. Optimal capacity allocation for standalone microgrids based on improved gray wolf algorithm. Taiyang Neng Xuebao 2022; 43(1): 256-62.
[28]
Yi L, Zhao J, Yu W, Sun H. A detection fault warning method of catenary based on dimensionality reduction fusion and factor analysis Patent CN109917213B, 2021.

Rights & Permissions Print Cite
© 2024 Bentham Science Publishers | Privacy Policy