1D CNN Based Detection and Localisation of Defective Droppers in Railway Catenary
Abstract
:1. Introduction
- (a)
- The impact of dropper defects on railway pantograph–catenary interaction is analysed, and the impact of varying degrees of damage to each dropper is categorised.
- (b)
- An integrated 1D CNN is used to improve classification performance compared with a conventional 1D CNN. Approaches including randomly searching the optimal hyper-parameters and K-fold cross-validation are considered to prevent overfitting and ensure model performance regardless of the training data subset selected.
- (c)
- The ability of the 1D CNN-based method to evaluate the degree of damage to catenary droppers and locate the position of defective droppers within a catenary system is demonstrated.
2. Pantograph–Catenary System Modelling
3. Simulations and Damage Classification
3.1. Static Analysis
3.2. Model Validation and Dynamic Simulation
3.3. Dropper Damage Categorisation
4. Fault Classification through CNNs
4.1. Structure of the Integrated 1D CNN Method
4.2. Result Analysis
4.3. Hyper-Parameter Tuning Technique
4.4. Performance Evaluation
5. Results Analysis and Discussion
6. Conclusions
Author Contributions
Funding
Data Availability Statement
Acknowledgments
Conflicts of Interest
References
- Koseki, T. Technical trends of railway traction in the world. In Proceedings of the 2010 International Power Electronics Conference-ECCE ASIA, Sapporo, Japan, 21–24 June 2010; pp. 2836–2841. [Google Scholar]
- International Union of Railway. UIC STATISTICS—Length of Electrified Lines. Available online: https://uic-stats.uic.org/ (accessed on 14 January 2023).
- Collina, A.; Fossati, F.; Papi, M.; Resta, F. Impact of overhead line irregularity on current collection and diagnostics based on the measurement of pantograph dynamics. Proc. Inst. Mech. Eng. Part F J. Rail Rapid Transit 2007, 221, 547–559. [Google Scholar] [CrossRef]
- Van, O.V.; Massat, J.-P.; Balmes, E. Waves, modes and properties with a major impact on dynamic pantograph-catenary interaction. J. Sound Vib. 2017, 402, 51–69. [Google Scholar] [CrossRef]
- Vesali, F.; Rezvani, M.A.; Molatefi, H.; Hecht, M. Static form-finding of normal and defective catenaries based on the analytical exact solution of the tensile Euler–Bernoulli beam. Proc. Inst. Mech. Eng. Part F J. Rail Rapid Transit 2019, 233, 691–700. [Google Scholar] [CrossRef]
- Song, Y.; Liu, Z.; Rønnquist, A.; Nåvik, P.; Liu, Z. Contact Wire Irregularity Stochastics and Effect on High-Speed Railway Pantograph–Catenary Interactions. IEEE Trans. Instrum. Meas. 2020, 69, 8196–8206. [Google Scholar] [CrossRef]
- Song, Y.; Liu, Z.; Lu, X. Dynamic performance of high-speed railway overhead contact line interacting with pantograph considering local dropper defect. IEEE Trans. Veh. Technol. 2020, 69, 5958–5967. [Google Scholar] [CrossRef]
- Song, Y.; Wang, H.; Liu, Z. An Investigation on the Current Collection Quality of Railway Pantograph-Catenary Systems with Contact Wire Wear Degradations. IEEE Trans. Instrum. Meas. 2021, 70, 1–11. [Google Scholar] [CrossRef]
- Bruni, S.; Bucca, G.; Carnevale, M.; Collina, A.; Facchinetti, A. Pantograph–catenary interaction: Recent achievements and future research challenges. Int. J. Rail Transp. 2018, 6, 57–82. [Google Scholar] [CrossRef]
- Chen, J.; Liu, Z.; Wang, H.; Núñez, A.; Han, Z. Automatic Defect Detection of Fasteners on the Catenary Support Device Using Deep Convolutional Neural Network. IEEE Trans. Instrum. Meas. 2017, 67, 257–269. [Google Scholar] [CrossRef] [Green Version]
- Zhong, J.; Liu, Z.; Han, Z.; Han, Y.; Zhang, W. A CNN-based defect inspection method for catenary split pins in high-speed railway. IEEE Trans. Instrum. Meas. 2018, 68, 2849–2860. [Google Scholar] [CrossRef]
- Lyu, Y.; Han, Z.; Zhong, J.; Li, C.; Liu, Z. A Generic Anomaly Detection of Catenary Support Components Based on Generative Adversarial Networks. IEEE Trans. Instrum. Meas. 2019, 69, 2439–2448. [Google Scholar] [CrossRef]
- Zhong, J.; Liu, Z.; Yang, C.; Wang, H.; Gao, S.; Nunez, A. Adversarial Reconstruction Based on Tighter Oriented Localization for Catenary Insulator Defect Detection in High-Speed Railways. IEEE Trans. Intell. Transp. Syst. 2020, 23, 1109–1120. [Google Scholar] [CrossRef]
- Liu, W.; Liu, Z.; Wang, H.; Han, Z. An Automated Defect Detection Approach for Catenary Rod-Insulator Textured Surfaces Using Unsupervised Learning. IEEE Trans. Instrum. Meas. 2020, 69, 8411–8423. [Google Scholar] [CrossRef]
- Liu, W.; Liu, Z.; Li, Y.; Wang, H.; Yang, C.; Wang, D.; Zhai, D. An Automatic Loose Defect Detection Method for Catenary Bracing Wire Components Using Deep Convolutional Neural Networks and Image Processing. IEEE Trans. Instrum. Meas. 2021, 70, 1–14. [Google Scholar] [CrossRef]
- Tan, P.; Li, X.; Wu, Z.; Ding, J.; Ma, J.; Chen, Y.; Fang, Y.; Ning, Y. Multialgorithm Fusion Image Processing for High Speed Railway Dropper Failure–Defect Detection. IEEE Trans. Syst. Man Cybern. Syst. 2021, 51, 4466–4478. [Google Scholar] [CrossRef]
- Song, Y.; Rønnquist, A.; Jiang, T.; Nåvik, P. Identification of short-wavelength contact wire irregularities in electrified railway pantograph–catenary system. Mech. Mach. Theory 2021, 162, 104338. [Google Scholar] [CrossRef]
- Wang, H.; Liu, Z.; Song, Y.; Lu, X.; Han, Z.; Zhang, J.; Wang, Y. Detection of Contact Wire Irregularities Using a Quadratic Time–Frequency Representation of the Pantograph–Catenary Contact Force. IEEE Trans. Meas. 2016, 65, 1385–1397. [Google Scholar] [CrossRef]
- Wang, H.; Liu, Z.; Nunez, A.; Dollevoet, R. Entropy-Based Local Irregularity Detection for High-Speed Railway Catenaries with Frequent Inspections. IEEE Trans. Instrum. Meas. 2018, 68, 3536–3547. [Google Scholar] [CrossRef]
- Zhou, N.; Yang, W.; Liu, J.; Zhang, W.; Wang, D. Investigation on monitoring system for pantograph and catenary based on condition-based recognition of pantograph. Shock. Vib. 2019, 2019, 3839191. [Google Scholar] [CrossRef]
- Collina, A.; Bruni, S. Numerical Simulation of Pantograph-Overhead Equipment Interaction. Veh. Syst. Dyn. 2002, 38, 261–291. [Google Scholar] [CrossRef]
- Paik, J.-S.; Park, C.-K.; Kim, Y.-G.; Kim, K.-H. A study on the measuring system of contact force of pantograph for the high-speed train. J. Adv. Mech. Des. Syst. Manuf. 2012, 6, 140–148. [Google Scholar] [CrossRef] [Green Version]
- Schröder, K.; Ecke, W.; Kautz, M.; Willett, S.; Jenzer, M.; Bosselmann, T. An approach to continuous on-site monitoring of contact forces in current collectors by a fiber optic sensing system. Opt. Lasers Eng. 2013, 51, 172–179. [Google Scholar] [CrossRef]
- Finner, L.; Poetsch, G.; Sarnes, B.; Kolbe, M. Program for catenary–pantograph analysis, PrOSA statement of methods and validation according EN 50318. Veh. Syst. Dyn. 2015, 53, 305–313. [Google Scholar] [CrossRef]
- Nåvik, P.; Rønnquist, A.; Stichel, S. Variation in predicting pantograph–catenary interaction contact forces, numerical simulations and field measurements. Veh. Syst. Dyn. 2017, 55, 1265–1282. [Google Scholar] [CrossRef]
- Bruni, S.; Ambrosio, J.; Carnicero, A.; Cho, Y.H.; Finner, L.; Ikeda, M.; Kwon, S.Y.; Massat, J.-P.; Stichel, S.; Tur, M.; et al. The results of the pantograph–catenary interaction benchmark. Veh. Syst. Dyn. 2015, 53, 412–435. [Google Scholar] [CrossRef]
- Beagles, A.; Fletcher, D.; Peffers, M.; Mak, P.; Lowe, C. Validation of a new model for railway overhead line dynamics. Proc. Inst. Civ. Eng. Transp. 2016, 169, 339–349. [Google Scholar] [CrossRef] [Green Version]
- BS EN 50318:2002; Railway Applications—Current Collection Systems—Validation of Simulation of the Dynamic Interaction between Pantograph and Overhead Contact Line. British Standards Institution: London, UK, 2002.
- LeCun, Y.; Boser, B.; Denker, J.; Henderson, D.; Howard, R.E.; Hubbard, W.E. Handwritten digit recognition with a back-propagation network. In Advances in Neural Information Processing Systems; Morgan Kaufmann: Burlington, MA, USA, 1989; pp. 396–404. [Google Scholar]
- Scherer, D.; Müller, A.; Behnke, S. Evaluation of pooling operations in convolutional architectures for object recognition. Int. Conf. Artif. Neural Netw. 2010, 6354, 92–101. [Google Scholar]
- Zhang, D.; Stewart, E.; Ye, J. Roller bearing degradation assessment based on a deep MLP convolution neural network considering outlier regions. IEEE Trans. Instrum. Meas. 2019, 69, 2996–3004. [Google Scholar] [CrossRef]
- Zhang, D.; Stewart, E.; Entezami, M.; Roberts, C.; Yu, D. Intelligent acoustic-based fault diagnosis of roller bearings using a deep graph convolutional network. Measurement 2020, 156, 156. [Google Scholar] [CrossRef]
- Schmidhuber, J. Deep Learning in neural networks: An overview. Neural Netw. 2015, 61, 85–117. [Google Scholar] [CrossRef] [Green Version]
- Kiranyaz, S.; Avci, O.; Abdeljaber, O.; Ince, T.; Gabbouj, M.; Inman, D.J. 1D convolutional neural networks and applications: A survey. Mech. Syst. Signal Process. 2021, 151, 107398. [Google Scholar] [CrossRef]
- Chen, Y.Q.; Fink, O.; Sansavini, G. Combined fault location and classification for power transmission lines fault diagnosis with integrated feature extraction. IEEE Trans. Ind. Electron. 2017, 65, 561–569. [Google Scholar] [CrossRef]
- Duan, H.; Dixon, R.; Stewart, E. A disturbance observer based lumped-mass catenary model for active pantograph design and validation. Veh. Syst. Dyn. 2022, 61, 1565–1582. [Google Scholar] [CrossRef]
- EN 50317:2012; Railway Applications—Current Collection Systems—Requirements for and Validation of Measurements of the Dynamic Interaction between Pantograph and Overhead Contact Line. British Standards Institution: London, UK, 2012.
- Cheadle, C.; Vawter, M.P.; Freed, W.J.; Becker, K.G. Analysis of microarray data using Z score transformation. J. Mol. Diagn. 2003, 5, 73–81. [Google Scholar] [CrossRef] [PubMed] [Green Version]
- Syed, A.R. A Review of Cross Validation and Adaptive Model Selection. Master’s Thesis, Department of Mathematics and Statistics, Georgia State University, Atlanta, GA, USA, 2011. [Google Scholar]
- Stone, M. Cross-validatory choice and assessment of statistical predictions. J. R. Stat. Soc. Ser. B 1974, 36, 111–133. [Google Scholar] [CrossRef]
- Esmaeelzadeh, S.R.; Adib, A.; Alahdin, S. Long-term streamflow forecasts by Adaptive Neuro-Fuzzy Inference System using satellite images and K-fold cross-validation (Case study: Dez, Iran). KSCE J. Civ. Eng. 2015, 19, 2298–2306. [Google Scholar] [CrossRef]
- Burman, P. A comparative study of ordinary cross-validation, v-fold cross-validation and the repeated learning-testing methods. Biometrika 1989, 76, 503–514. [Google Scholar] [CrossRef] [Green Version]
- Bergstra, J.; Bengio, Y. Random Search for Hyper-Parameter Optimization. J. Mach. Learn. Res. 2015, 13, 281–305. [Google Scholar]
- He, K.; Zhang, X.; Ren, S.; Sun, J. Deep residual learning for image recognition. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA, 26 June–1 July 2016; pp. 770–778. [Google Scholar]
- Glorot, X.; Bengio, Y. Understanding the difficulty of training deep feedforward neural networks. In Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics, JMLR Workshop and Conference Proceedings, Sardinia, Italy, 13–15 May 2010; pp. 249–256. [Google Scholar]
- Mishra, A.; Reddy, U.S. A novel approach for churn prediction using deep learning. In Proceedings of the 2017 IEEE International Conference on Computational Intelligence and Computing Research (ICCIC), Coimbatore, India, 14–16 December 2017; pp. 1–4. [Google Scholar]
- Šimundić, A.-M. Measures of diagnostic accuracy: Basic definitions. EJIFCC 2009, 19, 203–211. [Google Scholar]
- Turnbull, D.; Barrington, L.; Torres, D.; Lanckriet, G. Semantic annotation and retrieval of music and sound effects. IEEE Trans. Audio Speech Lang. Process. 2008, 16, 467–476. [Google Scholar] [CrossRef] [Green Version]
- Huang, H.; Xu, H.; Wang, X.; Silamu, W. Maximum F1-score discriminative training criterion for automatic mispronunciation detection. IEEE/ACM Trans. Audio Speech Lang. Process. 2015, 23, 787–797. [Google Scholar] [CrossRef]
Model | Component | Parameter | Value |
---|---|---|---|
Lumped-mass pantograph | Lower frame | Mass (kg) | 6 |
Spring coefficient (N/m) | 160 | ||
Damper coefficient (Ns/m) | 100 | ||
Upper frame | Mass (kg) | 9 | |
Spring coefficient (N/m) | 1.55 × 104 | ||
Damper coefficient (Ns/m) | 0.1 | ||
Pantograph head | Mass (kg) | 7.5 | |
Spring coefficient (N/m) | 7 × 103 | ||
Damper coefficient (Ns/m) | 45 | ||
FE catenary | Span structure | Span length (m) | 60 |
Dropper position (m) | [5; 10.5; 17; 23.5; 30; 36.5; 43; 49.5; 55] | ||
Dropper | Elasticity in extension (N/m) | 1 × 105 | |
Elasticity in compression (N/m) | 0 | ||
Contact wire | Steady arm stiffness (N/m) | 300 | |
Bending stiffness (Nm2) | 195 | ||
Density (kg/m) | 1.35 | ||
Tension (N) | 2 × 104 | ||
Messenger wire | Suspension stiffness (N/m) | 5 × 104 | |
Bending stiffness (Nm2) | 131.7 | ||
Density (kg/m) | 1.07 | ||
Tension (N) | 1.6 × 104 | ||
Wire damping coefficients | alpha (s−1) (proportional index to mass) | 0.0125 | |
beta (s) (proportional index to stiffness) | 1 × 10−4 |
Output | Simulation Results | EN 50318 Requirements |
---|---|---|
Mean force (N) | 116.65 | 110–120 |
Force standard deviation (N) | 27.25 | 26–31 |
Maximum force (N) | 185.94 | 175–210 |
Minimum force (N) | 54.31 | 50–75 |
Category | Damage Degree (%) | ||||||||
---|---|---|---|---|---|---|---|---|---|
D1 | D2 | D3 | D4 | D5 | D6 | D7 | D8 | D9 | |
Healthy (I < 1%) | <51 | <56.5 | <57.5 | <72 | <27 | <81.5 | <41 | <82.5 | <45 |
Low risk (1% ≤ I < 3%) | 51~68 | 56.5~88 | 57.5~100 | ≥72 | 27~62.5 | 81.5~89.5 | 41~93 | 82.5~99 | 45~68.5 |
High risk (I ≥ 3%) | ≥68 | ≥88 | ≥100 | None | ≥62.5 | ≥89.5 | ≥93 | ≥99 | ≥68.5 |
Dataset Details | Quantity | ||||||||
---|---|---|---|---|---|---|---|---|---|
Size of dataset | 2173 | ||||||||
Damage degree labels | 482 (high risk) | 672 (low risk) | 1019 (healthy) | ||||||
Dropper position labels | 234 (D1) | 225 (D2) | 249 (D3) | 200 (D4) | 200 (D5) | 292 (D6) | 245 (D7) | 281 (D8) | 247 (D9) |
Data used for K-fold | 1996 | ||||||||
Data used for testing | 177 | ||||||||
Features of each sample | 1200 |
CNN Hyper-Parameters | Selection Range |
---|---|
Number of filters in the convolutional layers | 64–1536 |
CNN layers | 1–5 |
Weight decay | 1 × 10−7–1 × 10−1 |
Learning rate | 1 × 10−6–1 × 10−1 |
Number of filters in the dense layers | 10–512 |
Optimal hyper-parameters of Sub-model 1 | CNN layers | 3 |
Number of filters in the first convolutional layer | 64 | |
Number of filters in the second convolutional layer | 928 | |
Number of filters in the third convolutional layer | 896 | |
Weight initialization | 3.9753 × 10−5 | |
Learning rate | 1.0379 × 10−3 | |
Number of filters in the dense layers | 150 | |
Kernel initialiser | He normal initialiser | |
Activation function | Relu | |
Optimal hyper-parameter of Sub-model 2 | CNN layers | 2 |
Number of filters in the first convolutional layer | 128 | |
Number of filters in the second convolutional layer | 1024 | |
Weight initialization | 1.1813 × 10−5 | |
Learning rate | 2.5224 × 10−4 | |
Number of filters in the dense layers | 120 | |
Kernel initialiser | Glorot uniform initialiser | |
Activation function | Relu | |
Optimal hyper-parameter of conventional 1D CNN | CNN layers | 5 |
Number of filters in the first convolutional layer | 320 | |
Number of filters in the second convolutional layer | 288 | |
Number of filters in the third convolutional layer | 704 | |
Number of filters in the fourth convolutional layer | 864 | |
Number of filters in the fifth convolutional layer | 576 | |
Weight initialization | 1.3829 × 10−5 | |
Learning rate | 4.1412 × 10−3 | |
Number of filters in the dense layers | 128 | |
Kernel initialiser | Glorot uniform initialiser | |
Activation function | Relu |
Noise power | Accuracy (%) | ||
Sub-model 1 | Sub-model 2 | Integrated model | |
5 dB | 96.33 | 100 | 96.33 |
10 dB | 95.28 | 100 | 95.28 |
15 dB | 95.00 | 100 | 95.00 |
20 dB | 93.94 | 100 | 93.94 |
25 dB | 88.76 | 97.7 | 86.72 |
Noise power | F1-score (%) | ||
Sub-model 1 | Sub-model 2 | Integrated model | |
5 dB | 95.88 | 100 | 95.88 |
10 dB | 95.08 | 100 | 95.08 |
15 dB | 95.83 | 100 | 95.83 |
20 dB | 94.84 | 100 | 94.84 |
25 dB | 88.87 | 96.60 | 86.73 |
Noise power | Precision (%) | ||
Sub-model 1 | Sub-model 2 | Integrated model | |
5 dB | 96.10 | 100 | 96.10 |
10 dB | 95.07 | 100 | 95.07 |
15 dB | 95.04 | 100 | 95.04 |
20 dB | 93.93 | 100 | 93.93 |
25 dB | 89.19 | 97.94 | 87.35 |
Noise power | Recall (%) | ||
Sub-model 1 | Sub-model 2 | Integrated model | |
5 dB | 95.80 | 100 | 95.80 |
10 dB | 95.25 | 100 | 95.25 |
15 dB | 94.69 | 100 | 94.69 |
20 dB | 93.58 | 100 | 93.58 |
25 dB | 88.68 | 97.55 | 86.49 |
Noise power | Accuracy (%) | F1-Score (%) | ||
Conventional | Integrated | Conventional | Integrated | |
5 dB | 91.24 | 96.33 | 93.26 | 95.88 |
10 dB | 90.57 | 95.28 | 92.31 | 95.08 |
15 dB | 89.70 | 95.00 | 90.71 | 95.83 |
20 dB | 88.46 | 93.94 | 87.69 | 94.84 |
25 dB | 85.28 | 86.72 | 83.17 | 86.73 |
Noise power | Precision (%) | Recall (%) | ||
Conventional | Integrated | Conventional | Integrated | |
5 dB | 95.28 | 96.10 | 94.62 | 95.80 |
10 dB | 94.26 | 95.07 | 93.74 | 95.25 |
15 dB | 93.82 | 95.04 | 91.77 | 94.69 |
20 dB | 90.42 | 93.93 | 88.49 | 93.58 |
25 dB | 89.28 | 87.35 | 82.89 | 86.49 |
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |
© 2023 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Yang, J.; Duan, H.; Li, L.; Stewart, E.; Huang, J.; Dixon, R. 1D CNN Based Detection and Localisation of Defective Droppers in Railway Catenary. Appl. Sci. 2023, 13, 6819. https://doi.org/10.3390/app13116819
Yang J, Duan H, Li L, Stewart E, Huang J, Dixon R. 1D CNN Based Detection and Localisation of Defective Droppers in Railway Catenary. Applied Sciences. 2023; 13(11):6819. https://doi.org/10.3390/app13116819
Chicago/Turabian StyleYang, Jingyuan, Huayu Duan, Linxiao Li, Edward Stewart, Junhui Huang, and Roger Dixon. 2023. "1D CNN Based Detection and Localisation of Defective Droppers in Railway Catenary" Applied Sciences 13, no. 11: 6819. https://doi.org/10.3390/app13116819
APA StyleYang, J., Duan, H., Li, L., Stewart, E., Huang, J., & Dixon, R. (2023). 1D CNN Based Detection and Localisation of Defective Droppers in Railway Catenary. Applied Sciences, 13(11), 6819. https://doi.org/10.3390/app13116819