Axis Orbit Recognition of the Hydropower Unit Based on Feature Combination and Feature Selection
Abstract
:1. Introduction
2. Theoretical Background
2.1. Random Forest Importance
2.2. Gravitational Search Algorithm
2.3. Support Vector Machine
3. The Proposed Method
3.1. Axis Orbit Image Processing
3.2. Feature Extraction and Combination of Axis Orbit Samples
3.3. Feature Selection
3.4. Axis Orbit Recognition
4. Case study and Result Analysis
4.1. Data Description
4.2. Data Processing
4.3. Analysis of Results
4.3.1. Recognition Result with Various Feature Sets
4.3.2. Comparison Experiments
4.3.3. Feature Selection
5. Conclusions
Author Contributions
Funding
Institutional Review Board Statement
Informed Consent Statement
Data Availability Statement
Conflicts of Interest
References
- Zheng, Y.; Chen, Q.; Yan, D.; Zhang, H. Equivalent circuit modeling of large hydropower plants with complex tailrace system for ultra-low frequency oscillation analysis. Appl. Math. Model. 2022, 103, 176–194. [Google Scholar] [CrossRef]
- Shan, Y.; Liu, J.; Xu, Y.; Zhou, J. A combined multi-objective optimization model for degradation trend prediction of pumped storage unit. Measurement 2021, 169, 108373. [Google Scholar] [CrossRef]
- Liu, W.; Zheng, Y.; Ma, Z.; Tian, B.; Chen, Q. An intelligent fault diagnosis scheme for hydropower units based on the pattern recognition of axis orbits. Meas. Sci. Technol. 2023, 34, 025104. [Google Scholar] [CrossRef]
- Zhu, W.; Zhou, J.; Xia, X.; Li, C.; Xiao, J.; Xiao, H.; Zhang, X. A novel KICA-PCA fault detection model for condition process of hydroelectric generating unit. Measurement 2014, 58, 197–206. [Google Scholar] [CrossRef]
- Liu, H.; Zhou, J.; Xu, Y.; Zheng, Y.; Peng, X.; Jiang, W. Unsupervised fault diagnosis of rolling bearings using a deep neural network based on generative adversarial networks. Neurocomputing 2018, 315, 412–424. [Google Scholar] [CrossRef]
- Suganthi, S.T.; Vinayagam, A.; Veerasamy, V.; Deepa, A.; Abouhawwash, M.; Thirumeni, M. Detection and classification of multiple power quality disturbances in Microgrid network using probabilistic based intelligent classifier. Sustain. Energy Technol. Assess. 2021, 47, 13. [Google Scholar] [CrossRef]
- Wu, H.; Zhou, J.; Xie, C.; Zhang, J.; Huang, Y. Two-dimensional time series sample entropy algorithm: Applications to rotor axis orbit feature identification. Mech. Syst. Signal Process. 2020, 147, 107123. [Google Scholar]
- Al-Obaidi, A.R. Detection of Cavitation Phenomenon within a Centrifugal Pump Based on Vibration Analysis Technique in both Time and Frequency Domains. Exp. Technol. 2020, 44, 329–347. [Google Scholar] [CrossRef]
- Wang, Y.; Zheng, L.; Gao, Y.; Li, S. Vibration Signal Extraction Based on FFT and Least Square Method. IEEE Access 2020, 8, 224092–224107. [Google Scholar] [CrossRef]
- Zhou, J.; Shan, Y.; Liu, J.; Xu, Y.; Zheng, Y. Degradation Tendency Prediction for Pumped Storage Unit Based on Integrated Degradation Index Construction and Hybrid CNN-LSTM Model. Sensors 2020, 20, 4277. [Google Scholar] [CrossRef]
- Kim, H.H.; Rakibuzzaman, M.; Suh, S.H. Flow and Fast Fourier Transform Analyses for Tip Clearance Effect in an Operating Kaplan Turbine. Energies 2019, 12, 264. [Google Scholar] [CrossRef] [Green Version]
- Xiao, Z.; Sun ZSong, L.; Zhang, X.; Malik, O.P. Simulated annealing-wavelet neural network for vibration fault diagnosis of hydro-turbine generating unit. J. Optoelectron. Adv. M. 2015, 17, 734–740. [Google Scholar]
- Mohanty, S.; Gupta, K.K.; Raju, K.S. Hurst based vibro-acoustic feature extraction of bearing using EMD and VMD. Measurement 2018, 117, 200–220. [Google Scholar] [CrossRef]
- An, X.; Pan, L.; Zhang, F. Analysis of hydropower unit vibration signals based on variational mode decomposition. J. Vib. Control. 2017, 23, 1938–1953. [Google Scholar] [CrossRef]
- Zhang, Y.; Xie, X.; Fu, W.; Chen, X.; Hu, S.; Zhang, L.; Xia, Y. An Optimal Combining Attack Strategy Against Economic Dispatch of Integrated Energy System. IEEE Trans. Circuits Syst. II Express Briefs 2022, 70, 246–250. [Google Scholar] [CrossRef]
- Zhang, Y.; Wei, L.; Fu, W.; Chen, X.; Hu, S. Secondary frequency control strategy considering DoS attacks for MTDC system. Electr. Power Syst. Res. 2023, 214, 108888. [Google Scholar] [CrossRef]
- Xu, Y.; Wang, Z. On Fuzzy Logic in Hydroturbine Temperature Fault Diagnosis in HESS. Adv. Mater. Res. 2011, 225–226, 39–42. [Google Scholar] [CrossRef]
- Zhao, W.; Wang, L. SVM multi-class classification based on binary tree for fault diagnosis of hydropower units. Information 2012, 15, 4615–4620. [Google Scholar]
- Feng, Z.; Niu, W.; Zhang, R.; Wang, S.; Cheng, C. Operation rule derivation of hydropower reservoir by k-means clustering method and extreme learning machine based on particle swarm optimization. J. Hydrol. 2019, 576, 229–238. [Google Scholar] [CrossRef]
- Cheng, J.; Zhu, C.; Fu, W.; Wang, C.; Sun, J. An Imitation medical diagnosis method of hydro-turbine generating unit based on Bayesian network. Trans. Inst. Meas. Control. 2019, 41, 3406–3420. [Google Scholar] [CrossRef]
- Zheng, Y.; Guo, B.; Chen, Z.; Li, C. A Fourier Descriptor of 2D Shapes Based on Multiscale Centroid Contour Distances Used in Object Recognition in Remote Sensing Images. Sensors 2019, 19, 486. [Google Scholar] [CrossRef] [Green Version]
- Paul, S.K.; Bouakaz, S.; Rahman, C.M.; Uddin, M.S. Component-based face recognition using statistical pattern matching analysis. Pattern Anal. Appl. 2021, 24, 299–319. [Google Scholar] [CrossRef]
- Maji, P.; Chatterjee, S.; Chakraborty, S.; Kausar, N.; Samanta, S. Effect of Euler number as a feature in gender recognition system from offline handwritten signature using neural networks. In Proceedings of the International Conference on Computing for Sustainable Global Development, New Delhi, India, 11–13 March 2015; IEEE: Piscataway, NJ, USA, 2015. [Google Scholar]
- Chen, X.; Zhang, K. Application of a new moment invariant to identification of axis orbit in hydro-generator unit. J. Huazhong Univ. Sci. Technol. (Nat. Sci. Ed.) 2006, 34, 79–81. [Google Scholar]
- Chen, X.; Yan, H.; Sun, J. Research on the Identification of Axis Orbit in Hydro-generator Unit Base on PSO-BP and Combined Moment Invariants. J. Vib. Meas. Diagn. 2016, 1, 108–114. [Google Scholar]
- Xue, Y.; Wang, Y.; Zhao, H. Axis orbit automatic identification on time-series similarity mining for hydropower units. J. Drain. Irrig. Mach. Eng. 2017, 35, 1054–1057. [Google Scholar]
- Yuan, Q.; Sun, D.; Fan, W. Automatic Identification Method of Axis Orbits Based on D-S Evidential Theory. Mach. Tool Hydraul. 2017, 45, 167–171+139, In Chinese. [Google Scholar]
- Pang, X.; Shao, J.; Xue, X.; Jiang, W. Application of axis orbit image optimization in fault diagnosis for rotor system. Int. J. Rotating Mach. 2020, 2020, 13. [Google Scholar] [CrossRef] [Green Version]
- Gan, M.; Zhang, L. Iteratively local fisher score for feature selection. Appl. Intell. 2021, 51, 6167–6181. [Google Scholar] [CrossRef]
- Liaw, A.; Wiener, M. Classification and Regression by random Forest. R News 2002, 23, 18–22. [Google Scholar]
- Shakir, M. Feature Selection of Time Series MODIS Data for Early Crop Classification Using Random Forest: A Case Study in Kansas, USA. Remote Sens. 2015, 7, 5347–5369. [Google Scholar]
- Rashedi, E.; Nezamabadi-Pour, H.; Saryazdi, S. GSA: A Gravitational Search Algorithm. Inf. Sci. 2009, 179, 2232–2248. [Google Scholar] [CrossRef]
- Zidi, S.; Moulahi, T.; Alaya, B. Fault Detection in Wireless Sensor Networks Through SVM Classifier. IEEE Sens. J. 2018, 18, 340–347. [Google Scholar] [CrossRef]
- Wang, C.; Zhou, J.; Kou, P.; Luo, Z.; Zhang, Y. Identification of shaft orbit for hydraulic generator unit using chain code and probability neural network. Appl. Soft Comput. 2012, 12, 423–429. [Google Scholar] [CrossRef]
Fault Status | Imbalance | Oil-Film Whirl | Misalignment | Imbalance and Misalignment |
---|---|---|---|---|
Axis orbit | Ellipse | Outer 8 | Banana | Inner 8 |
Feature Set | Merge Contour | Moment | Geometric | Multidimensional | |
---|---|---|---|---|---|
Axis Orbit | |||||
Original | 100 | 100 | 99.32 | 99.83 | |
SNR_30 | 96.89 | 98.29 | 99.54 | 99.72 | |
SNR_25 | 95.17 | 98.06 | 98.45 | 99.79 | |
SNR_20 | 89.04 | 97.17 | 97.4 | 99.68 |
Axis Orbit | Classifier | Accuracy(%) | |||
---|---|---|---|---|---|
Contour | Moment | Geometric | Multidimensional | ||
Original | RF | 96.92 | 97.81 | 99.06 | 99.95 |
BP | 93.85 | 97.64 | 99.52 | 99.8 | |
SVM | 95.06 | 97.42 | 98.58 | 99.83 | |
GSA–SVM | 97.74 | 98.92 | 100 | 100 | |
SNR = 30 | RF | 95.69 | 96.94 | 98.8 | 99.7 |
BP | 91.52 | 97.13 | 99.33 | 99.69 | |
SVM | 94.01 | 96.87 | 98.34 | 99.31 | |
GSA–SVM | 96.89 | 98.29 | 99.54 | 99.72 | |
SNR = 25 | RF | 93.3 | 96.2 | 97.14 | 99.56 |
BP | 88.67 | 96.59 | 97.96 | 99.58 | |
SVM | 88.82 | 95.9 | 96.08 | 99.01 | |
GSA–SVM | 95.17 | 98.06 | 98.45 | 99.79 | |
SNR = 20 | RF | 88.04 | 94.66 | 97.16 | 98.98 |
BP | 73.64 | 95.32 | 96.8 | 98.94 | |
SVM | 72.38 | 95.62 | 95.52 | 99.05 | |
GSA–SVM | 89.04 | 97.17 | 97.4 | 99.68 |
Original | SNR30 | SNR25 | SNR20 | |||||
---|---|---|---|---|---|---|---|---|
Accuracy (%) | Time (s) | Accuracy (%) | Time (s) | Accuracy (%) | Time(s) | Accuracy (%) | Time (s) | |
n = 24 | 99.91 | 14.637 | 99.72 | 15.6380 | 99.79 | 15.3885 | 99.68 | 12.3085 |
n = 10 | 99.87 | 7.4758 | 99.81 | 7.6680 | 99.44 | 5.4476 | 99.1 | 6.5624 |
n = 8 | 100 | 6.6776 | 99.79 | 5.4589 | 99.57 | 4.4267 | 99.03 | 5.0380 |
n = 5 | 100 | 2.4714 | 99.75 | 2.9931 | 99.3 | 3.2378 | 92.91 | 4.3200 |
n = 3 | 95.43 | 2.1678 | 93.79 | 2.2439 | 95.16 | 2.5835 | 91.34 | 4.2669 |
Data Set | Method | Recognition Accuracy with Different Selected Feature Number | |||||||
---|---|---|---|---|---|---|---|---|---|
10 | 8 | 7 | 6 | 5 | 4 | 3 | 2 | ||
original | mRMR | 99.89 | 99.88 | 99.91 | 99.94 | 99.13 | 98.87 | 96.78 | 95.53 |
laplacian | 99.92 | 99.85 | 99.06 | 95.89 | 95.9 | 93.12 | 92.72 | 92.18 | |
RF-Fisher | -- | 99.87 | -- | 100 | -- | -- | 100 | 95.43 | |
SNR30 | mRMR | 99.63 | 99.63 | 99.61 | 99.62 | 99.61 | 98.52 | 96.72 | 94.23 |
laplacian | 99.85 | 99.81 | 98.97 | 95.06 | 94.89 | 92.53 | 92.13 | 91.63 | |
RF-Fisher | -- | 99.81 | -- | -- | 99.79 | 99.75 | -- | 93.79 | |
SNR25 | mRMR | 99.77 | 99.92 | 99.95 | 99.91 | 97.7 | 97.46 | 96.94 | 94.66 |
laplacian | 99.82 | 99.41 | 99.38 | 98.84 | 94.04 | 94.71 | 94.78 | 90.86 | |
RF-Fisher | -- | -- | 99.44 | -- | 99.57 | 99.3 | -- | 95.16 | |
SNR20 | mRMR | 99.3 | 99.26 | 99.25 | 99.36 | 98.48 | 94.44 | 94.2 | 91.52 |
laplacian | 99.74 | 96.75 | 96.93 | 96.62 | 96.17 | 96.03 | 93.28 | 87.31 | |
RF-Fisher | -- | 99.1 | -- | -- | 99.03 | -- | 92.91 | 91.34 |
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
Liu, W.; Zheng, Y.; Zhou, X.; Chen, Q. Axis Orbit Recognition of the Hydropower Unit Based on Feature Combination and Feature Selection. Sensors 2023, 23, 2895. https://doi.org/10.3390/s23062895
Liu W, Zheng Y, Zhou X, Chen Q. Axis Orbit Recognition of the Hydropower Unit Based on Feature Combination and Feature Selection. Sensors. 2023; 23(6):2895. https://doi.org/10.3390/s23062895
Chicago/Turabian StyleLiu, Wushuang, Yang Zheng, Xuan Zhou, and Qijuan Chen. 2023. "Axis Orbit Recognition of the Hydropower Unit Based on Feature Combination and Feature Selection" Sensors 23, no. 6: 2895. https://doi.org/10.3390/s23062895