Partial Discharge Online Detection for Long-Term Operational Sustainability of On-Site Low Voltage Distribution Network Using CNN Transfer Learning
Abstract
:1. Introduction
- Few studies of PD fault detection in low voltage distribution network;
- Excessive expert diagnosis to obtain high possibilities to cause human errors of PD detection and increase the time and cost maintenance;
- Difference in physical and electrical properties between distribution and transmission networks;
- Development of deep learning models to use artificial PD data generated from the laboratory for developing the model due to insufficient real PD data.
- A field study of PD online detection for long-term operational sustainability of on-site low voltage distribution network;
- An automated PD online detection system for acquiring as many real PD data as possible through the continuous monitoring of PD occurrence;
- Verification of the effectiveness of the CNN transfer-learning models developed using only a small real PD dataset;
- Improved PD detection accuracy of the proposed CNN transfer-learning models compared with benchmark models, such as CNN and support vector machine (SVM) models.
2. Related Studies
- The automated PD online detection system can provide as many real PD data as possible through the continuous monitoring of PD occurrence for on-site low voltage distribution networks.
- The proposed CNN transfer-learning models can obtain improved accuracy compared to benchmark models with only real PD data acquired from the PD detection system.
3. Proposed Method
3.1. PD Online Detection System Architecture
Algorithm 1 PD online detection algorithm. |
|
3.2. PD and Noise Data Patterns
3.3. Proposed Model
- Introducing a previously trained transfer-learning model.
- Freezing them to avoid destroying any of the information for the model.
- Adding some new training layers on top of the frozen layers.
- Training the new layers using a new dataset.
- Fine-tuning, which is the process of adjusting parameters, can achieve meaningful improvements by adjusting parameters.
- ResNet50V2_C1: Baseline frozen model;
- ResNet50V2_C2: The fine-tuning model with modified layers closest to input;
- ResNet50V2_C3: The fine-tuning model with modified layers closest to output.
- MobileNetV2_C1: Baseline frozen model
- MobileNetV2_C2: The fine-tuning model with modified layers closest to input
- MobileNetV2_C3: The fine-tuning model with modified layers closest to output
3.4. Benchmark Model
- Sparse interaction,
- Fewer parameter operation, and
- Lower computation with efficiency.
4. PD Detection Accuracy Results
- True Positive (TP): The data are also PD when the proposed model judges as a PD.
- True Negative (TN): The data are also Noise when the proposed model judges as a Noise.
- False Positive (FP): The data are Noise when the proposed model judges as a PD.
- False Negative (FN): The data are PD when the proposed model judges as a Noise.
5. Discussion
- The PD online detection system was proposed for long-term operational sustainability of on-site low voltage distribution network since there are few studies of PD fault detection for a low voltage distribution network.
- The automated PD online detection system can obtain real PD data through the continuous monitoring of PD occurrence.
- The effectiveness of the proposed transfer-learning models was verified based on the fact that the CNN transfer-learning models developed using small real PD data (126 training samples only) showed improved test accuracy for real PD data (497 test samples) compared with other benchmark models.
- The proposed transfer-learning models (ResNet50V2_C3 and MobileNet50V2_C3) achieved the highest test score (96.2% and 97.4%, respectively) compared with benchmark models (CNN and SVM).
6. Conclusions
Author Contributions
Funding
Institutional Review Board Statement
Informed Consent Statement
Data Availability Statement
Conflicts of Interest
References
- Duan, L.; Hu, J.; Zhao, G.; Chen, K.; He, J.; Wang, S.X. Identification of Partial Discharge Defects Based on Deep Learning Method. IEEE Trans. Power Deliv. 2019, 34, 1557–1568. [Google Scholar] [CrossRef]
- Peng, X.; Yang, F.; Wang, G.; Wu, Y.; Li, L.; Li, Z.; Bhatti, A.A.; Zhou, C.; Hepburn, D.M.; Reid, A.J.; et al. A Convolutional Neural Network-Based Deep Learning Methodology for Recognition of Partial Discharge Patterns from High-Voltage Cables. IEEE Trans. Power Deliv. 2019, 34, 1460–1469. [Google Scholar] [CrossRef]
- Dai, J.; Teng, Y.; Zhang, Z.; Yu, Z.; Sheng, G.; Jiang, X. Partial Discharge Data Matching Method for GIS Case-Based Reasoning. Energies 2019, 12, 3677. [Google Scholar] [CrossRef] [Green Version]
- Wang, Y.; Yan, J.; Yang, Z.; Liu, T.; Zhao, Y.; Li, J. Partial Discharge Pattern Recognition of Gas-Insulated Switchgear via a Light-Scale Convolutional Neural Network. Energies 2019, 12, 4674. [Google Scholar] [CrossRef] [Green Version]
- Kweon, D.J.; Chin, S.B.; Kwak, H.R.; Kim, J.C.; Song, K.B. The Analysis of Ultrasonic Signals by Partial Discharge and Noise From the Transformer. IEEE Trans. Power Deliv. 2005, 20, 1976–1983. [Google Scholar] [CrossRef]
- Hikita, M.; Ohtsuka, S.; Wada, J.; Okabe, S.; Hoshino, T.; Maruyama, S. Study of partial discharge radiated electromagnetic wave propagation characteristics in an actual 154 kV model GIS. IEEE Trans. Dielectr. Electr. Insul. 2012, 19, 8–17. [Google Scholar] [CrossRef]
- Samuelsson, O.; Hemmingsson, M.; Nielsen, A.; Pedersen, K.; Rasmussen, J. Monitoring of Power System Events at Transmission and Distribution Level. IEEE Trans. Power Syst. 2006, 21, 1007–1008. [Google Scholar] [CrossRef]
- Barrios, S.; Buldain, D.; Comech, M.; Gilbert, I.; Orue, I. Partial Discharge Classification Using Deep Learning Methods—Survey of Recent Progress. Energies 2019, 12, 2485. [Google Scholar] [CrossRef] [Green Version]
- Iorkyase, E.T.; Tachtatzis, C.; Glover, I.A.; Lazaridis, P.; Upton, D.; Saeed, B.; Atkinson, R.C. Improving RF-Based Partial Discharge Localization via Machine Learning Ensemble Method. IEEE Trans. Power Deliv. 2019, 34, 1478–1489. [Google Scholar] [CrossRef] [Green Version]
- Zhang, X.; Shi, M.; Cai, J.; Li, J. A Novel Partial Discharge Detection Method for Power Transformers On Site Adopting Its Component as Ultra-High Frequency Sensor. IEEE Trans. Power Deliv. 2019, 34, 2269–2271. [Google Scholar] [CrossRef]
- Kong, W.; Men, K.; Guo, Z.; Dong, Z.Y.; Zhang, R.; Jia, Y. Automatic Online Partial Discharge Diagnosis via Deep Learning. In Proceedings of the 2020 IEEE Power & Energy Society Innovative Smart Grid Technologies Conference (ISGT), Washington, DC, USA, 17–20 February 2020; pp. 1–5. [Google Scholar] [CrossRef]
- Balouji, E.; Hammarstrom, T.; McKelvey, T. Partial Discharge Classification in Power Electronics Applications using Machine Learning. In Proceedings of the 2019 IEEE Global Conference on Signal and Information Processing (GlobalSIP), Ottawa, ON, Canada, 11–14 November 2019; pp. 1–5. [Google Scholar] [CrossRef]
- Yeo, J.; Jin, H.; Yuen, C.; Ng, C.S. Developing Neural Network Models for Partial Discharge Analysis. In Proceedings of the IECON 2020 46th Annual Conference of the IEEE Industrial Electronics Society, Singapore, 18–21 October 2020; pp. 1573–1577. [Google Scholar] [CrossRef]
- Wan, X.; Song, H.; Luo, L.; Li, Z.; Sheng, G.; Jiang, X. Pattern Recognition of Partial Discharge Image Based on One-dimensional Convolutional Neural Network. In Proceedings of the 2018 Condition Monitoring and Diagnosis (CMD), Perth, Australia, 23–26 September 2018; pp. 1–4. [Google Scholar] [CrossRef]
- Banno, K.; Nakamura, Y.; Fujii, Y.; Takano, T. Partial Discharge Source Classification for Switchgears with Transient Earth Voltage Sensor Using Convolutional Neural Network. In Proceedings of the 2018 Condition Monitoring and Diagnosis (CMD), Perth, Australia, 23–26 September 2018; pp. 1–5. [Google Scholar] [CrossRef]
- Puspitasari, N.; Khayam, U.; Suwarno; Kakimoto, Y.; Yoshikawa, H.; Kozako, M.; Hikita, M. Partial Discharge Waveform Identification using Image with Convolutional Neural Network. In Proceedings of the 2019 54th International Universities Power Engineering Conference (UPEC), Bucharest, Romania, 3–6 September 2019; pp. 1–4. [Google Scholar] [CrossRef]
- Zhang, A.; He, J.; Lin, Y.; Li, Q.; Yang, W.; Qu, G. Recognition of partial discharge of cable accessories based on convolutional neural network with small data set. COMPEL Int. J. Comput. Math. Electr. Electron. Eng. 2020, 39, 431–446. [Google Scholar] [CrossRef]
- Tuyet-Doan, V.N.; Do, T.D.; Tran-Thi, N.D.; Youn, Y.W.; Kim, Y.H. One-Shot Learning for Partial Discharge Diagnosis Using Ultra-High-Frequency Sensor in Gas-Insulated Switchgear. Sensors 2020, 20, 5562. [Google Scholar] [CrossRef]
- Li, G.; Wang, X.; Li, X.; Yang, A.; Rong, M. Partial Discharge Recognition with a Multi-Resolution Convolutional Neural Network. Sensors 2018, 18, 3512. [Google Scholar] [CrossRef] [PubMed] [Green Version]
- Liu, N.; Fan, B.; Xiao, X.; Yang, X. Cable Incipient Fault Identification with a Sparse Autoencoder and a Deep Belief Network. Energies 2019, 12, 3424. [Google Scholar] [CrossRef] [Green Version]
- Zhou, X.; Wu, X.; Ding, P.; Li, X.; He, N.; Zhang, G.; Zhang, X. Research on Transformer Partial Discharge UHF Pattern Recognition Based on Cnn-lstm. Energies 2019, 13, 61. [Google Scholar] [CrossRef] [Green Version]
- Florkowski, M. Classification of Partial Discharge Images Using Deep Convolutional Neural Networks. Energies 2020, 13, 5496. [Google Scholar] [CrossRef]
- Tuyet-Doan, V.N.; Nguyen, T.T.; Nguyen, M.T.; Lee, J.H.; Kim, Y.H. Self-Attention Network for Partial-Discharge Diagnosis in Gas-Insulated Switchgear. Energies 2020, 13, 2102. [Google Scholar] [CrossRef] [Green Version]
- Goodfellow, I.J.; Bengio, Y.; Courville, A. Deep Learning; MIT Press: Cambridge, MA, USA, 2016. [Google Scholar]
- Liu, T.; Yan, J.; Wang, Y.; Du, Y. Research on GIS Partial Discharge Pattern Recognition Based on Deep Residual Network and Transfer Learning in Ubiquitous Power Internet of Things Context. In Proceedings of the 2020 5th Asia Conference on Power and Electrical Engineering (ACPEE), Chengdu, China, 4–7 June 2020; pp. 207–211. [Google Scholar] [CrossRef]
- Tang, Z.; Cao, Z. Application of Convolutional Neural Network Transfer Learning in Partial Discharge Pattern Recognition. In Proceedings of the 2020 IEEE International Conference on High Voltage Engineering and Application (ICHVE), Beijing, China, 6–10 September 2020; pp. 1–4. [Google Scholar] [CrossRef]
- He, K.; Zhang, X.; Ren, S.; Sun, J. Identity Mappings in Deep Residual Networks. arXiv 2016, arXiv:1603.05027. [Google Scholar]
- Zhuang, F.; Qi, Z.; Duan, K.; Xi, D.; Zhu, Y.; Zhu, H.; Xiong, H.; He, Q. A Comprehensive Survey on Transfer Learning. arXiv 2019, arXiv:1911.02685. [Google Scholar] [CrossRef]
- Howard, A.G.; Zhu, M.; Chen, B.; Kalenichenko, D.; Wang, W.; Weyand, T.; Andreetto, M.; Adam, H. MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications. arXiv 2017, arXiv:1704.04861. [Google Scholar]
- Hao, L.; Lewin, P.L.; Swingler, S.G. Improving detection sensitivity for partial discharge monitoring of high voltage equipment. Meas. Sci. Technol. 2008, 19, 055707. [Google Scholar] [CrossRef]
Information for HFCT | Specification |
---|---|
Bandwidth | 50 kHz–20 MHz |
Load impedance | 50 |
Sensitivity | 15 mV/mA |
Type | Clamp |
Connector | BNC |
Parameter | Description |
---|---|
Training samples | 126 |
Test samples | 497 |
Epochs | 5 |
Input_shape | (224,224,3) |
Batch_size | 16 |
Parameter | Description |
---|---|
Training samples | 126 |
Test samples | 497 |
Epochs | 5 |
Input_shape | (224,224,3) |
Batch_size | 16 |
Parameter | Description |
---|---|
Layers | 2 (or 4) |
Training samples | 126 |
Test samples | 497 |
Epochs | 5 |
Input_shape | (224,224,3) |
Max_pooling | (2,2) |
Dropout | 0.25 |
Activation function | relu (convolution layer) |
softmax (dense layer) | |
Loss function | categorical_crossentropy |
Optimizer | adam |
Parameter | Description |
---|---|
Training samples | 126 |
Test samples | 313 |
Kernel | rbf |
C | 1 |
auto |
Model | Training Accuracy | Test Accuracy |
---|---|---|
ResNet50V2_C1 | 100% | 89.1% |
ResNet50V2_C2 | 73.0% | 51.5% |
ResNet50V2_C3 | 100% | 96.2% |
MobileNet50V2_C1 | 100% | 88.7% |
MobileNet50V2_C2 | 51.5% | 16.7% |
MobileNet50V2_C3 | 99.2% | 97.4% |
CNN_2 layers | 100% | 89.6% |
CNN_4 layers | 100% | 89.3% |
SVM | 50.0% | 49.8% |
Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations. |
© 2021 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
Kim, J.; Kim, K.-I. Partial Discharge Online Detection for Long-Term Operational Sustainability of On-Site Low Voltage Distribution Network Using CNN Transfer Learning. Sustainability 2021, 13, 4692. https://doi.org/10.3390/su13094692
Kim J, Kim K-I. Partial Discharge Online Detection for Long-Term Operational Sustainability of On-Site Low Voltage Distribution Network Using CNN Transfer Learning. Sustainability. 2021; 13(9):4692. https://doi.org/10.3390/su13094692
Chicago/Turabian StyleKim, Jinseok, and Ki-Il Kim. 2021. "Partial Discharge Online Detection for Long-Term Operational Sustainability of On-Site Low Voltage Distribution Network Using CNN Transfer Learning" Sustainability 13, no. 9: 4692. https://doi.org/10.3390/su13094692