A Seismic Response and AdaBoost Regressor-Based Vulnerability Analysis of an ±800 kV Suspended Filter Capacitor
Abstract
:1. Introduction
2. Structural Parameters and Simulation Model
2.1. Physical Structures and Structural Parameters
2.2. Simulation Model
2.3. Model Analysis and Accuracy Illustration
3. The Seismic Performance of an ±800 kV Suspended Filter Capacitor
3.1. Selection of Ground Motions
3.2. The Displacement Response of the Filter Capacitor
3.3. The Force Response of the Suspended Insulators
3.4. The Influence of Pre-Tension Force on Seismic Response
4. AdaBoost Regressor-Based Seismic Vulnerability Analysis Method
4.1. The Basic Theory of the Seismic Vulnerability Analysis of Electrical Equipment
4.2. The Material Uncertainty of the GFRP Composite Insulator
4.3. A Selection and Brief Introduction of the AdaBoost Regressor
4.4. AdaBoost Regressor-Based Seismic Vulnerability Analytical Procedures
4.4.1. Part A: Sample Collecting Based on Simulation Part B: Seismic Vulnerability Based on the Single-Variable-Input AdaBoost Regressor
4.4.2. Part B: Seismic Vulnerability Based on the Single-Variable-Input AdaBoost Regressor
4.4.3. Part C: Seismic Vulnerability Based on the Multi-Variable-Input AdaBoost Regressor
5. The Seismic Vulnerability of an ±800 kV Suspended Filter Capacitor
5.1. Material Parameter Combination and Ground Motion Sampling
5.2. The Single-Variable-Input AdaBoost Regressor and Vulnerability Curve
5.3. The Multi-Variable-Input AdaBoost Regressor and Response Prediction
5.4. A Comparison of Vulnerability Curves Based on AdaBoost Regressors and IDA
- (1)
- The material parameters except PGA were sampled by LHS and 15 groups of samples were obtained. The PGA was modulated from 0.2 g to 1.2 g at a step of 0.2 g, inducing six PGA values.
- (2)
- At each PGA, there were 20 × 15 = 300 responses and their mean value and standard deviation were computed as shown in Figure 19a.
- (3)
- Then, we got the response number that exceeds the material strength at each PGA so that the failure probability could be computed. Thus, there will be six PGA–failure probability pairings.
- (4)
- Using log-normal distribution, an IDA-based fragility curve can be obtained by fitting the relationship of the PGA–failure probability pairings, as shown in Figure 19b.
5.5. Computational Efficiency
5.6. Influence of the Sample Group
5.7. The Influence of Pre-Tension Force on Seismic Vulnerability
5.7.1. The Influence on the Mean and Standard Deviation of Responses
5.7.2. The Influence on Seismic Vulnerability Curves Produced by the AdaBoost Regressor
6. Conclusions and Future Work
6.1. Conclusions
- (1)
- The suspended insulators of the filter capacitor do not meet the seismic design requirement due to the safety factor slightly less than 1.67 recommended by Chinese code. It is recommended to reduce the pre-tension force for increasing the safety factor while ensuring the minimum axial force is larger than 0, which will also avoid the pressure stress in the insulators.
- (2)
- The effects of increasing the pre-tension force is twofold: one is avoiding the pressure generation in the suspended insulators and reducing the maximum displacement of the filter capacitor, another is increasing the seismic failure risk, so increasing pre-tension force should be carefully considered and studied by a balance analysis of the multifaceted influence.
- (3)
- The established AdaBoost regressors accurately predict the vulnerability curves as IDA does, and also reduce the computation cost. The single-variable-input regressor has a lower maximum probability prediction error of 2.55% compared to the multi-variable-input regressor’s error of 3.82%.
- (4)
- The failure risk of the filter capacitor will significantly increase as the pre-tension force increases from 20 kN, but the growth rate continues to fall. The increase in pre-tension force will increase the initial tension in the insulators so that the pressure could be reduced under a given earthquake. However, the tension increase in the insulators would make their stresses closer to the material strength, resulting in a higher failure risk. Due to the increased structural stiffness, the structural responses under a given earthquake will reduce, so the growth rate is gradually decreased.
6.2. Future Work
- (1)
- The selection of the AdaBoost regressor in this paper is based on its nonlinear fitting ability and advantages on small samples. In the future, some advanced machine learning algorithms can be employed to conduct comparative studies.
- (2)
- The simulation model developed in this case is validated only by the vibration frequencies of the similar structure. In the future, on-site tests can be performed to validate the simulation model.
- (3)
- This study considers only one failure mode, i.e., the failure of insulators. However, the steel members of the gantry may locally buckle or yield under extreme earthquakes. Therefore, the seismic fragility could be updated by considering multiple failure modes in the future.
- (4)
- This paper implements the proposed method using a suspended filter capacitor. In fact, its practicability can be further validated on other failure modes of other substation equipment, or general engineering structures.
Author Contributions
Funding
Data Availability Statement
Conflicts of Interest
References
- Shen, Y.; Gu, C.; Yang, X.; Zhao, P. Impact analysis of seismic events on integrated electricity and natural gas systems. IEEE Trans. Power Deliv. 2021, 36, 1923–1931. [Google Scholar] [CrossRef]
- Eidinger, J.; Davis, C.; Tang, A.; Kempner, L. M 9.0 Tohoku Earthquake March 11 2011 Performance of Water and Power Systems; G & E Engineering Systems Inc.: Oakland, CA, USA, 2012. [Google Scholar]
- Zhu, W.; Xie, Q.; Liu, X.; Mao, B.; Xue, Z. Towards 500 kV power transformers damaged in the 2022 Luding earthquake: Field investigation, failure analysis and seismic retrofitting. Nat. Hazards 2024, 120, 6275–6305. [Google Scholar] [CrossRef]
- Ersoy, S.; Saadeghvaziri, M.A. Seismic response of transformer-bushing systems. IEEE Trans. Power Deliv. 2004, 19, 131–137. [Google Scholar] [CrossRef]
- Wang, M.; He, J. Shake table test and finite element model for evaluating seismic performance of 220 kV transformer-bushing systems. Earthq. Spectra 2023, 39, 1755–1778. [Google Scholar] [CrossRef]
- Chun, N.; Jeon, B.; Kim, S.; Chang, S.; Son, S. Seismic response evaluation of 154 kV transformer porcelain bushing by shaking table tests. Struct. Eng. Mech. 2022, 84, 155–165. [Google Scholar]
- Zhu, W.; Xie, Q.; Lu, J. Seismic testing and fragility analysis considering material strength uncertainty of 1100 kV GFRP composite power transformer bushing. Case Stud. Constr. Mater. 2024, 21, e03564. [Google Scholar] [CrossRef]
- Li, S.; Cheng, Y.; Lu, Z.; Lam, N.; Xue, Y.; Wang, H. Full-scale testing on seismic performance of surge arrester with retrofitted composite insulators. Buildings 2022, 12, 1720. [Google Scholar] [CrossRef]
- Li, S.; Tsang, H.H.; Cheng, Y.; Lu, Z. Seismic testing and modeling of cylindrical electrical equipment with GFRP composite insulators. Compos. Struct. 2018, 194, 454–467. [Google Scholar] [CrossRef]
- He, C.; Xie, Q.; Jiang, L.; Jiang, L. Seismic terminal displacement of UHV post electrical equipment considering flange rotational stiffness. J. Constr. Steel Res. 2021, 183, 106701. [Google Scholar] [CrossRef]
- Bai, W.; Moustafa, M.A.; Dai, J. Seismic response of potential transformers and mitigation using innovative multiple tuned mass dampers. Eng. Struct. 2018, 174, 67–80. [Google Scholar]
- He, C.; He, Z.; Zhu, W. Seismic interconnecting effects of multi-span flexible conductor-post electrical equipment coupling system. J. Constr. Steel Res. 2024, 212, 108209. [Google Scholar] [CrossRef]
- Zhu, W.; Wu, M.; Xie, Q.; Xu, J. Floor response spectra and seismic design method of electrical equipment installed on floor in indoor substation. Soil Dyn. Earthq. Eng. 2023, 173, 108138. [Google Scholar] [CrossRef]
- Li, X.; Xie, Q.; Wen, J. Double friction pendulum-based isolation optimization for transformer-bushing systems. Eng. Struct. 2024, 320, 118909. [Google Scholar] [CrossRef]
- Alessandri, S.; Giannini, R.; Paolacci, F.; Malena, M. Seismic retrofitting of an HV circuit breaker using base isolation with wire ropes. Part 1, Preliminary tests and analyses. Eng. Struct. 2015, 98, 251–262. [Google Scholar] [CrossRef]
- Yang, Z.; Xie, Q.; He, C.; Xue, S. Numerical investigation of the seismic response of a UHV composite bypass switch retrofitted with wire rope isolators. Earthq. Eng. Eng. Vib. 2021, 20, 275–290. [Google Scholar] [CrossRef]
- Bai, W.; Dai, J.; Zhou, H.; Yang, Y.; Ning, X. Experimental and analytical studies on multiple tuned mass dampers for seismic protection of porcelain electrical equipment. Earthq. Eng. Eng. Vib. 2017, 16, 803–813. [Google Scholar] [CrossRef]
- Naeem, A.; Kim, J. Seismic retrofit of 3000 kVA power transformer using friction dampers and prestressed tendons. Structures 2021, 32, 641–650. [Google Scholar] [CrossRef]
- Yang, Z.; Xie, Q.; Zhou, Y.; Mosalam, K.M. Seismic performance and restraint system of suspended 800 kV thyristor valve. Eng. Struct. 2018, 169, 179–187. [Google Scholar] [CrossRef]
- Anagnos, T. Development of an Electrical Substation Equipment Performance Database for Evaluation of Equipment Fragilities; Report; Pacific Earthquake Engineering Center: Berkeley, CA, USA, 1999. [Google Scholar]
- Zareei, S.A.; Hosseini, M.; Ghafory-Ashtiany, M. Seismic failure probability of a 400 kV power transformer using analytical fragility curves. Eng. Fail. Anal. 2016, 70, 273–289. [Google Scholar] [CrossRef]
- Paolacci, F.; Giannini, R.; Alessandri, S.; De Felice, G. Seismic vulnerability assessment of a high voltage disconnect switch. Soil Dyn. Earthq. Eng. 2014, 67, 198–207. [Google Scholar] [CrossRef]
- Bai, W.; Moustafa, M.A.; Dai, J. Seismic fragilities of high-voltage substation disconnect switches. Earthq. Spectra 2019, 35, 1559–1582. [Google Scholar]
- He, C.; Jiang, L.Z.; Jiang, L.Q. Seismic failure risk assessment of post electrical equipment on supporting structures. IEEE Trans. Power Deliv. 2023, 38, 2757–2766. [Google Scholar] [CrossRef]
- He, C.; Liu, R.; He, Z. Seismic vulnerability assessment on porcelain electrical equipment based on Kriging model. Structures 2023, 55, 1692–1703. [Google Scholar] [CrossRef]
- Baghmisheh, A.G.; Khodaei, M.; Abadi, A.Z.F.; Estekanchi, H.E. Detailed seismic risk analysis of electrical substation equipment using a reliability based approach. Earthq. Eng. Eng. Vib. 2023, 22, 495–511. [Google Scholar] [CrossRef]
- Zhu, L.; Du, Y.; Gao, L.; Zhuang, Z.; Ji, S. Vibration distribution detection method for turn-to-turn short-circuit fault of dry-type air-core filter reactors. IEEE Trans. Power Deliv. 2022, 37, 4474–4476. [Google Scholar] [CrossRef]
- Zhang, Z.; Li, J.; Song, Y.; Sun, Y.; Zhang, X.; Hu, Y.; Guo, R.; Han, X.T. A novel ultrasound-vibration composite sensor for defects detection of electrical equipment. IEEE Trans. Power Deliv. 2022, 37, 4477–4480. [Google Scholar] [CrossRef]
- Zhu, W.; Xie, Q.; Liu, X. Seismic failure risk analysis of ± 800 kV coupling filter circuit considering material strength deviation. Structures 2023, 47, 1566–1578. [Google Scholar] [CrossRef]
- Liang, H.; Xie, Q. System vulnerability analysis simulation model for substation subjected to earthquakes. IEEE Trans. Power Deliv. 2022, 37, 2684–2692. [Google Scholar] [CrossRef]
- Liu, X.; Xie, Q. A probabilistic framework to evaluate seismic resilience of substations based on three-stage uncertainty. Reliab. Eng. Syst. Saf. 2024, 249, 110219. [Google Scholar] [CrossRef]
- Liu, X.; Xie, Q. A multi-model probabilistic framework to evaluate seismic resilience of UHV converter stations. Eng. Struct. 2024, 300, 117153. [Google Scholar] [CrossRef]
- Ibrahim, Y.E. Seismic risk analysis of multistory reinforced concrete structures in Saudi Arabia. Case Stud. Constr. Mater. 2018, 9, e00192. [Google Scholar] [CrossRef]
- Rong, X.L.; Yang, J.; Jun, L.; Zhang, Y.-X.; Zheng, S.-S.; Dong, L. Optimal ground motion intensity measure for seismic assessment of high-rise reinforced concrete structures. Case Stud. Constr. Mater. 2023, 18, e01678. [Google Scholar] [CrossRef]
- Wen, J.; Li, X.; Xue, J. Feasibility evaluation of Copula theory for substation equipment with multiple nonlinear-related seismic response indexes. Reliab. Eng. Syst. Saf. 2024, 247, 110132. [Google Scholar] [CrossRef]
- Valente, M. Seismic vulnerability assessment and earthquake response of slender historical masonry bell towers in South-East Lombardia. Eng. Fail. Anal. 2021, 129, 105656. [Google Scholar] [CrossRef]
- da Silva, L.C.M.; Milani, G.; Lourenço, P.B. Lourenço, Probabilistic-based discrete model for the seismic fragility assessment of masonry structures. Structures 2023, 52, 506–523. [Google Scholar] [CrossRef]
- Mohamed, H.; Skoulidou, D.; Romão, X. Quantification of the effects of different uncertainty sources on the seismic fragility functions of masonry-infilled RC frames. Structures 2023, 50, 1069–1088. [Google Scholar] [CrossRef]
- Yan, Y.; Xia, Y.; Sun, L. Hierarchical and mixed uncertainty quantification for simulation-based structural seismic fragility analysis. Eng. Struct. 2024, 316, 118579. [Google Scholar] [CrossRef]
- Valente, M. Earthquake response and damage patterns assessment of two historical masonry churches with bell tower. Eng. Fail. Anal. 2023, 151, 107418. [Google Scholar] [CrossRef]
- Zhao, Y.G.; Qin, M.J.; Lu, Z.H.; Zhang, L.W. Seismic fragility analysis of nuclear power plants considering structural parameter uncertainty. Reliab. Eng. Syst. Saf. 2021, 216, 107970. [Google Scholar] [CrossRef]
- Aktaş, A. Statistical analysis of bearing strength of glass-fiber composite materials. J. Reinf. Plast. Compos. 2007, 26, 555–564. [Google Scholar] [CrossRef]
- Zhu, W.; Xie, Q. Machine learning chain models for multi-response prediction of electrical equipment in substation subjected to earthquakes. Eng. Struct. 2024, 319, 118815. [Google Scholar] [CrossRef]
- Zhu, W.; Xie, Q. Post-earthquake rapid assessment for loop system in substation using ground motion signals. Mech. Syst. Signal Process. 2024, 208, 111058. [Google Scholar] [CrossRef]
- Quinci, G.; Paolacci, F.; Phan, H.N. Artificial neural network technique for seismic fragility analysis of a storage tank supported by multi-storey frame. J. Press. Vessel Technol. 2023, 145, 061901. [Google Scholar] [CrossRef]
- Sediek, O.A.; Wu, T.Y.; McCormick, J.; El-Tawil, S. Prediction of seismic collapse behavior of deep steel columns using machine learning. Structures 2022, 40, 163–175. [Google Scholar] [CrossRef]
- Liu, C.; Macedo, J. Machine learning-based models for estimating seismically-induced slope displacements in subduction earthquake zones. Soil Dyn. Earthq. Eng. 2022, 160, 107323. [Google Scholar] [CrossRef]
- Zhang, L.; Shen, J.; Zhu, B. A review of the research and application of deep learning-based computer vision in structural damage detection. Earthq. Eng. Eng. Vib. 2022, 21, 1–21. [Google Scholar]
- GB 50260-2013; Code for Seismic Design of Electrical Installation. China Planning Publishing House: Beijing, China, 2013.
- IEEE 693 Standard; Recommended Practice for Seismic Design of Substations. Institute of Electrical and Electronics Engineers: New York, NY, USA, 2018.
- Xie, Q.; Wang, Y.F.; Wei, S.H. Seismic failure analysis on substation equipment interconnected by flexible conductor. In Proceedings of the 2009 International Conference on Sustainable Power Generation and Supply, Nanjing, China, 6–7 April 2009; IEEE: Piscataway, NJ, USA, 2009; pp. 1–6. [Google Scholar]
- Xie, Q.; Zhu, R. Earth, wind, and ice. IEEE Power Energy Mag. 2011, 9, 28–36. [Google Scholar] [CrossRef]
- Yang, Z.; Xie, Q.; He, C.; Ma, G. Seismic response analysis of ±800 kV UHVDC converter valves. Proc. CSEE 2016, 36, 1836–1841. [Google Scholar]
- Quinci, G.; Paolacci, F.; Fragiadakis, M.; Bursi, O.S. A machine learning framework for seismic risk assessment of industrial equipment. Reliab. Eng. Syst. Saf. 2025, 254, 110606. [Google Scholar] [CrossRef]
- Zhu, W.; Bian, X.; Xie, Q. Refined seismic fragility curves of substation equipment considering ground motion classifications. Soil Dyn. Earthq. Eng. 2024, 187, 108995. [Google Scholar] [CrossRef]
- Gohil, P.P.; Shaikh, A.A. Strength characterization of fibers and fibrous materials: Experimental-reliability based novel approach. Mater. Des. 2013, 51, 105–112. [Google Scholar] [CrossRef]
- Lu, C.; Danzer, R.; Fischer, F.D. Fracture statistics of brittle materials: Weibull or normal distribution. Phys. Rev. E 2002, 65, 067102. [Google Scholar] [CrossRef] [PubMed]
- Bermejo, R.; Supancic, P.; Danzer, R. Influence of measurement uncertainties on the determination of the Weibull distribution. J. Eur. Ceram. Soc. 2012, 32, 251–255. [Google Scholar] [CrossRef]
- Freund, Y.; Schapire, R.E. A decision-theoretic generalization of on-line learning and an application to boosting. J. Comput. Syst. Sci. 1997, 55, 119–139. [Google Scholar] [CrossRef]
- Somerville, P.G. Development of Ground Motion Time Histories for Phase 2 of the FEMA/SAC Steel Project; SAC Joint Venture: Richmond, CA, USA, 1997. [Google Scholar]
- Myles, A.J.; Feudale, R.N.; Liu, Y.; Woody, N.A.; Brown, S.D. An introduction to decision tree modeling. J. Chemom. A J. Chemom. Soc. 2004, 18, 275–285. [Google Scholar] [CrossRef]
Component | Section Shape | Section Profile (Unit: mm) | |
---|---|---|---|
Gantry beam | Main beam | Pipe-shape | Φ304δ6 |
Braces | L-shape | L110δ10 | |
Suspender beam | T-shape | Web: L250δ10; Flange: L125δ10 | |
Gantry column | Main column | Pipe-shape | Φ304δ6 |
Braces | L-shape | L110δ10 | |
Suspended insulators | Top | Circle | Φ30 (Effective diameter) |
Middle | Circle | Φ45 (Effective diameter) | |
Bottom | Circle | Φ30 (Effective diameter) |
Order | Frequency (Hz) | Mode Shape | Direction | Effective Mass | |||||
---|---|---|---|---|---|---|---|---|---|
X-tra | Y-tra | Z-tra | X-rot | Y-rot | Z-rot | ||||
1 | 0.181 | Bend | Along Y-axis | 0.004 | 37,900 | 0 | 5,419,260 | 0.640 | 0 |
2 | 0.181 | Bend | Along X-axis | 37,560 | 0.004 | 0 | 0.644 | 5,449,320 | 0 |
3 | 0.253 | Torsion | Around Z-axis | 0 | 0 | 0 | 0 | 0.032 | 44,819 |
Ground Motion | The Bottom Insulators (kN) | The First-Layer Insulators (kN) |
---|---|---|
El Centro | 6.51 | 10.43 |
Taft | −10.95 | −3.65 |
AW | −5.07 | 0.76 |
Parameter | Unit | Mean | (Logarithmic) Std. dev. | Distribution |
---|---|---|---|---|
Ein | GPa | 40 | 5 | Normal distribution |
ρin | kg/m3 | 2160 | 200 | Normal distribution |
ηin | — | 0.02 | 0.005 | Log-normal distribution |
Eg | GPa | 206 | 50 | Log-normal distribution |
PGA | g | 0.60 | 0.346 | Uniform distribution |
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. |
© 2025 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
Zhou, Q.; Mao, Y.; Yin, Z.; He, C.; Yang, T. A Seismic Response and AdaBoost Regressor-Based Vulnerability Analysis of an ±800 kV Suspended Filter Capacitor. Appl. Sci. 2025, 15, 3314. https://doi.org/10.3390/app15063314
Zhou Q, Mao Y, Yin Z, He C, Yang T. A Seismic Response and AdaBoost Regressor-Based Vulnerability Analysis of an ±800 kV Suspended Filter Capacitor. Applied Sciences. 2025; 15(6):3314. https://doi.org/10.3390/app15063314
Chicago/Turabian StyleZhou, Quan, Yongheng Mao, Zhongkai Yin, Chang He, and Ting Yang. 2025. "A Seismic Response and AdaBoost Regressor-Based Vulnerability Analysis of an ±800 kV Suspended Filter Capacitor" Applied Sciences 15, no. 6: 3314. https://doi.org/10.3390/app15063314
APA StyleZhou, Q., Mao, Y., Yin, Z., He, C., & Yang, T. (2025). A Seismic Response and AdaBoost Regressor-Based Vulnerability Analysis of an ±800 kV Suspended Filter Capacitor. Applied Sciences, 15(6), 3314. https://doi.org/10.3390/app15063314