基于物理信息神经网络的充油设备高能电弧故障压力泄放装置结构优化方法

doi:10.19595/j.cnki.1000-6753.tces.251049

摘要
图/表
参考文献
相关文章 (15)

全文: PDF (0 KB) HTML
输出: BibTeX | EndNote (RIS)

摘要近年来,因内部电弧故障引发的充油设备燃爆事故接连发生,传统压力泄放装置越发难以满足大容量高电压等级充油设备的泄压需求。鉴于缺乏理论指导与试验数据,压力泄放技术的改进主要依赖工程经验与迭代试错。为此,该文提出了一种基于物理信息神经网络（PINN）的压力泄放优化方法。首先,建立了能够准确描述充油设备电弧故障油压特征的气-液-固多物理场耦合模型,为构建PINN模型提供训练数据集。其次,将油压与关键输入变量之间的单调性关系嵌入PINN,使模型在准确预测油压峰值的同时严格遵循物理规律约束,以提高模型的可解释性和泛化能力。然后,利用粒子群优化算法求解最低油压峰值目标下压力泄放装置结构参数的全局最优解。结果表明,优化方案充分增加了泄压面积并形成流线形导流通道,显著改善了压力泄放装置的泄压能力,降低了故障油压幅值。最后,通过搭建现场试验平台,开展了充油设备高能电弧故障现场试验,证实了优化后的高性能压力泄放装置的有效性。该优化方法在降低计算成本的同时,实现了压力泄放装置结构参数全局最优解的高效求解,将以往依赖经验的组部件结构设计方式提升至高效定量设计的新阶段。

	服务

	把本文推荐给朋友
	加入我的书架
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章
	刘浩
	闫晨光
	桑凡雅
	陈一悰
	梁栋

关键词 ：电弧故障, 充油设备, 压力泄放装置, 物理信息神经网络

Abstract：Recently, oil-filled equipment explosions caused by arcing faults have successively occurred. Conventional pressure relief devices are inadequate to meet the actual pressure relief demands of large-capacity, high-voltage oil-filled equipment. Due to the lack of theoretical guidance and experimental data, advancements in pressure relief technology have heavily relied on engineering experience and trial-and-error approaches. To this end, this paper proposes an optimization method for pressure relief devices based on physics-informed neural network (PINN). The proposed method combines accurate bubble-fluid-solid multiphysics simulations with the efficient predictive capability of the PINN model, achieving global optimization of structural parameters of pressure relief device with reduced computational cost. It advances the traditional experience-driven design for component structures into an efficient and quantitative phase.
First, a bubble-fluid-solid multiphysics coupled model capable of accurately describing the pressure during arcing faults in oil-filled equipment was established to generate training datasets for the PINN. Second, the monotonic relationships between oil pressure and key input variables were incorporated into the PINN model. This allowed the model to accurately predict peak oil pressure while strictly adhering to physical constraints, thereby improving its interpretability and generalization. Finally, the particle swarm optimization algorithm was employed to obtain the global optimal structural parameters of the pressure relief device under the objective of minimizing the oil pressure peak. The effectiveness of the optimized scheme was validated through both simulations and experiments.
Simulation results indicate that the optimized scheme effectively enlarges the pressure relief area and creates a streamlined venting path. The maximum flow rate of the optimized device reaches 248.2 L/s, representing a 53% improvement over the conventional design. Meanwhile, the oil discharge volume within 60 ms increases by 71%. Owing to its enhanced oil discharge capability, the oil pressure peak is reduced by 127 kPa. As the fault current increases, the mitigation effect becomes more pronounced. At 50 kA, the oil pressure peak is reduced by 226 kPa. Furthermore, arcing faults at depths of 250 mm, 500 mm, and 750 mm show that the peak pressures are decreased by 38.1%, 31.1%, and 30.4%, respectively. A greater pressure relief effect is observed when the fault occurs closer to the device. Subsequently, an optimized pressure relief device (PRD) prototype was manufactured and tested on the established on-site experimental platform. Under peak fault currents of 12 kA, 15 kA, and 20 kA, the measured peak pressures with the optimized device are 145 kPa, 177 kPa, and 254 kPa, respectively, representing reductions of 18.5%, 26.9%, and 34.0% compared to the conventional design. These results demonstrate the superior performance of the optimized pressure relief device in mitigating arc-induced oil pressure.
The following conclusions can be drawn from the experimental and calculation analysis: (1) By adjusting the structural parameters, the optimized scheme effectively mitigates the limitations of conventional designs, including the limited venting area and restricted oil discharge capacity. (2) Compared with traditional devices, the optimized prototype significantly reduces the peak oil pressure and moderates its growth rate with increasing fault current, demonstrating superior performance under different fault conditions and locations. (3) The developed PINN accurately approximates complex multiphysics simulation results within millisecond-level time. Combined with the global search capability of particle swarm optimization, the proposed approach overcomes the drawbacks of relying solely on numerical simulations for optimization, including low computational efficiency and the inability to guarantee global optimality.

Key words： Arcing fault oil-filled equipment pressure relief device physics-informed neural network

收稿日期: 2025-06-17

PACS:

TM774

基金资助:国家自然科学基金资助项目（52277125）

通讯作者: 闫晨光男,1987年生,副教授,博士生导师,研究方向为电力系统继电保护、电力设备故障机理与安全运行等。E-mail：chgyan@xjtu.edu.cn

作者简介: 刘浩男,1997年生,博士研究生,研究方向为油浸式电力设备新型继电保护与高速泄压技术等。E-mail：liuhao764555@stu.xjtu.edu.cn

引用本文:

刘浩, 闫晨光, 桑凡雅, 陈一悰, 梁栋. 基于物理信息神经网络的充油设备高能电弧故障压力泄放装置结构优化方法[J]. 电工技术学报, 2026, 41(9): 3129-3140. Liu Hao, Yan Chenguang, Sang Fanya, Chen Yicong, Liang Dong. Optimization Method for Pressure Relief Device Structure in Oil-Filled Equipment under High-Energy Arcing Faults Based on Physics-Informed Neural Network. Transactions of China Electrotechnical Society, 2026, 41(9): 3129-3140.

链接本文:

https://dgjsxb.ces-transaction.com/CN/10.19595/j.cnki.1000-6753.tces.251049 https://dgjsxb.ces-transaction.com/CN/Y2026/V41/I9/3129

[1] Yan Chenguang, Zhang Peng, Guo Jiaxu, et al.An improved coupled FE-circuit model for turn-to-turn short-circuit faults inside converter transformers[J]. IEEE Transactions on Magnetics, 2023, 59(5): TMAG. 2022.
[2] 闫晨光, 张保会, 郝治国, 等. 电力变压器油箱内部故障压力特征建模及仿真[J]. 中国电机工程学报, 2014, 34(1): 179-185.
Yan Chenguang, Zhang Baohui, Hao Zhiguo, et al.Modeling and simulation of pressure characteristics of power transformer tanks’ internal faults[J]. Proceedings of the CSEE, 2014, 34(1): 179-185.
[3] 闫晨光, 郝治国, 张保会. 基于压力特征的变压器数字式保护研究[J]. 中国电机工程学报, 2015, 35(24): 6405-6412.
Yan Chenguang, Hao Zhiguo, Zhang Baohui.Power transformer digital protection based on internal pressure characteristics[J]. Proceedings of the CSEE, 2015, 35(24): 6405-6412.
[4] 闫晨光, 郝治国, 张保会, 等. 电力变压器油箱形变破裂建模及仿真[J]. 电工技术学报, 2016, 31(3): 180-187.
Yan Chenguang, Hao Zhiguo, Zhang Baohui, et al.Modeling and simulation of power transformer tank deformation and rupture[J]. Transactions of China Electrotechnical Society, 2016, 31(3): 180-187.
[5] Brodeur S, Dastous J B.Design and testing of an arc resistant power transformer tank[J]. IEEE Transactions on Power Delivery, 2020, 35(2): 699-706.
[6] Yan Chenguang, Zhou Xian, Xu Ya, et al.Experimental study on the gas bubble temperature around an arc under insulation oil[J]. IEEE Transactions on Power Delivery, 2021, 36(2): 1245-1248.
[7] Yan Chenguang, Xu Ya, Zhang Peng, et al.Investigation of the gas bubble dynamics induced by an electric arc in insulation oil[J]. Plasma Science and Technology, 2022, 24(4): 044003.
[8] Yan Chenguang, Xu Che, Liu Hao, et al.Research on oil pressure rise and fluctuation due to arcing faults inside transformers[J]. IEEE Transactions on Power Delivery, 2023, 38(2): 1483-1492.
[9] Yan Chenguang, Guo Jiaxu, Zhang Peng, et al.Prevention of oil-immersed equipment rupture due to arcing faults based on metal foam[J]. IEEE Transactions on Power Delivery, 2023, 38(4): 2965-2968.
[10] Yan Chenguang, Liu Hao, Xu Che, et al.Limitations and performance of pressure relief devices in on-load tap changer compartments under arcing faults[J]. IEEE Transactions on Power Delivery, 2024, 39(4): 2520-2529.
[11] 李鹏, 孙建涛, 赵义焜, 等. 大型油浸式变压器油箱防爆技术研究综述[J]. 中国电机工程学报, 2025, 45(9): 3282-3297.
Li Peng, Sun Jiantao, Zhao Yikun, et al.Review on explosion-proof technology of large oil-immersed transformer tank[J]. Proceedings of the CSEE, 2025, 45(9): 3282-3297.
[12] 王卓非, 章程, 张耀, 等. 工频交流电压下变压器油中电弧放电初期压力波特性[J]. 中国电机工程学报, 2025, 45(9): 3320-3332.
Wang Zhuofei, Zhang Cheng, Zhang Yao, et al.Characteristics of shock waves during the initial arc discharge in transformer oil under power frequency AC voltage[J]. Proceedings of the CSEE, 2025, 45(9): 3320-3332.
[13] 张书琦, 赵义焜, 文韬, 等. 变压器油中电弧故障动态压力规律与仿真技术研究综述[J]. 中国电机工程学报, 2025, 45(9): 3357-3370.
Zhang Shuqi, Zhao Yikun, Wen Tao, et al.Research review on transient pressure law and simulation technology of arc fault in transformer oil[J]. Proceedings of the CSEE, 2025, 45(9): 3357-3370.
[14] 闫晨光, 徐彻, 李嘉熙, 等. 基于自适应FEM-SPH耦合的换流变压器电弧故障结构失效行为研究[J]. 中国电机工程学报, 2025, 45(9): 3370-3380.
Yan Chenguang, Xu Che, Li Jiaxi, et al.Research on the structural failure behavior of converter transformers under arcing faults based on adaptive FEM-SPH coupling method[J]. Proceedings of the CSEE, 2025, 45(9): 3370-3380.
[15] 刘刚, 高成龙, 胡万君, 等. 基于鲸鱼优化算法超参数优化的径向基函数响应面模型的油浸式变压器绕组挡板结构优化[J]. 电工技术学报, 2024, 39(17): 5331-5343.
Liu Gang, Gao Chenglong, Hu Wanjun, et al.Optimization of winding block washer structure for oil immersed transformers based on radial basis function response surface model with whale optimization algorithm hyper-parameters optimization[J]. Transactions of China Electrotechnical Society, 2024, 39(17): 5331-5343.
[16] 张志宇, 寇家俊, 张重远, 等. 基于本征正交分解和克里金代理模型的油浸式变压器绕组温度场快速计算方法[J]. 电工技术学报, 2025, 40(7): 2215-2225.
Zhang Zhiyu, Kou Jiajun, Zhang Zhongyuan, et al.A fast calculation method for temperature field of oil immersed transformer windings based on proper orthogonal decomposition and Kriging surrogate model[J]. Transactions of China Electrotechnical Society, 2025, 40(7): 2215-2225.
[17] Thakre U, Mote R G.Uncertainty quantification and statistical modeling of selective laser sintering process using polynomial chaos based response surface method[J]. Journal of Manufacturing Processes, 2022, 81: 893-906.
[18] 丰宇宸, 孙跃, 邓德强, 等. 基于替代模型的旋转磁耦合器磁心结构优化[J]. 电工技术学报, 2025, 40(4): 997-1008.
Feng Yuchen, Sun Yue, Deng Deqiang, et al.Optimization of the core structure for the rotary magnetic coupler based on surrogate model[J]. Transactions of China Electrotechnical Society, 2025, 40(4): 997-1008.
[19] 叶芳怡, 刘匀, 朱旺, 等. 基于机器学习的±800 kV干式平波电抗器震后状态评估方法[J]. 高压电器, 2025, 61(4): 1-11.
Ye Fangyi, Liu Yun, Zhu Wang, et al.Post-seismic state assessment method for ±800 kV dry-type smoothing reactor based on machine learning[J]. High Voltage Apparatus, 2025, 61(4): 1-11.
[20] Song Xueguan, Cui Lei, Cao Maosen, et al.A CFD analysis of the dynamics of a direct-operated safety relief valve mounted on a pressure vessel[J]. Energy Conversion and Management, 2014, 81: 407-419.
[21] Speziale C G, Thangam S.Analysis of an RNG based turbulence model for separated flows[J]. International Journal of Engineering Science, 1992, 30(10): 1379-1388.
[22] 张宇娇, 孙宏达, 赵志涛, 等. 基于物理信息神经网络的电磁场计算方法[J]. 电工技术学报, 2024, 39(17): 5251-5261.
Zhang Yujiao, Sun Hongda, Zhao Zhitao, et al.Electromagnetic field calculation method based on physical informed neural network[J]. Transactions of China Electrotechnical Society, 2024, 39(17): 5251-5261.
[23] 贠祥, 张鑫, 王超, 等. 基于联合参数辨识的粒子群优化扩展粒子滤波的锂电池荷电状态估计[J]. 电工技术学报, 2024, 39(2): 595-606.
Yun Xiang, Zhang Xin, Wang Chao, et al.State of charge estimation of Li-ion battery using particle swarm optimization extended Kalman particle filter based on joint parameter identification[J]. Transactions of China Electrotechnical Society, 2024, 39(2): 595-606.