-
摘要:
开关电源作为现代机电设备中重要的提供能量设备，对其健康状态进行实时的监测与评估，是保障系统高效运行的关键。针对传统基于物理模型和基于机器学习方法在复杂非平稳退化信号预测中的局限性，提出一种结合经验模态分解(EMD)与长短时记忆网络(LSTM)的混合模型对开关电源的退化信号展开预测的方法。该方法通过EMD对开关电源退化信号进行多尺度分解，通过对提取各个有效特征分量继续进行处理与筛选，利用LSTM捕捉时间序列中的长期依赖与非线性演化规律，从而实现对开关电源性能退化趋势的高精度预测，为寿命评估与可靠性保障提供了有效途径。为验证所提方法的有效性，设计并开发了开关电源退化模拟试验台，通过设计故障注入电路模拟开关电源中滤波模块中电容退化情况、完成开关电源关键元件退化的模拟。在退化实验中完成了对所提方法有效性的验证。
Abstract:As a crucial energy provider in electronic systems, accurate monitoring and assessment of the health status of switching power supplies are crucial for ensuring efficient system operation. This research suggests a hybrid strategy that combines empirical mode decomposition (EMD) with a long short-term memory (LSTM) network to overcome the shortcomings of both data-driven and classic physics model-based methods in predicting complicated, non-stationary degradation signals. In the proposed method, EMD is employed to decompose degradation signals into multi-scale intrinsic mode functions. The relevant components are then selected and further processed, while the LSTM network captures long-term dependencies and nonlinear temporal dynamics in the time series. This approach enables accurate prediction of degradation trends in switch-mode power supplies. To verify the effectiveness of the proposed algorithm, a degradation simulation test platform for a switch-mode power supply is designed, and the fault injection method is developed. In order to simulate component-level degradation processes realistically, a fault-injection circuit is expressly made to mimic the degradation behavior of important components, especially capacitor degradation within the filtering module of the switch-mode power supply. Based on the constructed degradation experimental setup, experiments are conducted under degradation conditions to systematically validate the effectiveness of the proposed method.
-
图 10 整流滤波电容退化实验EMD结果
Figure 10. EMD results of rectifier filter capacitor degradation experiment
图 11 整流滤波电容退化实验预测结果
Figure 11. Prediction results of rectifier filter capacitor degradation experiment
图 12 3种结果在6组实验下对比结果
Figure 12. Comparison results of three results across six experimental groups
表 1 退化注入实验条件
Table 1. Experimental conditions for degradation injection
电源故障电容种类 初始容值/$ \text{μF} $ 组别 额定电压/ V 退化注入电压/ V 设置温度/℃ 整流滤波电容 1000 正常 28 28 25 过压 28 35 25 高温 28 28 75 LC滤波电容 470 正常 28 28 25 过压 28 35 25 高温 28 28 75 
下载: 导出CSV
表 2 预测结果对比结果统计
Table 2. Statistical comparison of prediction and actual results
实验组别 方法 $ {E}_{\text{RMSE}} $ $ {E}_{\text{MAE}} $ R2 第1组 EMD-LSTM 0.0203 0.0156 0.9882 Transformer 0.0246 0.0235 0.9278 LSTM 0.0437 0.0412 0.9217 第2组 EMD-LSTM 0.0226 0.0199 0.9875 Transformer 0.0396 0.0269 0.9373 LSTM 0.1294 0.0238 0.9348 第3组 EMD-LSTM 0.0417 0.0158 0.9896 Transformer 0.0471 0.0171 0.9592 LSTM 0.0687 0.0221 0.9218 第4组 EMD-LSTM 0.0238 0.0164 0.9851 Transformer 0.0654 0.0545 0.9559 LSTM 0.0745 0.0742 0.9765 第5组 EMD-LSTM 0.0752 0.017 0.9852 Transformer 0.0874 0.0378 0.9650 LSTM 0.1454 0.0543 0.9562 第6组 EMD-LSTM 0.0304 0.0214 0.9753 Transformer 0.0676 0.0654 0.9713 LSTM 0.0656 0.0565 0.9504
下载: 导出CSV
-
[1] Mattos E, Santos Spencer Andrade A M, Hollweg G V, et al. A review of boost converter analysis and design in aerospace applications[J]. IEEE Latin America Transactions, 2018, 16(2): 305-313. [2] Shan Y, Xu Z W, Dong J Q. Analysis of electrolytic capacitor life prediction in switching power supply[J]. Journal of Power Supply, 2016, 14(6): 87-92,121. [3] Wang H R, Davari P, Wang H, et al. Lifetime estimation of DC-link capacitors in adjustable speed drives under grid voltage unbalances[J]. IEEE Transactions on Power Electronics, 2019, 34(5): 4064-4078. [4] Yang S Y, Xiang D W, Bryant A, et al. Condition monitoring for device reliability in power electronic converters: a review[J]. IEEE Transactions on Power Electronics, 2010, 25(11): 2734-2752. [5] Sun B, Fan X J, Qian C, et al. PoF-simulation-assisted reliability prediction for electrolytic capacitor in LED drivers[J]. IEEE Transactions on Industrial Electronics, 2016, 63(11): 6726-6735. [6] Liu M, Lu Y S, Bian X Y, et al. Low ripple switching power supply for thermoelectric driving based on resonance analysis[C]//Proceedings of the 14th IEEE International Conference on Electronic Measurement & Instruments. Piscataway: IEEE Press, 2020: 698-704. [7] Duan X X, Zou J, Li B, et al. An online monitoring scheme of output capacitor’s equivalent series resistance for buck converters without current sensors[J]. IEEE Transactions on Industrial Electronics, 2021, 68(10): 10107-10117. [8] Zhang Y N, Lian Z, Fu W L, et al. An ESR quasi-online identification method for the fractional-order capacitor of forward converters based on variational mode decomposition[J]. IEEE Transactions on Power Electronics, 2022, 37(4): 3685-3690. [9] Liu K L, Shang Y L, Ouyang Q, et al. A data-driven approach with uncertainty quantification for predicting future capacities and remaining useful life of lithium-ion battery[J]. IEEE Transactions on Industrial Electronics, 2021, 68(4): 3170-3180. [10] Chang Y, Fang H J, Zhang Y. A new hybrid method for the prediction of the remaining useful life of a lithium-ion battery[J]. Applied Energy, 2017, 206: 1564-1578. [11] Jia Z, Liu Z B, Vong C M, et al. Real-time response-based fault analysis and prognostics techniques of nonisolated DC-DC converters[J]. IEEE Access, 2019, 7: 67996-68009. [12] Quan S, Wang Y R, Wu Y, et al. Remaining useful life prediction method for power converters based on unscented particle filter[J]. Journal of Power Supply, 2019, 17(5): 197-202. [13] Cheng W, Xie S S, Xing J, et al. Interactive hybrid model for remaining useful life prediction with uncertainty quantification of bearing in nuclear circulating water pump[J]. IEEE Transactions on Industrial Informatics, 2024, 20(2): 2154-2166. [14] Chen Z H, Wu M, Zhao R, et al. Machine remaining useful life prediction via an attention-based deep learning approach[J]. IEEE Transactions on Industrial Electronics, 2021, 68(3): 2521-2531. [15] Lu W G, Lu X M, Han J X, et al. Online estimation of ESR for DC-link capacitor of boost PFC converter using wavelet transform based time-frequency analysis method[J]. IEEE Transactions on Power Electronics, 2020, 35(8): 7755-7764. [16] Wang L, Yue J G, Su Y Q, et al. A novel remaining useful life prediction approach for superbuck converter circuits based on modified grey wolf optimizer-support vector regression[J]. Energies, 2017, 10(4): 459. [17] Wu Y, Wang Y R, Jiang Y Y, et al. Fault prediction method of DC/DC converter based on characteristic parameter degradation[J]. Journal of Power Supply, 2020, 18(4): 111-119. [18] Ilhan F, Karaahmetoglu O, Balaban I, et al. Markovian RNN: an adaptive time series prediction network with HMM-based switching for nonstationary environments[J]. IEEE Transactions on Neural Networks and Learning Systems, 2023, 34(2): 715-728. [19] Yang X W, Lu Y, Wang J, et al. Multiple IGBT open-circuit fault diagnosis strategy for MMC using feature reconstruction-based recurrent neural network[J]. IEEE Journal of Emerging and Selected Topics in Power Electronics, 2024, 12(6): 5625-5637. [20] Ma W, Tan L, Feng H, et al. A data-driven LSTM soft sensor model based on Bayesian optimization for hydraulic pressure measurement of excavator[J]. IEEE Sensors Journal, 2023, 23(21): 25749-25759. [21] Xiang S, Qin Y, Luo J, et al. Multicellular LSTM-based deep learning model for aero-engine remaining useful life prediction[J]. Reliability Engineering & System Safety, 2021, 216: 107927. [22] Amaral A M R, Cardoso A J M. Use of ESR to predict failure of output filtering capacitors in boost converters[C]//Proceedings of the IEEE International Symposium on Industrial Electronics. Piscataway: IEEE Press, 2006: 1309-1314. [23] Kwon J E, Shifat T A, Kareem A B, et al. RUL prediction of switched mode power supply using a Kalman filter assisted deep neural network[J]. Processes, 2022, 10(1): 55. [24] Karmiani D, Kazi R, Nambisan A, et al. Comparison of predictive algorithms: backpropagation, SVM, LSTM and Kalman filter for stock market[C]//Proceedings of the Amity International Conference on Artificial Intelligence. Piscataway: IEEE Press, 2019: 228-234. [25] 勾玄, 肖先勇. 基于经验模式分解与LSTM神经网络的短期电价预测模型[J]. 西安理工大学学报, 2020, 36(1): 129-134.Gou X, Xiao X Y. Short-term electricity price forecasting model based on empirical mode decomposition and LSTM neural network[J]. Journal of Xi’an University of Technology, 2020, 36(1): 129-134(in Chinese). [26] Chen D Q, Hong W C, Zhou X Z. Transformer network for remaining useful life prediction of lithium-ion batteries[J]. IEEE Access, 2022, 10: 19621-19628. [27] Hochreiter S, Schmidhuber J. Long short-term memory[J]. Neural Computation, 1997, 9(8): 1735-1780. -
下载:
点击查看大图
计量
- 文章访问数: 135
- HTML全文浏览量: 88
- PDF下载量: 4
- 被引次数: 0
