基于多尺度特征融合的并行神经网络剩余寿命预测方法

余萍; 王浩年; 曹洁

doi:10.19912/j.0254-0096.tynxb.2024-1676

PDF(1649 KB)

太阳能学报 ›› 2026, Vol. 47 ›› Issue (1) : 785-796. DOI: 10.19912/j.0254-0096.tynxb.2024-1676

基于多尺度特征融合的并行神经网络剩余寿命预测方法

余萍^1~3, 王浩年¹, 曹洁¹

作者信息 +

REMAINING USEFUL LIFE PREDICTION METHOD BASED ON PARALLEL NEURAL NETWORKS WITH MULTI-SCALE FEATURE FUSION

Yu Ping^1~3, Wang Haonian¹, Cao Jie¹

Author information +

文章历史 +

摘要

为更准确预测锂电池的剩余使用寿命（RUL）,提高其可靠性,确保稳定运行,提出一种基于多尺度特征融合的并行神经网络预测方法。首先,利用不同尺度的时间卷积网络（TCN）提取锂电池的多尺度特征,从而增强局部和全局特征的提取能力;接着,引入交叉注意力机制对特征进行筛选与融合,以提取关键的退化信息;随后,构建并行的Bi-LSTM和Bi-GRU网络,以学习退化特征并建立时间尺度上的长期依赖关系,最终实现RUL预测。通过美国航空航天局（NASA）和CALCE锂电池数据集验证,证明了所提方法在不同背景下的有效性。

Abstract

To achieve more accurate predictions of the remaining useful life （RUL） of lithium-ion batteries and enhance their reliability to ensure stable operation, this paper proposes a parallel neural network prediction method based on multi-scale feature fusion. First, multi-scale features of the lithium-ion batteryies are extracted using temporal convolutional network （TCN） at different scales, enhancing the capture of both local and global features. Then, a cross-attention mechanism is introduced to filter and fuse the features, focusing on key degradation information. Next, parallel Bi-LSTM and Bi-GRU networks are constructed to learn degradation features and establish long-term dependencies on the time scale, ultimately achieving RUL prediction. The proposed method is validated using the NASA and CALCE lithium battery datasets, demonstrating its effectiveness in various contexts.

导出引用

余萍, 王浩年, 曹洁. 基于多尺度特征融合的并行神经网络剩余寿命预测方法[J]. 太阳能学报. 2026, 47(1): 785-796 https://doi.org/10.19912/j.0254-0096.tynxb.2024-1676

Yu Ping, Wang Haonian, Cao Jie. REMAINING USEFUL LIFE PREDICTION METHOD BASED ON PARALLEL NEURAL NETWORKS WITH MULTI-SCALE FEATURE FUSION[J]. Acta Energiae Solaris Sinica. 2026, 47(1): 785-796 https://doi.org/10.19912/j.0254-0096.tynxb.2024-1676

中图分类号： TM912

参考文献

[1] LI H Q, ZHANG Z X, LI T M, et al.A review on physics-informed data-driven remaining useful life prediction: challenges and opportunities[J]. Mechanical systems and signal processing, 2024, 209: 111120.
[2] FERREIRA C, GONÇALVES G. Remaining useful life prediction and challenges: a literature review on the use of machine learning methods[J]. Journal of manufacturing systems, 2022, 63: 550-562.
[3] 李彦夫, 韩特. 基于深度学习的工业装备PHM研究综述[J]. 振动、测试与诊断, 2022, 42(5): 835-847.LI Y F, HAN T. Summary of research on PHM of industrial equipment based on deep learning[J]. Journal of vibration, measurement & diagnosis, 2022, 42(5): 835-847.
[4] 李炳金, 韩晓霞, 张文杰, 等. 锂离子电池剩余使用寿命预测方法综述[J]. 储能科学与技术, 2024, 13(4): 1266-1276.LI B J, HAN X X, ZHANG W J, et al. Review of the remaining useful life prediction methods for lithium-ion batteries[J]. Energy storage science and technology, 2024, 13(4): 1266-1276.
[5] ZHANG C L, ZHAO S S, HE Y G.An integrated method of the future capacity and RUL prediction for lithium-ion battery pack[J]. IEEE transactions on vehicular technology, 2022, 71(3): 2601-2613.
[6] CHEN C, WEI J, LI Z H.Remaining useful life prediction for lithium-ion batteries based on a hybrid deep learning model[J]. Processes, 2023, 11(8): 2333.
[7] ZHANG Y, LI Y F.Prognostics and health management of Lithium-ion battery using deep learning methods: a review[J]. Renewable and sustainable energy reviews, 2022, 161: 112282.
[8] 任超, 李慧琴, 李天梅, 等. 基于退化模型动态校准的设备剩余寿命预测方法[J]. 航空学报, 2023, 44(19): 171-186.REN C, LI H Q, LI T M, et al. Equipment remaining useful life prediction method with dynamic calibration of degradation model[J]. Acta aeronautica et astronautica sinica, 2023, 44(19): 171-186.
[9] REN C, LI T M, ZHANG Z X, et al.An online remaining useful life prediction method with adaptive degradation model calibration[J]. IEEE sensors journal, 2023, 23(23): 29774-29792.
[10] 邓飞跃, 陈哲, 郝如江, 等. 基于MsTCN-Transformer模型的轴承剩余使用寿命预测研究[J]. 振动与冲击, 2024, 43(4): 279-287.DENG F Y, CHEN Z, HAO R J, et al. Research on bearing remaining useful life prediction based on an MsTCN-Transformer model[J]. Journal of vibration and shock, 2024, 43(4): 279-287.
[11] 徐洲常, 王林军, 刘洋, 等. 采用改进回归型支持向量机的滚动轴承剩余寿命预测方法[J]. 西安交通大学学报, 2022, 56(3): 197-205.XU Z C, WANG L J, LIU Y, et al. A prediction method for remaining life of rolling bearing using improved regression support vector machine[J]. Journal of Xi’an Jiaotong University, 2022, 56(3): 197-205.
[12] 梁佳佳, 何晓霞, 肖浩逸. 基于CS-DBN的锂电池剩余寿命预测[J]. 太阳能学报, 2024, 45(3): 251-259.LIANG J J, HE X X, XIAO H Y. Prediction of remaining useful life of lithium batteries based on CS-DBN[J]. Acta energiae solaris sinica, 2024, 45(3): 251-259.
[13] 张然, 刘天宇, 金光. 基于核自构建-高斯过程回归的锂离子电池剩余使用寿命预测[J]. 系统工程与电子技术, 2023, 45(8): 2623-2633.ZHANG R, LIU T Y, JIN G. Remaining useful life prediction of lithium-ion batteries based on Gaussian process regression with self-constructed kernel[J]. Systems engineering and electronics, 2023, 45(8): 2623-2633.
[14] 贺宁, 张思媛, 李若夏, 等. 粒子滤波和GRU神经网络融合的锂电池RUL预测[J]. 哈尔滨工业大学学报, 2024, 56(5): 142-151.HE N, ZHANG S Y, LI R X, et al. RUL prediction of lithium battery based on particle filter and GRU neural network fusion[J]. Journal of Harbin Institute of Technology, 2024, 56(5): 142-151.
[15] WANG B, LEI Y G, YAN T, et al.Recurrent convolutional neural network: a new framework for remaining useful life prediction of machinery[J]. Neurocomputing, 2020, 379: 117-129.
[16] 吴诗淼, 王文波, 朱婷, 等. 基于跳跃连接多尺度CNN的锂离子电池剩余寿命预测[J]. 太阳能学报, 2024, 45(7): 199-208.WU S M, WANG W B, ZHU T, et al. Prediction of residual life of lithium ion battery based on multi-scale CNN with jump connection CNN[J]. Acta energiae solaris sinica, 2024, 45(7): 199-208.
[17] 叶林峰, 石元博, 黄越洋. 基于BiGRU网络的锂电池寿命预测[J]. 电源技术, 2021, 45(5): 598-601.YE L F, SHI Y B, HUANG Y Y. Lithium battery life prediction based on BiGRU network[J]. Chinese journal of power sources, 2021, 45(5): 598-601.
[18] 高德欣, 刘欣, 杨清. 基于卷积神经网络与双向长短时融合的锂离子电池剩余使用寿命预测[J]. 信息与控制, 2022, 51(3): 318-329, 360.GAO D X, LIU X, YANG Q. Remaining useful life prediction of lithium-ion battery based on CNN and BiLSTM fusion[J]. Information and control, 2022, 51(3): 318-329, 360.
[19] WANG L, CAO H R, XU H, et al.A gated graph convolutional network with multi-sensor signals for remaining useful life prediction[J]. Knowledge-based systems, 2022, 252: 109340.
[20] BAI S J, KOLTER J Z, KOLTUN V. An empirical evaluation of generic convolutional and recurrent networks for sequence modeling[EB/OL]. 2018: arXiv: 1803.01271. https://arxiv.org/abs/1803.01271
[21] SONG Y, GAO S Y, LI Y B, et al.Distributed attention-based temporal convolutional network for remaining useful life prediction[J]. IEEE internet of things journal, 2021, 8(12): 9594-9602.
[22] LIN L, WU J L, FU S, et al.Channel attention & temporal attention based temporal convolutional network: a dual attention framework for remaining useful life prediction of the aircraft engines[J]. Advanced engineering informatics, 2024, 60: 102372.
[23] 朱元富, 贺文武, 李建兴, 等. 基于Bi-LSTM/Bi-GRU循环神经网络的锂电池SOC估计[J]. 储能科学与技术, 2021, 10(3): 1163-1176.ZHU Y F, HE W W, LI J X, et al. SOC estimation for Li-ion batteries based on Bi-LSTM and Bi-GRU[J]. Energy storage science and technology, 2021, 10(3): 1163-1176.
[24] TANG X L, WAN H, WANG W W, et al.Lithium-ion battery remaining useful life prediction based on hybrid model[J]. Sustainability, 2023, 15(7): 6261.
[25] LI H, ZHAO W, ZHANG Y X, et al.Remaining useful life prediction using multi-scale deep convolutional neural network[J]. Applied soft computing, 2020, 89: 106113.
[26] LIU H, LIU Z Y, JIA W Q, et al.Remaining useful life prediction using a novel feature-attention-based end-to-end approach[J]. IEEE transactions on industrial informatics, 2021, 17(2): 1197-1207.
[27] 杨硕, 高成. 基于长短期记忆网络与轻梯度提升机的航空发动机大修期内剩余寿命预测[J]. 航空发动机, 2024, 50(3): 87-92.
YANG S, GAO C.Remaining useful life prediction of aeroengine during during overhaul based on long short-term memory network and light gradient boosting machine[J]. Aeroengine, 2024, 50(3): 87-92.
[28] SONG T, LIU C, WU R, et al.A hierarchical scheme for remaining useful life prediction with long short-term memory networks[J]. Neurocomputing, 2022, 487: 22-33.
[29] ZHANG J S, JIANG Y C, WU S M, et al.Prediction of remaining useful life based on bidirectional gated recurrent unit with temporal self-attention mechanism[J]. Reliability engineering & system safety, 2022, 221: 108297.
[30] REN L K, QIN H Q, XIE Z B, et al.Aero-engine remaining useful life estimation based on multi-head networks[J]. IEEE transactions on instrumentation and measurement, 2022, 71: 3505810.
[31] YANG Q C, TANG B P, LI Q K, et al.Dual-frequency enhanced attention network for aircraft engine remaining useful life prediction[J]. ISA transactions, 2023, 141: 167-183.