计算机科学 ›› 2026, Vol. 53 ›› Issue (8): 103-116.doi: 10.11896/jsjkx.250500134
廖雪超, 邹航, 吕沛东, 曾志强
LIAO Xuechao, ZOU Hang, LYU Peidong, ZENG Zhiqiang
摘要： 锂离子电池容量预测对于提高锂电池的经济性和安全性具有重要意义,而现有方法在处理锂电池数据时存在局部信息缺失和数据质量不佳的问题。为解决上述问题,首先将STL分解方法嵌入扩散模型,设计了DMnet扩散模型,提取STL分解特征作为先验条件改善扩散模型的数据生成;然后将STL分解方法引入编解码注意力模型,来更好地发现时间序列的特征依赖性,从而设计了STLnet预测模型;最后结合以上扩散模型和预测模型,提出了SDMnet集成模型,采用STL提取的特征动态调节数据增强和预测两个过程,从而实现锂电池容量的高精度预测。通过对比实验可知,在STL分解的调节下,使用扩散模型进行数据增强有效提高了预测模型的泛化能力,而改进的EDAnet能够更高精度地预测锂电池容量,综合以上方法的SDMnet展现了卓越的预测性能和泛化能力。
中图分类号:
| [1] ZHAO X,DOERING O C,TYNER W E.The economic competitiveness and emissions of battery electric vehicles in China[J].Applied Energy,2015,156:666-675. [2] BAUMHÖFER T,BRÜHL M,ROTHGANG S,et al.Production caused variation in capacity aging trend and correlation to initial cell performance[J].Journal of Power Sources,2014,247:332-338. [3] PINSON M B,BAZANT M Z.Theory of SEI formation in rechargeable batteries:capacity fade,accelerated aging and lifetime prediction[J].Journal of the Electrochemical Society,2013,160:243. [4] SHI X,CHEN Z,WANG H,et al.Convolutional LSTM net-work:A machine learning approach for precipitation nowcasting[C]//Advances in Neural Information Processing Systems 28(NIPS 2015).MIT Press,2015. [5] LIU X,ZHANG Q.Combining seasonal and trend decompositionusing LOESS with a gated recurrent unit for climate time series forecasting[J].IEEE Access,2024,12:85275-85290. [6] JIAO M,WANG D,QIU J.A GRU-RNN based momentum optimized algorithm for SOC estimation[J].Journal of Power Sources,2020,459(31):228051. [7] VASWANI A,SHAZEER N,PARMAR N,et al.Attention is all you need[C]//Proceedings of the 31st International Conference on Neural Information Processing Systems.2017:6000-6010. [8] NIU Z,ZHONG G,YU H.A review on the attention mechanism of deep learning[J].Neurocomputing,2021,452:48-62. [9] ZHOU H,ZHANG S,PENG J,et al.Informer:Beyond efficient transformer for long sequence time-series forecasting[J].Proceedings of the AAAI Conference on Artificial Intelligence,2021,35(12):11106-11115. [10] HAN Y,LI C,ZHENG L,et al.Remaining useful life prediction of lithium-ion batteries by using a denoising transformer-based neural network[J].Energies,2023,16(17):6328. [11] WOO G,LIU C,SAHOO D,et al.ETSformer:Exponentialsmoothing transformers for time-series forecasting[J].arXiv:2202.01381,2022. [12] FAUZI M R,YUDISTIRA N,MAHMUDY W F.State-of-Health prediction of lithium-ion batteries using exponential smoothing transformer with seasonal and growth embedding[J].IEEE Access,2024,12:14659-14670. [13] KULEVOME D K B,KHOKAR S U D,YANG C C,et al.STFT-DA:a time-frequency domain data augmentation for enhancing fault diagnosis in rotating equipment with limited data[EB/OL].https://doi.org/10.1080/10589759.2025.2560024. [14] YANG Z,LI Y,ZHOU G.TS-GAN:Time-series GAN for sensor-based health data augmentation[J].ACM Transactions on Computing for Healthcare,2023,4(2):12. [15] HU C,CHENG F,ZHAO Y,et al.State of charge estimation for lithium-ion batteries based on data augmentation with generative adversarial network[J].Journal of Energy Storage,2024,80:110004. [16] HO J,JAIN A,ABBEEL P.Denoising diffusion probabilisticmodels[C]//Advances in Neural Information Processing Systems.2020:6840-6851. [17] LI Y,LU X,WANG Y,et al.Generative time series forecasting with diffusion,denoise,and disentanglement[C]//Advances in Neural Information Processing Systems.2022:23009-23022. [18] SOLIS-MARTIN D,GALAN-PAEZ J,BORREGO-DIAZ J.D3A-TS:Denoising-driven data augmentation in time series[J].arXiv:2312.05550,2023. [19] WEN H,LIN Y,XIA Y,et al.DiffSTG:Probabilistic spatio-temporal graph forecasting with denoising diffusion models[C]//Proceedings of the 31st ACM International Conference on Advances in Geographic Information Systems.2023. [20] KOLLOVIEH M,ANSARI A F,BOHLKE-SCHNEIDER M,et al.Predict,refine,synthesize:Self-guiding diffusion models for probabilistic time series forecasting[J].Advances in Neural Information Processing Systems,2023,36:28341-28364. [21] WANG Z,WEN Q,ZHANG C,et al.DiffLoad:Uncertaintyquantification in electrical load forecasting with the diffusion model[J].IEEE Transactions on Power Systems,2025,40(2):1777-1789. [22] SCHÖLKOPF B,LOCATELLO F,BAUER S,et al.Towardcausal representation learning[J].Proceedings of the IEEE,2021,105(5):612-634. [23] LING Z,YU K,ZHANG Y,et al.Causal Learner:A Toolbox for Causal Structure and Markov Blanket Learning[J].Pattern Recognition Letters,2022,163:92-95. [24] WANG Y,YU K,XIANG G,et al.Discovering causally invariant features for out-of-distribution generalization[J].Pattern Recognition,2024,150:100338. [25] LING Z,LI Y,ZHANG Y,et al.A Light Causal Feature Selection Approach to High-Dimensional Data[J].IEEE Transactions on Knowledge and Data Engineering,2023,35(8):7639-7650. [26] QIU Y,HE Z,ZHANG W,et al.MSGCN-ISTL:A multi-scaledself-attention-enhanced graph convolutional network with improved STL decomposition for probabilistic load forecasting[J].Expert Systems with Applications,2024,238:121737. [27] YAN X,CHANG Y,YANG Y,et al.Monthly runoff prediction using modified CEEMD-based weighted integrated model[J].Journal of Water and Climate Change,2021,12(5):1744-1760. [28] CLEVELAND R B,CLEVELAND W S,MCRAE J E,et al.STL:A seasonal-trend decomposition[J].Journal of Official Statistics,1990,6(1):3-73. [29] LIAO X,LIU Z,ZHENG X,et al.Wind power prediction based on periodic characteristic decomposition and multi-layer attention network[J].Neurocomputing,2023,534:119-132. [30] CAO H,ZHANG Z,LIU S,et al.A survey on generative diffusion models[J].IEEE Transactions on Knowledge and Data Engineering,2024,36(7):2814-2830. [31] ZHANG L,RAO A,AGRAWALA M.Adding conditional control to text-to-image diffusion models[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision.2023:3836-3847. [32] BENAVOLI A,CORANI G,MANGILI F,et al.A BayesianWilcoxon signed-rank test based on the Dirichlet process[C]//International Conference on Machine Learning.2014. |
|
||
首页