Model Migration Neural Network for Predicting Battery Aging Trajectories

Tang, Xiaopeng; Liu, Kailong; Wang, Xin; Gao, Furong; Macro, James; Widanage, Widanalage Dhammika

doi:10.1109/tte.2020.2979547

Cited by 141 publications

(60 citation statements)

References 59 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Where, represents one of the samples, and represents the batch size. The mean and variance 2 of the input data can be calculated by (10) and (11), respectively:…”

Section: ) Batch Normalizationmentioning

confidence: 99%

“…With the continuous development of machine learning technology, advanced methods emerge one after another [11,12] and are widely applied in various fields, such as medical fitting prediction [13], battery capacity and aging prediction [14][15][16], natural language processing [17], image processing [18] and so on. And the classification methods of HSIs are also gradually developed, which can be roughly divided into two categories according to whether the use of high-level features-the traditional classification methods and the classification methods based on deep learning.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

SSDANet: Spectral-Spatial Three-Dimensional Convolutional Neural Network for Hyperspectral Image Classification

et al. 2020

View full text Add to dashboard Cite

Recently, the classification of hyperspectral images has made great process. Especially, the classification methods based on three-dimensional convolutional neural network have remarkable performance due to the uniqueness of hyperspectral images. However, the hyperspectral classification still faces great challenges due to a series of problems such as the insufficient extraction of spectral-spatial features, the lack of labeled samples, the large amount of noise, the tendency of overfitting and so on. Therefore, SSDANet is proposed to solve the above problems and promote the further development of hyperspectral classification technology based on deep learning. SSDANet is a spectral-spatial three-dimensional convolutional neural network with a deep and wide structure that can significantly improve classification performance. In SSDANet, the spectral-spatial dense connectivity is put forward to protect the integrity of information. It is made up of the spectral branch and the spatial branch, which can learn and reuse the spectralspatial features. Besides, the spectral-spatial attention mechanism is proposed to adapt the special structure of hyperspectral images. It can excite important spectral-spatial information and suppress unimportant spectral-spatial information. In addition, a series of optimization methods including data augmentation, batch normalization, dropout, exponential decay learning rate, and L2 regularization are adopted to alleviate the problem of overfitting and improve the classification results. To verify the performance of SSDANet, experiments were implemented on two widely used datasets-Pavia University and Indian Pines. Under the condition of limited labeled samples, the classification evaluation indexes of OA, AA, and Kappa on the two datasets all exceeded 99%, reaching state-of-the-art performance. INDEX TERMS artificial intelligence, hyperspectral imaging, image processing, pattern recognition, remote sensing

show abstract

“…Where, represents one of the samples, and represents the batch size. The mean and variance 2 of the input data can be calculated by (10) and (11), respectively:…”

Section: ) Batch Normalizationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

SSDANet: Spectral-Spatial Three-Dimensional Convolutional Neural Network for Hyperspectral Image Classification

et al. 2020

View full text Add to dashboard Cite

show abstract

“…Lithium-ion (Li-ion) batteries are generally connected in series or in parallel to provide enough voltage and power for electric vehicles (EVs) [1]- [4]. One key but challenging issue is to equalize the inconsistent voltages among cells, owing to that the performance and safety of battery packs/modules are strongly related to the voltage consistency level [5].…”

Section: Introductionmentioning

confidence: 99%

Automotive Battery Equalizers Based on Joint Switched-Capacitor and Buck-Boost Converters

Liu

Yang

Tang

et al. 2020

IEEE Trans. Veh. Technol.

Self Cite

View full text Add to dashboard Cite

A series of integrated equalizers based on joint buckboost (BB) and switched-capacitor (SC) converters are proposed for balancing the voltages of series-connected battery packs. All these equalizers realize the any-cells-to-any-cells (AC2AC) equalization mode without increasing any MOSFETs and drivers. Corresponding operational principles are analyzed and the expressions of balancing currents are verified by experimental waveforms. According to the comparative balancing experiments for four and six series-connected Li-ion cells, one proposed CBB-PCSC equalizer, which achieves the dual AC2AC balancing modes through the integration of both coupled buck-boost (CBB) and parallel-connected switched-capacitor (PCSC) converters, leads to the highest balancing speed and efficiency. Moreover, compared with several conventional equalizers, this CBB-PCSC topology also has the compact size and low cost, making it become a well-performing integrated topology for automotive battery voltages equalization.

show abstract

“…There are mainly artificial intelligence methods and statistical data-driven methods. Among them, artificial intelligence methods include support vector machine regression [9], correlation vector machine [10], neural network [11,12], ant colony algorithm [13], etc. This type of method is based on a large amount of degradation data.…”

Section: Introductionmentioning

confidence: 99%

Remaining Useful Life Prediction Under Imperfect Prior Degradation Information

et al. 2020

View full text Add to dashboard Cite

The remaining useful life (RUL) prediction is the core of equipment maintenance and decisionmaking. Accurate RUL prediction can make effective maintenance before the failure occurs to reduce the probability of equipment failure. However, in industrial practice, we often face the situation that prior information is insufficient or inaccurate, which could influence our prediction of RUL and reduce the prediction accuracy severely. To solve this problem, we study the issue of RUL prediction under imperfect prior degradation data by reasonably fusing the prior information and the field degradation data. Firstly, based on the linear Wiener degradation process, we prove a conclusion that the random parameter estimation results by the joint Bayesian algorithm and the expectation-maximization (EM) algorithm are the same as that by the maximum likelihood estimation (MLE) method. It shows that the joint estimation method completely overcomes the influence of prior information, and the more iterations, the smaller proportion of prior information. Secondly, we also prove that the random parameter joint updating method for the nonlinear Wiener degradation process has the same characteristics. Then, a heuristic algorithm that reasonably fuses the prior information and the field degradation data is proposed, which controls the number of iterations of the joint updating algorithm based on the credibility of the prior information. It is also applied to the nonlinear degradation process by not iterating the nonlinear coefficients. Finally, the correctness of the conclusion of this paper is verified by the simulated degradation data, and the effectiveness of the proposed heuristic updating method is verified by the actual lithium battery degradation data.

show abstract

Model Migration Neural Network for Predicting Battery Aging Trajectories

Abstract: Please refer to published version for the most recent bibliographic citation information. If a published version is known of, the repository item page linked to above, will contain details on accessing it.

Cited by 141 publications

References 59 publications

SSDANet: Spectral-Spatial Three-Dimensional Convolutional Neural Network for Hyperspectral Image Classification

SSDANet: Spectral-Spatial Three-Dimensional Convolutional Neural Network for Hyperspectral Image Classification

Automotive Battery Equalizers Based on Joint Switched-Capacitor and Buck-Boost Converters

Remaining Useful Life Prediction Under Imperfect Prior Degradation Information

Contact Info

Product

Resources

About