Small sample state of health estimation based on weighted Gaussian process regression

Sheng, Hanmin; Liu, Xin; Bai, Libing; Dong, Hanchuan; Cheng, Yuhua

doi:10.1016/j.est.2021.102816

Cited by 36 publications

(11 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…At present, for the strong nonlinearity of Li‐ion batteries, 27 the SOH researches is mainly divided into two categories: mathematical‐model‐driven and data‐driven methods 28 . These two broad categories of methods contain more than a dozen kinds of ways 29 …”

Section: Introductionmentioning

confidence: 99%

“…26 At present, for the strong nonlinearity of Li-ion batteries, 27 the SOH researches is mainly divided into two categories: mathematical-model-driven and datadriven methods. 28 These two broad categories of methods contain more than a dozen kinds of ways. 29 The mathematical-model-driven method appeared early and is a kind of mature method, which mainly simplifies the complex reaction inside the Li-ion battery and improves the efficiency by establishing the equivalent model of the Li-ion battery.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Fusion estimation strategy based on dual adaptive Kalman filtering algorithm for the state of charge and state of health of hybrid electric vehicle Li‐ion batteries

Ren

Wang

Chen

et al. 2022

Intl J of Energy Research

View full text Add to dashboard Cite

Summary To accurately evaluate the state of charge (SOC) and state of health (SOH) of Li‐ion battery, the second‐order RC equivalent‐circuit model is used to characterize the battery performance, a novel dual adaptive Kalman filtering algorithm is presented by adding double cycles and noise adaptive steps to realize the joint estimation of the SOC and internal resistance. The state variables can be corrected with each other as go through the cycle under three operating conditions. The accuracy of the SOC estimation method proposed in this paper is significantly improved compared with the extended Kalman filtering and the unscented Kalman filtering algorithm. Under three operating conditions, the average error and the maximum error decreased obviously. An equation for calculating the SOH in terms of internal resistance increase was built. The estimation result of the SOH effectively simulated the actual situation, compared with the actual result, the maximum error under the three operating conditions are within a lower level than the improved unscented Kalman filtering algorithm. The convergence effect of the algorithm has obvious advantages over that of the algorithm used for comparison, which could effectively track the state change of the battery.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Fusion estimation strategy based on dual adaptive Kalman filtering algorithm for the state of charge and state of health of hybrid electric vehicle Li‐ion batteries

Ren

Wang

Chen

et al. 2022

Intl J of Energy Research

View full text Add to dashboard Cite

show abstract

“…Tang et al (2019) presented a systematic method combining experimental and computational approaches for key parameter acquisition of an electrochemical model. However, model-based estimation requires fundamental knowledge of electrochemical behaviors inside the battery and heavily depends on the model's accuracy (Sheng et al, 2021).…”

Section: Introductionmentioning

confidence: 99%

Intelligent Online Health Estimation for Lithium-Ion Batteries Based on a Parallel Attention Network Combining Multivariate Time Series

et al. 2022

View full text Add to dashboard Cite

With the development of cloud and edge computing, data-driven methods for estimating a Li-ion battery’s state of health are becoming increasingly attractive. However, existing data-driven estimation methods have problems of low accuracy and weak robustness that need to be solved. Focusing on these points, this paper proposes a parallel attention network combining multivariate time series to extract the mapping relationship between the selected health features and the state of health. First, multivariate time series are extracted, which can describe battery aging characteristics at different scales. Then, a novel parallel learning framework is designed by integrating long short-term memory cells and an attention mechanism, which can make full use of the health features and help to solve the challenging issues of estimation accuracy and robustness. Experimental results show that the proposed model is able to obtain estimation results for different batteries with a mean absolute percentage error of less than 1%. Compared with existing methods, the maximum error of the proposed model is 38% lower on average. Furthermore, even under measurement noise injections of 50 dB, a preferable estimation result (maximum error of 3.36%) can still be achieved.

show abstract

“…West et al 14 utilise the capacity of interpolation and extrapolation of GPR with sparse, highly clustered data to produce smoother estimates of radiation intensity in the reconstruction of nuclear radiation map when provided with uncertain, irregularly spaced observations. The fields of the applications of GPR include but are not limited to environment 15 – 17 , materials 18 , engineering 19 , 20 , and finance 21 . For the research target of this paper, the available data also express the above features, such as small samples, complex interrelationships and irregular observations.…”

Section: Introductionmentioning

confidence: 99%

Stiffness estimation of planar spiral spring based on Gaussian process regression

Liu

Osman

Kouzbary

et al. 2022

Sci Rep

View full text Add to dashboard Cite

Planar spiral spring is important for the dimensional miniaturisation of motor-based elastic actuators. However, when the stiffness calculation of the spring arm is based on simple beam bending theory, the results possess substantial errors compared with the stiffness obtained from finite-element analysis (FEA). It deems that the errors arise from the spiral length term in the calculation formula. Two Gaussian process regression models are trained to amend this term in the stiffness calculation of spring arm and complete spring. For the former, 216 spring arms’ data sets, including different spiral radiuses, pitches, wrap angles and the stiffness from FEA, are employed for training. The latter engages 180 double-arm springs’ data sets, including widths instead of wrap angles. The simulation of five spring arms and five planar spiral springs with arbitrary dimensional parameters verifies that the absolute values of errors between the predicted stiffness and the stiffness from FEA are reduced to be less than 0.5% and 2.8%, respectively. A planar spiral spring for a powered ankle–foot prosthesis is designed and manufactured to verify further, of which the predicted value possesses a 3.25% error compared with the measured stiffness. Therefore, the amendment based on the prediction of trained models is available.

show abstract

Small sample state of health estimation based on weighted Gaussian process regression

Cited by 36 publications

References 25 publications

Fusion estimation strategy based on dual adaptive Kalman filtering algorithm for the state of charge and state of health of hybrid electric vehicle Li‐ion batteries

Fusion estimation strategy based on dual adaptive Kalman filtering algorithm for the state of charge and state of health of hybrid electric vehicle Li‐ion batteries

Intelligent Online Health Estimation for Lithium-Ion Batteries Based on a Parallel Attention Network Combining Multivariate Time Series

Stiffness estimation of planar spiral spring based on Gaussian process regression

Contact Info

Product

Resources

About