Adaptive Neural Network-Based Prescribed-Time Observer for Battery State-of-Charge Estimation

Pan, Chenyang; Peng, Zhaoxia; Yang, Shichun; Wen, Guoguang; Huang, Tingwen

doi:10.1109/tpel.2022.3205437

Cited by 28 publications

(10 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…GRU is an improved model based on LSTM, and the two principles are similar. Compared with LSTM, GRU [1,31] has a simpler network structure, fewer parameters, and faster convergence. Specifically, GRU lacks forgetting gates and units, which are updated to control the information transfer at the previous moment and the hidden layer computed at the current moment.…”

Section: Gru Networkmentioning

confidence: 99%

See 1 more Smart Citation

Lithium Battery SOC Estimation Based on Multi-Head Attention Mechanism and GRU Algorithm

Li,

Dumlao

2023

AJST

View full text Add to dashboard Cite

Pure electric vehicles have been widely used due to their non-pollution, low noise, high energy conversion efficiency and other advantages. SOC (State of Charge) is a crucial indicator for lithium batteries and pure electric vehicles. SOC cannot be directly measured. This article designs a new network structure. It is the GRU-Attention network structure. The stacked GRU algorithm in GRU-Attention network extracts the temporal characteristics of lithium battery test data, and the stacked multi-head self-attention network extracts the global information. The GRU-Attention network can avoid long-term dependency and gradient disappearance problems. The proposed network utilizes Stacked FFN as the dense layer. This article will test the network designed in the public data set at the University of Maryland. Simultaneously, this article compares the effects of different BatchSize on the performance of the algorithm. The network training process converges more effectively with a smaller BatchSize. Both too large and too small BatchSize have a negative impact on the generalization performance of the network. The extraction of the time-order character, however, may be hampered if the timestamp is too small. At the same time, the paper also compares the GRU-Attention network horizontally with the GRU and Attention networks. Eventually, the GRU-Attention network proposed in this article could better meet the estimate of the lithium battery SOC.

show abstract

Section: Gru Networkmentioning

confidence: 99%

“…Global energy shortage [1] and environmental problems have become urgent research hotspots. Conventional fuelpowered vehicles are fueled by fossil fuels.…”

Section: Introductionmentioning

confidence: 99%

Lithium Battery SOC Estimation Based on Multi-Head Attention Mechanism and GRU Algorithm

Li,

Dumlao

2023

AJST

View full text Add to dashboard Cite

show abstract

“…Relevant research shows that, based on the battery principle, the battery equivalent circuit model, which is composed of resistors, can be applied to model the energy consumption of many kinds of batteries [9]. Furthermore, in order to describe the highly nonlinear characteristics of battery performance, scholars used a neural network battery model to explore the operation performance of lithium batteries [10]. In addition, the electromotor equipped for EVs and the recovery of braking energy are also the focus of researchers [11].…”

Section: Introductionmentioning

confidence: 99%

A Driving-Adapt Strategy for the Electric Vehicle with Magneto-Rheological Fluid Transmission Considering the Powertrain Characteristics

Liao

Ning

Wang

et al. 2022

Sensors

View full text Add to dashboard Cite

The additional energy consumption caused by the incompatibility between existing electric vehicle (EV) powertrain characteristics and driving conditions inevitably curbs the promotion and development of EVs. Hence, there is an urgent demand for the driving-adapt strategy, which aims to minimize EV energy consumption due to both powertrain characteristics and driving conditions. In order to fully explore the EV driving-adapt potential, this paper equips the EV with a magneto-rheological fluid transmission (MRFT). First, an EV dynamics analysis of the driving conditions, the powertrain model considering the energy transmission process, and the driving-adapt transmission model considering magneto-rheological fluid (MRF) is conducted to clarify the quantitative relation between the driving conditions and the powertrain. Second, a driving-adapt optimization strategy in the specific driving condition is proposed. Finally, the results and discussions are executed to study (i) the determination of the MRFT fixed speed ratio and variable speed ratio range, (ii) the application potential analysis of the proposed strategy, and (iii) the feasibility analysis of the proposed strategy. The results indicate that (i) the urban driving condition has higher requirements for the MRFT, (ii) EVs equipped with MRFT achieve the expected driving performance at the most states of charge (SOCs) and environmental temperatures, except for the SOC lower than 10%, and (iii) the driving time with efficiency greater than 80% can be increased by the MRFT from 10.1% to 58.7% and from 66.8% to 88.8% in the urban and suburban driving conditions, respectively. Thus, the proposed driving-adapt strategy for the EV equipped with the MRFT has the potential to alleviate or eliminate the traffic problems caused by the incompatibility of the EV powertrain characteristics and the driving conditions.

show abstract

“…3) Data-driven methods. Data-driven methods for SOC estimation encompass machine learning and neural networks [27]- [29], which have been applied extensively to create advanced SOC prediction methods without requiring additional details about battery chemistry, internal properties, or extra filters. Reference [30] demonstrated the outstanding performance of optimized machine-learning techniques for enhancing battery SOC prediction.…”

mentioning

confidence: 99%

Multi-scale Fusion Model Based on Gated Recurrent Unit for Enhancing Prediction Accuracy of State-of-charge in Battery Energy Storage Systems

Liu,

Liang,

et al. 2024

Journal of Modern Power Systems and Clean Energy

View full text Add to dashboard Cite

Accurate prediction of the state-of-charge (SOC) of battery energy storage system (BESS) is critical for its safety and lifespan in electric vehicles. To overcome the imbalance of existing methods between multi-scale feature fusion and global feature extraction, this paper introduces a novel multi-scale fusion (MSF) model based on gated recurrent unit (GRU), which is specifically designed for complex multi-step SOC prediction in practical BESSs. Pearson correlation analysis is first employed to identify SOC-related parameters. These parameters are then input into a multi-layer GRU for point-wise feature extraction. Concurrently, the parameters undergo patching before entering a dual-stage multi-layer GRU, thus enabling the model to capture nuanced information across varying time intervals. Ultimately, by means of adaptive weight fusion and a fully connected network, multi-step SOC predictions are rendered. Following extensive validation over multiple days, it is illustrated that the proposed model achieves an absolute error of less than 1.5% in real-time SOC prediction. Index Terms--Electric vehicle, battery energy storage system (BESS), state-of-charge (SOC) prediction, gated recurrent unit (GRU), multi-scale fusion (MSF). X i  Y iValues of the i th datapoint X ˉ Y ˉSample means of variables X and Y z tUpdate gate of a GRU

show abstract

Adaptive Neural Network-Based Prescribed-Time Observer for Battery State-of-Charge Estimation

Cited by 28 publications

References 31 publications

Lithium Battery SOC Estimation Based on Multi-Head Attention Mechanism and GRU Algorithm

Lithium Battery SOC Estimation Based on Multi-Head Attention Mechanism and GRU Algorithm

A Driving-Adapt Strategy for the Electric Vehicle with Magneto-Rheological Fluid Transmission Considering the Powertrain Characteristics

Multi-scale Fusion Model Based on Gated Recurrent Unit for Enhancing Prediction Accuracy of State-of-charge in Battery Energy Storage Systems

Contact Info

Product

Resources

About