A Novel Adaptive Particle Swarm Optimization Algorithm Based High Precision Parameter Identification and State Estimation of Lithium-Ion Battery

He, Mingfang

doi:10.20964/2021.05.55

Cited by 14 publications

(3 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The parameter identification method proposed in this study is competitive with methods in other studies. For example, He et al (32) used PSO incorporating an adaptive optimization strategy for parameter identification of LIBs, and MAPE of the identification results was 1.5%. The recursive LS method used by Yang et al (33) was applied to the experimental data in this study, and the RMSE value was 0.0473.…”

Section: Experimental Results and Analysismentioning

confidence: 99%

Equivalent Circuit Modeling and Parameter Identification for Lithium-ion Batteries Based on Improved Barnacle Mating Optimizer

Li¹,

Lin²,

Li³

et al. 2022

Sensors and Materials

View full text Add to dashboard Cite

To address the current problems of accuracy and reliability of the equivalent circuit models for lithium-ion batteries and sensors, in this study we propose an improved barnacle mating optimizer (IBMO) to accurately identify parameters. First, an improved second-order RC model (ISO RC) is derived by segmenting the battery hysteresis voltage and introducing it into the second-order RC model (SO RC model) as a controlled source, which better reflects the dynamic effects of the battery than the SO RC model. Second, the tent chaos mapping, cosine control factor, and Levy flight strategy are introduced to enhance the convergence performance of the IBMO. Its convergence performance is verified by comparison with other existing intelligent algorithms using five single-peak and four multipeak test functions. Finally, the IBMO-ISO RC model is established by using the IBMO as the identification strategy of the ISO RC model in the simulation of two real operating conditions of lithium-ion batteries. The root mean square error of the model under the two operating conditions is only 0.0431 and 0.0483, and the mean absolute percentage error is only 0.38 and 0.56%, outperforming other existing models. The IBMO proposed in this study enables higher model recognition accuracy, making it highly convenient for lithium-ion battery and sensor-related research.

show abstract

Section: Experimental Results and Analysismentioning

confidence: 99%

Equivalent Circuit Modeling and Parameter Identification for Lithium-ion Batteries Based on Improved Barnacle Mating Optimizer

Li¹,

Lin²,

Li³

et al. 2022

Sensors and Materials

View full text Add to dashboard Cite

show abstract

“…Adaptive PSO [269], exponential decay PSO (EDPSO) [270], PSO with chaos theory [271], hybrid PSO and gravitational search algorithm (PSO-CGSA) [243] Power System controllers Hybrid PSO-pattern search [244], PSO with Pade approximation [245] Capacitor Placement Constriction factor PSO [272], hybrid PSO [247] Generation expansion problem Comprehensive learning PSO [273], fuzzy adaptive chaotic binary PSO [274] Power system reliability and security…”

Section: State Estimationmentioning

confidence: 99%

Particle Swarm Optimization: A Comprehensive Survey

et al. 2022

View full text Add to dashboard Cite

Particle swarm optimization (PSO) is one of the most well-regarded swarm-based algorithms in the literature. Although the original PSO has shown good optimization performance, it still severely suffers from premature convergence. As a result, many researchers have been modifying it resulting in a large number of PSO variants with either slightly or significantly better performance. Mainly, the standard PSO has been modified by four main strategies: modification of the PSO controlling parameters, hybridizing PSO with other well-known meta-heuristic algorithms such as genetic algorithm (GA) and differential evolution (DE), cooperation and multi-swarm techniques. This paper attempts to provide a comprehensive review of PSO, including the basic concepts of PSO, binary PSO, neighborhood topologies in PSO, recent and historical PSO variants, remarkable engineering applications of PSO, and its drawbacks. Moreover, this paper reviews recent studies that utilize PSO to solve feature selection problems. Finally, eight potential research directions that can help researchers further enhance the performance of PSO are provided.

show abstract

“…[1][2][3][4][5] Literature review.-Currently, several techniques regarding SOC estimation of LIBs have been studied and applied. Mainly composed of four categories: traditional methods including open-circuit voltage method (OCV), 6,7 coulomb counting (CC), 8 and Kalman filter (KF) algorithm, 9 novel algorithms including various adaptive observers, [10][11][12][13] deformation of algorithms Kalman filter and particle swarm optimization (PSO) algorithm, 14,15 Gaussian process regression method (GPR); 16 machine learning algorithms including neural network algorithms and support vector machine method and hybrid methods including coulomb counting and Kalman filter combination, 17 and neural network algorithms with Kalman filter compound. 18,19 Concerning various algorithms, this paper mainly introduces traditional methods, the popular deformation algorithms of the Kalman algorithm, and the neural network algorithms.…”

mentioning

confidence: 99%

State of Charge Estimation for Lithium-Ion Batteries Based on TCN-LSTM Neural Networks

Cheng

et al. 2022

J. Electrochem. Soc.

View full text Add to dashboard Cite

Accurately estimating the state of charge (SOC) of lithium-ion batteries is critical for developing more reliable and efficient electric vehicles. However, the commonly used models cannot simultaneously extract effective spatial and temporal features from the original data, leading to an inefficient SOC estimation. This paper proposes a novel neural network method for accurate and robust battery SOC estimation, which incorporates the temporal convolutional network (TCN) and the long short-term memory (LSTM), namely TCN-LSTM model. Specifically, the TCN is employed to extract more advanced spatial features among multivariate variables, and the LSTM captures long-term dependencies from time-series data and maps battery temporal information into current SOC and historical inputs. The proposed model performs well in various estimation conditions. The average value of mean absolute error, root mean square error, and maximum error of SOC estimation achieve 0.48%, 0.60%, and 2.3% at multiple temperature conditions, respectively, and reach 0.70%, 0.81%, and 2.7% for a different battery, respectively. In addition, the proposed method has better accuracy than the LSTM or TCN used independently and the CNN-LSTM network. The computational burden with varying length of input is also investigated. In summary, experiment results show that the proposed method has excellent generalization and robustness.

show abstract

A Novel Adaptive Particle Swarm Optimization Algorithm Based High Precision Parameter Identification and State Estimation of Lithium-Ion Battery

Cited by 14 publications

References 39 publications

Equivalent Circuit Modeling and Parameter Identification for Lithium-ion Batteries Based on Improved Barnacle Mating Optimizer

Equivalent Circuit Modeling and Parameter Identification for Lithium-ion Batteries Based on Improved Barnacle Mating Optimizer

Particle Swarm Optimization: A Comprehensive Survey

State of Charge Estimation for Lithium-Ion Batteries Based on TCN-LSTM Neural Networks

Contact Info

Product

Resources

About