Muyao Wu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Muyao Wu has a total of 25 co-authors. Here are the top co-authors by number of shared publications:
- Li Wang
School of Automotive and Transportation Engineering, Hefei University of Technology, Hefei, China
7 shared publications - Ji Wu
Hefei University of Technology
5 shared publications - Yu-Qing Wang
Hefei University of Technology
3 shared publications Changpeng Tan
2 shared publications- Changpeng Tan2 shared publications
Li Wang
2 shared publications
Latest Publications
- 22 October 2026
- Published by Elsevier in Journal of Energy Storage
- Vol. 183
Domain adaptation state of health estimation for lithium-ion batteries accounting for state of charge dependence
- 22 October 2026
- Published by Elsevier in Journal of Energy Storage
- Vol. 183
Domain adaptation state of health estimation for lithium-ion batteries accounting for state of charge dependence
- 2 September 2026
- Published by Elsevier in Journal of Energy Storage
- Vol. 181
A physics-guided multi-source collaborative fault diagnosis framework for real-world lithium-ion batteries
- 2 September 2026
- Published by Elsevier in Journal of Energy Storage
- Vol. 181
A physics-guided multi-source collaborative fault diagnosis framework for real-world lithium-ion batteries
- 17 April 2026
- Published by Elsevier in Electric Power Systems Research
- Vol. 258
Equivalent strain model construction and rapid convergence SOC estimation of the cylindrical LiFePO4 battery
- 17 April 2026
- Published by Elsevier in Electric Power Systems Research
- Vol. 258
Equivalent strain model construction and rapid convergence SOC estimation of the cylindrical LiFePO4 battery
- Open Access
- 1 April 2026
- Published by Elsevier in SSRN Electronic Journal
Domain adaptation state of health estimation for lithium-ion batteries accounting for state of charge dependence
Accurate State of Health (SOH) estimation is essential for ensuring the safety, reliability, and long-term performance of electric vehicle batteries. However, the generalization performance of Artificial Intelligence methods depends on the quality and coverage of training data. Acquiring high-quality labeled data with sufficient coverage remains a challenge. To address this, this paper first comprehensively compares and analyzes the State of Charge (SOC) dependence of the mechanical, electrical, and thermal features of batteries under different initial SOC. Features with weak SOC dependence are selected as model inputs, enabling robust SOH estimation in partial charge-discharge scenarios using only fully completed charge-discharge data. This effectively reduces the model’s demand for broad data coverage. Then, this paper proposes a domain adaptation method based on Maximum Mean Discrepancy (MMD), which integrates the Transformer and Kolmogorov-Arnold Network (KAN). Experimental results show that adopting features with weak SOC dependence reduces the relative Mean Absolute Percentage Error (MAPE) by 85.48% for slow charging and 64.33% for fast charging. Moreover, the proposed domain adaptation method achieves a 47.69% relative reduction in MAPE.
- 1 April 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessDomain adaptation state of health estimation for lithium-ion batteries accounting for state of charge dependence
Accurate State of Health (SOH) estimation is essential for ensuring the safety, reliability, and long-term performance of electric vehicle batteries. However, the generalization performance of Artificial Intelligence methods depends on the quality and coverage of training data. Acquiring high-quality labeled data with sufficient coverage remains a challenge. To address this, this paper first comprehensively compares and analyzes the State of Charge (SOC) dependence of the mechanical, electrical, and thermal features of batteries under different initial SOC. Features with weak SOC dependence are selected as model inputs, enabling robust SOH estimation in partial charge-discharge scenarios using only fully completed charge-discharge data. This effectively reduces the model’s demand for broad data coverage. Then, this paper proposes a domain adaptation method based on Maximum Mean Discrepancy (MMD), which integrates the Transformer and Kolmogorov-Arnold Network (KAN). Experimental results show that adopting features with weak SOC dependence reduces the relative Mean Absolute Percentage Error (MAPE) by 85.48% for slow charging and 64.33% for fast charging. Moreover, the proposed domain adaptation method achieves a 47.69% relative reduction in MAPE.
- 21 June 2025
- Published by Elsevier in Journal of Energy Storage
- Vol. 131
Capacity estimation of Lithium-ion batteries based on discharge rate compensation model under different discharge rates
- 21 June 2025
- Published by Elsevier in Journal of Energy Storage
- Vol. 131
Capacity estimation of Lithium-ion batteries based on discharge rate compensation model under different discharge rates
- Open Access
- 21 December 2024
- Published by Kaunas University of Technology (KTU) in Mechanics
- Vol. 30 (6) , 507-513
Optimization of restrictor parameters and static characteristics study on orifice type hydrostatic thrust bearing
Gas bearings play a crucial role in maintaining the precision of ultra-precision machine tools. However, the bearing capacity is inferior to that of rolling bearings. The bearing capacity of gas bearings is directly influenced by restrictor structural parameters. To clarify the combined effect of restrictor structural parameters on the static bearing capacity of gas bearings and enhance the bearing capacity. The orthogonal test method was used to investigate the impact of various combinations of parameter levels (e.g. diameter of orifices d1, thickness of gas film h1, diameter d2 of pressure-equalizing groove (PEG), and PEG depth h2 on the static load carrying capacity of the bearings). The load-carrying capacity (LCC) and mass flow rate (MFR) were selected as the experimental indicators. Results showed that gas film thickness, orifice diameter, PEG diameter and PEG depth dominated LCC. Additionally, it was observed that diameter of orifices has the most significant impact on MFR, followed by thickness of gas film, PEG diameter, and PEG depth having the smallest influence on MFR. LCC serves as a critical manifestation of the static bearing capacity of bearings. However, this increase in LCC unavoidably resulted in higher gas consumption, leading to an elevated MFR. Consequently, the structural parameters of restrictor were optimized based on the principle of optimal LCC, while also ensuring that there was no significant rise in MFR. The optimized parameter combinations were thickness of gas film h1=0.01 mm, diameter of orifices d1=0.25 mm, PEG diameter d2=5 mm, and PEG depth h2=0.07 mm. This study can contribute to a profound understanding of the nonlinear dynamic mechanism and structural optimization design application of air bearing.
- 21 December 2024
- Published by Kaunas University of Technology (KTU) in Mechanics
- Vol. 30 (6) , 507-513
Open AccessOptimization of restrictor parameters and static characteristics study on orifice type hydrostatic thrust bearing
Gas bearings play a crucial role in maintaining the precision of ultra-precision machine tools. However, the bearing capacity is inferior to that of rolling bearings. The bearing capacity of gas bearings is directly influenced by restrictor structural parameters. To clarify the combined effect of restrictor structural parameters on the static bearing capacity of gas bearings and enhance the bearing capacity. The orthogonal test method was used to investigate the impact of various combinations of parameter levels (e.g. diameter of orifices d1, thickness of gas film h1, diameter d2 of pressure-equalizing groove (PEG), and PEG depth h2 on the static load carrying capacity of the bearings). The load-carrying capacity (LCC) and mass flow rate (MFR) were selected as the experimental indicators. Results showed that gas film thickness, orifice diameter, PEG diameter and PEG depth dominated LCC. Additionally, it was observed that diameter of orifices has the most significant impact on MFR, followed by thickness of gas film, PEG diameter, and PEG depth having the smallest influence on MFR. LCC serves as a critical manifestation of the static bearing capacity of bearings. However, this increase in LCC unavoidably resulted in higher gas consumption, leading to an elevated MFR. Consequently, the structural parameters of restrictor were optimized based on the principle of optimal LCC, while also ensuring that there was no significant rise in MFR. The optimized parameter combinations were thickness of gas film h1=0.01 mm, diameter of orifices d1=0.25 mm, PEG diameter d2=5 mm, and PEG depth h2=0.07 mm. This study can contribute to a profound understanding of the nonlinear dynamic mechanism and structural optimization design application of air bearing.
- Open Access
- 29 October 2024
- Published by Science Publishing Group in Journal of Energy and Natural Resources
- Vol. 13 (4) , 166-177
State of Charge-State of Health Collaborative Estimation of the Lithium-ion Battery Based on an Innovative Hybrid Optimization Network
Lithium-ion battery is one of the core components of electric vehicles, and the state of charge-state of health estimation results of it is the key to restrict the safe and efficient use of it, which then affects the comprehensive performance of electric vehicles. However, SOC and SOH of lithium-ion batteries have a coupling relationship, and have fast and slow time-varying characteristics respectively, with inconsistent time scales. Hence, it is necessary to carry out SOC-SOH collaborative estimation and select a suitable time scale, which can ensure the accuracy and robustness of SOC-SOH collaborative estimation without consuming too much calculation cost. This article proposed an innovative hybrid optimization network to improve the ability of the analysis and feature extraction capability of the input sequences for precise SOC estimation. This hybrid network fully combines the advantages of convolutional neural network, bidirectional long short-term memory, attention mechanism. Additionally, kepler optimization algorithm is applied for hyperparameter optimization of the hybrid network for the first time according to our knowledge, and SOH is also estimated accurately for more ideal SOC estimation results. The experimental results of lithium-ion batteries indicate that the innovative hybrid optimization network can reach ideal SOC estimation results under different working conditions and ambient temperatures. The mean absolute error and root mean square error are 0.55% and 0.72% respectively, only about a third of the SOC estimation results without considering SOH, which means that SOC-SOH collaborative estimation are very essential. Hence, this article is of great significance for the development of smarter battery management system.
- 29 October 2024
- Published by Science Publishing Group in Journal of Energy and Natural Resources
- Vol. 13 (4) , 166-177
Open AccessState of Charge-State of Health Collaborative Estimation of the Lithium-ion Battery Based on an Innovative Hybrid Optimization Network
Lithium-ion battery is one of the core components of electric vehicles, and the state of charge-state of health estimation results of it is the key to restrict the safe and efficient use of it, which then affects the comprehensive performance of electric vehicles. However, SOC and SOH of lithium-ion batteries have a coupling relationship, and have fast and slow time-varying characteristics respectively, with inconsistent time scales. Hence, it is necessary to carry out SOC-SOH collaborative estimation and select a suitable time scale, which can ensure the accuracy and robustness of SOC-SOH collaborative estimation without consuming too much calculation cost. This article proposed an innovative hybrid optimization network to improve the ability of the analysis and feature extraction capability of the input sequences for precise SOC estimation. This hybrid network fully combines the advantages of convolutional neural network, bidirectional long short-term memory, attention mechanism. Additionally, kepler optimization algorithm is applied for hyperparameter optimization of the hybrid network for the first time according to our knowledge, and SOH is also estimated accurately for more ideal SOC estimation results. The experimental results of lithium-ion batteries indicate that the innovative hybrid optimization network can reach ideal SOC estimation results under different working conditions and ambient temperatures. The mean absolute error and root mean square error are 0.55% and 0.72% respectively, only about a third of the SOC estimation results without considering SOH, which means that SOC-SOH collaborative estimation are very essential. Hence, this article is of great significance for the development of smarter battery management system.
- 13 June 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Transportation Electrification
- Vol. 11 (1) , 1939-1948
Screening and Echelon Utilization of Lithium-Ion Power Batteries Using Clustering and Stepwise Regrouping Approach
LIB regrouping echelon utilization application scenarios are very wide, such as communication base station backup power supply, distributed energy storage system, photovoltaic power station, etc. A key challenge is to ensure the consistency and scale of the regrouping LIB module. However, the inadequacies of existing solutions have hindered the widespread adoption of echelon utilization. Hence, two optimized features are determined as the screening criteria. Meanwhile, FCM clustering algorithm and subtractive clustering algorithm are proposed to combine to carry out LIB clustering efficiently. Furthermore, a new stepwise regrouping approach based on internal-external Euclidean distance is put forward to ensure the scale same of each LIB module and meet the direct echelon utilization application scenario requirements. Compared with the random regrouping method, the innovatively proposed multidimensional evaluation indexes including maximum available capacity, terminal voltage and SOC, indicate that the consistency of the LIB module based on the proposed method in this paper is obviously improved. The inconsistency evaluation indexes of each dimension are all decreased by more than 20%, which may contribute to the advancement of LIB regrouping echelon utilization.
- 13 June 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Transportation Electrification
- Vol. 11 (1) , 1939-1948
Screening and Echelon Utilization of Lithium-Ion Power Batteries Using Clustering and Stepwise Regrouping Approach
LIB regrouping echelon utilization application scenarios are very wide, such as communication base station backup power supply, distributed energy storage system, photovoltaic power station, etc. A key challenge is to ensure the consistency and scale of the regrouping LIB module. However, the inadequacies of existing solutions have hindered the widespread adoption of echelon utilization. Hence, two optimized features are determined as the screening criteria. Meanwhile, FCM clustering algorithm and subtractive clustering algorithm are proposed to combine to carry out LIB clustering efficiently. Furthermore, a new stepwise regrouping approach based on internal-external Euclidean distance is put forward to ensure the scale same of each LIB module and meet the direct echelon utilization application scenario requirements. Compared with the random regrouping method, the innovatively proposed multidimensional evaluation indexes including maximum available capacity, terminal voltage and SOC, indicate that the consistency of the LIB module based on the proposed method in this paper is obviously improved. The inconsistency evaluation indexes of each dimension are all decreased by more than 20%, which may contribute to the advancement of LIB regrouping echelon utilization.