Xugang Zhang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Xugang Zhang has a total of 30 co-authors. Here are the top co-authors by number of shared publications:
Yan Wang
8 shared publicationsQingshan Gong
5 shared publications- Zhigang Jiang
Key Laboratory of Metallurgical Equipment and Control Technology, Wuhan University of Science & Technology, Wuhan 430081, China
4 shared publications Feng Ma
2 shared publicationsHua Zhang
Key Laboratory of Metallurgical Equipment and Control Technology, Ministry of Education, Wuhan University of Science and Technology, Wuhan, China
2 shared publicationsShuangli Zhu
2 shared publications
Latest Publications
- 22 September 2026
- Published by Elsevier in Computers & Industrial Engineering
- Vol. 222
Dismantling sequence planning of end-of-life products considering parts recovery strategies
- 22 September 2026
- Published by Elsevier in Computers & Industrial Engineering
- Vol. 222
Dismantling sequence planning of end-of-life products considering parts recovery strategies
- 13 October 2025
- Published by Elsevier in Computers & Industrial Engineering
- Vol. 211
Parallel disassembly sequence planning for used products considering part quality status
- 13 October 2025
- Published by Elsevier in Computers & Industrial Engineering
- Vol. 211
Parallel disassembly sequence planning for used products considering part quality status
- 1 October 2025
- Published by The Electrochemical Society in Journal of the Electrochemical Society
- Vol. 172 (10) , 100523
Hybrid Neural Networks for Lithium-Ion Batteries State of Health Estimation and Remaining Useful Life Prediction
Lithium-ion batteries deteriorate due to long-term charging and discharging, leading to performance degradation and safety hazards, so precisely evaluating the state of health (SOH) and remaining useful life (RUL) of lithium-ion batteries is essential for battery safety assurance. To address the issue of poor accuracy of current SOH estimation and RUL prediction methods, this paper proposes a hybrid VMD-BiLSTM-Transformer model. First, a variational modal decomposition is applied to reduce noise and segment the raw data, eliminating capacity regeneration. Second, a combination of bidirectional long short-term memory network (BiLSTM) and Transformer is employed to accurately capture features and fuse global information by utilizing its bidirectional information processing and self-attention mechanisms. Finally, the proposed model is verified on CALCE and Oxford datasets to demonstrate superior prediction accuracy compared to the benchmark models. Specifically, for SOH prediction, the root mean square error is 1.27% for CALCE and 0.23% for Oxford, while the mean absolute error is 0.99% for CALCE and 0.45% for Oxford. Similarly, for RUL prediction, the mean squared error is 0.02% for CALCE and 0.0006% for Oxford. This fully demonstrates that the proposed model exhibits excellent generalization capability and robustness.
- 1 October 2025
- Published by The Electrochemical Society in Journal of the Electrochemical Society
- Vol. 172 (10) , 100523
Hybrid Neural Networks for Lithium-Ion Batteries State of Health Estimation and Remaining Useful Life Prediction
Lithium-ion batteries deteriorate due to long-term charging and discharging, leading to performance degradation and safety hazards, so precisely evaluating the state of health (SOH) and remaining useful life (RUL) of lithium-ion batteries is essential for battery safety assurance. To address the issue of poor accuracy of current SOH estimation and RUL prediction methods, this paper proposes a hybrid VMD-BiLSTM-Transformer model. First, a variational modal decomposition is applied to reduce noise and segment the raw data, eliminating capacity regeneration. Second, a combination of bidirectional long short-term memory network (BiLSTM) and Transformer is employed to accurately capture features and fuse global information by utilizing its bidirectional information processing and self-attention mechanisms. Finally, the proposed model is verified on CALCE and Oxford datasets to demonstrate superior prediction accuracy compared to the benchmark models. Specifically, for SOH prediction, the root mean square error is 1.27% for CALCE and 0.23% for Oxford, while the mean absolute error is 0.99% for CALCE and 0.45% for Oxford. Similarly, for RUL prediction, the mean squared error is 0.02% for CALCE and 0.0006% for Oxford. This fully demonstrates that the proposed model exhibits excellent generalization capability and robustness.
- 23 January 2025
- Published by The Electrochemical Society in Journal of the Electrochemical Society
- Vol. 172 (2) , 020503
State of Health Estimation of Lithium-Ion Batteries Based on Hybrid Neural Networks with Residual Connections
Accurately estimating the state of health (SOH) of lithium-ion batteries is essential for ensuring the stability and safety of the battery. Although the hybrid neural network model demonstrates strong performance in estimating the SOH, network degradation becomes a significant issue as the depth of the neural network increases, potentially undermining the accuracy of the estimation. This paper presents a hybrid neural network estimation model with residual connections to address the issue of network degradation. First, the model utilizes a combination of convolutional neural networks and an attention mechanism to automatically extract feature information highly correlated with SOH from the partial charging data of lithium-ion batteries. Subsequently, a multi-layer gated recurrent unit (GRU) is employed to capture temporal information within the extracted features. To address the issue of network degradation that arises from stacking multiple layers of neural networks, residual connections are incorporated into the multi-layer GRUs, mitigating the accumulation of errors within deep networks. Finally, three distinct datasets are employed to validate the proposed model. The experimental results demonstrate that the model exhibits an average mean absolute error and root mean square error of less than 1.8% on both of these datasets.
- 23 January 2025
- Published by The Electrochemical Society in Journal of the Electrochemical Society
- Vol. 172 (2) , 020503
State of Health Estimation of Lithium-Ion Batteries Based on Hybrid Neural Networks with Residual Connections
Accurately estimating the state of health (SOH) of lithium-ion batteries is essential for ensuring the stability and safety of the battery. Although the hybrid neural network model demonstrates strong performance in estimating the SOH, network degradation becomes a significant issue as the depth of the neural network increases, potentially undermining the accuracy of the estimation. This paper presents a hybrid neural network estimation model with residual connections to address the issue of network degradation. First, the model utilizes a combination of convolutional neural networks and an attention mechanism to automatically extract feature information highly correlated with SOH from the partial charging data of lithium-ion batteries. Subsequently, a multi-layer gated recurrent unit (GRU) is employed to capture temporal information within the extracted features. To address the issue of network degradation that arises from stacking multiple layers of neural networks, residual connections are incorporated into the multi-layer GRUs, mitigating the accumulation of errors within deep networks. Finally, three distinct datasets are employed to validate the proposed model. The experimental results demonstrate that the model exhibits an average mean absolute error and root mean square error of less than 1.8% on both of these datasets.
- 17 October 2024
- Published by Springer Nature in Ionics
- Vol. 30 (12) , 8053-8072
A residual service life prediction of lithium-ion batteries based on decomposition algorithm and fully connected neural network
- 17 October 2024
- Published by Springer Nature in Ionics
- Vol. 30 (12) , 8053-8072
A residual service life prediction of lithium-ion batteries based on decomposition algorithm and fully connected neural network
- 1 February 2024
- Published by The Electrochemical Society in Journal of the Electrochemical Society
- Vol. 171 (2) , 020511
Remaining Life Prediction of Li-Ion Batteries Considering Sufficiency of Historical Data
With the development of new batteries, the historical data available for training for remaining useful life (RUL) prediction of li-ion batteries will be greatly reduced, and the capacity regeneration phenomenon (CRP) of batteries will also bring challenges to the prediction. This paper proposes a hybrid model that combines decomposition algorithms incorporating the broad learning system with dropout (BLSD) to predict the RUL of batteries. Firstly, the improved complete ensemble empirical mode decomposition with adaptive noise (ICEEMDAN) method is employed to decompose the raw data into several intrinsic mode function (IMF) which is divided into the global components (GC) and local components (LC) by introducing the Pearson correlation coefficient (PCC). Secondly, considering that traditional BLS methods might exacerbate overfitting and lack the capacity to express uncertainty, Dropout techniques are incorporated into BLS to address these issues. Thirdly, multiple distinct BLSD models are employed to individually train GC and LC, and the summation of multiple predicted values yields the final capacity curve. Finally, the maximum observed root mean square error (RMSE) is 0.006679 when the battery history data is sufficient, and the maximum RMSE is 0.005737 when the battery history data is insufficient, which verifies the validity of the model.
- 1 February 2024
- Published by The Electrochemical Society in Journal of the Electrochemical Society
- Vol. 171 (2) , 020511
Remaining Life Prediction of Li-Ion Batteries Considering Sufficiency of Historical Data
With the development of new batteries, the historical data available for training for remaining useful life (RUL) prediction of li-ion batteries will be greatly reduced, and the capacity regeneration phenomenon (CRP) of batteries will also bring challenges to the prediction. This paper proposes a hybrid model that combines decomposition algorithms incorporating the broad learning system with dropout (BLSD) to predict the RUL of batteries. Firstly, the improved complete ensemble empirical mode decomposition with adaptive noise (ICEEMDAN) method is employed to decompose the raw data into several intrinsic mode function (IMF) which is divided into the global components (GC) and local components (LC) by introducing the Pearson correlation coefficient (PCC). Secondly, considering that traditional BLS methods might exacerbate overfitting and lack the capacity to express uncertainty, Dropout techniques are incorporated into BLS to address these issues. Thirdly, multiple distinct BLSD models are employed to individually train GC and LC, and the summation of multiple predicted values yields the final capacity curve. Finally, the maximum observed root mean square error (RMSE) is 0.006679 when the battery history data is sufficient, and the maximum RMSE is 0.005737 when the battery history data is insufficient, which verifies the validity of the model.
- Open Access
- 18 July 2023
- Published by MDPI AG in Sustainability
- Vol. 15 (14) , 11213
Research on Talent Cultivating Pattern of Industrial Engineering Considering Smart Manufacturing
In-depth exploration of the theory and technological applications of smart manufacturing (SM) is lacking in the current talent training model for industrial engineering (IE) majors, and there is a lack of practical education for SM environments. This makes it difficult for students of traditional IE majors to adapt to the modern trend of industrial intelligence and meet the needs of market demand and enterprise development. Therefore, how to cultivate IE talents for SM has become an urgent problem for IE majors to solve. To this end, this paper proposes a new “SM+IE” talent training model, aiming to cultivate more high-quality composite application talents. This model is based on the Lean Manufacturing course and analyzes the effect of the training mode of SM. Secondly, we used the topic of “Sorting Efficiency Improvement” to verify the effectiveness of the new talent training model. The materials were divided into three types: large, medium, and small, and the materials were sorted using traditional IE practices and smart manufacturing-oriented practices. Finally, interviews were conducted with the participants, and both teachers and students indicated that the learning effect of this teaching reform practice was significantly better than that of the traditional IE teaching mode. The results show that the new talent training model improved not only the application and practical skills of the IE students, but also their teamwork and leadership skills.
- 18 July 2023
- Published by MDPI AG in Sustainability
- Vol. 15 (14) , 11213
Open AccessResearch on Talent Cultivating Pattern of Industrial Engineering Considering Smart Manufacturing
In-depth exploration of the theory and technological applications of smart manufacturing (SM) is lacking in the current talent training model for industrial engineering (IE) majors, and there is a lack of practical education for SM environments. This makes it difficult for students of traditional IE majors to adapt to the modern trend of industrial intelligence and meet the needs of market demand and enterprise development. Therefore, how to cultivate IE talents for SM has become an urgent problem for IE majors to solve. To this end, this paper proposes a new “SM+IE” talent training model, aiming to cultivate more high-quality composite application talents. This model is based on the Lean Manufacturing course and analyzes the effect of the training mode of SM. Secondly, we used the topic of “Sorting Efficiency Improvement” to verify the effectiveness of the new talent training model. The materials were divided into three types: large, medium, and small, and the materials were sorted using traditional IE practices and smart manufacturing-oriented practices. Finally, interviews were conducted with the participants, and both teachers and students indicated that the learning effect of this teaching reform practice was significantly better than that of the traditional IE teaching mode. The results show that the new talent training model improved not only the application and practical skills of the IE students, but also their teamwork and leadership skills.
- Open Access
- 23 October 2022
- Published by MDPI AG in Mathematics
- Vol. 10 (21) , 3929
Economic, Environmental and Social Benefits Analysis of Remanufacturing Strategies for Used Products
The operating environment and using conditions of mechanical products are complex and diverse, which has caused a large number of mechanical products to be unable to be remanufactured or have low-remanufacturability. Such products are often ignored by remanufacturing companies and society, which aggravates environmental pollution and waste of resources. Therefore, this article provides a decision-making model for two strategies of complete machine remanufacturing (CMR) and part remanufacturing (PR) for used products with low-remanufacturability. Firstly, from the perspective of the remanufacturing process under the existing technical conditions, the economic, environmental, and social benefits of different remanufacturing solutions are analyzed. Secondly, the entropy method is used to weigh the economic, environmental, and social benefits to reduce the model error, and the linear regression method is used to find the comprehensive benefits of its different remanufacturing strategies. Finally, through the decision-making research on the remanufacturing strategies of the used machine tool CA6180, the results show that the tested machine tool should choose the remanufacturing strategy of PR and put it on the market. Moreover, the decision-making strategy proposed in this paper helps to realize a resource-saving and environment-friendly manufacturing ecology and provides a new perspective for remanufacturing research.
- 23 October 2022
- Published by MDPI AG in Mathematics
- Vol. 10 (21) , 3929
Open AccessEconomic, Environmental and Social Benefits Analysis of Remanufacturing Strategies for Used Products
The operating environment and using conditions of mechanical products are complex and diverse, which has caused a large number of mechanical products to be unable to be remanufactured or have low-remanufacturability. Such products are often ignored by remanufacturing companies and society, which aggravates environmental pollution and waste of resources. Therefore, this article provides a decision-making model for two strategies of complete machine remanufacturing (CMR) and part remanufacturing (PR) for used products with low-remanufacturability. Firstly, from the perspective of the remanufacturing process under the existing technical conditions, the economic, environmental, and social benefits of different remanufacturing solutions are analyzed. Secondly, the entropy method is used to weigh the economic, environmental, and social benefits to reduce the model error, and the linear regression method is used to find the comprehensive benefits of its different remanufacturing strategies. Finally, through the decision-making research on the remanufacturing strategies of the used machine tool CA6180, the results show that the tested machine tool should choose the remanufacturing strategy of PR and put it on the market. Moreover, the decision-making strategy proposed in this paper helps to realize a resource-saving and environment-friendly manufacturing ecology and provides a new perspective for remanufacturing research.