Tao Chen
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Tao Chen has a total of 9 co-authors. Here are the top co-authors by number of shared publications:
- Mingze Lei
Faculty of Engineering, Mahasarakham University, Mahasarakham 44150, Thailand
3 shared publications - Buncha Wattana
Electrical and Computer Engineering Research Unit, Faculty of Engineering, Mahasarakham University, Maha Sarakham 44150, Thailand
2 shared publications - Caixia Yang
College of Electrical Engineering, Hunan Mechanical and Electrical Polytechnic, Changsha 410073, China
2 shared publications - Chonlatee Photong
Mahasarakham University
2 shared publications - Yao Xiao
College of Electrical Engineering, Hunan Mechanical and Electrical Polytechnic, Changsha 410073, China
2 shared publications - Supannika Wattana
Electrical and Computer Engineering Research Unit, Faculty of Engineering, Mahasarakham University, Maha Sarakham 44150, Thailand
1 shared publication
Latest Publications
- Open Access
- 3 April 2025
- Published by Learning Gate in Edelweiss Applied Science and Technology
- Vol. 9 (4) , 2667-2680
Wind turbine blade icing prediction based on CNN-BiGRU with Optimized training strategy
Wind turbine blade icing significantly impacts the safety of wind farms and the efficiency of power generation, making precise and timely prediction a critical challenge. This study proposes an innovative deep learning framework that integrates Convolutional Neural Networks (CNNs) and Bidirectional Gated Recurrent Units (BiGRU) to enhance icing prediction. CNNs extract spatial features, while BiGRU captures temporal dependencies, enabling the model to effectively distinguish icing occurrences. To improve model optimization, cosine annealing was employed for dynamic learning rate adjustment, while cross-entropy loss was used to address class imbalance. Experimental results demonstrate that a 2-layer CNN architecture trained over 50 epochs achieves a balance between accuracy and computational efficiency, with CNN_2Layer-BiGRU attaining 96.55% accuracy and a 96.51% F1-score, outperforming traditional models. This approach reduces dependency on manual feature engineering, improves prediction accuracy and computational efficiency, and provides a foundation for an intelligent diagnostic system for wind turbine blade icing prediction.
- 3 April 2025
- Published by Learning Gate in Edelweiss Applied Science and Technology
- Vol. 9 (4) , 2667-2680
Open AccessWind turbine blade icing prediction based on CNN-BiGRU with Optimized training strategy
Wind turbine blade icing significantly impacts the safety of wind farms and the efficiency of power generation, making precise and timely prediction a critical challenge. This study proposes an innovative deep learning framework that integrates Convolutional Neural Networks (CNNs) and Bidirectional Gated Recurrent Units (BiGRU) to enhance icing prediction. CNNs extract spatial features, while BiGRU captures temporal dependencies, enabling the model to effectively distinguish icing occurrences. To improve model optimization, cosine annealing was employed for dynamic learning rate adjustment, while cross-entropy loss was used to address class imbalance. Experimental results demonstrate that a 2-layer CNN architecture trained over 50 epochs achieves a balance between accuracy and computational efficiency, with CNN_2Layer-BiGRU attaining 96.55% accuracy and a 96.51% F1-score, outperforming traditional models. This approach reduces dependency on manual feature engineering, improves prediction accuracy and computational efficiency, and provides a foundation for an intelligent diagnostic system for wind turbine blade icing prediction.
- Open Access
- 28 February 2025
- Published by Learning Gate in Edelweiss Applied Science and Technology
- Vol. 9 (3) , 633-650
A transfer learning method based on MC-1DCNN for elevator guideway fault diagnosis
Elevator guideway vibration fault diagnosis is essential for ensuring elevator safety and stability. However, vibration signals exhibit complex non-stationary characteristics, and abnormal vibration samples are limited. This paper proposes an advanced fault diagnosis method combining Multi-Channel One-Dimensional Convolutional Neural Networks (MC-1DCNN) with transfer learning for elevator guideways. 1D-CNN is employed to extract local temporal correlations in vibration signals, while Empirical Mode Decomposition (EMD) decomposes signals into Intrinsic Mode Functions (IMFs) to provide multi-frequency features as multi-channel inputs. The MC-1DCNN is pre-trained on the Case Western Reserve University (CWRU) bearing fault dataset to learn general mechanical fault features and is then fine-tuned on the elevator guideway dataset by freezing lower convolutional layers and adjusting higher layers. Experimental results demonstrate that the proposed method achieves high classification accuracy and fast convergence in small-sample scenarios. This study validates the effectiveness of transfer learning in elevator fault diagnosis and provides a practical solution for real-world applications.
- 28 February 2025
- Published by Learning Gate in Edelweiss Applied Science and Technology
- Vol. 9 (3) , 633-650
Open AccessA transfer learning method based on MC-1DCNN for elevator guideway fault diagnosis
Elevator guideway vibration fault diagnosis is essential for ensuring elevator safety and stability. However, vibration signals exhibit complex non-stationary characteristics, and abnormal vibration samples are limited. This paper proposes an advanced fault diagnosis method combining Multi-Channel One-Dimensional Convolutional Neural Networks (MC-1DCNN) with transfer learning for elevator guideways. 1D-CNN is employed to extract local temporal correlations in vibration signals, while Empirical Mode Decomposition (EMD) decomposes signals into Intrinsic Mode Functions (IMFs) to provide multi-frequency features as multi-channel inputs. The MC-1DCNN is pre-trained on the Case Western Reserve University (CWRU) bearing fault dataset to learn general mechanical fault features and is then fine-tuned on the elevator guideway dataset by freezing lower convolutional layers and adjusting higher layers. Experimental results demonstrate that the proposed method achieves high classification accuracy and fast convergence in small-sample scenarios. This study validates the effectiveness of transfer learning in elevator fault diagnosis and provides a practical solution for real-world applications.
- Open Access
Strategies of a Wind–Solar–Storage System in Jiangxi Province Using the LEAP–NEMO Framework for Achieving Carbon Peaking Goals
Jiangxi Province relies heavily on thermal power and energy imports but is rich in natural resources, particularly lithium. This study explores strategies for advancing wind–solar–storage systems to help Jiangxi transition to a low-carbon energy structure. Using LEAP and NEMO models, four scenarios are examined: the reference (REF) scenario, new energy storage policy scenario (NPS), high wind–solar power capacity scenario (HWSS), and comprehensive optimization scenario (COS). Key findings show that the COS and HWSS offer significant advantages over the REF scenario and NPS in terms of energy storage efficiency, carbon emission reduction, and cost savings. By 2035, under the COS, wind and solar power share rises to 48%, reducing coal use by 5.9 million tons and electricity imports by 40.0 TWh compared to the REF scenario. Battery storage utilization increases by 1499.8 GWh, nearly four times that of the REF scenario. This scenario also cuts CO2 emissions by 16.8% and lowers cumulative social costs by 5.19 billion USD, delivering optimal economic efficiency. The study also identifies challenges such as high investment costs, underdeveloped business models, and low resource utilization, and recommends setting higher targets, implementing flexible solutions, promoting market reforms, and increasing R&D efforts, among other measures.
Open AccessStrategies of a Wind–Solar–Storage System in Jiangxi Province Using the LEAP–NEMO Framework for Achieving Carbon Peaking Goals
Jiangxi Province relies heavily on thermal power and energy imports but is rich in natural resources, particularly lithium. This study explores strategies for advancing wind–solar–storage systems to help Jiangxi transition to a low-carbon energy structure. Using LEAP and NEMO models, four scenarios are examined: the reference (REF) scenario, new energy storage policy scenario (NPS), high wind–solar power capacity scenario (HWSS), and comprehensive optimization scenario (COS). Key findings show that the COS and HWSS offer significant advantages over the REF scenario and NPS in terms of energy storage efficiency, carbon emission reduction, and cost savings. By 2035, under the COS, wind and solar power share rises to 48%, reducing coal use by 5.9 million tons and electricity imports by 40.0 TWh compared to the REF scenario. Battery storage utilization increases by 1499.8 GWh, nearly four times that of the REF scenario. This scenario also cuts CO2 emissions by 16.8% and lowers cumulative social costs by 5.19 billion USD, delivering optimal economic efficiency. The study also identifies challenges such as high investment costs, underdeveloped business models, and low resource utilization, and recommends setting higher targets, implementing flexible solutions, promoting market reforms, and increasing R&D efforts, among other measures.
- Open Access
- 23 January 2025
- Published by Learning Gate in Edelweiss Applied Science and Technology
- Vol. 9 (2) , 793-814
Renewable energy strategy impacts on electricity system and carbon emissions in Hunan Province of China
This study investigates the impact of increasing renewable energy capacity on the power industry in Hunan Province, China, focusing on power demand, electricity generation, and CO2 emissions reductions. Using the Low Emission Analysis Platform (LEAP) model, five scenarios (BAU, RES, HEF, HST, and COP) were developed to assess the effects of renewable energy strategies from 2022 to 2035. The analysis considered renewable energy growth, energy storage, and efficiency improvements. The Comprehensive Optimization Scenario (COP) emerged as the most optimal, achieving a 48% share of renewable energy, 17% energy storage, and 23% efficient coal use, leading to significant CO2 emissions reductions while ensuring system flexibility and reliability. The study concludes that the COP scenario is the most effective in supporting a low-carbon transition and maintaining energy security. Practical implications include the need for policy support in areas such as diversified energy storage, distributed energy systems, V2G/V2X technologies, and smart grid development to enhance renewable energy integration and ensure sustainable development in Hunan.
- 23 January 2025
- Published by Learning Gate in Edelweiss Applied Science and Technology
- Vol. 9 (2) , 793-814
Open AccessRenewable energy strategy impacts on electricity system and carbon emissions in Hunan Province of China
This study investigates the impact of increasing renewable energy capacity on the power industry in Hunan Province, China, focusing on power demand, electricity generation, and CO2 emissions reductions. Using the Low Emission Analysis Platform (LEAP) model, five scenarios (BAU, RES, HEF, HST, and COP) were developed to assess the effects of renewable energy strategies from 2022 to 2035. The analysis considered renewable energy growth, energy storage, and efficiency improvements. The Comprehensive Optimization Scenario (COP) emerged as the most optimal, achieving a 48% share of renewable energy, 17% energy storage, and 23% efficient coal use, leading to significant CO2 emissions reductions while ensuring system flexibility and reliability. The study concludes that the COP scenario is the most effective in supporting a low-carbon transition and maintaining energy security. Practical implications include the need for policy support in areas such as diversified energy storage, distributed energy systems, V2G/V2X technologies, and smart grid development to enhance renewable energy integration and ensure sustainable development in Hunan.