Yongjie Li
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Yongjie Li has a total of 47 co-authors. Here are the top co-authors by number of shared publications:
- Guangchao Geng
College of Electrical Engineering, Zhejiang University, Hangzhou 310027, China
4 shared publications Xuhua Shi
4 shared publicationsQuanyuan Jiang
College of Electrical Engineering, Zhejiang University, Hangzhou, China
3 shared publicationsChengyi Zhang
State Grid Ningbo Elect Power Supply Co, Ningbo 315000, Zhejiang, Peoples R China
2 shared publicationsDi He
Ningbo Power Supply Company, State Grid Zhejiang Electric Power Co., Ltd., Ningbo, Zhejiang, China, 315000
2 shared publications- Quanyuan Jiang
College of Electrical Engineering, Zhejiang University, Hangzhou 310027, China
2 shared publications
Latest Publications
- Open Access
- 14 July 2026
- Published by Elsevier in SSRN Electronic Journal
Response-Driven Capacity Allocation of Grid-Following/Forming Energy Storage in Renewable Energy Clusters
Renewable energy clusters with integrated energy storage systems (ESSs) require appropriate allocation of grid-forming (GFM) and grid-following (GFL) control modes to enhance dynamic security under grid faults and renewable power fluctuations. Under a prescribed total ESS capacity, the key planning task is to determine the proportion of ESS capacity operated in GFM mode, so as to provide sufficient voltage and frequency support while avoiding unnecessary GFM deployment. This paper proposes a response-driven capacity allocation method for determining the optimal GFM/GFL ESS capacity proportion in renewable energy clusters. Candidate GFM shares are embedded into a generic aggregated equivalent model (GAEM), where the relative weighting of GFM- and GFL-controlled ESS equivalents modifies the equivalent inertia, damping, and voltage-support capability at the point of common coupling. For each candidate share, nonlinear time-domain simulations are conducted under representative disturbance scenarios. The simulated frequency, PCC voltage, and active/reactive-power trajectories are then transformed into a transient-response feature vector, including integrated frequency deviation, rate-of-change-of-frequency violation area, integrated voltage sag, active- and reactive-power overshoot, and integral-absolute-error-based power response indices. These response features form a vectorized transient-performance constraint set, through which infeasible candidates are screened and promising intervals are refined using implicit enumeration with adaptive discretization. By preserving the effects of cluster topology and resource composition in the aggregated dynamic representation, the proposed method can be adapted to renewable energy clusters with different structural characteristics. High-fidelity simulations show that the required GFM-controlled ESS share ranges from 39.58\% to 55.36\% under the tested disturbance scenarios, indicating that the proposed method can identify scenario-dependent GFM capacity requirements and avoid full-GFM deployment while satisfying the prescribed dynamic constraints.
- 14 July 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessResponse-Driven Capacity Allocation of Grid-Following/Forming Energy Storage in Renewable Energy Clusters
Renewable energy clusters with integrated energy storage systems (ESSs) require appropriate allocation of grid-forming (GFM) and grid-following (GFL) control modes to enhance dynamic security under grid faults and renewable power fluctuations. Under a prescribed total ESS capacity, the key planning task is to determine the proportion of ESS capacity operated in GFM mode, so as to provide sufficient voltage and frequency support while avoiding unnecessary GFM deployment. This paper proposes a response-driven capacity allocation method for determining the optimal GFM/GFL ESS capacity proportion in renewable energy clusters. Candidate GFM shares are embedded into a generic aggregated equivalent model (GAEM), where the relative weighting of GFM- and GFL-controlled ESS equivalents modifies the equivalent inertia, damping, and voltage-support capability at the point of common coupling. For each candidate share, nonlinear time-domain simulations are conducted under representative disturbance scenarios. The simulated frequency, PCC voltage, and active/reactive-power trajectories are then transformed into a transient-response feature vector, including integrated frequency deviation, rate-of-change-of-frequency violation area, integrated voltage sag, active- and reactive-power overshoot, and integral-absolute-error-based power response indices. These response features form a vectorized transient-performance constraint set, through which infeasible candidates are screened and promising intervals are refined using implicit enumeration with adaptive discretization. By preserving the effects of cluster topology and resource composition in the aggregated dynamic representation, the proposed method can be adapted to renewable energy clusters with different structural characteristics. High-fidelity simulations show that the required GFM-controlled ESS share ranges from 39.58\% to 55.36\% under the tested disturbance scenarios, indicating that the proposed method can identify scenario-dependent GFM capacity requirements and avoid full-GFM deployment while satisfying the prescribed dynamic constraints.
- Open Access
- 26 September 2024
- Published by Taylor & Francis in Engineering Applications of Computational Fluid Mechanics
- Vol. 18 (1)
An incremental learning framework for pipeline weld crack damage identification and leakage rate prediction
- 26 September 2024
- Published by Taylor & Francis in Engineering Applications of Computational Fluid Mechanics
- Vol. 18 (1)
Open AccessAn incremental learning framework for pipeline weld crack damage identification and leakage rate prediction
- 23 September 2024
- Published by Elsevier in Electric Power Systems Research
- Vol. 238
A scalable method with synchronous parallelization for computing selected eigenvalues of large-scale power system model
- 23 September 2024
- Published by Elsevier in Electric Power Systems Research
- Vol. 238
A scalable method with synchronous parallelization for computing selected eigenvalues of large-scale power system model
- Open Access
A Hybrid Prognostic Method for Proton-Exchange-Membrane Fuel Cell with Decomposition Forecasting Framework Based on AEKF and LSTM
Durability and reliability are the major bottlenecks of the proton-exchange-membrane fuel cell (PEMFC) for large-scale commercial deployment. With the help of prognostic approaches, we can reduce its maintenance cost and maximize its lifetime. This paper proposes a hybrid prognostic method for PEMFCs based on a decomposition forecasting framework. Firstly, the original voltage data is decomposed into the calendar aging part and the reversible aging part based on locally weighted regression (LOESS). Then, we apply an adaptive extended Kalman filter (AEKF) and long short-term memory (LSTM) neural network to predict those two components, respectively. Three-dimensional aging factors are introduced in the physical aging model to capture the overall aging trend better. We utilize the automatic machine-learning method based on the genetic algorithm to train the LSTM model more efficiently and improve prediction accuracy. The aging voltage is derived from the sum of the two predicted voltage components, and we can further realize the remaining useful life estimation. Experimental results show that the proposed hybrid prognostic method can realize an accurate long-term voltage-degradation prediction and outperform the single model-based method or data-based method.
Open AccessA Hybrid Prognostic Method for Proton-Exchange-Membrane Fuel Cell with Decomposition Forecasting Framework Based on AEKF and LSTM
Durability and reliability are the major bottlenecks of the proton-exchange-membrane fuel cell (PEMFC) for large-scale commercial deployment. With the help of prognostic approaches, we can reduce its maintenance cost and maximize its lifetime. This paper proposes a hybrid prognostic method for PEMFCs based on a decomposition forecasting framework. Firstly, the original voltage data is decomposed into the calendar aging part and the reversible aging part based on locally weighted regression (LOESS). Then, we apply an adaptive extended Kalman filter (AEKF) and long short-term memory (LSTM) neural network to predict those two components, respectively. Three-dimensional aging factors are introduced in the physical aging model to capture the overall aging trend better. We utilize the automatic machine-learning method based on the genetic algorithm to train the LSTM model more efficiently and improve prediction accuracy. The aging voltage is derived from the sum of the two predicted voltage components, and we can further realize the remaining useful life estimation. Experimental results show that the proposed hybrid prognostic method can realize an accurate long-term voltage-degradation prediction and outperform the single model-based method or data-based method.
- 4 March 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 6, 827-833
Swing Speed Control Strategy of Fuzzy PID Roadheader Based on PSO-BP Algorithm
Aiming at the problem that the boom-type roadheader cannot quickly adjust the cutting swing speed to adapt to the hardness of the coal and rock when the coal hardness changes in coal mines, a control strategy for the driving swing speed is proposed. In this strategy, firstly, the PSO-BP neural network is used to construct a cutting load recognizer to provide a basis for adjusting the cutting swing speed of the roadheader; secondly, the PID control is optimized based on the fuzzy algorithm, and the fuzzy PID controller is established to improve the regulation of the cutting The efficiency of the swing speed; Finally, the roadheader swing speed simulation control system model is built in Matlab/Simulink, and the proposed roadheader cutting swing speed control strategy is simulated. The simulation experiment results show that the roadheader swing speed adjustment system using PSO neural network algorithm combined with fuzzy PID control has significantly improved response speed and control accuracy, and has good superiority and stability. The strategy based on particle swarm BP neural network algorithm combined with fuzzy PID control can provide certain theoretical guidance for stabilizing the cutting motor power of the roadheader and improving the efficiency of roadway work.
- 4 March 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 6, 827-833
Swing Speed Control Strategy of Fuzzy PID Roadheader Based on PSO-BP Algorithm
Aiming at the problem that the boom-type roadheader cannot quickly adjust the cutting swing speed to adapt to the hardness of the coal and rock when the coal hardness changes in coal mines, a control strategy for the driving swing speed is proposed. In this strategy, firstly, the PSO-BP neural network is used to construct a cutting load recognizer to provide a basis for adjusting the cutting swing speed of the roadheader; secondly, the PID control is optimized based on the fuzzy algorithm, and the fuzzy PID controller is established to improve the regulation of the cutting The efficiency of the swing speed; Finally, the roadheader swing speed simulation control system model is built in Matlab/Simulink, and the proposed roadheader cutting swing speed control strategy is simulated. The simulation experiment results show that the roadheader swing speed adjustment system using PSO neural network algorithm combined with fuzzy PID control has significantly improved response speed and control accuracy, and has good superiority and stability. The strategy based on particle swarm BP neural network algorithm combined with fuzzy PID control can provide certain theoretical guidance for stabilizing the cutting motor power of the roadheader and improving the efficiency of roadway work.
- 1 February 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 212-216
Application of GRU in Prediction of Subway Wheel Wear
Predicting various indicators of the wheels can help the subway operation and maintenance department to formulate a reasonable maintenance plan, allocate maintenance resources, reduce maintenance time costs, and improve maintenance efficiency. In this paper, based on the analysis of the current research of wheel wear prediction at home and abroad, a tread wear sequence prediction model combining Ensemble Empirical Mode Decomposition (EEMD) and Gate Recurrent Unit (GRU) modeling method is proposed to address the time lag problem in the existing prediction. Firstly, EEMD algorithm is used to decompose the tread wear sequence into different intrinsic mode function(IMF), then the neural network is trained and predicted for each component, and finally, the prediction results of each component are linearly superimposed to obtain the prediction results of tread wear. In order to illustrate the effectiveness and superiority of the algorithm, a variety of prediction methods were applied and analyzed based on the actual measured train wheel wear data. The results show that after EEMD processing, forecast accuracy has been improved.
- 1 February 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 212-216
Application of GRU in Prediction of Subway Wheel Wear
Predicting various indicators of the wheels can help the subway operation and maintenance department to formulate a reasonable maintenance plan, allocate maintenance resources, reduce maintenance time costs, and improve maintenance efficiency. In this paper, based on the analysis of the current research of wheel wear prediction at home and abroad, a tread wear sequence prediction model combining Ensemble Empirical Mode Decomposition (EEMD) and Gate Recurrent Unit (GRU) modeling method is proposed to address the time lag problem in the existing prediction. Firstly, EEMD algorithm is used to decompose the tread wear sequence into different intrinsic mode function(IMF), then the neural network is trained and predicted for each component, and finally, the prediction results of each component are linearly superimposed to obtain the prediction results of tread wear. In order to illustrate the effectiveness and superiority of the algorithm, a variety of prediction methods were applied and analyzed based on the actual measured train wheel wear data. The results show that after EEMD processing, forecast accuracy has been improved.
- 1 January 2022
- Published by Elsevier in Electric Power Systems Research
- Vol. 202
A flexible and reliable method for spectrum analysis of large-scale power systems
- 1 January 2022
- Published by Elsevier in Electric Power Systems Research
- Vol. 202
A flexible and reliable method for spectrum analysis of large-scale power systems
- 29 September 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 21 (21) , 24879-24889
NL-Locate: An Inaudible Multi-Targets Indoor Localization for IoT Devices via Microphone Nonlinearity
Ubiquitous connection applications have become unprecedentedly attractive recently, and increasing demand for real-time multiple targets localization is proposed. Traditional methods face challenges on efficient localization simultaneously due to signal conflict. In this paper, a real-time multiple-object localization mechanism NL-Locate is proposed. By utilizing the nonlinearity of the microphone modules, we design a modulated ultrasound signal for each target device, which enables the receiver to identify each device simultaneously. Such a method does not require any channel negotiation or preallocation, and we implement the prototype of the localization system and evaluate the system performance in both simulations and real systems. The experiment results demonstrate that NL-Locate can achieve a decimeter-level localization accuracy for multiple targets efficiently.
- 29 September 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 21 (21) , 24879-24889
NL-Locate: An Inaudible Multi-Targets Indoor Localization for IoT Devices via Microphone Nonlinearity
Ubiquitous connection applications have become unprecedentedly attractive recently, and increasing demand for real-time multiple targets localization is proposed. Traditional methods face challenges on efficient localization simultaneously due to signal conflict. In this paper, a real-time multiple-object localization mechanism NL-Locate is proposed. By utilizing the nonlinearity of the microphone modules, we design a modulated ultrasound signal for each target device, which enables the receiver to identify each device simultaneously. Such a method does not require any channel negotiation or preallocation, and we implement the prototype of the localization system and evaluate the system performance in both simulations and real systems. The experiment results demonstrate that NL-Locate can achieve a decimeter-level localization accuracy for multiple targets efficiently.
- 1 October 2020
- Published by Elsevier in Electric Power Systems Research
- Vol. 187
Moving window optimization with flexible temporal structure for operating grid-connected photovoltaic microgrids
- 1 October 2020
- Published by Elsevier in Electric Power Systems Research
- Vol. 187
Moving window optimization with flexible temporal structure for operating grid-connected photovoltaic microgrids
- 8 November 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Power Systems
- Vol. 35 (3) , 2176-2189
Distributed Penalty Dual Decomposition Algorithm for Optimal Power Flow in Radial Networks
- 8 November 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Power Systems
- Vol. 35 (3) , 2176-2189
Distributed Penalty Dual Decomposition Algorithm for Optimal Power Flow in Radial Networks