Xinli Wang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Xinli Wang has a total of 78 co-authors. Here are the top co-authors by number of shared publications:
Lei Wang
11 shared publications- Lei Wang
School of Control Science and Engineering, Shandong University, Jinan 250061, China
11 shared publications Wenjian Cai
11 shared publicationsXiaohong Yin
College of Automation and Electronic Engineering, Qingdao University of Science and Technology, Qingdao, China
11 shared publicationsLei Jia
9 shared publicationsQiong Wu
8 shared publications
Latest Publications
- 29 May 2026
- Published by Elsevier in Building and Environment
- Vol. 301
Graph attention-based decomposed-critic multi-agent deep reinforcement learning for multi-zone HVAC control
- 29 May 2026
- Published by Elsevier in Building and Environment
- Vol. 301
Graph attention-based decomposed-critic multi-agent deep reinforcement learning for multi-zone HVAC control
- Open Access
Nonlinear Pressure Fluctuation Management for Ejector-Based Hydrogen Recirculation System in Large-Power Vehicular PEMFCs
The ejector-based hydrogen recirculation systems in vehicular proton exchange membrane fuel cells (PEMFCs) have been the research focus of fuel cell technology. However, the anode pressure fluctuations and nonlinear characteristics urgently need to be addressed under the varying operating conditions of the ejector-based hydrogen recirculation system. In this paper, an Adaptive Model Predictive Control strategy is proposed to stabilize anode pressure and smooth pressure fluctuations during current changes and purges. An ejector is designed and a nonlinear control model is established for the ejector-based hydrogen recirculation system of the 110 kW PEMFC. The proposed strategy achieves the mean absolute error (MAE) of 0.044 kPa and the root mean square error of 1.041 kPa in anode pressure management, outperforming traditional Model Predictive Control and Proportional-Integral-Derivative strategies. The hydrogen excess ratio exceeding 1.5 ensures compliance with the operational requirements of system. The experimental results with the pressure MAE of 0.482 kPa and the current fluctuation of ±0.7 A validate the effectiveness of the proposed strategy in practical applications.
Open AccessNonlinear Pressure Fluctuation Management for Ejector-Based Hydrogen Recirculation System in Large-Power Vehicular PEMFCs
The ejector-based hydrogen recirculation systems in vehicular proton exchange membrane fuel cells (PEMFCs) have been the research focus of fuel cell technology. However, the anode pressure fluctuations and nonlinear characteristics urgently need to be addressed under the varying operating conditions of the ejector-based hydrogen recirculation system. In this paper, an Adaptive Model Predictive Control strategy is proposed to stabilize anode pressure and smooth pressure fluctuations during current changes and purges. An ejector is designed and a nonlinear control model is established for the ejector-based hydrogen recirculation system of the 110 kW PEMFC. The proposed strategy achieves the mean absolute error (MAE) of 0.044 kPa and the root mean square error of 1.041 kPa in anode pressure management, outperforming traditional Model Predictive Control and Proportional-Integral-Derivative strategies. The hydrogen excess ratio exceeding 1.5 ensures compliance with the operational requirements of system. The experimental results with the pressure MAE of 0.482 kPa and the current fluctuation of ±0.7 A validate the effectiveness of the proposed strategy in practical applications.
- 3 March 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE/CAA Journal of Automatica Sinica
- Vol. 12 (3) , 596-605
Enhanced Tube-Based Event-Triggered Stochastic Model Predictive Control with Additive Uncertainties
This paper proposes an event-triggered stochastic model predictive control for discrete-time linear time-invariant (LTI) systems under additive stochastic disturbances. It first constructs a probabilistic invariant set and a probabilistic reachable set based on the priori knowledge of system uncertainties. Assisted with enhanced robust tubes, the chance constraints are then formulated into a deterministic form. To alleviate the online computational burden, a novel event-triggered stochastic model predictive control is developed, where the triggering condition is designed based on the past and future optimal trajectory tracking errors in order to achieve a good trade-off between system resource utilization and control performance. Two triggering parameters σ and γ are used to adjust the frequency of solving the optimization problem. The probabilistic feasibility and stability of the system under the event-triggered mechanism are also examined. Finally, numerical studies on the control of a heating, ventilation, and air conditioning (HVAC) system confirm the efficacy of the proposed control.
- 3 March 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE/CAA Journal of Automatica Sinica
- Vol. 12 (3) , 596-605
Enhanced Tube-Based Event-Triggered Stochastic Model Predictive Control with Additive Uncertainties
This paper proposes an event-triggered stochastic model predictive control for discrete-time linear time-invariant (LTI) systems under additive stochastic disturbances. It first constructs a probabilistic invariant set and a probabilistic reachable set based on the priori knowledge of system uncertainties. Assisted with enhanced robust tubes, the chance constraints are then formulated into a deterministic form. To alleviate the online computational burden, a novel event-triggered stochastic model predictive control is developed, where the triggering condition is designed based on the past and future optimal trajectory tracking errors in order to achieve a good trade-off between system resource utilization and control performance. Two triggering parameters σ and γ are used to adjust the frequency of solving the optimization problem. The probabilistic feasibility and stability of the system under the event-triggered mechanism are also examined. Finally, numerical studies on the control of a heating, ventilation, and air conditioning (HVAC) system confirm the efficacy of the proposed control.
- 1 January 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Smart Grid
- Vol. 16 (3) , 2599-2610
Federated Accelerated Deep Reinforcement Learning for Multi-Zone HVAC Control in Commercial Buildings
Deep Reinforcement Learning (DRL) has demonstrated a promising prospect in optimizing Heating, Ventilation, and Air Conditioning (HVAC) systems to minimize energy costs and improve thermal comfort without requiring the knowledge of building thermal dynamic models. However, DRL training can be difficult to converge due to its long exploration, especially in multi-agent scenarios. To address these concerns, we propose a novel Federated Accelerated Multi-Agent DRL (FA-MADRL) algorithm for HVAC control in commercial buildings with multizone offices. To be specific, we reformulate the optimal control problem of indoor temperature, CO2 concentration and humidity in multi-zone HVAC as a Markov Decision Process (MDP). Then, we establish a MADRL framework for HVAC system control and utilize a federated learning (FL) mechanism to accelerate the convergence during real-time deployment. Experimental studies have been carried out on a TRNSYS-based commercial building HVAC system with multiple zones. The results demonstrate the superiority of our proposed algorithm, with improved convergence speed, reduced energy consumption, and satisfied thermal comfort.
- 1 January 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Smart Grid
- Vol. 16 (3) , 2599-2610
Federated Accelerated Deep Reinforcement Learning for Multi-Zone HVAC Control in Commercial Buildings
Deep Reinforcement Learning (DRL) has demonstrated a promising prospect in optimizing Heating, Ventilation, and Air Conditioning (HVAC) systems to minimize energy costs and improve thermal comfort without requiring the knowledge of building thermal dynamic models. However, DRL training can be difficult to converge due to its long exploration, especially in multi-agent scenarios. To address these concerns, we propose a novel Federated Accelerated Multi-Agent DRL (FA-MADRL) algorithm for HVAC control in commercial buildings with multizone offices. To be specific, we reformulate the optimal control problem of indoor temperature, CO2 concentration and humidity in multi-zone HVAC as a Markov Decision Process (MDP). Then, we establish a MADRL framework for HVAC system control and utilize a federated learning (FL) mechanism to accelerate the convergence during real-time deployment. Experimental studies have been carried out on a TRNSYS-based commercial building HVAC system with multiple zones. The results demonstrate the superiority of our proposed algorithm, with improved convergence speed, reduced energy consumption, and satisfied thermal comfort.
- 28 December 2024
- Published by Springer Nature
- p. 394-405
A Multitask Learning Model for Temperature and Relative Humidity Prediction in Multi-zone Buildings
- 28 December 2024
- Published by Springer Nature
- p. 394-405
A Multitask Learning Model for Temperature and Relative Humidity Prediction in Multi-zone Buildings
- Open Access
- 17 May 2024
- Published by Association for Computing Machinery (ACM)
- p. 353-358
A Medical Sample Collection Robot Based on Improved YOLO Algorithm
Medical sample collection is a crucial foundation for clinical diagnosis and biomedical research. With the Healthy China initiative, the importance of health medical big data is increasingly recognized, and the demand for medical sample collection in China continues to grow. The development of high-precision medical testing technologies like gene testing has heightened the quality requirements for sample collection. Therefore, developing a more efficient and safer automated medical sample collection robot is of significant importance. Traditional medical sample collection methods, which rely on direct operation by medical staff, present certain risks and challenges. These include the risk of cross-infection, insufficient standardization in sampling, and low efficiency when dealing with large-scale sample collection needs. To address these issues, we have designed a medical sample collection robot that enhances sampling efficiency and safety while reducing the risk of infection for healthcare workers. The design is divided into hardware and software components. The software part utilizes an improved YOLO v5 algorithm with an enhanced attention mechanism layer for better target area recognition. The hardware part features a 6-axis robotic arm, 3D-printed for precision, controlled by an Arduino and STM32 microcontroller system, with a force feedback device at the gripper for safety. Our medical sample collection robot, equipped with the improved YOLOv5 model, has demonstrated robust performance in accurately identifying target sampling locations. The 6-DOF robotic arm, mimicking the actions of medical staff, successfully collects medical samples. Experimental validation confirms the robot's capability to effectively collect medical sample information.
- 17 May 2024
- Published by Association for Computing Machinery (ACM)
- p. 353-358
Open AccessA Medical Sample Collection Robot Based on Improved YOLO Algorithm
Medical sample collection is a crucial foundation for clinical diagnosis and biomedical research. With the Healthy China initiative, the importance of health medical big data is increasingly recognized, and the demand for medical sample collection in China continues to grow. The development of high-precision medical testing technologies like gene testing has heightened the quality requirements for sample collection. Therefore, developing a more efficient and safer automated medical sample collection robot is of significant importance. Traditional medical sample collection methods, which rely on direct operation by medical staff, present certain risks and challenges. These include the risk of cross-infection, insufficient standardization in sampling, and low efficiency when dealing with large-scale sample collection needs. To address these issues, we have designed a medical sample collection robot that enhances sampling efficiency and safety while reducing the risk of infection for healthcare workers. The design is divided into hardware and software components. The software part utilizes an improved YOLO v5 algorithm with an enhanced attention mechanism layer for better target area recognition. The hardware part features a 6-axis robotic arm, 3D-printed for precision, controlled by an Arduino and STM32 microcontroller system, with a force feedback device at the gripper for safety. Our medical sample collection robot, equipped with the improved YOLOv5 model, has demonstrated robust performance in accurately identifying target sampling locations. The 6-DOF robotic arm, mimicking the actions of medical staff, successfully collects medical samples. Experimental validation confirms the robot's capability to effectively collect medical sample information.
- 11 January 2024
- Published by Elsevier in International Journal of Hydrogen Energy
- Vol. 57, 515-529
Auxiliary-ejector-based hydrogen recirculation system to broaden PEMFC operating range
- 11 January 2024
- Published by Elsevier in International Journal of Hydrogen Energy
- Vol. 57, 515-529
Auxiliary-ejector-based hydrogen recirculation system to broaden PEMFC operating range
- Open Access
- 25 October 2023
- Published by MDPI AG in Inventions
- Vol. 8 (6) , 133
A Wide Operating Range Ejector with Part Nested Nozzles for PEMFC Hydrogen Recirculation System
The ejector drives unreacted hydrogen from the anode to improve fuel utilization ratio and discharges redundant water to prevent flooding and shutdown in the proton exchange membrane fuel cell (PEMFC). However, the traditional fixed structure ejector cannot meet the recycling requirements in the whole dynamic working condition of the fuel cell. In this article, a part nested four-nozzle (PNFN) ejector is proposed to enhance the hydrogen recycling efficiency under variable working conditions of the PEMFC by restricting the nozzle flow as 10%, 20%, 20%, and 50% of the fuel cell-rated power, respectively. Systematical analyses are performed on the experimentally verified 3D model to study inner flow characteristics and performance under different nozzle running modes. The results indicate that the PNFN ejector satisfies the recirculation ratio requirements in the power range of 34–220 kW within the 7–9 bar suitable supply pressure. By comparing with traditional ejectors, the PNFN ejector has a wider working range and especially outputs better performance in the low power range.
- 25 October 2023
- Published by MDPI AG in Inventions
- Vol. 8 (6) , 133
Open AccessA Wide Operating Range Ejector with Part Nested Nozzles for PEMFC Hydrogen Recirculation System
The ejector drives unreacted hydrogen from the anode to improve fuel utilization ratio and discharges redundant water to prevent flooding and shutdown in the proton exchange membrane fuel cell (PEMFC). However, the traditional fixed structure ejector cannot meet the recycling requirements in the whole dynamic working condition of the fuel cell. In this article, a part nested four-nozzle (PNFN) ejector is proposed to enhance the hydrogen recycling efficiency under variable working conditions of the PEMFC by restricting the nozzle flow as 10%, 20%, 20%, and 50% of the fuel cell-rated power, respectively. Systematical analyses are performed on the experimentally verified 3D model to study inner flow characteristics and performance under different nozzle running modes. The results indicate that the PNFN ejector satisfies the recirculation ratio requirements in the power range of 34–220 kW within the 7–9 bar suitable supply pressure. By comparing with traditional ejectors, the PNFN ejector has a wider working range and especially outputs better performance in the low power range.
- 19 April 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Informatics
- Vol. 20 (1) , 482-491
Distributed LSTM-GCN-Based Spatial–Temporal Indoor Temperature Prediction in Multizone Buildings
Indoor temperature prediction of multiple zones in near future horizons is vital in developing an optimal regulation strategy of heating, ventilation, and air conditioning systems in large-scale complex buildings. This is, however, challenging due to the spatial–temporal correlation and multivariable coupling characteristics. This article proposes a novel deep learning framework incorporating the distributed long short-term memory and graph convolution network namely DL-GCN for indoor temperature prediction in large public buildings, aiming to learn the spatial–temporal correlation and multivariable coupling features. First, the indoor temperature and humidity data from different zones are handled by GCN networks to extract the temperature spatial features. Then, in the distributed LSTM module, other data, such as light and ac power consumption, are fused with the outputs of the GCN module, respectively, in a distributed way to learn the coupling interactions and temporal characteristics between these variables. Comparison study and ablation experiments are conducted using real datasets from a large-scale building to verify its effectiveness and superior performance in multizone indoor temperature prediction.
- 19 April 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Informatics
- Vol. 20 (1) , 482-491
Distributed LSTM-GCN-Based Spatial–Temporal Indoor Temperature Prediction in Multizone Buildings
Indoor temperature prediction of multiple zones in near future horizons is vital in developing an optimal regulation strategy of heating, ventilation, and air conditioning systems in large-scale complex buildings. This is, however, challenging due to the spatial–temporal correlation and multivariable coupling characteristics. This article proposes a novel deep learning framework incorporating the distributed long short-term memory and graph convolution network namely DL-GCN for indoor temperature prediction in large public buildings, aiming to learn the spatial–temporal correlation and multivariable coupling features. First, the indoor temperature and humidity data from different zones are handled by GCN networks to extract the temperature spatial features. Then, in the distributed LSTM module, other data, such as light and ac power consumption, are fused with the outputs of the GCN module, respectively, in a distributed way to learn the coupling interactions and temporal characteristics between these variables. Comparison study and ablation experiments are conducted using real datasets from a large-scale building to verify its effectiveness and superior performance in multizone indoor temperature prediction.
- 5 August 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Informatics
- Vol. 19 (4) , 5743-5751
An LSTM and ANN Fusion Dynamic Model of a Proton Exchange Membrane Fuel Cell
A proton exchange membrane fuel cell (PEMFC) has great application prospects due to its low emission and high efficiency. An accurate model to predict the dynamic output voltage is essential for the optimal control of the PEMFC for the applications on vehicles and power stations. In this article, a novel deep learning framework with the long short-term memory (LSTM) and artificial neural network (ANN) fusion is proposed to develop the PEMFC dynamic model by extracting both the historical and current information. The LSTM extracts the temporal information from the past PEMFC states with its order determined with autocorrelation and partial autocorrelation functions, while the influence of the system current inputs is learnt by the ANN. Then, the outputs of LSTM and ANN are concatenated with the multiple information fused to predict the PEMFC dynamic output voltage. After validated by the operating data from a laboratory-scale PEMFC system, the LSTM and ANN fusion model is compared with the existing models, such as support vector regression, ANN, and LSTM methods. The comparison results show that the proposed LSTM and ANN fusion model can provide the best prediction performance with the lowest mean square error of 1.303. The proposed LSTM and ANN fusion model can be helpful to develop the optimal control strategy of the PEMFC.
- 5 August 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Informatics
- Vol. 19 (4) , 5743-5751
An LSTM and ANN Fusion Dynamic Model of a Proton Exchange Membrane Fuel Cell
A proton exchange membrane fuel cell (PEMFC) has great application prospects due to its low emission and high efficiency. An accurate model to predict the dynamic output voltage is essential for the optimal control of the PEMFC for the applications on vehicles and power stations. In this article, a novel deep learning framework with the long short-term memory (LSTM) and artificial neural network (ANN) fusion is proposed to develop the PEMFC dynamic model by extracting both the historical and current information. The LSTM extracts the temporal information from the past PEMFC states with its order determined with autocorrelation and partial autocorrelation functions, while the influence of the system current inputs is learnt by the ANN. Then, the outputs of LSTM and ANN are concatenated with the multiple information fused to predict the PEMFC dynamic output voltage. After validated by the operating data from a laboratory-scale PEMFC system, the LSTM and ANN fusion model is compared with the existing models, such as support vector regression, ANN, and LSTM methods. The comparison results show that the proposed LSTM and ANN fusion model can provide the best prediction performance with the lowest mean square error of 1.303. The proposed LSTM and ANN fusion model can be helpful to develop the optimal control strategy of the PEMFC.