Zhonghua Liu
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
Zhonghua Liu has a total of 31 co-authors. Here are the top co-authors by number of shared publications:
- Bin Song
Xidian University
1 shared publication - Chaohui Xie
School of Engineering Science, University of Chinese Academy of Sciences, Beijing, China
1 shared publication - Donghai Wang
Faculty of Mechanical Engineering and Automation, Zhejiang Sci-Tech University, Hangzhou, China
1 shared publication - Gang Liu
Tsinghua University
1 shared publication - Guangzhi Chen
Beihang University
1 shared publication Hua Yu
School of Engineering SciencesUniversity of the Chinese Academy of Sciences Beijing China
1 shared publication
Latest Publications
- Open Access
- 11 November 2026
- Published by MDPI AG in Mathematics
- Vol. 14 (22) , 4149
Coordinated Scheduling of Hydrogen Production and Flexible Loads in Offshore Wind-Powered Underwater Data Centers
Offshore wind-powered hydrogen production is increasingly recognized as an effective pathway for improving renewable energy utilization and facilitating the decarbonization of energy systems. However, the lack of flexible, high-demand local consumption scenarios limits the effective integration of offshore wind energy. In this context, underwater data centers (UDCs), characterized by high energy demand and operational flexibility, constitute a promising solution as controllable loads to support hydrogen-based energy systems. This study proposes an integrated offshore wind-powered hydrogen production system coupled with underwater data centers, directed at enhancing both economic performance and renewable energy utilization. A comprehensive system modeling framework is developed, in which hydrogen production, storage operations, and heterogeneous UDC loads are jointly considered. The UDC loads are classified into four categories to capture their distinct operational characteristics. A coordinated optimization model is formulated to minimize the net system cost, and three operational scenarios are designed to investigate different coordination strategies. The results demonstrate that coordinated optimization of hydrogen production–storage processes and flexible UDC load scheduling significantly improves overall system performance. The optimal scenario achieves a minimum net system cost of CNY 311,911.50 and a maximum wind power utilization rate of 91.59%, corresponding to cost reductions of 31.32% and 54.00% compared with benchmark scenarios. These findings highlight that integrating hydrogen production systems with flexible data center loads can effectively mitigate renewable energy curtailment and improve system-level efficiency. This work provides a new perspective for the design and operation of offshore hydrogen-based integrated energy systems by introducing flexible digital infrastructure as a key coupling component.
- 11 November 2026
- Published by MDPI AG in Mathematics
- Vol. 14 (22) , 4149
Open AccessCoordinated Scheduling of Hydrogen Production and Flexible Loads in Offshore Wind-Powered Underwater Data Centers
Offshore wind-powered hydrogen production is increasingly recognized as an effective pathway for improving renewable energy utilization and facilitating the decarbonization of energy systems. However, the lack of flexible, high-demand local consumption scenarios limits the effective integration of offshore wind energy. In this context, underwater data centers (UDCs), characterized by high energy demand and operational flexibility, constitute a promising solution as controllable loads to support hydrogen-based energy systems. This study proposes an integrated offshore wind-powered hydrogen production system coupled with underwater data centers, directed at enhancing both economic performance and renewable energy utilization. A comprehensive system modeling framework is developed, in which hydrogen production, storage operations, and heterogeneous UDC loads are jointly considered. The UDC loads are classified into four categories to capture their distinct operational characteristics. A coordinated optimization model is formulated to minimize the net system cost, and three operational scenarios are designed to investigate different coordination strategies. The results demonstrate that coordinated optimization of hydrogen production–storage processes and flexible UDC load scheduling significantly improves overall system performance. The optimal scenario achieves a minimum net system cost of CNY 311,911.50 and a maximum wind power utilization rate of 91.59%, corresponding to cost reductions of 31.32% and 54.00% compared with benchmark scenarios. These findings highlight that integrating hydrogen production systems with flexible data center loads can effectively mitigate renewable energy curtailment and improve system-level efficiency. This work provides a new perspective for the design and operation of offshore hydrogen-based integrated energy systems by introducing flexible digital infrastructure as a key coupling component.
- Open Access
- 18 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 668-673
Research on Measuring Default Risk of Internet Microloans Based on the CreditRisk+ Model
With the rapid growth of internet finance, fintech companies are increasingly entering the "Internet + Consumer Finance" sector, offering personal consumer loans. Effectively preventing and managing credit risk from borrower defaults has become crucial for small loan businesses. This paper analyzes the credit risks faced by personal microloans in China's internet finance sector, using M Fintech Company's loan data as a case study. A binary logistic regression model is constructed to predict default probabilities, and the Credit-Risk+ model is applied to measure credit risk, improving calculation accuracy. Empirical research validates the model's effectiveness, and the influence of borrower characteristics on credit risk is discussed. This study aids microloan companies in risk control and management improvement, while also serving as a reference for related research.
- 18 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 668-673
Open AccessResearch on Measuring Default Risk of Internet Microloans Based on the CreditRisk+ Model
With the rapid growth of internet finance, fintech companies are increasingly entering the "Internet + Consumer Finance" sector, offering personal consumer loans. Effectively preventing and managing credit risk from borrower defaults has become crucial for small loan businesses. This paper analyzes the credit risks faced by personal microloans in China's internet finance sector, using M Fintech Company's loan data as a case study. A binary logistic regression model is constructed to predict default probabilities, and the Credit-Risk+ model is applied to measure credit risk, improving calculation accuracy. Empirical research validates the model's effectiveness, and the influence of borrower characteristics on credit risk is discussed. This study aids microloan companies in risk control and management improvement, while also serving as a reference for related research.
- Open Access
- 30 May 2024
- Published by MDPI AG in Mathematics
- Vol. 12 (11) , 1700
A Study on Caregiver Activity Recognition for the Elderly at Home Based on the XGBoost Model
This paper aims to discuss the implementation of data analysis and information management for elderly nursing care from a data-driven perspective. It addresses the current challenges of in-home caregivers, providing a basis for decision making in analyzing nursing service content and evaluating job performance. The characteristics of caregivers’ activities were analyzed during the design of a wearable device-wearing scheme and a sensor data collection system. XGBoost, SVM, and Random Forest models were used in the experiments, with the Cuckoo search algorithm employed to optimize the XGBoost model parameters. Based on the control group experiment, it was confirmed that the XGBoost model, after adjusting the parameters using the Cuckoo search algorithm, exhibited better recognition performance than the SVM and RandomForest models, and the accuracy reached 0.9438. Wearable devices present high recognition accuracy in caregiver activity recognition research, which greatly improves the inspection of caregivers’ work and further promotes the completion of services. This study actively explores the applications of information technology and artificial intelligence theory to address practical problems and effectively promote the digitalization and intelligent development of the elderly nursing care industry.
- 30 May 2024
- Published by MDPI AG in Mathematics
- Vol. 12 (11) , 1700
Open AccessA Study on Caregiver Activity Recognition for the Elderly at Home Based on the XGBoost Model
This paper aims to discuss the implementation of data analysis and information management for elderly nursing care from a data-driven perspective. It addresses the current challenges of in-home caregivers, providing a basis for decision making in analyzing nursing service content and evaluating job performance. The characteristics of caregivers’ activities were analyzed during the design of a wearable device-wearing scheme and a sensor data collection system. XGBoost, SVM, and Random Forest models were used in the experiments, with the Cuckoo search algorithm employed to optimize the XGBoost model parameters. Based on the control group experiment, it was confirmed that the XGBoost model, after adjusting the parameters using the Cuckoo search algorithm, exhibited better recognition performance than the SVM and RandomForest models, and the accuracy reached 0.9438. Wearable devices present high recognition accuracy in caregiver activity recognition research, which greatly improves the inspection of caregivers’ work and further promotes the completion of services. This study actively explores the applications of information technology and artificial intelligence theory to address practical problems and effectively promote the digitalization and intelligent development of the elderly nursing care industry.
- Open Access
- 2 June 2023
- Published by Elsevier in Energy Reports
- Vol. 9, 2054-2068
A study on the energy storage scenarios design and the business model analysis for a zero-carbon big data industrial park from the perspective of source-grid-load-storage collaboration
- 2 June 2023
- Published by Elsevier in Energy Reports
- Vol. 9, 2054-2068
Open AccessA study on the energy storage scenarios design and the business model analysis for a zero-carbon big data industrial park from the perspective of source-grid-load-storage collaboration
- 8 July 2022
- Published by European Society of Computational Methods in Sciences and Engineering in Journal of Computational Methods in Sciences and Engineering
- Vol. 22 (4) , 1393-1408
An improved SSD method for infrared target detection based on convolutional neural network
Target detection is the basis for automatic target recognition system of infrared imaging guidance to complete subsequent tasks such as recognition and tracking. Existing systems have not the autonomous learning ability of target feature, and it will be powerless once the task environment exceeds the pre-planned condition. The single-stage target detection based on deep learning has the ability of autonomous learning and high computational efficiency, which is an effective way to solve the problem of infrared imaging guidance target detection in complex environment. SSD (Single Shot MultiBox Detector) is a classical single-stage detection model, however, the convolution layer with strong semantic information in SSD has low resolution, which is not conducive to small target detection. In addition, the location loss of SSD does not consider the impact of target scale change. Therefore, this paper puts forward two improvement ideas in view of SSD: (1) Starting from FPN (Feature Pyramid Network), feature channel’s importance is distinguished through efficient channel attention mechanism, the contribution of each feature layer to the fusion output is described based on the learnable weight, and the feature weighted fusion of bidirectional multi-scale is realized between the feature layer which has low resolution and strong semantics and the feature layer which has high resolution and weak semantics. (2) Starting from IoU (Intersection over Union) and considering non overlapping parts and geometric relationship between the predicted box and the ground-truth box, the location loss of SSD that remains invariable to the target scale change is constructed to improve the sensitivity of the detection model to the locating error of small target. The experimental results show that, for 300 × 300 input, the presented method achieves 84.7% mAP (mean Average Precision) on VOC2007 test and for 512 × 512 input, it reaches 86.6%. On the self-built infrared aircraft data set, the proposed method achieves 81.1% mAP and can detect more small targets. Without affecting detection speed, the presented method on experimental results outperforms some comparable state-of-the-art models such as YOLOv3 (You Only Look Once), DSSD (Deconvolutional Single Shot Multibox Detector), RSSD (Rainbow Single Shot Multibox Detector) and FSSD (Fusion Single Shot Multibox Detector).
- 8 July 2022
- Published by European Society of Computational Methods in Sciences and Engineering in Journal of Computational Methods in Sciences and Engineering
- Vol. 22 (4) , 1393-1408
An improved SSD method for infrared target detection based on convolutional neural network
Target detection is the basis for automatic target recognition system of infrared imaging guidance to complete subsequent tasks such as recognition and tracking. Existing systems have not the autonomous learning ability of target feature, and it will be powerless once the task environment exceeds the pre-planned condition. The single-stage target detection based on deep learning has the ability of autonomous learning and high computational efficiency, which is an effective way to solve the problem of infrared imaging guidance target detection in complex environment. SSD (Single Shot MultiBox Detector) is a classical single-stage detection model, however, the convolution layer with strong semantic information in SSD has low resolution, which is not conducive to small target detection. In addition, the location loss of SSD does not consider the impact of target scale change. Therefore, this paper puts forward two improvement ideas in view of SSD: (1) Starting from FPN (Feature Pyramid Network), feature channel’s importance is distinguished through efficient channel attention mechanism, the contribution of each feature layer to the fusion output is described based on the learnable weight, and the feature weighted fusion of bidirectional multi-scale is realized between the feature layer which has low resolution and strong semantics and the feature layer which has high resolution and weak semantics. (2) Starting from IoU (Intersection over Union) and considering non overlapping parts and geometric relationship between the predicted box and the ground-truth box, the location loss of SSD that remains invariable to the target scale change is constructed to improve the sensitivity of the detection model to the locating error of small target. The experimental results show that, for 300 × 300 input, the presented method achieves 84.7% mAP (mean Average Precision) on VOC2007 test and for 512 × 512 input, it reaches 86.6%. On the self-built infrared aircraft data set, the proposed method achieves 81.1% mAP and can detect more small targets. Without affecting detection speed, the presented method on experimental results outperforms some comparable state-of-the-art models such as YOLOv3 (You Only Look Once), DSSD (Deconvolutional Single Shot Multibox Detector), RSSD (Rainbow Single Shot Multibox Detector) and FSSD (Fusion Single Shot Multibox Detector).
- Open Access
- 13 June 2022
- Published by Frontiers Media SA in Frontiers in Energy Research
- Vol. 10
Acoustic Prediction of a Multilateral-Well Unconventional Reservoir Based on a Hybrid Feature-Enhancement Long Short-Term Memory Neural Network
Due to the complexity of unconventional reservoir measurement, log data acquired are often incomplete, which results in inaccurate formation evaluation and higher operational risks. Common solutions, such as coring, are typically high cost related while not being sufficiently representative. In recent years, neural network has received increasing attention given its strong ability in data prediction. Nevertheless, most neural networks only focus on one specific feature of the selected data, thus prohibiting their prediction accuracy for reservoir logs where data are often dominated by more than one key feature. To address this challenge, a novel multi-channel hybrid Long Short-Term Memory (LSTM) neural network for effective acoustic log prediction is proposed. The network combines Convolutional Neural Network (CNN) and LSTM, where CNN is used to extract spatial features of the logs and LSTM network extracts temporal features with the assistance of an adaptive attention mechanism implemented for key feature recognition. In addition, the strong heterogeneity of unconventional reservoirs also increases the difficulty of prediction. Therefore, according to the characteristics of the unconventional reservoir, we designed three feature enhancement methods to mine the hidden information of logs. To prove the performance of the proposed network, a case study is presented with data acquired from Jimusar Oilfield, one of the largest unconventional reservoirs in China. Four groups of experiments are conducted, and the proposed network is employed for acoustic log prediction. The predicted results are validated against measurement (R2: 92.27%, 91.42%, 93.31%, and 92.03%; RMSE: 3.32%, 3.92%, 3.06%, and 3.53%). The performance of the proposed network is compared to other networks such as CNN, LSTM, CNN-LSTM, and random forest (RF). The comparisons show that the proposed network has the highest accuracy level of prediction, which means it provides an effective approach to complement missing data during complicated unconventional reservoir measurement and, therefore, could be of significant potential in energy exploration.
- 13 June 2022
- Published by Frontiers Media SA in Frontiers in Energy Research
- Vol. 10
Open AccessAcoustic Prediction of a Multilateral-Well Unconventional Reservoir Based on a Hybrid Feature-Enhancement Long Short-Term Memory Neural Network
Due to the complexity of unconventional reservoir measurement, log data acquired are often incomplete, which results in inaccurate formation evaluation and higher operational risks. Common solutions, such as coring, are typically high cost related while not being sufficiently representative. In recent years, neural network has received increasing attention given its strong ability in data prediction. Nevertheless, most neural networks only focus on one specific feature of the selected data, thus prohibiting their prediction accuracy for reservoir logs where data are often dominated by more than one key feature. To address this challenge, a novel multi-channel hybrid Long Short-Term Memory (LSTM) neural network for effective acoustic log prediction is proposed. The network combines Convolutional Neural Network (CNN) and LSTM, where CNN is used to extract spatial features of the logs and LSTM network extracts temporal features with the assistance of an adaptive attention mechanism implemented for key feature recognition. In addition, the strong heterogeneity of unconventional reservoirs also increases the difficulty of prediction. Therefore, according to the characteristics of the unconventional reservoir, we designed three feature enhancement methods to mine the hidden information of logs. To prove the performance of the proposed network, a case study is presented with data acquired from Jimusar Oilfield, one of the largest unconventional reservoirs in China. Four groups of experiments are conducted, and the proposed network is employed for acoustic log prediction. The predicted results are validated against measurement (R2: 92.27%, 91.42%, 93.31%, and 92.03%; RMSE: 3.32%, 3.92%, 3.06%, and 3.53%). The performance of the proposed network is compared to other networks such as CNN, LSTM, CNN-LSTM, and random forest (RF). The comparisons show that the proposed network has the highest accuracy level of prediction, which means it provides an effective approach to complement missing data during complicated unconventional reservoir measurement and, therefore, could be of significant potential in energy exploration.
- 1 March 2022
- Published by Springer Nature in Frontiers of Mechanical Engineering
- Vol. 17 (1) , 1-17
Optimization of aero-engine pipeline for avoiding vibration based on length adjustment of straight-line segment
- 1 March 2022
- Published by Springer Nature in Frontiers of Mechanical Engineering
- Vol. 17 (1) , 1-17
Optimization of aero-engine pipeline for avoiding vibration based on length adjustment of straight-line segment
- 1 January 2021
- Published by Elsevier in Science of The Total Environment
- Vol. 751, 141597
Optimization of water resource dispatching for Huanghua Port under uncertain water usage scenario
- 1 January 2021
- Published by Elsevier in Science of The Total Environment
- Vol. 751, 141597
Optimization of water resource dispatching for Huanghua Port under uncertain water usage scenario
- 10 March 2020
- Published by Wiley in International Journal of Energy Research
- Vol. 44 (7) , 5425-5440
A prediction‐based optimization strategy to balance the use of diesel generator and emergency battery in the microgrid
- 10 March 2020
- Published by Wiley in International Journal of Energy Research
- Vol. 44 (7) , 5425-5440
A prediction‐based optimization strategy to balance the use of diesel generator and emergency battery in the microgrid
- Open Access
- 1 January 1999
- Published by Acta Physica Sinica, Chinese Physical Society and Institute of Physics, Chinese Academy of Sciences in Acta Physica Sinica
- Vol. 48 (4) , 581-588
A MODIFIED PERIODIC PULSE METHOD TO CONTROL THE CHAOS OF CONSERVATIVE FLOW
Firstly, we find out the convergent scope in limited time of the conservation flow x…+x·-x2+B=0 (0≤B≤0.005) in a certain time, whose scope Lyapunov exponents is below zero, and restrained in Poincaré section, and then get the steady periodic orbits through periodic pulse method. With the above-mentioned rule, we can control systematic high periodic orbits.This rule is, to some extent, robust against external noise.
- 1 January 1999
- Published by Acta Physica Sinica, Chinese Physical Society and Institute of Physics, Chinese Academy of Sciences in Acta Physica Sinica
- Vol. 48 (4) , 581-588
Open AccessA MODIFIED PERIODIC PULSE METHOD TO CONTROL THE CHAOS OF CONSERVATIVE FLOW
Firstly, we find out the convergent scope in limited time of the conservation flow x…+x·-x2+B=0 (0≤B≤0.005) in a certain time, whose scope Lyapunov exponents is below zero, and restrained in Poincaré section, and then get the steady periodic orbits through periodic pulse method. With the above-mentioned rule, we can control systematic high periodic orbits.This rule is, to some extent, robust against external noise.