Lianfeng Han
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Lianfeng Han has a total of 19 co-authors. Here are the top co-authors by number of shared publications:
- Gongbo Zhou
China University of Mining and Technology
7 shared publications - Ping Zhou
China University of Mining and Technology
7 shared publications - Xiaodong Yan
China University of Mining and Technology
6 shared publications - Zhenzhi He
School of Mechatronic Engineering, Jiangsu Normal University, Xuzhou, China
3 shared publications Qing Li
Jiangsu Key Laboratory of Mine Mechanical and Electrical Equipment, China University of Mining and Technology, Xuzhou, China
2 shared publications- Wei Wang
Jiangsu Key Laboratory of Mine Mechanical and Electrical Equipment, School of Mechatronic Engineering, China University of Mining and Technology, Xuzhou, China
2 shared publications
Latest Publications
- 18 March 2026
- Published by IOP Publishing in Measurement Science and Technology
- Vol. 37 (14)
A cross-condition fault diagnosis method for bearings based on feature enhancement and semantic information constraints
Unsupervised domain adaptation (UDA) has garnered widespread attention in the field of rolling bearings fault diagnosis, thanks to its remarkable performance in transfer-based diagnostic tasks. However, in a noisy environment, the existing domain adaptive networks are difficult to accurately mine domain invariant features and effectively align edge distribution and conditional distribution, which lead to the problem of low diagnostic accuracy in the existing models. In response to the above challenges, a cross-condition fault diagnosis method for bearings based on feature enhancement and semantic information constraints (CC-FESIC) is proposed. Firstly, a networked blind deconvolution (NBD) module is designed based on the time-domain autoencoder and frequency-domain filter, which enhances the expression of domaininvariant features in the fault signal domain of rolling bearings. Secondly, the fusion of domain-invariant features is accomplished through a multi-scale feature extractor. Again, a joint distribution framework with semantic information constraints (JDF-SIC) is constructed, the framework realizes the joint distribution alignment of features respectively through multi-core maximum mean discrepancy (MK-MMD) and the improved MK-MMD (SMK-MMD). In addition, the joint distribution alignment is constrained through a semantic information constraints (SIC) module. Finally, extensive crosscondition diagnostic experiments are carried out on two public bearing datasets to verify the effectiveness of the proposed method.
- 18 March 2026
- Published by IOP Publishing in Measurement Science and Technology
- Vol. 37 (14)
A cross-condition fault diagnosis method for bearings based on feature enhancement and semantic information constraints
Unsupervised domain adaptation (UDA) has garnered widespread attention in the field of rolling bearings fault diagnosis, thanks to its remarkable performance in transfer-based diagnostic tasks. However, in a noisy environment, the existing domain adaptive networks are difficult to accurately mine domain invariant features and effectively align edge distribution and conditional distribution, which lead to the problem of low diagnostic accuracy in the existing models. In response to the above challenges, a cross-condition fault diagnosis method for bearings based on feature enhancement and semantic information constraints (CC-FESIC) is proposed. Firstly, a networked blind deconvolution (NBD) module is designed based on the time-domain autoencoder and frequency-domain filter, which enhances the expression of domaininvariant features in the fault signal domain of rolling bearings. Secondly, the fusion of domain-invariant features is accomplished through a multi-scale feature extractor. Again, a joint distribution framework with semantic information constraints (JDF-SIC) is constructed, the framework realizes the joint distribution alignment of features respectively through multi-core maximum mean discrepancy (MK-MMD) and the improved MK-MMD (SMK-MMD). In addition, the joint distribution alignment is constrained through a semantic information constraints (SIC) module. Finally, extensive crosscondition diagnostic experiments are carried out on two public bearing datasets to verify the effectiveness of the proposed method.
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 13 (17) , 1
A Novel Wireless Sensor Node Protective Device with Enhanced Network Resilience
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 13 (17) , 1
A Novel Wireless Sensor Node Protective Device with Enhanced Network Resilience
- 16 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Network Science and Engineering
- Vol. 13, 2902-2922
Level Queue Perception-Based Quality of Service Optimization for Scraper Chain Tension Monitoring in Wireless Sensor Networks
Scraper conveyors are critical equipment in coal mine transportation, and their health directly impacts production safety. Scraper chains, which bear the load, are the components most prone to failure, accounting for over 40% of breakdowns. Deploying energy-harvesting wireless sensor network nodes to monitor scraper chain tension provides an effective means of assessing chain health. However, transmitting high-sampling-rate data in sensor networks is costly, leading to network congestion and high energy consumption. Notably, scraper chains experience over 1.5 times greater load during the upward phase than during the downward phase, making data sampled in this phase more informative for health assessment. Leveraging these characteristics can optimize network communication. Nevertheless, monitoring nodes harvest limited energy from the scraper chain system, and the collected data have diverse quality-of-service (QoS) requirements, posing significant challenges for energy management. To address this challenge, a queue model based on data priority was first established, followed by the development of a level queue perception–based QoS optimization algorithm within an improved Lyapunov optimization framework. Results show that when harvested energy meets the minimum node operation requirement (above 0.17 mW to support at least one data transmission per minute), the proposed method ensures the stability of network energy and data queues of different levels, while reducing the number of packet losses in monitoring nodes. Compared with existing approaches, this method decreases high-level data packet loss by over 46.64%, offering a promising solution for high-quality and continuous scraper chain status monitoring.
- 16 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Network Science and Engineering
- Vol. 13, 2902-2922
Level Queue Perception-Based Quality of Service Optimization for Scraper Chain Tension Monitoring in Wireless Sensor Networks
Scraper conveyors are critical equipment in coal mine transportation, and their health directly impacts production safety. Scraper chains, which bear the load, are the components most prone to failure, accounting for over 40% of breakdowns. Deploying energy-harvesting wireless sensor network nodes to monitor scraper chain tension provides an effective means of assessing chain health. However, transmitting high-sampling-rate data in sensor networks is costly, leading to network congestion and high energy consumption. Notably, scraper chains experience over 1.5 times greater load during the upward phase than during the downward phase, making data sampled in this phase more informative for health assessment. Leveraging these characteristics can optimize network communication. Nevertheless, monitoring nodes harvest limited energy from the scraper chain system, and the collected data have diverse quality-of-service (QoS) requirements, posing significant challenges for energy management. To address this challenge, a queue model based on data priority was first established, followed by the development of a level queue perception–based QoS optimization algorithm within an improved Lyapunov optimization framework. Results show that when harvested energy meets the minimum node operation requirement (above 0.17 mW to support at least one data transmission per minute), the proposed method ensures the stability of network energy and data queues of different levels, while reducing the number of packet losses in monitoring nodes. Compared with existing approaches, this method decreases high-level data packet loss by over 46.64%, offering a promising solution for high-quality and continuous scraper chain status monitoring.
- 16 September 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 25 (21) , 39465-39477
Design and Performance Analysis of a Mining Wireless Sensor Node for Disaster–Resistance
Wireless sensor networks are often used to monitor environmental information underground in coal mines, but gas/thermal disasters can easily damage wireless sensor nodes, making them ineffective. To solve the problems of poor adaptability and short survival time of traditional wireless sensor nodes in coal mine disaster environments, this paper designs a mining disaster-resistant variable sensor node with a secondary protection structure. The dynamic and thermodynamic performance of the node in gas/thermodynamic disaster environments was analyzed through simulation, and based on this, a physical node was developed and communication experiments were conducted. The research results indicate that when a gas/thermodynamic disaster occurs and the node interacts with rocks and shock waves in two main postures, it benefits from the first layer of protective shell (P1 shell) and the buffering and damping effects of rubber shock absorbers. The second layer of protective shell (P2 shell) and internal circuit board are not damaged; The node had good heat dissipation before the disaster; After the disaster, the node still has at least 1632s of effective working time within a range of 0-250m from the 9.5%, 200m ³ gas explosion source. The proposed mining disaster-resistant sensor nodes can provide conditional support for the construction of post-disaster emergency rescue information systems.
- 16 September 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 25 (21) , 39465-39477
Design and Performance Analysis of a Mining Wireless Sensor Node for Disaster–Resistance
Wireless sensor networks are often used to monitor environmental information underground in coal mines, but gas/thermal disasters can easily damage wireless sensor nodes, making them ineffective. To solve the problems of poor adaptability and short survival time of traditional wireless sensor nodes in coal mine disaster environments, this paper designs a mining disaster-resistant variable sensor node with a secondary protection structure. The dynamic and thermodynamic performance of the node in gas/thermodynamic disaster environments was analyzed through simulation, and based on this, a physical node was developed and communication experiments were conducted. The research results indicate that when a gas/thermodynamic disaster occurs and the node interacts with rocks and shock waves in two main postures, it benefits from the first layer of protective shell (P1 shell) and the buffering and damping effects of rubber shock absorbers. The second layer of protective shell (P2 shell) and internal circuit board are not damaged; The node had good heat dissipation before the disaster; After the disaster, the node still has at least 1632s of effective working time within a range of 0-250m from the 9.5%, 200m ³ gas explosion source. The proposed mining disaster-resistant sensor nodes can provide conditional support for the construction of post-disaster emergency rescue information systems.
- 26 March 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE/ASME Transactions on Mechatronics
- Vol. 30 (6) , 5891-5903
Network Monitoring Method for Scraper Posture of Mine Scraper Conveyor via Frictional Piezoelectric Effect and Triangular Constrained Filtering
The scraper conveyor is the core equipment to underground coal transportation, its health condition is related to production efficiency and personnel safety. Using wireless sensor network (WSN) technology to monitor scraper posture can determine whether there are faults such as chain jamming or breakage in the scraper conveyor. However, the harsh working conditions and dynamic characteristics of scrapers pose challenges for continuous and accurate monitoring through monitoring nodes with limited energy. Thus, we utilize WSN technology to first design a node friction piezoelectric energy harvester (FPEH) adapted to the motion characteristics of scraper, to ensure the sustainability of node operation and obtain large amount of monitoring data. Then, to reduce the impact of noise on the accuracy of monitoring data under harsh underground conditions, a fusion method of triangle constrained average interpolation and adaptive extended Kalman filtering (TCAI-AEKF) is proposed based on the constraint relationship between adjacent scrapers. The experimental results indicate that when mutually attractive magnets and piezoelectric beam are vertically arranged, the FPEH can achieve optimal power generation performance. Compared with the AEKF method, the proposed TCAI-AEKF method has better filtering performance, can identify and update erroneous values in measured results, and improve the credibility of actual values.
- 26 March 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE/ASME Transactions on Mechatronics
- Vol. 30 (6) , 5891-5903
Network Monitoring Method for Scraper Posture of Mine Scraper Conveyor via Frictional Piezoelectric Effect and Triangular Constrained Filtering
The scraper conveyor is the core equipment to underground coal transportation, its health condition is related to production efficiency and personnel safety. Using wireless sensor network (WSN) technology to monitor scraper posture can determine whether there are faults such as chain jamming or breakage in the scraper conveyor. However, the harsh working conditions and dynamic characteristics of scrapers pose challenges for continuous and accurate monitoring through monitoring nodes with limited energy. Thus, we utilize WSN technology to first design a node friction piezoelectric energy harvester (FPEH) adapted to the motion characteristics of scraper, to ensure the sustainability of node operation and obtain large amount of monitoring data. Then, to reduce the impact of noise on the accuracy of monitoring data under harsh underground conditions, a fusion method of triangle constrained average interpolation and adaptive extended Kalman filtering (TCAI-AEKF) is proposed based on the constraint relationship between adjacent scrapers. The experimental results indicate that when mutually attractive magnets and piezoelectric beam are vertically arranged, the FPEH can achieve optimal power generation performance. Compared with the AEKF method, the proposed TCAI-AEKF method has better filtering performance, can identify and update erroneous values in measured results, and improve the credibility of actual values.
- 1 January 2024
- Published by AIP Publishing in Review of Scientific Instruments
- Vol. 95 (1)
A machine vision-based wear detection method for guide pair of the mine hoisting system
The wear detection of the guide pair (GP) plays a key role in the safe operation of the mine hoist system. Due to the actual working conditions of the well, manual detection is still the main detection method for GP wear, which has the problems of time consumption, low detection accuracy, and being unable to realize real-time detection. In view of this situation, this paper studies a machine vision-based wear detection method of GP in a mine hoisting system. First, the wear detection algorithm of GP is designed by means of image correction, image preprocessing, and edge extraction. Then, the hardware of the detection system is selected and designed, and the interface of the upper computer is designed by LABVIEW. Finally, according to the actual underground working conditions, a test platform for the wear detection system is built, and the detection experiment is carried out. The results show that the method can detect the wear and the location of the GP’s wear in real time. The maximum average error of the detection under three different wear conditions is 3.54%, which meets the requirements of the specified measurement accuracy. It can provide technical support for the automatic detection of the wear of GP in mine hoisting systems.
- 1 January 2024
- Published by AIP Publishing in Review of Scientific Instruments
- Vol. 95 (1)
A machine vision-based wear detection method for guide pair of the mine hoisting system
The wear detection of the guide pair (GP) plays a key role in the safe operation of the mine hoist system. Due to the actual working conditions of the well, manual detection is still the main detection method for GP wear, which has the problems of time consumption, low detection accuracy, and being unable to realize real-time detection. In view of this situation, this paper studies a machine vision-based wear detection method of GP in a mine hoisting system. First, the wear detection algorithm of GP is designed by means of image correction, image preprocessing, and edge extraction. Then, the hardware of the detection system is selected and designed, and the interface of the upper computer is designed by LABVIEW. Finally, according to the actual underground working conditions, a test platform for the wear detection system is built, and the detection experiment is carried out. The results show that the method can detect the wear and the location of the GP’s wear in real time. The maximum average error of the detection under three different wear conditions is 3.54%, which meets the requirements of the specified measurement accuracy. It can provide technical support for the automatic detection of the wear of GP in mine hoisting systems.
- 13 October 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 72 (00189456) , 1-11
A Power Allocation Method for Wireless Sensor Networks Based on Data Priority: A Case Study of Scraper Chain Tension Monitoring Network
Using wireless sensor network technology to monitor the tension of scraper conveyor chain can determine whether there are faults such as chain jamming or breakage. However, the scraper chain is in a bad working condition and has mobility, leading to the problems of limited energy and different importance of monitoring data in the uplink and downlink areas of the scraper conveyor tension monitoring network. To this end, we establishes a scraper conveyor chain tension monitoring network model based on data priority (DP). Then, combined with the operation characteristics (OC) of the scraper conveyor, a node transmission power allocation method based on Lyapunov (TPAL) is proposed. The simulation results demonstrate that even when the statistical information of the dynamic system is unknown, the proposed data priority-operation characteristics-transmission power allocation method based on Lyapunov (DP-OC-TPAL) can not only meet the stability and priority requirements of the network data queue, but also minimize the transmission power of the monitoring nodes, achieving a compromise between the queue length, transmission power, and the proportion of high-level data transmission. Compared with the full power allocation (FPA) algorithm, the proposed algorithm improves the transmission ratio of high-level data by 16%.
- 13 October 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 72 (00189456) , 1-11
A Power Allocation Method for Wireless Sensor Networks Based on Data Priority: A Case Study of Scraper Chain Tension Monitoring Network
Using wireless sensor network technology to monitor the tension of scraper conveyor chain can determine whether there are faults such as chain jamming or breakage. However, the scraper chain is in a bad working condition and has mobility, leading to the problems of limited energy and different importance of monitoring data in the uplink and downlink areas of the scraper conveyor tension monitoring network. To this end, we establishes a scraper conveyor chain tension monitoring network model based on data priority (DP). Then, combined with the operation characteristics (OC) of the scraper conveyor, a node transmission power allocation method based on Lyapunov (TPAL) is proposed. The simulation results demonstrate that even when the statistical information of the dynamic system is unknown, the proposed data priority-operation characteristics-transmission power allocation method based on Lyapunov (DP-OC-TPAL) can not only meet the stability and priority requirements of the network data queue, but also minimize the transmission power of the monitoring nodes, achieving a compromise between the queue length, transmission power, and the proportion of high-level data transmission. Compared with the full power allocation (FPA) algorithm, the proposed algorithm improves the transmission ratio of high-level data by 16%.
- Open Access
- 23 December 2022
- Published by Association for Computing Machinery (ACM)
- p. 159-164
A novel parallel hybrid model for forecasting the stock price
In recent years, in addition to the growth in the number of investors in the stock market, there has been a growing interest in predicting stock prices. Accurate stock prices can effectively improve investment returns on the premise of reducing investment risks for stock investors. Therefore, this study presents a hybrid Bo-LSTM-SVR model to predict the next day's stock closing price. Firstly, the hyper-parameters of LSTM and SVR as well as the length of their respective sliding windows are optimized by the Bayesian optimization method, so as to obtain more accurate predicted values of the single models. The genetic algorithm is then adopted every day to decide the weight of the two single models, and finally, the combined predicted values are obtained. In order to ensure that the prediction of the proposed model is more accurate, this model and the other six models are applied to predict the closing prices of the Shanghai Composite Index on the next trading day. The results reveal that the model proposed in this study is the most accurate, with the smallest MAE and RMSE as well as the largest R^2. Compared with other models, the proposed model is more suitable for stock price prediction, which provides a dependable tool for investors to make stock investment decisions.
- 23 December 2022
- Published by Association for Computing Machinery (ACM)
- p. 159-164
Open AccessA novel parallel hybrid model for forecasting the stock price
In recent years, in addition to the growth in the number of investors in the stock market, there has been a growing interest in predicting stock prices. Accurate stock prices can effectively improve investment returns on the premise of reducing investment risks for stock investors. Therefore, this study presents a hybrid Bo-LSTM-SVR model to predict the next day's stock closing price. Firstly, the hyper-parameters of LSTM and SVR as well as the length of their respective sliding windows are optimized by the Bayesian optimization method, so as to obtain more accurate predicted values of the single models. The genetic algorithm is then adopted every day to decide the weight of the two single models, and finally, the combined predicted values are obtained. In order to ensure that the prediction of the proposed model is more accurate, this model and the other six models are applied to predict the closing prices of the Shanghai Composite Index on the next trading day. The results reveal that the model proposed in this study is the most accurate, with the smallest MAE and RMSE as well as the largest R^2. Compared with other models, the proposed model is more suitable for stock price prediction, which provides a dependable tool for investors to make stock investment decisions.