Chensheng Wang
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
Research Subjects
Chensheng Wang has a total of 30 co-authors. Here are the top co-authors by number of shared publications:
- Guang Yang
School of Artificial and Intelligence, Beijing University of Posts and Telecommunications, Beijing 100876, China
4 shared publications - Cen Li
School of Modern Post Beijing University of Posts and Telecommunications 100876 Beijing China
2 shared publications - Guo Li
Institute of Artificial Intelligence and Future Networks, Beijing Normal University, Zhuhai, China
2 shared publications - Liang Dong
School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing 100876, China
2 shared publications - Wentie Niu
Key Laboratory of Mechanism Theory and Equipment Design of Ministry of Education, Tianjin University, Tianjin 300350, China
2 shared publications - Yanqin Zhao
School of Mechanical Engineering, Yangzhou University, China
2 shared publications
Latest Publications
- 8 June 2024
- Published by Elsevier in Mechanical Systems and Signal Processing
- Vol. 219, 111601
A piezoelectric and electromagnetic hybrid energy harvester based on two-stage magnetic coupling
- 8 June 2024
- Published by Elsevier in Mechanical Systems and Signal Processing
- Vol. 219, 111601
A piezoelectric and electromagnetic hybrid energy harvester based on two-stage magnetic coupling
- Open Access
- 8 September 2023
- Published by Springer Nature in Research Square
Feature Selection Algorithm Based on CFS Algorithm Emphasizing Data Discrimination
In the training of the neural network model, the large number of features in the data set will lead to the complexity of the network model and high time cost. Therefore, the feature selection operation of the original data set is carried out to select the feature subset conducive to model training to improve the model's performance. The traditional feature selection algorithm has the problems of a thin process and needs help to eliminate the features with small discrimination. Therefore, this paper proposes the discrimination filtering formula and DI-CFS feature selection algorithm. The discrimination filtering formula can filter out invalid features and inefficient features with small discrimination. DI-CFS algorithm combines discrimination filtering formula, isolation forest algorithm, and improved CFS algorithm. On a set of wind turbine data, the DI-CFS algorithm and other traditional feature selection algorithms are used to select features from the data, respectively, and the obtained feature subsets are input into the same neural network model for training and performing classification tasks. The experimental results show that the discrimination filtering formula has a positive effect, and the DI-CFS algorithm has a better feature selection effect.
- 8 September 2023
- Published by Springer Nature in Research Square
Open AccessFeature Selection Algorithm Based on CFS Algorithm Emphasizing Data Discrimination
In the training of the neural network model, the large number of features in the data set will lead to the complexity of the network model and high time cost. Therefore, the feature selection operation of the original data set is carried out to select the feature subset conducive to model training to improve the model's performance. The traditional feature selection algorithm has the problems of a thin process and needs help to eliminate the features with small discrimination. Therefore, this paper proposes the discrimination filtering formula and DI-CFS feature selection algorithm. The discrimination filtering formula can filter out invalid features and inefficient features with small discrimination. DI-CFS algorithm combines discrimination filtering formula, isolation forest algorithm, and improved CFS algorithm. On a set of wind turbine data, the DI-CFS algorithm and other traditional feature selection algorithms are used to select features from the data, respectively, and the obtained feature subsets are input into the same neural network model for training and performing classification tasks. The experimental results show that the discrimination filtering formula has a positive effect, and the DI-CFS algorithm has a better feature selection effect.
- Open Access
- 3 February 2023
- Published by Springer Nature in Research Square
INS-YOLOX: Improved YOLOX for Detecting Insulator Defects
One of the methods for detecting transmission line damage is image defect detection of transmission line insulators. The industrialization of image defect detection has made the construction of detection algorithm models with quick detection times, high accuracy, and compact models into a fundamental issue. In order to efficiently address the issues of accuracy and speed of insulator defect detection, this work offers an enhanced version of the INS-YOLOX model based on a one-stage detector. The history of the insulator defect is complicated, as are its potential targets. The target is tiny, and there is little distinction between the images of a faulty insulator and a lossless insulator. The first step is the proposal of a new loss function, L-SIoU, which not only considers the vector Angle between necessary regressions, redefines the penalty index, but also considers the influence of the aspect ratio between the prediction box and regression box, which increases reasoning accuracy and speed. The detection precision of the imbalanced data set was then increased by switching from BCE Loss to Varifocal Loss. In order to improve the feature point extraction, the CBAM attention mechanism was lastly integrated to the Decoupled Head structure. Additionally, INS-YOLOX adds the SGD optimizer and successfully optimizes the model's training parameters. A total of 6227 photos were gathered as a data set to evaluate the model's validity. The test results demonstrate the real-time detection capabilities of INS-YOLOX. The final map, at 83.2%, is 11.1% higher than the benchmark model of YOLOX-tiny and 6% higher than the most recent Yolov7. This represents a major accomplishment.
- 3 February 2023
- Published by Springer Nature in Research Square
Open AccessINS-YOLOX: Improved YOLOX for Detecting Insulator Defects
One of the methods for detecting transmission line damage is image defect detection of transmission line insulators. The industrialization of image defect detection has made the construction of detection algorithm models with quick detection times, high accuracy, and compact models into a fundamental issue. In order to efficiently address the issues of accuracy and speed of insulator defect detection, this work offers an enhanced version of the INS-YOLOX model based on a one-stage detector. The history of the insulator defect is complicated, as are its potential targets. The target is tiny, and there is little distinction between the images of a faulty insulator and a lossless insulator. The first step is the proposal of a new loss function, L-SIoU, which not only considers the vector Angle between necessary regressions, redefines the penalty index, but also considers the influence of the aspect ratio between the prediction box and regression box, which increases reasoning accuracy and speed. The detection precision of the imbalanced data set was then increased by switching from BCE Loss to Varifocal Loss. In order to improve the feature point extraction, the CBAM attention mechanism was lastly integrated to the Decoupled Head structure. Additionally, INS-YOLOX adds the SGD optimizer and successfully optimizes the model's training parameters. A total of 6227 photos were gathered as a data set to evaluate the model's validity. The test results demonstrate the real-time detection capabilities of INS-YOLOX. The final map, at 83.2%, is 11.1% higher than the benchmark model of YOLOX-tiny and 6% higher than the most recent Yolov7. This represents a major accomplishment.
- Open Access
An Improved ResNet-1d with Channel Attention for Tool Wear Monitor in Smart Manufacturing
Tool wear is a key factor in the machining process, which affects the tool life and quality of the machined work piece. Therefore, it is crucial to monitor and diagnose the tool condition. An improved CaAt-ResNet-1d model for multi-sensor tool wear diagnosis was proposed. The ResNet18 structure based on a one-dimensional convolutional neural network is adopted to make the basic model architecture. The one-dimensional convolutional neural network is more suitable for feature extraction of time series data. Add the channel attention mechanism of CaAt1 to the residual network block and the channel attention mechanism of CaAt5 automatically learns the features of different channels. The proposed method is validated on the PHM2010 dataset. Validation results show that CaAt-ResNet-1d can reach 89.27% accuracy, improving by about 7% compared to Gated-Transformer and 3% compared to Resnet18. The experimental results demonstrate the capacity and effectiveness of the proposed method for tool wear monitor.
Open AccessAn Improved ResNet-1d with Channel Attention for Tool Wear Monitor in Smart Manufacturing
Tool wear is a key factor in the machining process, which affects the tool life and quality of the machined work piece. Therefore, it is crucial to monitor and diagnose the tool condition. An improved CaAt-ResNet-1d model for multi-sensor tool wear diagnosis was proposed. The ResNet18 structure based on a one-dimensional convolutional neural network is adopted to make the basic model architecture. The one-dimensional convolutional neural network is more suitable for feature extraction of time series data. Add the channel attention mechanism of CaAt1 to the residual network block and the channel attention mechanism of CaAt5 automatically learns the features of different channels. The proposed method is validated on the PHM2010 dataset. Validation results show that CaAt-ResNet-1d can reach 89.27% accuracy, improving by about 7% compared to Gated-Transformer and 3% compared to Resnet18. The experimental results demonstrate the capacity and effectiveness of the proposed method for tool wear monitor.
- Top Cited PapersOpen Access
MSFT-YOLO: Improved YOLOv5 Based on Transformer for Detecting Defects of Steel Surface
With the development of artificial intelligence technology and the popularity of intelligent production projects, intelligent inspection systems have gradually become a hot topic in the industrial field. As a fundamental problem in the field of computer vision, how to achieve object detection in the industry while taking into account the accuracy and real-time detection is an important challenge in the development of intelligent detection systems. The detection of defects on steel surfaces is an important application of object detection in the industry. Correct and fast detection of surface defects can greatly improve productivity and product quality. To this end, this paper introduces the MSFT-YOLO model, which is improved based on the one-stage detector. The MSFT-YOLO model is proposed for the industrial scenario in which the image background interference is great, the defect category is easily confused, the defect scale changes a great deal, and the detection results of small defects are poor. By adding the TRANS module, which is designed based on Transformer, to the backbone and detection headers, the features can be combined with global information. The fusion of features at different scales by combining multi-scale feature fusion structures enhances the dynamic adjustment of the detector to objects at different scales. To further improve the performance of MSFT-YOLO, we also introduce plenty of effective strategies, such as data augmentation and multi-step training methods. The test results on the NEU-DET dataset show that MSPF-YOLO can achieve real-time detection, and the average detection accuracy of MSFT-YOLO is 75.2, improving about 7% compared to the baseline model (YOLOv5) and 18% compared to Faster R-CNN, which is advantageous and inspiring.
Top Cited PapersOpen AccessMSFT-YOLO: Improved YOLOv5 Based on Transformer for Detecting Defects of Steel Surface
With the development of artificial intelligence technology and the popularity of intelligent production projects, intelligent inspection systems have gradually become a hot topic in the industrial field. As a fundamental problem in the field of computer vision, how to achieve object detection in the industry while taking into account the accuracy and real-time detection is an important challenge in the development of intelligent detection systems. The detection of defects on steel surfaces is an important application of object detection in the industry. Correct and fast detection of surface defects can greatly improve productivity and product quality. To this end, this paper introduces the MSFT-YOLO model, which is improved based on the one-stage detector. The MSFT-YOLO model is proposed for the industrial scenario in which the image background interference is great, the defect category is easily confused, the defect scale changes a great deal, and the detection results of small defects are poor. By adding the TRANS module, which is designed based on Transformer, to the backbone and detection headers, the features can be combined with global information. The fusion of features at different scales by combining multi-scale feature fusion structures enhances the dynamic adjustment of the detector to objects at different scales. To further improve the performance of MSFT-YOLO, we also introduce plenty of effective strategies, such as data augmentation and multi-step training methods. The test results on the NEU-DET dataset show that MSPF-YOLO can achieve real-time detection, and the average detection accuracy of MSFT-YOLO is 75.2, improving about 7% compared to the baseline model (YOLOv5) and 18% compared to Faster R-CNN, which is advantageous and inspiring.
- 27 March 2022
- Published by SPIE-Intl Soc Optical Eng
- Vol. 12169, 480-2268
Long-distance underwater wireless optical communication with a single photon-counting system
We proposed a long-distance underwater wireless optical communication with a single photon-counting system in a laboratory environment by using non-return to zero on-off keying modulation. The system successfully achieved a data rate of 1Mbps through a 15m PVC tube by adding in 80dB attenuator and using a pigtailed fiber 450nm blue laser diode. The water channel was measured to have an attenuation coefficient comparable to clean seawater. The experimental results show that under condition of only average 1.2 photons in single optical pulse, photon counting UOWC with a BER of 1. 6×10−4 and a baud rate of 1 Mbps can be achieved. Based on the measured minimum required power in the water channel, the transmission performance was predicted to be 140m and 310m in the clean seawater and pure seawater, respectively.
- 27 March 2022
- Published by SPIE-Intl Soc Optical Eng
- Vol. 12169, 480-2268
Long-distance underwater wireless optical communication with a single photon-counting system
We proposed a long-distance underwater wireless optical communication with a single photon-counting system in a laboratory environment by using non-return to zero on-off keying modulation. The system successfully achieved a data rate of 1Mbps through a 15m PVC tube by adding in 80dB attenuator and using a pigtailed fiber 450nm blue laser diode. The water channel was measured to have an attenuation coefficient comparable to clean seawater. The experimental results show that under condition of only average 1.2 photons in single optical pulse, photon counting UOWC with a BER of 1. 6×10−4 and a baud rate of 1 Mbps can be achieved. Based on the measured minimum required power in the water channel, the transmission performance was predicted to be 140m and 310m in the clean seawater and pure seawater, respectively.
- Open Access
An Improved Feature Selection Method Based on Random Forest Algorithm for Wind Turbine Condition Monitoring
Feature selection and dimensionality reduction are important for the performance of wind turbine condition monitoring models using supervisory control and data acquisition (SCADA) data. In this paper, an improved random forest algorithm, namely Feature Simplification Random Forest (FS_RF), is proposed, which is capable of identifying features closely correlated with wind turbine working conditions. The Euclidian distances are employed to distinguish the weight of the same feature among different samples, and its importance is measured by means of the random forest algorithm. The selected features are finally verified by a two-layer gated recurrent unit (GRU) neural network facilitating condition monitoring. The experimental results demonstrate the capacity and effectiveness of the proposed method for wind turbine condition monitoring.
Open AccessAn Improved Feature Selection Method Based on Random Forest Algorithm for Wind Turbine Condition Monitoring
Feature selection and dimensionality reduction are important for the performance of wind turbine condition monitoring models using supervisory control and data acquisition (SCADA) data. In this paper, an improved random forest algorithm, namely Feature Simplification Random Forest (FS_RF), is proposed, which is capable of identifying features closely correlated with wind turbine working conditions. The Euclidian distances are employed to distinguish the weight of the same feature among different samples, and its importance is measured by means of the random forest algorithm. The selected features are finally verified by a two-layer gated recurrent unit (GRU) neural network facilitating condition monitoring. The experimental results demonstrate the capacity and effectiveness of the proposed method for wind turbine condition monitoring.
- 1 September 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 39, 1-5
A Method of Primary Frequency and Inertia Control of Photo-voltaic Station
Consumption of traditional fossil fuel is becoming a very serious problem, so countries all over the world have begun to pay more and more attention to clean renewable energy generation such as photovoltaic generation and the in-grid technologies. Most new types of generation need to be connected to power grid with inverters. The inverters have no inherent rotational inertia and its primary frequency modulation characteristics are different from that of electric machine, which will bring harmful impact to power grid. Firstly, the primary frequency modulation characteristic of synchronous machine is analyzed, and a new frequency modulation strategy considering dead zone and equivalent offset of rotor speed is proposed, advantages and feasibility of the strategy is verified by simulation example of photovoltaic station. Secondly, characteristics of mechanical inertia of synchronous machine are analyzed, and a feedback control method not relying on external frequency signals but on measured power deviation is proposed and verified by simulation as above. Finally, a combined control strategy considering equivalent mechanical inertia and primary frequency modulation is proposed, which is also verified by simulation case.
- 1 September 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 39, 1-5
A Method of Primary Frequency and Inertia Control of Photo-voltaic Station
Consumption of traditional fossil fuel is becoming a very serious problem, so countries all over the world have begun to pay more and more attention to clean renewable energy generation such as photovoltaic generation and the in-grid technologies. Most new types of generation need to be connected to power grid with inverters. The inverters have no inherent rotational inertia and its primary frequency modulation characteristics are different from that of electric machine, which will bring harmful impact to power grid. Firstly, the primary frequency modulation characteristic of synchronous machine is analyzed, and a new frequency modulation strategy considering dead zone and equivalent offset of rotor speed is proposed, advantages and feasibility of the strategy is verified by simulation example of photovoltaic station. Secondly, characteristics of mechanical inertia of synchronous machine are analyzed, and a feedback control method not relying on external frequency signals but on measured power deviation is proposed and verified by simulation as above. Finally, a combined control strategy considering equivalent mechanical inertia and primary frequency modulation is proposed, which is also verified by simulation case.
- Open Access
- 1 April 2020
- Published by SAGE Publications in Science Progress
- Vol. 103 (2)
A rapid performance evaluation approach for lower mobility hybrid robot based on gravity-center position
This article develops a rapid performance evaluation approach for lower mobility hybrid robot, which provides guidance for manipulator evaluation, design, and optimization. First, a general position vector model of gravity center for the lower mobility hybrid robot in the whole workspace is constructed based on a general inverse kinematic model. A performance evaluation index based on gravity-center position is then proposed, where the coordinates pointing to the supporting direction are selected as the evaluation index of the robot performance. Furthermore, the credibility of the evaluation approach is verified from a 5-DOF hybrid robot (TriMule) by comparing with the condition number and the first natural frequency. Analysis results demonstrate that the evaluation index can not only reflect the performance spatial distribution in the whole workspace but also is sensitive to the performance difference caused by mass distribution. The proposed performance evaluation approach provides a new index for the rapid design and optimization of the cantilever robot.
- 1 April 2020
- Published by SAGE Publications in Science Progress
- Vol. 103 (2)
Open AccessA rapid performance evaluation approach for lower mobility hybrid robot based on gravity-center position
This article develops a rapid performance evaluation approach for lower mobility hybrid robot, which provides guidance for manipulator evaluation, design, and optimization. First, a general position vector model of gravity center for the lower mobility hybrid robot in the whole workspace is constructed based on a general inverse kinematic model. A performance evaluation index based on gravity-center position is then proposed, where the coordinates pointing to the supporting direction are selected as the evaluation index of the robot performance. Furthermore, the credibility of the evaluation approach is verified from a 5-DOF hybrid robot (TriMule) by comparing with the condition number and the first natural frequency. Analysis results demonstrate that the evaluation index can not only reflect the performance spatial distribution in the whole workspace but also is sensitive to the performance difference caused by mass distribution. The proposed performance evaluation approach provides a new index for the rapid design and optimization of the cantilever robot.
- 14 June 2019
- Published by Springer Nature
- p. 2917-2926
Kinematic Performance Comparison of Two Parallel Kinematics Machines
- 14 June 2019
- Published by Springer Nature
- p. 2917-2926
Kinematic Performance Comparison of Two Parallel Kinematics Machines