Feng Chen
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Feng Chen has a total of 23 co-authors. Here are the top co-authors by number of shared publications:
- Fengjuan Ding
College of Intelligent Manufacturing, Anhui Science and Technology University, Chuzhou 233100, China
2 shared publications - Hua Zhang
College of Mechanical Engineering, Anhui Science and Technology University, Fengyang 233100, China
2 shared publications - Juan Wang
College of Intelligent Manufacturing, Anhui Science and Technology University, Chuzhou 233100, China
2 shared publications - Qiliang Zeng
College of Mechanical Engineering, Anhui Science and Technology University, Fengyang 233100, China
2 shared publications - Tengjiao Hong
College of Intelligent Manufacturing, Anhui Science and Technology University, Chuzhou 233100, China
2 shared publications Bin Chen
Department of Information Engineering, Hefei Vocational College of Science and Technology, Hefei, 231201, China
1 shared publication
Latest Publications
- Open Access
- 31 March 2026
- Published by Springer Nature in Scientific Reports
- Vol. 16 (1)
YOLO-LSBA: A high-precision model for detecting stems of small-sized cherry tomatoes
The diversity in fruit posture has become the key factor that limits improvements in stem recognition precision during cherry tomato harvesting. To effectively enhance the recognition of small target features in cherry tomato stems, data augmentation strategies are employed to expand the dataset selectively, improving the model’s adaptability to complex scenarios. First, based on the YOLO11n model, the Large Separable Kernel Attention (LSKA) mechanism is integrated into the Spatial Pyramid Pooling-Fast (SPPF) to construct the SPPL module. This design effectively improves detection accuracy and model robustness while expanding the receptive field and enhancing feature extraction capabilities. This reduces computational complexity and enhances model robustness. Second, the Spatial and Channel Reconstruction Convolution (ScConv) module is embedded into the Bottleneck architecture to replace the original C3K2 module, thereby reducing feature redundancy and improving the extraction of fine-grained features. Finally, the BAFPN module was designed, which integrates the Asymptotic Feature Pyramid Network (AFPN) module to enhance the perception capability for small objects. Experimental results indicate that the YOLO-LSBA model achieves a precision of 97.1% and a recall of 78.3% for fruit stem recognition, with an AP of 92.4%. These metrics show improvements of 3.9%, 0.6%, and 2.2%, respectively, compared to the baseline model. Field trials further demonstrate that this model outperforms baseline models in detecting fruit stems under real agricultural conditions. This method offers new insights for intelligent harvesting.
- 31 March 2026
- Published by Springer Nature in Scientific Reports
- Vol. 16 (1)
Open AccessYOLO-LSBA: A high-precision model for detecting stems of small-sized cherry tomatoes
The diversity in fruit posture has become the key factor that limits improvements in stem recognition precision during cherry tomato harvesting. To effectively enhance the recognition of small target features in cherry tomato stems, data augmentation strategies are employed to expand the dataset selectively, improving the model’s adaptability to complex scenarios. First, based on the YOLO11n model, the Large Separable Kernel Attention (LSKA) mechanism is integrated into the Spatial Pyramid Pooling-Fast (SPPF) to construct the SPPL module. This design effectively improves detection accuracy and model robustness while expanding the receptive field and enhancing feature extraction capabilities. This reduces computational complexity and enhances model robustness. Second, the Spatial and Channel Reconstruction Convolution (ScConv) module is embedded into the Bottleneck architecture to replace the original C3K2 module, thereby reducing feature redundancy and improving the extraction of fine-grained features. Finally, the BAFPN module was designed, which integrates the Asymptotic Feature Pyramid Network (AFPN) module to enhance the perception capability for small objects. Experimental results indicate that the YOLO-LSBA model achieves a precision of 97.1% and a recall of 78.3% for fruit stem recognition, with an AP of 92.4%. These metrics show improvements of 3.9%, 0.6%, and 2.2%, respectively, compared to the baseline model. Field trials further demonstrate that this model outperforms baseline models in detecting fruit stems under real agricultural conditions. This method offers new insights for intelligent harvesting.
- Open Access
- 12 January 2024
- Published by Kaunas University of Technology (KTU) in Information Technology And Control
- Vol. 52 (4) , 878-886
Pepper Target Recognition and Detection Based on Improved YOLO v4
In order to improve visual recognition accuracy of pepper and provide reliable technical support for agricultural production, an improved YOLOv4 algorithm for pepper target recognition and detection was proposed in this paper. By adding Mosaic data enhancement and CBAM (Conventional block attention module) attention mechanism to the primitive character extraction network, the method enhanced the learning ability of the target detection algorithm, made the network effectively suppress the interference features, and increased the attention to effective features. To improve the accuracy of identification. The improved network model was trained, verified and tested on the self-made data set. The results showed that the proposed algorithm could effectively improve the accuracy of pepper recognition under natural light, and finally improved the mean Average Precision (mAP) of the existing YOLOv4 algorithm from 88.95% to 98.36%.
- 12 January 2024
- Published by Kaunas University of Technology (KTU) in Information Technology And Control
- Vol. 52 (4) , 878-886
Open AccessPepper Target Recognition and Detection Based on Improved YOLO v4
In order to improve visual recognition accuracy of pepper and provide reliable technical support for agricultural production, an improved YOLOv4 algorithm for pepper target recognition and detection was proposed in this paper. By adding Mosaic data enhancement and CBAM (Conventional block attention module) attention mechanism to the primitive character extraction network, the method enhanced the learning ability of the target detection algorithm, made the network effectively suppress the interference features, and increased the attention to effective features. To improve the accuracy of identification. The improved network model was trained, verified and tested on the self-made data set. The results showed that the proposed algorithm could effectively improve the accuracy of pepper recognition under natural light, and finally improved the mean Average Precision (mAP) of the existing YOLOv4 algorithm from 88.95% to 98.36%.
- Open Access
Mechanical Properties of 6061 Aluminum Alloy under Cyclic Tensile Loading
During the service process of an aluminum alloy structure, its complex deformation zone experiences repeated loading problems such as repeated tension, compression, bending and reverse bending. At the same time, the cyclic loading and heat treatment process also have a certain impact on the mechanical properties of aluminum alloy extruded tubes. Therefore, the study of heat treatment process parameters has important engineering and practical value for the mechanical properties of aluminum alloy extrusion tubes under cyclic loading conditions. The experiment takes 6061-T6 aluminum alloy extruded tubes as the research objects. In the study, heat treatment and cyclic tensile tests were carried out on 26 aluminum alloy specimens to study the effects of different heat treatment parameters (such as heating temperature, holding time, and cooling method) on the stress–strain hysteresis curves, stress characteristics, hysteretic energy, skeleton curves and failure characteristics of the alloy under the same loading system. In addition, different cyclic tensile tests were carried out on 20 aluminum alloy samples without secondary heat treatment to discuss the effects of different cyclic loading regimes on the mechanical properties of the alloy. The research results indicate that the effect of heating temperature on the cyclic loading performance of the alloy is greater than that of the holding time, and the effect of the cooling method on the cyclic loading performance of the alloy is not obvious. A cyclic tensile loading regime has a significant impact on the strength, elongation and hysteresis energy of the alloy. The hysteretic behavior of the alloy during cyclic tensile loading depends on the applied stress level and loading history. As the number of cycles increases, the shape of the hysteresis curve tends to be stable, but there is no monotonic relationship between the number of cycles loaded and the hysteresis energy.
Open AccessMechanical Properties of 6061 Aluminum Alloy under Cyclic Tensile Loading
During the service process of an aluminum alloy structure, its complex deformation zone experiences repeated loading problems such as repeated tension, compression, bending and reverse bending. At the same time, the cyclic loading and heat treatment process also have a certain impact on the mechanical properties of aluminum alloy extruded tubes. Therefore, the study of heat treatment process parameters has important engineering and practical value for the mechanical properties of aluminum alloy extrusion tubes under cyclic loading conditions. The experiment takes 6061-T6 aluminum alloy extruded tubes as the research objects. In the study, heat treatment and cyclic tensile tests were carried out on 26 aluminum alloy specimens to study the effects of different heat treatment parameters (such as heating temperature, holding time, and cooling method) on the stress–strain hysteresis curves, stress characteristics, hysteretic energy, skeleton curves and failure characteristics of the alloy under the same loading system. In addition, different cyclic tensile tests were carried out on 20 aluminum alloy samples without secondary heat treatment to discuss the effects of different cyclic loading regimes on the mechanical properties of the alloy. The research results indicate that the effect of heating temperature on the cyclic loading performance of the alloy is greater than that of the holding time, and the effect of the cooling method on the cyclic loading performance of the alloy is not obvious. A cyclic tensile loading regime has a significant impact on the strength, elongation and hysteresis energy of the alloy. The hysteretic behavior of the alloy during cyclic tensile loading depends on the applied stress level and loading history. As the number of cycles increases, the shape of the hysteresis curve tends to be stable, but there is no monotonic relationship between the number of cycles loaded and the hysteresis energy.
- Open Access
Study on the Fracture Behaviour of 6061 Aluminum Alloy Extruded Tube during Different Stress Conditions
To study the deformation and fracture mechanism of 6061 aluminum alloy extruded pipe after secondary heat treatment under different stress triaxiality, a Johnson–Cook failure model was developed. Through the FEM method and SEM, the fracture mechanism of different types of aluminum alloy tensile specimens was analyzed. The research results show that the Johnson–Cook failure model could better simulate the tensile deformation of 6061 aluminum alloy specimens of different types, the parameters of the Johnson–Cook failure model were finally obtained D1 = 0.29, D2 = 1.356, and D3 = −2.567. With the increase of the stress triaxiality, the fracture strain showed a decreasing trend as a whole, and the fracture mechanism changed from a shear type to a hole aggregation type. The stress triaxiality gradually decreased with the increase of the notch radius/angles of the aluminum alloy notch specimen, and the stress triaxiality at the center of the notch was higher than the stress triaxiality at the root of the notch.
Open AccessStudy on the Fracture Behaviour of 6061 Aluminum Alloy Extruded Tube during Different Stress Conditions
To study the deformation and fracture mechanism of 6061 aluminum alloy extruded pipe after secondary heat treatment under different stress triaxiality, a Johnson–Cook failure model was developed. Through the FEM method and SEM, the fracture mechanism of different types of aluminum alloy tensile specimens was analyzed. The research results show that the Johnson–Cook failure model could better simulate the tensile deformation of 6061 aluminum alloy specimens of different types, the parameters of the Johnson–Cook failure model were finally obtained D1 = 0.29, D2 = 1.356, and D3 = −2.567. With the increase of the stress triaxiality, the fracture strain showed a decreasing trend as a whole, and the fracture mechanism changed from a shear type to a hole aggregation type. The stress triaxiality gradually decreased with the increase of the notch radius/angles of the aluminum alloy notch specimen, and the stress triaxiality at the center of the notch was higher than the stress triaxiality at the root of the notch.
- 28 February 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 72 (00189456) , 1-12
UWB Anchor Node Optimization Deployment Using MGWO for the Coal Mine Working Face End
Appropriate deployment of anchor nodes (ANs) is an essential prerequisite for achieving high-precision positioning. To ameliorate the comprehensive positioning performance, the weight position dilution of precision (WPDOP) that is utilized to evaluate the appropriateness of the ANs placement geometry is proposed by taking into account different error variances for each AN. A simple closed-form calculation WPDOP method is theoretically derived for ultrawideband (UWB) positioning system by utilizing elementary symmetric polynomials and Newton’s identity, which is applied to evaluate the UWB deployment at the end of coal mine working face (CMWF). Several basic ANs layout strategies, based on the projection shape in the $xy$ plane, are designed for the end of CMWF, and the modified gray wolf optimizer (MGWO) algorithm is executed to optimize the ANs deployment scheme to attain the better configuration and higher positioning accuracy. Simulation and experiments verification are simultaneously performed via the UWB positioning system. The experimental results sufficiently demonstrate that MGWO deployment scheme offers lower average WPDOP values than the obtained ones when applying random placement, and the lowest average improvement percentage was approximately equal to 37.6%. Furthermore, after implementing the MGWO algorithm, the V-shape deployment configuration is capable to provide the lowest average WPDOP values and outperforms the other arrangements, keeping the lowest localization error. This is regarded as the best deployment and it gives significant guidance for the ANs sensor deployment at the end of CMWF.
- 28 February 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 72 (00189456) , 1-12
UWB Anchor Node Optimization Deployment Using MGWO for the Coal Mine Working Face End
Appropriate deployment of anchor nodes (ANs) is an essential prerequisite for achieving high-precision positioning. To ameliorate the comprehensive positioning performance, the weight position dilution of precision (WPDOP) that is utilized to evaluate the appropriateness of the ANs placement geometry is proposed by taking into account different error variances for each AN. A simple closed-form calculation WPDOP method is theoretically derived for ultrawideband (UWB) positioning system by utilizing elementary symmetric polynomials and Newton’s identity, which is applied to evaluate the UWB deployment at the end of coal mine working face (CMWF). Several basic ANs layout strategies, based on the projection shape in the $xy$ plane, are designed for the end of CMWF, and the modified gray wolf optimizer (MGWO) algorithm is executed to optimize the ANs deployment scheme to attain the better configuration and higher positioning accuracy. Simulation and experiments verification are simultaneously performed via the UWB positioning system. The experimental results sufficiently demonstrate that MGWO deployment scheme offers lower average WPDOP values than the obtained ones when applying random placement, and the lowest average improvement percentage was approximately equal to 37.6%. Furthermore, after implementing the MGWO algorithm, the V-shape deployment configuration is capable to provide the lowest average WPDOP values and outperforms the other arrangements, keeping the lowest localization error. This is regarded as the best deployment and it gives significant guidance for the ANs sensor deployment at the end of CMWF.