QHQing He

Qing He

*This is an algorithmically generated author record based on publicly available information.

Qing He has a total of 21 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • An Improved Lightweight Yolov5 Algorithm for Strawberry Ripeness Detection

    by Qing He, Shaoyuan Wang, Chuanwei Wu, Jiayi Xu

    Strawberry ripeness detection is of great significance for evaluating fruit growth in strawberry orchards. However, the existing detection technology has challenges in mobile terminal deployment due to the large computing amount and large model size. Therefore, an improved lightweight Y010v5 algorithm for strawberry ripeness detection was proposed in this study. To reduces the calculated amount and model scale, Partial Convolution (PConv) is introduced to substitute the normal convolution, which is in the original C3(Cross Stage Partial Bottleneck with 3 convolutions.), and C3_Faster module is introduced to substitute the C3 module in yolov5. SIoU is used as the boundary box loss function to accelerate the regression prediction and improve the positioning accuracy of the object bounding box. Experiments on jetson nano on public dataset show that compared with the previous Y010v5 model, the mAP of the modified model is increased by 1.1%, FLOPs and params are decreased by 17.1% and 17.6%, respectively.


  • Automatic alignment technique for the suspended coil in the joule balance

    by Yang Bai, Dawei Wang, Zhengkun Li, Yunfeng Lu, Pengcheng Hu, Qing He, Zhonghua Zhang, Jiubin Tan

    An automatic alignment technique was developed for the joule balance to reduce the uncertainty caused by alignment errors. Using the flexures and decoupling structure of the suspended coil, the proposed alignment system can automatically recognize the linear relationship between the initial position and posture of the suspended coil when the current is off, and its parasitic horizontal linear and angular displacements when the current is on. Subsequently, several actuators including mini-motors and an X – Y stage are controlled to adjust the position and posture of the coil, minimizing the parasitic forces and torques and reducing them by approximately 100 times in comparison with the alignment results of the joule balance obtained in 2019, whilst maintaining the adjustment time to several minutes only.


  • Open Access

    Research on the Prediction Model of Shield Advancement Rate in Sandy Cobble Ground of Beijing

    by Qing He, Liying Xu, Zhiyong Yang, Weiqiang Qi, Zhigang Zhang, Ziyu Shen

    The long distance and tight construction period of the earth pressure balance shield tunneling in Beijing sandy cobble ground have a very positive impact on grasping the construction progress and improving the organization efficiency. Based on the real‐time monitoring data of on‐site earth pressure, cutter head speed, total thrust, screw conveyor speed, and cutter head torque, this study investigated the correlation between the shield advancement rate and the above parameters based on multiple nonlinear regression analysis method, which lay down the foundation of shield advancement rate prediction. The prediction model achieved satisfactory results and was further applied to an airport project. The results show that it is of guiding significance to use multiple regression method to establish shield prediction model and put forward the best advancement parameters to ensure the construction progress. The order in which the four operational parameters affect the advancement rate is total thrust, cutter head torque, screw conveyor speed, and cutter head speed. When the advancement time is greater than 57 min, the average advancement rate and daily progress are highly positively correlated. The research provides a reliable basis for the advancement rate prediction, safety control, and parameter optimization of shield advancement in similar ground.

  • Smart Meter Working Status Evaluation Method Based on Evidence Theory

    by He Qing, Liu Fangxing, Wang Lei, Huang Hongtao, Jia Zhengsen

    This paper presents a method to evaluate smart meter working status by analyzing multi-data of smart meters. It is a multi-source data fusion technique based on D-S evidence theory. In the proposed algorithm, entropy method used to compute the weight of indicators, then we use convex function to assign the probabilities of evidence. Finally, we obtain the evaluation working status by D-S evidence theory. The results of simulation indicate the applicability of the approach in real time scenarios.