Jiawei Yi

Jiawei Yi

Auto-generated profile, based on publicly available information

Jiawei Yi

Inner Mongolia University of Technolog, Inner Mongolia

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 July 2024 in Chinese Journal of Electronics
Verified
Journal Article
Closed access
YLYanshan LI
Yanshan LI
JWJiarong Wang
Jiarong Wang
KZKunhua Zhang
Kunhua Zhang
JYJiawei Yi
Jiawei Yi
MWMiaomiao Wei
Miaomiao Wei
WXWei-xin Xie
Wei-xin Xie
Existing high-precision object detection algorithms for UAV (unmanned aerial vehicle) aerial images often have a large number of parameters and heavy weight, which makes it difficult to be applied to mobile devices. We propose three YOLO-based lightweight object detection networks for UAVs, named YOLO-L, YOLO-S, and YOLO-M, respectively. In YOLO-L, we adopt a deconvolution approach to explore suitable upsampling rules during training to improve the detection accuracy. The convolution-batch normalization-SiLU activation function (CBS) structure is replaced with Ghost CBS to reduce the number of parameters and weight, meanwhile Maxpool maximum pooling operation is proposed to replace the CBS structure to avoid generating parameters and weight. YOLO-S greatly reduces the weight of the network by directly introducing CSPGhostNeck residual structures, so that the parameters and weight are respectively decreased by about 15% at the expense of 2.4% mAP. And YOLO-M adopts the CSPGhostNeck residual structure and deconvolution to reduce parameters by 5.6% and weight by 5.7%, while mAP only by 1.8%. The results show that the three lightweight detection networks proposed in this paper have good performance in UAV aerial image object detection task.

5 October 2022 in IEEE Transactions on Industrial Electronics
Verified
Journal Article
Closed access
Dongdong ZhangDongdong Zhang
Dongdong Zhang
JYJiawei Yi
Jiawei Yi
Xiang LiXiang Li
Xiang Li
TLTianhao Liu
Tianhao Liu
HZHaisen Zhao
Haisen Zhao
TWThomas Wu
Thomas Wu
In order to estimate the core loss resistance of converter-fed induction motor accurately and efficiently, an analytical piecewise variable-coefficient core loss model is proposed. By introducing two voltage harmonics related coefficients, the influence of converter harmonics on core loss is simply and effectively considered. In addition, the surface and pulse loss caused by slot harmonics and the additional harmonic core loss caused by harmonic magnetic potential of stator winding under load condition are also considered. Based on the proposed model, an advanced core loss equivalent resistance model of converter-fed induction motor considering supply and spatial harmonics is proposed. The effectiveness of the proposed model is validated by comparisons with the measured core losses of 5.5 kW induction motor under no-load condition. In addition, compared with the finite-element method under load condition, the proposed analytical model reduces the computational time significantly while maintaining high accuracy.

12 August 2021 in IEEE Transactions on Transportation Electrification
Verified
Journal Article
Closed access
Dongdong ZhangDongdong Zhang
Dongdong Zhang
JYJiawei Yi
Jiawei Yi
HZHongyu Zhu
Hongyu Zhu
TATanveer Ahmad
Tanveer Ahmad
HZHaisen Zhao
Haisen Zhao
TWThomas Wu
Thomas Wu
Compared with the fundamental loss, the harmonic losses become very complicated because of the coupling between the power supply harmonics and the motor harmonics. To dispose of this problem, a multislice 2-D finite element model considering the interbar currents and a fast rotor harmonics identification method is employed to identify the harmonics of the rotor current density and flux density of the inverter-fed induction motor (IM). Considering the complex coupling phenomenon of time–space harmonics, a two-term iron model with piecewise-defined variable coefficients (PVCIL model) and a finite element analysis (FEA)-based copper loss method are then used to calculate the iron and copper loss components of the inverter-fed IM. Finally, based on the introduced methods, both the electromagnetic field and different losses terms of the same 5.5-kW inverter-fed IM under different load and supply conditions are calculated and analyzed. The experimental validation of those two losses’ calculation methods is performed on a 5.5-kW IM with different operating conditions. The results obtained in this article can provide the theoretical basis for targeted harmonic elimination and loss reduction in the design phase of the inverter-fed IM.

21 November 2022 in IEEE Transactions on Power Electronics
Verified
Journal Article
Closed access
JYJiawei Yi
Jiawei Yi
CLChunjiao Li
Chunjiao Li
Dongdong ZhangDongdong Zhang
Dongdong Zhang
Xiang LiXiang Li
Xiang Li
MJMeihui Jiang
Meihui Jiang
XWXinzhang Wu
Xinzhang Wu
In the traditional optimization model of central air-conditioner, the loss model of converter-fed motor is very rough, resulting in a large amount of energy waste. In this paper, a new energy loss model of central air-conditioning system from power to client is proposed. In the establishment of the loss model, the characteristics of pump load and variable frequency speed regulation are fully considered, and the electromagnetic variables which are difficult to be collected are replaced by the motor speed which can be directly calculated, so that the motor loss model can be introduced into the optimization model of the central air-conditioning system. A 5.5 kW converter-fed induction motor is tested under different speeds and loads, and the two-dimensional loss data were obtained. Then, one-dimensional data were extracted from the measured two-dimensional data combined with the load characteristics of the pump, and compared with the calculated values of the proposed model in this paper. The results show that the proposed loss model is of good accuracy and versatility. Because the proposed analytical model only needs the variable of motor speed to accurately estimate the losses, it can be easily applied to the optimization of central air-conditioning system.

27 April 2025 in Chinese Journal of Information Fusion
Verified
Journal Article
Open access
PDF file
JYJiawei Yi
Jiawei Yi
YLYing Liu
Ying Liu
YLYanshan LI
Yanshan LI
WXWei-xin Xie
Wei-xin Xie
Due to the poor imaging quality of remote sensing images and the small size of targets, remote sensing small target detection has become a current research difficulty and hotspot. Recent years have seen many new algorithms. Remote sensing small target detection methods based on image super-resolution reconstruction have attracted many researchers due to their excellent performance. However, these algorithms still have problems such as weak feature extraction capability and insufficient feature fusion. Then, we propose Enhanced Feature based Small Target Detection Network in Remote Sensing Images (EFSOD), which includes a Edge Enhancement Super-Resolution Reconstruction Module (EESRM) and a Cross-Model Feature Fusion Module (CMFFM). EESRM enhances the recognizability of small target contours by fusing extracted edge features with the original features through residual connections, alleviating the constraints of feature blurring on detection performance. CMFFM achieves deep integration of the detailed features extracted by the EESRM network with the semantic features extracted by the target detection network, improving the model's sensitivity and accuracy in recognizing small targets in complex backgrounds. Additionally, considering the effects of blurring, noise, illumination changes, and atmospheric scattering on remote sensing images, a remote sensing image degradation simulation algorithm is proposed. This algorithm realistically simulates the generation process of low-resolution remote sensing images under natural conditions, providing more realistic training and testing data. The experimental results show that the proposed EFSOD significantly enhances the performance of small object detection in remote sensing.

1 January 2026 in IEEE Transactions on Transportation Electrification
Verified
Journal Article
Closed access
ZZZhihao Zhu
Zhihao Zhu
Xiang LiXiang Li
Xiang Li
JYJiawei Yi
Jiawei Yi
XWXinzhang Wu
Xinzhang Wu
SWSuyan Wang
Suyan Wang