Hai Tang

Hai Tang

Auto-generated profile, based on publicly available information

Hai Tang

School of Electrical and Information Engineering, Hubei Key Laboratory of Energy Storage and Power Battery, Hubei University of Automotive Technology, Shiyan, China

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

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

Representative Publications

View All Publications
19 October 2023 in IEEE Sensors Journal
Verified
Journal Article
Closed access
YLYuan Lei
Yuan Lei
CYChen Yanrong
Chen Yanrong
THTang Hai
Tang Hai
GRGao Ren
Gao Ren
WWWu Wenhuan
Wu Wenhuan
As an essential component of the new energy vehicle battery, current collectors affect the performance of battery and are crucial to the safety of passengers. The significant differences in shape and scale among defect types make it challenging for the model detection of current collector defects. In order to reduce application costs, and conduct real-time detection with limited computing resources, we propose an end-to-end adaptive and lightweight defect detection model for the battery current collector, DGNet. Firstly, we designed an adaptive lightweight backbone network (DOS module) to adaptively extract useful features adaptively along all four dimensions of kernel space while maintaining low computational complexity. Secondly, we designed a lightweight feature fusion network (GS_FPN), which reduces parameter redundancy and fully utilizes the semantic information of the feature maps of backbone network while ensuring detection accuracy. Experimental results show that DGNet achieves a mAP50 (mean Average Precision at IoU threshold 0.5) of 91.8% on the self-made BCC surface defect database, with a model size of 4.0M, only 3.7 GFLOPs (Giga Floating-point Operations per Second), and FPS (Frames Per Second) of 181.8. To further demonstrate the capabilities of DGNet, we test it on the publicly NEU surface defect database, and the results showed that the DGNet exhibited good generalization. Compared to current advanced lightweight network models, it achieves higher detection accuracy and lower computational overhead, reaching the state-of-the-art level. Finally, we deployed DGNet on the embedded platform NVIDIA Jetson Nano for real-time detection, achieving a detection time of 0.074s per image, meeting the accuracy and real-time detection requirements for battery current collector defect detection tasks in practical industrial applications.

11 May 2020 in IEEE Access
Verified
Journal Article
Open access
HTHai Tang
Hai Tang
ZHZhihui Hu
Zhihui Hu
In this paper, we propose a new method for CT pathological image analysis of brain and chest to extract image features and classify images. Because the deep neural network needs a large number of labeled samples to complete the training, and the cost of medical image labeling is very high, the training samples needed to train the deep neural network are insufficient. In this paper, a semi supervised learning based image classification method is proposed, which uses a small amount of labeled pathological image data to train the network model, and then integrates the features extracted by the network to classify the image. The results show that the classification effect of the neural network is better than convolution neural network and other traditional image classification models. To some extent, it can reduce the dependence of neural network on a large number of training samples, and effectively reduce the over fitting phenomenon of the network. Through the analysis of the overall classification accuracy and kappa coefficient of different classification methods under different sample numbers, it is found that the overall classification accuracy and kappa coefficient are increasing with the increasing number of training samples. Especially in the case of a small number of training samples, compared with other deep neural networks and traditional classification methods, the classification accuracy of the counter neural network is about 10% higher than that of other neural networks and traditional classification methods, and the advantages are more obvious.

10 January 2022 in Scientific Programming
Verified
Journal Article
Open access
PDF file
ZHZhihui Hu
Zhihui Hu
HTHai Tang
Hai Tang
With the improvement of urbanization and the continuous expansion of transportation scale, traffic problem has become an important problem in our life. How to ensure traffic safety has become the key issue for the government to implement social management. Nowadays, Internet of Things (IOT) technology is widely used in the industrial technology field. It will have a great impact on human production and life. Intelligent transportation system is a research field involving many high and new technologies. This paper proposes an intelligent transportation system based on Internet of Things technology. This paper presents the optimal design structure of intelligent transportation system based on Internet of Things technology. The experimental results show that the intelligent transportation system can effectively realize the information interaction between the vehicle and the control center and understand the road conditions in advance. At the same time, the intelligent transportation system can improve the driving speed of vehicles on the road, make effective use of resources, reduce economic losses during vehicle operation, and reduce air pollution caused by gasoline emission.

15 May 2024 in IEEE Sensors Journal
Verified
Journal Article
Closed access
LYLei Yuan
Lei Yuan
YCYanrong Chen
Yanrong Chen
HTHai Tang
Hai Tang
RGRen Gao
Ren Gao
WWWenhuan Wu
Wenhuan Wu
The future direction of global automotive development is electrification, and the battery current collector is an essential component of new energy vehicle batteries. However, the welding defects in the battery current collector during the welding process are characterized by a disorganized distribution, extensive size variations, multiple types, and ambiguous features, posing challenges for detecting welding defects in the current collector. This paper proposes a lightweight deep-learning algorithm called MGNet for detecting welding defects in the current collectors. We introduce a lightweight MDM module based on multi-scale channels, which utilizes deep dynamic convolutions as its basic structure to extract compelling features while reducing computational complexity. We also propose a lightweight feature fusion network called GS_GFPN, which fully leverages the semantic information of the backbone network feature maps while reducing parameter redundancy and maintaining detection accuracy. Experimental evaluations on both the BCC (battery current collector) surface defect database and the publicly available NEU (Northeastern University) surface defect database demonstrate that MGNet outperforms existing methods with significant improvements in detection accuracy. The mean average precision (mAP) at IoU threshold 0.5 is 93.9% and 78.0%, respectively, with Frames Per Second (FPS) of 212.8 and 238.1 and a model weights of only 3.1M. Moreover, the algorithm is successfully deployed on the NVIDIA Jetson Nano embedded device, enabling real-time defect detection for practical industrial applications.

29 October 2024 in PLOS ONE
Verified
Journal Article
Open access
PDF file
HTHai Tang
Hai Tang
LYLei Yuan
Lei Yuan
YCYanrong Chen
Yanrong Chen
RGRen Gao
Ren Gao
WWWenhuan Wu
Wenhuan Wu
The future trend in global automobile development is electrification, and the current collector is an essential component of the battery in new energy vehicles. Aiming at the misjudgment and omission caused by the confusing distribution, a wide range of sizes and types, and ambiguity of target defects in current collectors, an improved target detection model DCS-YOLO (DC-SoftCBAM YOLO) based on YOLOv5 is proposed. Firstly, the detection rate of defects with different scales is improved by adding detection layers; Secondly, we use the designed DC module as the backbone network to help the model capture the global information and semantic dependencies of the target, and effectively improve the generalization ability and detection performance of the model. Finally, in the neck part, we integrate our designed Convolutional Block Attention Module (SoftPool Convolutional Block Attention Module, SoftCBAM), which can adaptively learn the importance of channels, enhance feature representation, and enable the model to better deal with target details. Experimental results show that the mAP50 of the proposed DCS-YOLO model is 92.2%, which is 5.1% higher than the baseline model. The FPS reaches 147.1, and the detection accuracy of various defect categories is improved, especially Severely bad and No cover, and the detection recall rate reaches 100%. This method has high target detection model efficiency and meets the requirements of real-time detection of battery collector defects.

17 November 2023
Verified
Conference Paper
Closed access
LYLei Yuan
Lei Yuan
YCYanrong Chen
Yanrong Chen
HTHai Tang
Hai Tang
ZLZhengxuan Liu
Zhengxuan Liu
RGRen Gao
Ren Gao
WWWenhuan Wu
Wenhuan Wu
The quality of the current collector, an essential component in new energy vehicle batteries, is crucial for battery performance and significantly impacts the safety of vehicle occupants. However, detecting defects in battery current collector in real-time industrial applications with limited computational resources poses a major challenge. To address this, our paper proposes SGNet (ShuffleNet V2 + G_GFPN), a lightweight model for current collector defect detection. SGNet utilizes ShuffleNet V2 as the backbone feature extraction network and a designed G_GFPN as the feature fusion network, reducing parameter redundancy to ensure high detection accuracy while minimizing computational costs. Our experimental results demonstrate that the SGNet model achieves an impressive 90.7% detection accuracy. Boasting a compact model size of merely 3.5M and remarkably low GFLOPs of 4.1, SGNet achieves an outstanding FPS (Frames Per Second) rate of 178.6. In comparison to other sophisticated lightweight network models, SGNet surpasses them by delivering superior detection accuracy while demanding less computational resources. The successful deployment of the SGNet model on the embedded NVIDIA Jetson Nano platform paves the way for real-time defect detection. With a swift detection time of 0.073 seconds per image, the model meets the stringent requirements for accuracy and real-time performance in identifying battery collector tray defects within real-world industrial environments.