High-precision intelligent identification method of truck overload based on TOI-Net

被引：0
作者：
Liang, Jian [1 ]
Kang, Jiehu [1 ]
Zhao, Zongyang [1 ]
Wu, Bin [1 ]
Wang, Xuesen [2 ]
机构：
[1] State Key Laboratory of Precision Measurement Technology and Instruments, Tianjin University, Tianjin
[2] Tianjin Municipal Engineering Design & Research Institute, Tianjin
来源：
Yi Qi Yi Biao Xue Bao/Chinese Journal of Scientific Instrument | 2024年 / 45卷 / 05期
关键词：
artificial intelligence; attention mechanism; convolutional neural networks; intelligent transportation system; truck overload identification;
D O I：
10.19650/j.cnki.cjsi.J2312227
中图分类号：
学科分类号：
摘要：
Truck overload transportation is an enormous threat to road safety. Currently, the main identification method for truck overload has low identification efficiency and a small scope of supervision. To address these problems, this article proposes a truck overload identification method based on deep learning. Firstly, a method is designed for generating truck trajectory images specifically for the overload determination task, which can transform multidimensional spatiotemporal truck trajectory data into truck trajectory images, reducing data complexity while aggregating features. Then, we design a high-accuracy truck overload intelligent identification model TOI-Net, which consists of RepVGG modules and location attention modules. It can fully extract overload information features from truck trajectory data and efficiently complete the overload checkpoints task. Experiments are implemented on the truck overload dataset. The results show that the accuracy of the proposed method for overload identification is 96. 1%, with performance metrics higher than mainstream recognition networks, achieving precise, rapid, and comprehensive identification of overload behavior. © 2024 Science Press. All rights reserved.
引用
收藏
页码：319 / 328
页数：9
相关论文
共 38 条
  • [1] HAN W, WU J, CAI C S, Et al., Characteristics and dynamic impact of overloaded extra heavy trucks on typical highway bridges [ J ], Journal of Bridge Engineering, 20, 2, (2015)
  • [2] LI ZH K, RONG CH H., Research on long-term mechanism and countermeasures of controlling highway overload and over-limit transportation, China Journal of Highway and Transport, 18, 4, pp. 96-99, (2005)
  • [3] QIAO X X, ZHAO Y D., Vehicle overload detection system based on magnetoresistance sensor [ C ], 2018 International Conference on Electronics Technology (ICET), pp. 102-105, (2018)
  • [4] BURNOS P, GAJDA J, SROKA R, Et al., High accuracy weigh-in-motion systems for direct enforcement [ J ], Sensors, 21, 23, (2021)
  • [5] KONIOR A, KONIOR T, BRZOZOWSKI K, Et al., New functionalities of the weigh-in-motion system: IWIM solution, Transport Problems, 18, 2, pp. 161-170, (2023)
  • [6] LIU Y L, LIU ZH H., An optimized method for dynamic measurement of truck loading capacity [ C], 2018 3rd IEEE International Conference on Intelligent Transportation Engineering (ICITE), pp. 120-124, (2018)
  • [7] FU H, ZHANG Y, GANG X, Et al., Research on on-board dynamic weighing algorithm based on two-degree-of-freedom 1 / 4 vehicle model [ J ], International Journal of Heavy Vehicle Systems, 28, 6, pp. 792-807, (2021)
  • [8] ZHAO SH F, YANG J W, TANG ZH H, Et al., Methodological study on the influence of truck driving state on the accuracy of weigh-in-motion system [ J], Information, 13, 3, (2022)
  • [9] TANG S H, TENG ZH SH, SUN B, Et al., ADAM improved BP neural network and its application in dynamic weighing, Journal of Electronic Measurement and Instrumentation, 35, 4, pp. 127-135, (2021)
  • [10] LEE H H, YOON K T, CHOI Y M., Checkweigher using an EMFC weighting cell with magnetic springs and air-bearings, Metrology and Measurement Systems, 28, 3, pp. 465-478, (2021)
1234