Korean Journal of Artificial Intelligence (한국인공지능학회지)

Korea Artificial Intelligence Association (한국인공지능학회)
권호 표지
DOI QR코드

DOI QR Code

Road Surface Data Collection and Analysis using A2B Communication in Vehicles from Bearings and Deep Learning Research

  • Young-Min KIM (Department of Information & Communication Engineering, Daejeon University) ;
  • Jae-Yong HWANG (Department of Information & Communication Engineering, Daejeon University) ;
  • Sun-Kyoung KANG (Department of Computer Software Engineering, Wonkwang University)
  • Received : 2023.07.31
  • Accepted : 2023.09.04
  • Published : 2023.12.30
Download PDF
⟨ Previous Next ⟩

Abstract

This paper discusses a deep learning-based road surface analysis system that collects data by installing vibration sensors on the 4-axis wheel bearings of a vehicle, analyzes the data, and appropriately classifies the characteristics of the current driving road surface for use in the vehicle's control system. The data used for road surface analysis is real-time large-capacity data, with 48K samples per second, and the A2B protocol, which is used for large-capacity real-time data communication in modern vehicles, was used to collect the data. CAN and CAN-FD commonly used in vehicle communication, are unable to perform real-time road surface analysis due to bandwidth limitations. By using A2B communication, data was collected at a maximum bandwidth for real-time analysis, requiring a minimum of 24K samples/sec for evaluation. Based on the data collected for real-time analysis, performance was assessed using deep learning models such as LSTM, GRU, and RNN. The results showed similar road surface classification performance across all models. It was also observed that the quality of data used during the training process had an impact on the performance of each model.

Keywords

Acknowledgement

This research was supported by "Regional Innovation Strategy (RIS)" through the National Research Foundation of Korea(NRF) funded by the Ministry of Education(MOE)(2021RIS-004)

References

  1. Baskar, P., Joseph, M. A., Narayanan, N., & Loya, R. B. (2013, April). Experimental investigation of oxygen enrichment on performance of twin cylinder diesel engine with variation of injection pressure. In 2013 International Conference on Energy Efficient Technologies for Sustainability (pp. 682-687). IEEE.
  2. De Andrade, R., Hodel, K. N., Justo, J. F., Lagana, A. M., Santos, M. M., & Gu, Z. (2018). Analytical and experimental performance evaluations of CAN-FD bus. IEEE Access, 6, 21287-21295. https://doi.org/10.1109/ACCESS.2018.2826522
  3. Jung, D. Y., & Koo, B. Y. (2019). Comparative e study of piezoelectric and MEMS accelerometers for vibrational measurements. Journal of the Korean Society for Nondestructive Testing, 39(3), 168-175. https://doi.org/10.7779/JKSNT.2019.39.3.168
  4. Noh, K. J, Lee, D. C, Jin, J. M, Jung, I. S, & Chang, J. H. (2023) Development of Deep Learning-based Vehicle Diagnosis Technology Using Noise Data. Trans. Korean Soc. Noise Vib. Eng., 33(3), 306~312, 2023. https://doi.org/10.5050/KSNVE.2023.33.3.306
  5. Pentachloride, N. METALLURGICAL ABSTRACTS.
  6. Shang, R., Zhang, Y., & Shen, Z. J. M. (2021). Analyzing the effects of road type and rainy weather on fuel consumption and emissions: A mesoscopic model based on big traffic data. IEEE Access, 9, 62298-62315. https://doi.org/10.1109/ACCESS.2021.3074303
  7. Son, S. R., & Jeong, Y. N. (2022). The Road condition-based Braking Strength Calculation System for a fully autonomous driving vehicle. Journal of Internet Computing and Services, 23(2), 53-59. https://doi.org/10.7472/JKSII.2022.23.2.53
  8. Triggs, J. (2020). The A to Z of A2B Applications. Analog Dialogue, 54(3), 1-4.
  9. Varona, B., Monteserin, A. & Teyseyre, A. A deep learning approach to automatic road surface monitoring and pothole detection. Pers Ubiquit Comput 24, 519-534 (2020). https://doi.org/10.1007/s00779-019-01234-z
  10. Zargar, S. (2021). Introduction to sequence learning models: RNN, LSTM, GRU. Department of Mechanical and Aerospace Engineering, North Carolina State University, Raleigh, North Carolina, 27606.