Development of a Salt Spreader Controller Program Using Machine-Sensed Roadway Weather Parameters

Details

• Creators:
  Ai, Chengbo ; Tessier, Russell ; Avhad, Vaishnavi
• Corporate Creators:
  University of Massachusetts at Amherst
• Corporate Publisher:
  Massachusetts. Department of Transportation
• Corporate Contributors:
  Massachusetts. Department of Transportation. Office of Transportation Planning ; United States. Department of Transportation. Federal Highway Administration
• Subject/TRT Terms:
  • Winter maintenance
  • Snow and ice control
  • Deicing
  • Sensors
  • Machine learning
  • Deep Learning Safety
• Publication/ Report Number:
  24-056
• Resource Type:
  Tech Report
• Geographical Coverage:
  Massachusetts ; United States
• Edition:
  Final Report - July 2024 (April 2022 - July 2024)
• Contracting Officer:
  Goldstein, Mark
• Description:
  Massachusetts owns over 300 and contracts 1,200 additional material spreaders that deliver salt, salt, sand mixtures, or liquid deicers to more than 15,000 lane miles of roadways during winter seasons. It is critical to efficiently and effectively deliver the materials so that the impacts of winter storms on road operations are minimized while the utilization of the materials is maximized to reduce potential environmental impacts. MassDOT deploys mobile RWIS sensors (e.g., Vaisala MD30) to better monitor the road surface and ambient weather conditions. This study developed an automated system to optimize material utilization by leveraging mobile RWIS sensors by developing hardware, software, algorithm (road surface condition deep learning algorithm), and model (salt rate prediction model). Based on the experimental results, the newly developed system can potentially save salt applications by approximately 34% and 37%, compared with the auto grip mode and the manual mode, while maintaining the similar performance of the treatment (i.e., maintaining or improving the grip values).
• Format:
  PDF
• Download URL:
  https://rosap.ntl.bts.gov/view/dot/77734/dot_77734_DS1.pdf
• File Type:
  [PDF - 10.33 MB]
• Collection(s):
  Artificial Intelligence Deployment Center of Excellence (AI COE) ; US Transportation Collection
• Main Document Checksum:
  urn:sha-512:dde4d98d94430a9a6463b2243ba95f10cc1238a74db61286f3cc436bf8460a77c558f57d9e2b2c265f8a3edd1f0be0059da9e384db11b978a28a5bbb66eb50ec