Application of Artificial-Computational Intelligence (ACI) for Botswana Gravel loss Condition Modeling and Prediction

In recent years, Artificial-Computational Intelligence (ACI) have found increasing applications in all areas of modeling of transportation infrastructures. However, compared to transportation planning and operations, research of ACI methods applied to infrastructure modeling has been relatively limited. The modern world relies on increasingly complex and demanding transportation infrastructures. Current technology allows for extensive streams of data to be collected; such data are necessary for modeling pavement conditions efficiently. Modeling of gravel loss conditions are required in order to predict their conditions in the future and provide information on the manner in which pavements perform. Such information can be applied to transportation planning, decision making processes and identification of future maintenance interventions. This paper developed accurate and reliable performance models which best capture the effects of gravel loss condition influencing factors using Feed Forward Neural Network (FFNN) modeling technique trained with Levenberg-Marquardt (L-M) method to predict gravel loss condition. FFNN produced better prediction accuracy for categorical condition rating of gravel loss (Excellent – 1; Good – 2; Fair – 3; Poor – 4; Bad – 5). Moreover, the developed FFNN gravel loss condition (GVL) prediction model yielded R2 = 0.95 > 0.9 benchmark based on minimum MSE = 0.055 < 0.1. Threshold value = 3 (fair condition) was specified for triggering maintenance interventions when gravel road subgrade exposure due to gravel loss is between 10 – 25%. In conclusion, the models reflect the history of gravel loss condition to predict future performance for gravel road in Botswana as a threshold to trigger optimal maintenance interventions.

• Supplemental Notes:
  • This paper was sponsored by TRB committee AFB30 Low-Volume Roads. Alternate title: Application of Artificial Computational Intelligence for Botswana Gravel Loss Condition Modeling and Prediction.
• Corporate Authors:

  Transportation Research Board

  500 Fifth Street, NW
  Washington, DC  United States  20001
• Authors:
  • Oladele, Adewole S
  • Vokolkova, Vera
  • Egwurube, Jerome A
• Conference:
  • Transportation Research Board 93rd Annual Meeting
  • Location: Washington DC
  • Date: 2014-1-12 to 2014-1-16
• Date: 2014

Language

• English

Media Info

• Media Type: Digital/other
• Features: Figures; References; Tables;
• Pagination: 8p
• Monograph Title: TRB 93rd Annual Meeting Compendium of Papers

Subject/Index Terms

• TRT Terms: Condition surveys; Decision making; Feedforward control; Gravel roads; Pavement maintenance; Pavement performance
• Identifier Terms: Artificial-Computation Intelligence (ACI)
• Geographic Terms: Botswana
• Subject Areas: Highways; Maintenance and Preservation; Pavements; I60: Maintenance;

Filing Info

• Accession Number: 01519293
• Record Type: Publication
• Report/Paper Numbers: 14-5640
• Files: TRIS, TRB, ATRI
• Created Date: Mar 24 2014 12:02PM