The vehicle classification system developed by Federal Highway Administration (FHWA) of United States divides vehicle type into 13 categories depending on the number of axles and the wheelbase. However, establishing a fixed threshold for classifying a vehicle is difficult. The overlapping between vehicles pattern in the system needs a pattern recognition technique to distinguish between different vehicle categories. In this study, machine learning algorithms were used to classify various vehicles based on the collected traffic data from the embedded three-dimension Glass Fiber-Reinforced Polymer packaged Fiber Bragg Grating sensors (3D GFRP-FBG). The investigated machine learning algorithms include the support vector machines (SVM), Neural Network, and k-nearest neighbors (KNN) algorithms.
The Department of Transportation classifies a vehicle depending on the number of axles and the space between them (wheelbase). Vehicle classification accuracy depends on the accuracy in estimating the speed and the wheelbase. In this study, a three-dimension Glass Fiber-Reinforced Polymer packaged Fiber Bragg Grating sensor (3D GFRP-FBG) is introduced for vehicle speed and wheelbase estimation. The experimental results show the ability of the sensor to estimate the speed and the wheelbase of a reference vehicle, with an accuracy of 95% or higher.
The demand on high-speed weigh-in-motion (WIM) measurement rises significantly in last decade to collect weight information for traffic managements especially after the introduction of weigh-station bypass programs such as Pre-Pass. In this study, a three-dimension glass fiber-reinforced polymer packaged fiber Bragg grating sensor (3D GFRP-FBG) is introduced to be embedded inside flexible pavements for weigh-in-motion (WIM) measurement at high speed. Sensitivity study showed that the developed sensor is very sensitive to the passing weights at high speed. Field tests also validated that the developed sensor was able to detect weights at a vehicle driving speed up to 55mph, which can be applied for WIM measurements at high speed.
The weight of rolling trucks on roads is one of the critical factors for the management of road networks due to the continuous increase in truck weight. Weigh-in-motion (WIM) sensors have been widely used for weight enforcement. A three-dimensional glass fiber-reinforced polymer packaged fiber Bragg grating sensor (3-D GFRP-FBG) is introduced for in-pavement WIM measurement at low vehicle passing speed. A sensitivity study shows that the developed sensor is very sensitive to the sensor installation depth and the longitudinal and transverse locations of the wheel loading position. The developed 3-D GFRP-FBG sensor is applicable for most practical pavements with a panel length larger than 6 ft, and it also shows a very good long-term durability. For the three components in 3-D of the developed sensor, the longitudinal component has the highest sensitivity for WIM measurements, followed by the transverse and vertical components. Field testing validated the sensitivity and repeatability of the developed 3-D GFRP-FBG sensor. The developed sensor provides the transportation agency one alternative solution for WIM measurement, which could significantly improve the measurement efficiency and long-term durability.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.