Search

The pavement surface will inevitably develop cracks, subsidence, pits, ruts, and other defects due to the effects of traffic and the environment. In road engineering, vibration-based pavement condition monitoring has been widely adopted. Due to differences in vehicle dynamics, acquisition equipment, and road quality, the application of these techniques to the identification of minor pavement damage is limited. With the widespread adoption of the inertial navigation system (INS) in autonomous vehicles, INS-based pavement evaluation has emerged as a promising new technique. In this paper, the acceleration sensor, gyroscope, GPS, and other INS-integrated devices were used to collect data on vehicle attitude changes. For the detection of pavement apparent millimetre disease, a new method utilising INS data and machine learning was proposed. The method analyses the original vibration signal in time domain, determines the degree of sensing parameter influence, and extracts the index that can characterise the signal change. Multiple machine learning recognition models have been built to effectively classify road conditions, with the best-performing model achieving an F1 score of 99.61% and precision of 99.33%. The recall rate, accuracy rate, and F1 score of disease height classification were all above 0.7 on a macro and micro scale. [ABSTRACT FROM AUTHOR]

The pavement surface will inevitably develop cracks, subsidence, pits, ruts, and other defects due to the effects of traffic and the environment. In road engineering, vibration-based pavement condition monitoring has been widely adopted. Due to differences in vehicle dynamics, acquisition equipment, and road quality, the application of these techniques to the identification of minor pavement damage is limited. With the widespread adoption of the inertial navigation system (INS) in autonomous vehicles, INS-based pavement evaluation has emerged as a promising new technique. In this paper, the acceleration sensor, gyroscope, GPS, and other INS-integrated devices were used to collect data on vehicle attitude changes. For the detection of pavement apparent millimetre disease, a new method utilising INS data and machine learning was proposed. The method analyses the original vibration signal in time domain, determines the degree of sensing parameter influence, and extracts the index that can characterise the signal change. Multiple machine learning recognition models have been built to effectively classify road conditions, with the best-performing model achieving an F1 score of 99.61% and precision of 99.33%. The recall rate, accuracy rate, and F1 score of disease height classification were all above 0.7 on a macro and micro scale. [ABSTRACT FROM AUTHOR]