Failure Detection Method using Aggregated Vehicle Detector Data

Abstract

Vehicle detectors play an indispensable role in traffic management and control systems (TMCS). The data collected via vehicle detectors are used to fulfill various functions such as signal control and traffic information provision. In Japan, TMCS use mainly ultrasonic detectors. Owing to their aged deterioration, their detection accuracy gradually reduces over many years, and thus their efficient operation and maintenance requires accomplished engineers. In recent years, it has become difficult to maintain great numbers of ultrasonic detectors because of the financial constraints in public resources and shortfall of accomplished engineers. In this paper, we propose failure detection methods, and confirm their validity by using actual data. First, we propose an aggregation method of detector data for classifying installation positions, and validate the method by using large amount of data. Moreover, we propose a few failure detection methods with the aggregated data, and compare their decision results by using the actual data.