Fuzzy Reliability-Based Traction Control Model for Intelligent Transportation Systems

In this paper, a fuzzy Bayesian traction control system was developed for rail vehicles with speed sensors in intelligent transportation systems. The system included three main components to sense, process, and classify the traction conditions. The information received from the speed sensors is used to avoid any error that might cause service interruption and unnecessary maintenance. There are, however, occasions when these signals may not be sensed, transmitted, or received precisely due to unexpected conditions such as noise. Therefore, in this study, the γ-level fuzzy Bayesian model was proposed for sensor-based traction control systems. In order to apply the fuzzy Bayesian concept, the wheel acceleration was assumed to be a fuzzy random variable for membership function with fuzzy prior distribution. Using the fuzzy signals, the intelligent model calculates the risk of classification for the system that results in determining the misclassification decision at a minimum cost. The model's engine involves a mathematical problem which can be solved in any programming language in onboard or embedded computers. The conceptual model was applied to a case study with promising results, which can be used for target systems or simulation.