Velocity measurement-based friction estimation for railway vehicles running on adhesion limit: swarm intelligence-based multiple models approach

Abstract Model-based condition monitoring is an increasingly important area for rail transportation. The key elements of such condition monitoring methodologies are low-cost vehicle sensors and intelligent algorithms. In this study, a swarm intelligence-based multiple models approach is proposed to detect different friction conditions by using velocity measurements of a railway vehicle. In this case of application, estimated parameter is the maximum friction coefficient. Additionally, proposed methodology is tested experimentally by using the measurements taken from a tram wheel test stand. Multiple mathematical models of the test stand are created with different maximum friction coefficients, whereas all initial conditions and other system parameters are same for each model. Therefore, comparison of the output of each model with measurements is considered to interpret the parameter value of the model, which best represents the system, is selected as parameter estimate. Unlike the traditional multiple models approach, a swarm intelligence-based evolution of the models is proposed. Experiments carried out on the test stand reveal that the proposed methodology is promising to be used as an on-board friction condition monitoring tool for railway vehicles with traction. Furthermore, it can be considered to detect weather conditions since friction conditions change due to the weather events such as rain, ice, snowfall, condensation of water droplets, and leaves on the line and it can be used as an auxiliary system for intelligent traction and high adhesion control systems.