Time-Series Friction Torque Prediction for Drum Brake Systems via Mixed-Effects Random Forest Framework

The application of drum brake systems is expanding due to increasing cost competitiveness requirements in EV and purpose-built vehicle markets, as well as the introduction of EURO-7 particulate emission regulations. In spite of this trend, drum brake friction behavior is not yet fully understood because it is governed by complex and strongly coupled complicating mechanisms, including temperature history, braking conditions, and interactions between drum brake components. To address this gap, this study presents a method for developing a time-series friction torque prediction model using the Mixed-effects Random Forest (MERF) machine learning framework. Time-series data collected from sensors during drum brake dynamometer tests were analyzed to identify the key variables that govern the friction torque. Significant inputs were selected through Exploratory Data Analysis (EDA), considering test-to-test variability and potential mixed effects, and were then used to train and tune the MERF model. Model performance was evaluated by comparing predicted friction torque with measured torque, and prediction error was quantified by using Mean Absolute Error (MAE) to check whether predicted model is reliable. The proposed prediction model demonstrates a high level of agreement with experimental measurements, confirming that the MERF approach can effectively capture the non-linear and transient characteristics of drum brake friction torque from time-series sensor signals. These results indicate that friction torque estimation is feasible using only sensor signals already available from conventional test instrumentation, without additional dedicated sensors. This capability is expected to support broader applications, including brake performance prediction for vehicles equipped with drum brakes and enhanced simulation of drum brake thermal performance across operating conditions.