Automatic transmission fluid (ATF) or automatic transmission oil which has high potential resource conservation capability considering the current servicing methods. It also plays a crucial role in the performance and longevity of the transmission system. Predicting the actual life of the ATF can be challenging due to various factors such as its application, driving conditions, driving behavior, oil grade, and maintenance schedules, which can help prevent costly repairs and improve the vehicle’s overall performance.
Present work is focused on developing a predictive model utilizing the critical oil properties in real time by giving an indication to the driver/fleet owner. Data is gathered by considering various vehicle parameters, including usage patterns such as shift density, vehicle load, torque, current gear, lock-up state, input/output shaft speed, oil temperature, and more. This data is obtained from a test vehicle over a specific period. The approach encompasses several steps, including data preprocessing, feature selection, model selection, model training, and evaluating the model.
ML model is trained by using the data obtained from the test vehicle which classifies the oil quality and predicts the remaining mileage of the vehicle. The prediction can be done at any given time and is independent of the vehicle’s operating conditions. This model was deployed for live computations (classification - ok/not ok and remainder mileage) to simulate real-time monitoring of the end user. The future work will focus on real-time testing of an automatic transmission using ML approaches to predict transmission fluid’s life coupled with dynamic scenarios and potential fluid failure modes for informed decisions about ATF replacement schedules and maintenance.