Application of Machine Learning to Automatic Gear Shift Schedule Design of Alternative Drive Systems

Abstract

Intelligent automatic transmission shift schedule design has been well established in the last decade. However, due to the paradigm change is currently taking place in mobility sector, which resulted in a rapid progress of Electric Vehicles and Autonomous Vehicles, intelligent automatic gear shift strategies are still in the focus of much research. In addition, the proper transmission shift schedule generation is especially important from the viewpoint of energy efficiency optimizing algorithms, which is affected by the driving style, power losses, etc. Fundamentally, conventional shift schedule design relies on lookup tables obtained from test-bench measurements and real-world driving measurements. During real time test data collection, the measurement of some variables may be impractical and/or patterns of important driving conditions may be unavailable during short-distance routes neglecting the comprehensive effects of the transient operation. Machine Learning methods in combination with model-based data generation is a promising alternative, which allows a significant reduction in development time and a more precise calibration by using rich historical data rich. Such models can be easily fitted to alternative drive systems also, which may raise more specific requirements regarding gear shift scheduling issues coupled with efficiency. In this paper the performances of Machine Learning models are investigated in automatic gear shift schedule generation based on simulated driving cycle test data. Results of simulation investigations validate the applicability and efficiency of the proposed approach.