Machine-Learning-Based Digital Twins for Transient Vehicle Cycles and Their Potential for Predicting Fuel Consumption

Transient car emission tests generate huge amount of test data, but their results are usually evaluated only using “accumulated” cycle values according to the homologation limits. In this work, two machine learning models were developed and applied a truck RDE light-duty vehicle chassis tests. Different from conventional approach, engine parameters fuel consumption acquired Engine Control Unit, not measurement equipment. Instantaneous used as input in machine-learning-based digital twins. This novel approach allows for much less costly optimizations. The paper’s twins model able predict both instantaneous accumulated with good accuracy, also cycles different one train model.