Deep Learning Based Distributed Meta-Learning for Fast and Accurate Online Adaptive Powertrain Fuel Consumption Modeling
- 26 January 2023
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Vehicular Technology
- Vol. 72 (6) , 7251-7264
Abstract
Connected vehicle-based distributed meta-regression (CV-DMR) algorithms from our previous work facilitate online adaptive microscopic fuel consumption modeling, which can support model-based vehicle and powertrain control (MB-VPC) for fuel-efficient vehicle operations. By taking advantage of accessible online computational resources from connected vehicles (CVs) and CV remote data center, CV-DMR can adapt the microscopic fuel consumption model to an unseen driving condition with limited training data. However, the computational complexity of obtaining the normalized feature map in CV-DMR during training is high. It can take long time to adapt the model to a new driving condition, especially when the new driving condition is considerably different from the pre-learnt driving conditions. To reduce the computational complexity of learning/training, we propose to apply deep neural networks as the model representation method and newly design efficient deep learning based CV-supported distributed meta-learning (CV-DML) algorithms for adaptive fuel consumption modeling. To further generalize the model and reduce model adaptation time, the concept of meta-suggestion is newly proposed in CV-DML. Substantial proof-of-concept experiments are conducted with steady-state and transient vehicle engine data to evaluate the model performance in terms of model prediction accuracy, model adaptation speed, and fuel saving. Compared to the physical model and non-CV-supported model adaptation, the prediction accuracy of CV-DML is improved by 34% - 87% and 17% - 30%, respectively. Due to the improved accuracy, up to 9.4% of fuel is saved. To achieve the same the prediction accuracy and fuel saving, the model adaptation of CV-DML is 18 to 1,300 times faster than that of CV-DMR.Keywords
Funding Information
- National Science Foundation (CNS-0644056)
This publication has 27 references indexed in Scilit:
- A review of recent research on green road freight transportationEuropean Journal of Operational Research, 2014
- Assessment of Alternative Polynomial Fuel Consumption Models for Use in Intelligent Transportation Systems ApplicationsJournal of Intelligent Transportation Systems, 2012
- Development and experimental validation of a control-oriented Diesel engine model for fuel consumption and brake torque predictionsMathematical and Computer Modelling of Dynamical Systems, 2011
- Deep, Big, Simple Neural Nets for Handwritten Digit RecognitionNeural Computation, 2010
- MetalearningScholarpedia, 2010
- Look-ahead control for heavy trucks to minimize trip time and fuel consumptionControl Engineering Practice, 2009
- Robust Recurrent Neural Network Control of Biped RobotJournal of Intelligent & Robotic Systems, 2007
- Estimating Vehicle Fuel Consumption and Emissions based on Instantaneous Speed and Acceleration LevelsJournal of Transportation Engineering, 2002
- Learning to Control Fast-Weight Memories: An Alternative to Dynamic Recurrent NetworksNeural Computation, 1992
- Fuel consumption and emission modelling by power demand and a comparison with other modelsTransportation Research Part A: General, 1984