MaLTESE: Large-Scale Simulation-Driven Machine Learning for Transient Driving Cycles

TL;DR

This paper introduces MaLTESE, a large-scale simulation-driven machine learning framework that uses a physics-based engine simulator and deep neural networks to efficiently predict engine performance and emissions during transient driving cycles, reducing calibration costs.

Contribution

The work presents a scalable, high-fidelity simulation approach combined with deep learning to accurately and rapidly predict engine behavior across diverse transient conditions, enabling more efficient engine calibration.

Findings

Deep neural network surrogate models achieve high accuracy in predicting engine parameters.

The approach significantly reduces prediction time from 0.5 seconds to 16 microseconds per configuration.

Transfer learning allows incremental updates to the model for new configurations.

Abstract

Optimal engine operation during a transient driving cycle is the key to achieving greater fuel economy, engine efficiency, and reduced emissions. In order to achieve continuously optimal engine operation, engine calibration methods use a combination of static correlations obtained from dynamometer tests for steady-state operating points and road and/or track performance data. As the parameter space of control variables, design variable constraints, and objective functions increases, the cost and duration for optimal calibration become prohibitively large. In order to reduce the number of dynamometer tests required for calibrating modern engines, a large-scale simulation-driven machine learning approach is presented in this work. A parallel, fast, robust, physics-based reduced-order engine simulator is used to obtain performance and emission characteristics of engines over a wide range of control parameters under various transient driving conditions (drive cycles). We scale the simulation up to 3,906 nodes of the Theta supercomputer at the Argonne Leadership Computing Facility to generate data required to train a machine learning model. The trained model is then used to predict various engine parameters of interest. Our results show that a deep-neural-network-based surrogate model achieves high accuracy for various engine parameters such as exhaust temperature, exhaust pressure, nitric oxide, and engine torque. Once trained, the deep-neural-network-based surrogate model is fast for inference: it requires about 16 micro sec for predicting the engine performance and emissions for a single design configuration compared with about 0.5 s per configuration with the engine simulator. Moreover, we demonstrate that transfer learning and retraining can be leveraged to incrementally retrain the surrogate model to cope with new configurations that fall outside the training data space.