Modeling and Predicting Heavy-Duty Vehicle Engine-Out and Tailpipe Nitrogen Oxide (NO x ) Emissions Using Deep Learning.

Rinav Pillai,Matthew Brusstar,Tim Nevius,André L Boehman,Albert S Berahas,Ruonan Sun,Vassilis Triantopoulos

doi:10.3389/fmech.2022.840310

Abstract

As emissions regulations for transportation become stricter, it is increasingly important to develop accurate nitrogen oxide (NOx) emissions models for heavy-duty vehicles. However, estimation of transient NOx emissions using physics-based models is challenging due to its highly dynamic nature, which arises from the complex interactions between power demand, engine operation, and exhaust aftertreatment efficiency. As an alternative to physics-based models, a multi-dimensional data-driven approach is proposed as a framework to estimate NOx emissions across an extensive set of representative engine and exhaust aftertreatment system operating conditions. This paper employs Deep Neural Networks (DNN) to develop two models, an engine-out NOx and a tailpipe NOx model, to predict heavy-duty vehicle NOx emissions. The DNN models were developed using variables that are available from On-board Diagnostics from two datasets, an engine dynamometer and a chassis dynamometer dataset. Results from trained DNN models using the engine dynamometer dataset showed that the proposed approach can predict NOx emissions with high accuracy, where R2 scores are higher than 0.99 for both engine-out and tailpipe NOx models on cold/hot Federal Test Procedure (FTP) and Ramped Mode Cycle (RMC) data. Similarly, the engine-out and tailpipe NOx models using the chassis dynamometer dataset achieved R2 scores of 0.97 and 0.93, respectively. All models developed in this study have a mean absolute error percentage of approximately 1% relative to maximum NOx in the datasets, which is comparable to that of physical NOx emissions measurement analyzers. The input feature importance studies conducted in this work indicate that high accuracy DNN models (R2 = 0.92–0.95) could be developed by utilizing minimal significant engine and aftertreatment inputs. This study also demonstrates that DNN NOx emissions models can be very effective tools for fault detection in Selective Catalytic Reduction (SCR) systems.

Highlights

Heavy-duty vehicles employ compression ignition engines due to their high power density, reliability and powertrain efficiency
Instantaneous nitrogen oxide (NOx) error Since the Deep Neural Networks (DNN) models developed in this study are used to predict instantaneous NOx emissions, we propose a novel instantaneous NOx error metric that captures the error at every point in the training set
The results are divided into the following sub-sections: model evaluation metrics (Section 4.1), error metrics (Section 4.2), and instantaneous actual vs predicted NOx emissions (Section 4.3), on the train, validation and test sets for each model and dataset

Summary

Introduction

Heavy-duty vehicles employ compression ignition engines due to their high power density, reliability and powertrain efficiency. Even with the anticipated changes in Greenhouse Gas regulations, diesel engine-powered trucks will continue to be used in heavy-duty transportation for several years, especially in the legacy fleet (EPA, 2021b). Stringent emissions regulations have been put in place to curb vehicular NOx emissions (EPA, 2021b). This has put tremendous pressure on the diesel engine industry to design and develop technologies that limit NOx emissions from the engine and from the tailpipe using exhaust aftertreatment systems. Accurate models for tailpipe NOx predictions are important in understanding the potential for future emissions reductions, and as a tool for identifying possible modes of noncompliance during in-use operation

Methods

Results

Discussion

Conclusion