A multi-pronged approach to strengthen diesel vehicle emission monitoring

China is constructing an vehicle emission monitoring system, aimed at combining remote OBD, periodic inspections, remote sensing and roadside checks. In this study, the exhaust emissions from diesel vehicles were investigated and analysed.

A Deep Transfer NOx Emission Inversion Model of Diesel Vehicles with Multisource External Influence

By installing on-board diagnostics (OBD) on tested vehicles, the after-treatment exhaust emissions can be monitored in real time to construct driving cycle-based emission models, which can provide data support for the construction of dynamic emission inventories of mobile source emission. However, in actual vehicle emission detection systems, due to the equipment installation costs and differences in vehicle driving conditions, engine operating conditions, and driving behavior patterns, it is impossible to ensure that the emission monitoring data of different vehicles always follow the same distribution. The traditional machine learning emission model usually assumes that the training set and test set of emission test data are derived from the same data distribution, and a unified emission model is used for estimation of different types of vehicles, ignoring the difference in monitoring data distribution. In this study, we attempt to build a diesel vehicle NOx emission prediction model based on the deep transfer learning framework with a few emission monitoring data. The proposed model firstly uses Spearman correlation analysis and Lasso feature selection to accomplish the selection of factors with high correlation with NOx emission from multiple sources of external factors. Then, the stacked sparse AutoEncoder is used to map different vehicle working condition emission data into the same feature space, and then, the distribution alignment of different vehicle working condition emission data features is achieved by minimizing maximum mean discrepancy (MMD) in the feature space. Finally, we validated the proposed method with the diesel vehicle OBD data that were collected by the Hefei Environmental Protection Bureau. The comprehensive experiment results show that our method can achieve the feature distribution alignment of emission data under different vehicle working conditions and improve the prediction performance of the NOx inversion model given a little amount of NOx emission monitoring data.

NOx Emission of a Correlation between the PEMS and SEMS over Different Test Modes and Real Driving Emission

The aim of this study is to verify the reliability of NOx emissions measured using Smart Emissions Measurement System (SEMS) equipment in comparison with the NOx emissions measured using certified Portable Emissions Measurement System (PEMS) equipment. The SEMS equipment is simple system, and it is less expensive than the PEMS equipment, as it comprises an On-Board Diagnostics (OBD) signal from the test vehicle and a NOx sensor. The SEMS equipment based on low-cost sensors has an advantage of building big data, but there are insufficient previous studies comparing of NOx emissions with certified the PEMS equipment. Therefore, this study is important in verifying the suitability of the SEMS equipment by comparing the NOx emissions measured by the various test modes and RDE using the two types of equipment. To analyze the correlation between the PEMS and SEMS equipment, the advanced diesel vehicle was equipped with the two types of equipment to simultaneously measure NOx emissions. After installing the equipment on the test vehicle, it was conducted under various test modes in the laboratory and the Real Driving Emission (RDE) test to verify the correlation of NOx emissions measured by the SEMS equipment. The correlation analysis for the NOx emissions measured by the PEMS and SEMS equipment under various test conditions and the RDE test indicated that the slope of the NOx emissions was approximately equal to 1, and the coefficient of determination was 0.9 or higher. Based on these test results, it was concluded that NOx emissions measured by the PEMS and SEMS equipment are highly similar.

Simulation of Optimal Driving for Minimization of Fuel Consumption or NOx Emissions in a Diesel Vehicle

Significant reduction in fuel consumption and NOx emissions can be achieved just by changing the driving along the road. In this paper, dynamic programming is employed to find two different driving profiles optimized for fuel consumption and NOx creation minimization in a diesel vehicle. Results, show that the fuel reduction driving cycle leads to fuel savings of 4% compared with the average consumption with arbitrary driving. The NOx reduction driving profile improves the emissions of arbitrary driving by a 34.5%. NOx oriented driving profile improves the emissions of the fuel-oriented cycle by a 38% at the expense of a fuel consumption penalty of 10%. This result points out the difficulty of a simultaneous NOx and fuel consumption reduction, stressing the efforts to be done in this field during the following years. Strategies followed and conclusions drawn from this paper are relevant concerning vehicle autonomy integration.