NOx emission deterioration in modern heavy-duty diesel vehicles based on long-term real driving measurements

The impacts of improving heavy-duty internal combustion engine technology on reducing NOx emissions inventories going into the future

In an effort to reduce nitrogen oxide (NOx) emissions and other pollutants from heavy-duty vehicles (HDVs), regulators have been implementing more stringent regulations that have included a combination of significantly more stringent emissions standards with the introduction of battery electric vehicles (BEVs). This study analyzed in-use NOx emissions data from 63 HDVs across various vocations, model years, and engine technologies/fuels to assess which current technologies offer a realistic path toward reducing NOx emissions without significantly burdening fleet operators or electrical infrastructure. All 63 HDVs were equipped with portable emissions measurement systems when they were tested for in-use NOx emissions during their routine operation on California roadways. The data was analyzed using the moving average window method proposed by the Environmental Protection Agency (EPA) in which the in-use emissions are broken up into two bins dependent on the engine load: ≤6 % (idle) and >6 % of maximum rated power. It was found that diesel engines manufactured after 2020 and natural gas engines certified to the 0.02 g/bhp-h NOx standard met the 2027 and 2035 EPA in-use NOx standards for both bins even though the future standards do not apply to these older engines. In addition, over an 80 % reduction in average NOx emissions is seen in both bins and fuels as modern NOx and greenhouse gas standards were implemented in 2017. With the implementation of ultralow NOx diesel technology engines, capable of meeting 0.035 g/bhp-h NOx limits, it was found that reductions in the NOx emissions inventories from 90.0 to 91.9 % could be achieved by 2050, depending on the deployment of BEVs. In conclusion, current and upcoming engine technologies can serve as benchmark powertrain solutions for emissions inventory reductions in the near and intermediate terms solutions even to the extent that the transition to battery electric HDVs becomes more gradual.

Clarifying the impact of engine operating parameters of heavy-duty diesel vehicles on NOx and CO2 emissions using multimodal fusion methods

The issue of air pollution from transportation sources remains a major concern, particularly the emissions from heavy-duty diesel vehicles, which pose serious threats to ecosystems and human health. China VI emission standards mandate On-Board Diagnostics (OBD) systems in heavy-duty diesel vehicles for real-time data transmission, yet the current data quality, especially concerning crucial parameters like NOx output, remains inadequate for effective regulation. To address this, a novel approach integrating Multimodal Feature Fusion with Particle Swarm Optimization (OBD-PSOMFF) is proposed. This network employs Long Short-Term Memory (LSTM) networks to extract features from OBD indicators, capturing temporal dependencies. PSO optimizes feature weights, enhancing prediction accuracy. Testing on 23 heavy-duty vehicles demonstrates significant improvements in predicting NOx and CO2 mass emission rates, with mean squared errors reduced by 65.205 % and 70.936 % respectively compared to basic LSTM models. This innovative multimodal fusion method offers a robust framework for emission prediction, crucial for effective vehicle emission regulation and environmental preservation.

Light-duty gasoline vehicle emission deterioration insights from large-scale inspection/maintenance data: The synergistic impact of usage characteristics

Accurately estimating vehicle emissions is crucial for effective air quality management. As key data for emission inventory construction, emission factors (EFs) are influenced by vehicle usage characteristics and experience deterioration. Current deterioration models often employ single-factor approaches based on vehicle age or accumulated mileage, which fail to capture the effects of varying usage intensities within the same mileage or age intervals. This study addressed this limitation by developing a novel emission deterioration model that incorporates multi-dimensional usage characteristics and that utilizes a large-scale inspection and maintenance (I/M) dataset for light-duty gasoline vehicles (LDGVs). The modeling results reveal distinct deterioration patterns for different pollutants and highlight the synergistic effects of the usage duration and intensity: natural aging significantly impacts HC and NOx emissions, while CO emissions are more strongly affected by intensive use. Specifically, China V LDGVs that were driven 4 × 104 km/yr exhibited HC, CO, and NOx deterioration rates per mile that were approximately 4.1 % lower, 10.3 % higher, and 1.1 % higher, respectively, than those of vehicles driven 2 × 104 km/yr as the mileage increased from 5 × 104 km to 10 × 104 km. By leveraging timely emission data and explicitly accounting for usage intensity, this study corrected biases in local emission estimates by 5-85 % with respect to estimates from commonly used models. This framework enables the development of more effective control strategies and refinements to policy evaluations in megacities with I/M programs.

Enhancing vehicular emissions monitoring: A GA-GRU-based soft sensors approach for HDDVs

Vehicle emissions have a serious impact on urban air quality and public health, so environmental authorities around the world have introduced increasingly stringent emission regulations to reduce vehicle exhaust emissions. Nowadays, PEMS (Portable Emission Measurement System) is the most widely used method to measure on-road NOx (Nitrogen Oxides) and PN (Particle Number) emissions from HDDVs (Heavy-Duty Diesel Vehicles). However, the use of PEMS requires a lot of workforce and resources, making it both costly and time-consuming. This study proposes a neural network based on a combination of GA (Genetic Algorithm) and GRU (Gated Recurrent Unit), which uses CC (Pearson Correlation Coefficient) to determine and simplify OBD (On-board Diagnosis) data. The GA-GRU model is trained under three real driving conditions of HDDVs, divided by vehicle driving parameters, and then embedded as a soft sensor in the OBD system to monitor real-time emissions of NOx and PN within the OBD system. This research addresses the existing research gap in the development of soft sensors specifically designed for NOx and PN emission monitoring. In this study, it is demonstrated that the described soft sensor has excellent R2 values and outperforms other conventional models. This research highlights the ability of the proposed soft sensor to eliminate outliers accurately and promptly while consistently tracking predictions throughout the vehicle's lifetime. This method is a groundbreaking update to the vehicle's OBD system, permanently adding monitoring data to the vehicle's OBD, thus fundamentally improving the vehicle's self-monitoring capabilities.