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.

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

NOx emissions from diesel vehicles generally deteriorate with increased durability mileage owing to the wear and deterioration of engines and after-treatment systems. Three China-VI heavy-duty diesel vehicles (HDDVs) were selected for four-phase long-term real driving emission (RDE) tests using the portable emission measurement system (PEMS). After 200,000 km of on-road driving, the maximum NOx emission factor of the test vehicles (387.06 mg/kWh) was found to be significantly lower than the NOx limit of 690 mg/kWh. Under all driving conditions, the NOx conversion efficiency of selected catalytic reduction (SCR) decreased almost linearly as the durability mileage increased. Importantly, the deterioration rate of the NOx conversion efficiency in low-temperature intervals was discernibly higher than that in high-temperature intervals. The NOx conversion efficiency at 200 °C dropped by 16.67-19.82% with higher durability mileage; however, the highest values at 275-400 °C only decreased by 4.11%. Interestingly, the SCR catalyst at 250 °C showed strong NOx conversion efficiency and durability (maximum decline of 2.11%). Overall, the poor de-NOx performance of SCR catalysts at low temperatures significantly challenges the long-term effective control of NOx emissions from HDDVs. Thus, improving the NOx conversion efficiency and durability at low-temperature intervals is the top priority for SCR catalyst optimization; NOx emissions from HDDVs at low velocities and loads should also be monitored by environmental authorities. The linear fitting coefficient for the NOx emission factors of the four-phase RDE tests was 0.90-0.92, indicating that NOx emissions deteriorated linearly with an increase in mileage. Based on the linear fitting results, the NOx emission control of the test vehicles during 700,000 km of on-road driving was highly likely to be qualified. These results can be used by environmental authorities to supervise the NOx emission conformity of in-use HDDVs after validation using other types of vehicles.