Off-road machinery is one of the significant contributors to air pollution due to its large quantity. In this study, a deep learning model was developed to predict the transient engine emissions of CO, NO, NO₂, and NO_x, which are the main pollutants emitted by off-road machinery. A portable emission measurement system (PEMS) was used to measure the exhaust emission features of four types of construction machinery. The raw PEMS data were preprocessed using data compensation, local linear regression, and normalization to ensure that the data could handle transient conditions. The proposed model utilizes the preprocessing PEMS data to estimate the CO, NO, NO₂, and NO_x emissions from off-road machinery using a recurrent neural network (RNN) based on a long short-term memory (LSTM) model. The experimental results show that the proposed method can effectively predict the emissions from off-road construction machinery under transient conditions and can be applied to controlling the emissions from off-road construction machinery.

Global warming is directly related to heavy-duty vehicle fuel consumption and greenhouse gas (CO₂ mainly) emissions, which, in China, are certified on the vehicle chassis dynamometer. Currently, vast amounts of vehicle real-road data from the portable emission measurement system (PEMS) and remote monitoring are being collected worldwide. In this study, a binning-reconstruction calculation model is proposed, to predict the chassis dynamometer fuel consumption and CO₂ emissions with real-road data, regardless of operating conditions. The model is validated against chassis dynamometer and PEMS test results, and remote monitoring data. Furthermore, based on the proposed model, the fuel consumption levels of 1408 heavy-duty vehicles in China are analyzed, to evaluate the challenge to meet the upcoming China fourth stage fuel consumption limits. For accumulated fuel consumption based on the on-board diagnostic (OBD) data stream, a predictive relative error less than 5% is expected for the present model. For bag sampling results, the proposed model’s accuracy is expected to be within 10%. The average relative errors between the average fuel consumption and the China fourth stage limits are about 3%, 8%, and 0.7%, for current trucks, tractors, and dump trucks, respectively. The urban operating condition, with lower vehicle speeds, is the main challenge for fuel consumption optimization.

The physicochemical properties of catalysts significantly influence the overall performance of proton exchange membrane fuel cells (PEMFCs). However, the complexity arising from numerous interrelated parameters presents significant challenges in establishing comprehensive structure–performance relationships for advanced PEMFC systems. This study systematically evaluates three commercial Pt/C catalysts with distinct morphology and structural characteristics to reveal their specific functional impacts on fuel cell performance. The results indicate the abundant micropores and small-sized Pt nanoparticles, embedded in micropores, can significantly enhance the catalytic performance at the cathode side. Conversely, hydrogen oxidation reaction (HOR), at the anode side, prefers to occur on the surface-active site of carbon support. Furthermore, an asymmetric membrane electrode assembly configuration incorporating optimized catalysts and gas diffusion layer achieves a maximum power density of 2.52 W cm⁻² (200 kPa absolute pressure with H₂ and O₂ supplying) with good stability, attributed to synergistic improvements in active site utilization and the mass transfer process. This work enhances the fundamental understanding of catalyst microstructure-performance correlations while offering practical insights for Pt/C catalyst selection and electrode architecture design in PEMFC applications.

This paper studied the engine test cycles including world harmonized steady cycle (WHSC), world harmonized transient cycle (WHTC) , china heavy-duty steady cycle (CHSC) and china heavy-duty transient cycle (CHTC) based on a diesel engine which meet the China VI heavy duty vehicle emission standard. The results show that regression analysis of speed, torque and power all meet the requirements of the China VI heavy duty vehicle standard. For this engine, NOx, PM and THC pollutants under CHSC are 134.5%, 29.6% and 94.4% higher than those under WHSC, respectively. PN emissions of CHSC is 65.6% lower than that of WHSC. NOx, PM and PN pollutants under CHTC are 62.9%, 96.4% and 64.3% higher than those under WHTC, respectively. The exhaust temperature of the first 350 seconds at CHTC is lower, which poses a greater challenge to the conversion efficiency of the after-treatment system at low speed and low load.

This work proposes a single regime speed–flow model to fit the speed–flow relationship on the M25, London’s main motorway which is recurrently congested, especially near Heathrow Airport. The proposed model had a better performance compared with the existing classic models. A whole year’s field data on various sites of the M25 motorway were collected by the National Highways MIDAS (Motorway Incident Detection and Automatic Signalling) system and analysed. The proposed model was fitter on both four-lane and lane-by-lane conditions than the existing models, in terms of lower relative error and RMSE values and higher R² values (minimum R² = 0.79), which means the proposed model captured the speed–flow relationship better. In addition, the proposed model was used to fit traffic characteristics under different weather conditions and decided the threshold of the CM algorithms using the Gaussian function. The results showed that both free-flow speed and road capacity were significantly reduced by up to 7% and 11%, respectively, under different rainfall conditions, and that congestion management should be triggered in advance on rainy days. Further analysis of extensive data over a wider space and time is required to test the transferability of these findings to other contexts.