Modelling of instantaneous emissions from diesel vehicles with a special focus on NOx: Insights from machine learning techniques

Perspectives on NO X Emissions and Impacts from Ammonia Combustion Processes

Climate change and global warming necessitate the shift toward low-emission, carbon-free fuels. Although hydrogen boasts zero carbon content and high performance, its utilization is impeded by the complexities and costs involved in liquefaction, preservation, and transportation. Ammonia has emerged as a viable alternative that offers potential as a renewable energy storage medium and supports the global economy's decarbonization. With its broader applicability in large power output applications, decentralized energy sources, and industrial locations off the grid, ammonia is increasingly regarded as an essential fuel for the future. Although ammonia provides a sustainable solution for future low-carbon energy fields, its wide-scale adoption is limited by NO X emissions and poor combustion performance under certain conditions. As research on ammonia combustion expands, recent findings reveal factors impacting the chemical reaction pathways of ammonia-based fuels, including the equivalence ratio, fuel mixture, pressure, and temperature. Investigations into ammonia combustion and NO X emissions, at both laboratory and industrial scales, have identified NO X production peaks at equivalence ratios of 0.8-0.9 for ammonia/hydrogen blends. The latest studies about the NO X emissions of the ammonia flame at different conditions and their generating pathways are reviewed in this work. Effective reduction in NO production from ammonia-based flames can be achieved with richer blends, which generate more NH i radicals. Other advanced NO X mitigation techniques such as plasma-assisted combustion have been also explored. Further research is required to address these challenges, reduce emissions, and improve efficiencies of ammonia-based fuel blends. Finally, the extinction limit of ammonia turbulent flame, its influential factors, and different strategies to promote the ammonia flame stability were discussed. The present review contributes to disseminating the latest advancements in the field of ammonia combustion and highlights the importance of refining reaction mechanisms, computational models, and understanding fundamental phenomena for practical implications.

Forecasting CO2 emissions of fuel vehicles for an ecological world using ensemble learning, machine learning, and deep learning models

Background

The continuous increase in carbon dioxide (CO2) emissions from fuel vehicles generates a greenhouse effect in the atmosphere, which has a negative impact on global warming and climate change and raises serious concerns about environmental sustainability. Therefore, research on estimating and reducing vehicle CO2 emissions is crucial in promoting environmental sustainability and reducing greenhouse gas emissions in the atmosphere.

Methods

This study performed a comparative regression analysis using 18 different regression algorithms based on machine learning, ensemble learning, and deep learning paradigms to evaluate and predict CO2 emissions from fuel vehicles. The performance of each algorithm was evaluated using metrics including R2, Adjusted R2, root mean square error (RMSE), and runtime.

Results

The findings revealed that ensemble learning methods have higher prediction accuracy and lower error rates. Ensemble learning algorithms that included Extreme Gradient Boosting (XGB), Random Forest, and Light Gradient-Boosting Machine (LGBM) demonstrated high R2 and low RMSE values. As a result, these ensemble learning-based algorithms were discovered to be the most effective methods of predicting CO2 emissions. Although deep learning models with complex structures, such as the convolutional neural network (CNN), deep neural network (DNN) and gated recurrent unit (GRU), achieved high R2 values, it was discovered that they take longer to train and require more computational resources. The methodology and findings of our research provide a number of important implications for the different stakeholders striving for environmental sustainability and an ecological world.

Instantaneous CO2 emission modelling for a Euro 6 start-stop vehicle based on portable emission measurement system data and artificial intelligence methods

One of the increasingly common methods to counteract the increased fuel consumption of vehicles is start-stop technology. This paper introduces a methodology which presents the process of measuring and creating a computational model of CO2 emissions using artificial intelligence techniques for a vehicle equipped with start-stop technology. The method requires only measurement data of velocity, acceleration of vehicle, and gradient of road to predict the emission of CO2. In this paper, three methods of machine learning techniques were analyzed, while the best prediction results are shown by the gradient boosting method. For the developed models, the results were validated using the coefficient of determination, the mean squared error, and based on visual evaluation of residual and instantaneous emission plots and CO2 emission maps. The developed models present a novel methodology and can be used for microscale environmental analysis.

Do we need high temporal resolution modelling of exposure in urban areas? A test case

Roadside concentrations of harmful pollutants such as NOx are highly variable in both space and time. This is rarely considered when assessing pedestrian and cyclist exposures. We aim to fully describe the spatio-temporal variability of exposures of pedestrians and cyclists travelling along a road at high resolution. We evaluate the value added of high spatio-temporal resolution compared to high spatial resolution only. We also compare high resolution vehicle emissions modelling to using a constant volume source. We highlight conditions of peak exposures, and discuss implications for health impact assessments. Using the large eddy simulation code Fluidity we simulate NOx concentrations at a resolution of 2 m and 1 s along a 350 m road segment in a complex real-world street geometry including an intersection and bus stops. We then simulate pedestrian and cyclist journeys for different routes and departure times. For the high spatio-temporal method, the standard deviation in 1 s concentration experienced by pedestrians (50.9 μg.m-3) is nearly three times greater than that predicted by the high-spatial only (17.5 μg.m-3) or constant volume source (17.6 μg.m-3) methods. This exposure is characterised by low concentrations punctuated by short duration, peak exposures which elevate the mean exposure and are not captured by the other two methods. We also find that the mean exposure of cyclists on the road (31.8 μg.m-3) is significantly greater than that of cyclists on a roadside path (25.6 μg.m-3) and that of pedestrians on a sidewalk (17.6 μg.m-3). We conclude that ignoring high resolution temporal air pollution variability experienced at the breathing time scale can lead to a mischaracterization of pedestrian and cyclist exposures, and therefore also potentially the harm caused. High resolution methods reveal that peaks, and hence mean exposures, can be meaningfully reduced by avoiding hyper-local hotspots such as bus stops and junctions.

Automated Estimation of Construction Equipment Emission Using Inertial Sensors and Machine Learning Models

The construction industry is one of the main producers of greenhouse gasses (GHG). With the looming consequences of climate change, sustainability measures including quantifying the amount of air pollution during a construction project have become an important project objective in the construction industry. A major contributor to air pollution during construction projects is the use of heavy equipment. Therefore, efficient operation and management can substantially reduce a project’s carbon footprint and other environmental harms. Using unintrusive and indirect methods to predict on-road vehicle emissions has been a widely researched topic. Nevertheless, the same is not true in the case of construction equipment. This paper describes the development and deployment of a framework that uses machine learning (ML) methods to predict the level of emissions from heavy construction equipment. Data is collected via an Internet of Things (IoT) approach with accelerometer and gyroscope sensors as data collection nodes. The developed framework was validated using an excavator performing real-world construction work. A portable emission measurement system (PEMS) was used along with the inertial sensors to record the amount of CO, NOX, CO2, SO2, and CH4 pollution emitted by the equipment. Different ML algorithms were developed and compared to identify the best model to predict emission levels from inertial sensors data. The results show that Random Forest with the coefficient of determination (R2) of 0.94, 0.91, and 0.94, and normalized root-mean-square error (NRMSE) of 4.25, 6.42, and 5.17 for CO, NOX, and CO2, respectively, was the best algorithm among different models evaluated in this study.

Development of a cold-start emission model for diesel vehicles using an artificial neural network trained with real-world driving data

During the cold start and warm-up phase, modern vehicles emit considerable amounts of pollutants due to the incomplete combustion and deteriorated performance of aftertreatment devices. In terms of emission modeling, there have been many attempts to estimate cold start emission such as cold-hot conversion factor, regression model, and physis-based model. However, as the emission characteristic become complicated due to the adoption of aftertreatment devices and various emission control strategies for the strengthened emission regulations, the conventional cold start emission models do not always show satisfactory performances. In this study, artificial neural networks were used to predict the cold start emissions of carbon dioxide, nitrogen oxides, carbon monoxide, and total hydrocarbon of diesel passenger vehicles. We used real-world driving data to train neural networks as an emission prediction tool. Through machine leaning, numerous trainable variables of neural networks were properly adjusted to predict cold start emissions. For input variables of the ANN model, the velocity, vehicle specific power, engine speed, engine torque, and engine coolant temperature were used. The proposed ANN models accurately predicted sharp increases in carbon monoxide, hydrocarbon, and nitrogen oxides during the cold start phase. In addition to the quantitative estimations, the correlations between the operating variables and exhaust gas emissions were visually described in the form of emission maps. The emission map graphically showed the emission levels according to the vehicle and engine operating parameters.

Analysis and Prediction Model of Fuel Consumption and Carbon Dioxide Emissions of Light-Duty Vehicles

Due to the alarming rate of climate change, fuel consumption and emission estimates are critical in determining the effects of materials and stringent emission control strategies. In this research, an analytical and predictive study has been conducted using the Government of Canada dataset, containing 4973 light-duty vehicles observed from 2017 to 2021, delivering a comparative view of different brands and vehicle models by their fuel consumption and carbon dioxide emissions. Based on the findings of the statistical data analysis, this study makes evidence-based recommendations to both vehicle users and producers to reduce their environmental impacts. Additionally, Convolutional Neural Networks (CNN) and various regression models have been built to estimate fuel consumption and carbon dioxide emissions for future vehicle designs. This study reveals that the Univariate Polynomial Regression model is the best model for predictions from one vehicle feature input, with up to 98.6% accuracy. Multiple Linear Regression and Multivariate Polynomial Regression are good models for predictions from multiple vehicle feature inputs, with approximately 75% accuracy. Convolutional Neural Network is also a promising method for prediction because of its stable and high accuracy of around 70%. The results contribute to the quantifying process of energy cost and air pollution caused by transportation, followed by proposing relevant recommendations for both vehicle users and producers. Future research should aim towards developing higher performance models and larger datasets for building APIs and applications.

Super-learner model realizes the transient prediction of CO2 and NOx of diesel trucks: Model development, evaluation and interpretation

The transient simulation of CO₂ and NO_X from motor vehicles has essential applications in evaluating vehicular greenhouse gas emissions and pollutant emissions. However, accurately estimating vehicular transient emissions is challenging due to the heterogeneity between different vehicles and the continuous upgrading of vehicle exhaust purification technology. To accurately characterize the transient emissions of motor vehicles, a Super-learner model is used to build CO₂ and NOx transient emission models. The actual onboard test data of 9 China VI N₂ vehicles were used to train the model, and the test data of another China VI N₂ vehicle were selected for further robustness verification. There were significant differences in the emissions between the vehicles, but the constructed transient model could capture the common law of transient emissions from China VI N₂ vehicles. The R² values of CO₂ and NOx emission in the test data of the validation vehicle were 0.71 and 0.82, respectively. In addition, to further prove the model's robustness, the training data were synchronously modelled based on the Moves-method. The Super-learner model has a smaller RMSE on the validation set than the model based on the Moves-method, indicating that the Super-learner model has more transient simulation advantages. The marginal contributions of the model characteristics to the model results were analysed by SHapley Additive exPlanation (SHAP) value interpretation, and the marginal contributions of different pollutant characteristic parameters varied. Therefore, when establishing transient models of different pollutants, the selection of the model parameters demands considering the generation and purification process of different pollutants. The present work provides novel insights into the parameter selection, construction, and interpretation of the transient vehicle emission model.

Hybrid Machine Learning Approaches and a Systematic Model Selection Process for Predicting Soot Emissions in Compression Ignition Engines

The standards for emissions from diesel engines are becoming more stringent and accurate emission modeling is crucial in order to control the engine to meet these standards. Soot emissions are formed through a complex process and are challenging to model. A comprehensive analysis of diesel engine soot emissions modeling for control applications is presented in this paper. Physical, black-box, and gray-box models are developed for soot emissions prediction. Additionally, different feature sets based on the least absolute shrinkage and selection operator (LASSO) feature selection method and physical knowledge are examined to develop computationally efficient soot models with good precision. The physical model is a virtual engine modeled in GT-Power software that is parameterized using a portion of experimental data. Different machine learning methods, including Regression Tree (RT), Ensemble of Regression Trees (ERT), Support Vector Machines (SVM), Gaussian Process Regression (GPR), Artificial Neural Network (ANN), and Bayesian Neural Network (BNN) are used to develop the black-box models. The gray-box models include a combination of the physical and black-box models. A total of five feature sets and eight different machine learning methods are tested. An analysis of the accuracy, training time and test time of the models is performed using the K-means clustering algorithm. It provides a systematic way for categorizing the feature sets and methods based on their performance and selecting the best method for a specific application. According to the analysis, the black-box model consisting of GPR and feature selection by LASSO shows the best performance with test R2 of 0.96. The best gray-box model consists of SVM-based method with physical insight feature set along with LASSO for feature selection with test R2 of 0.97.

Prediction of instantaneous real-world emissions from diesel light-duty vehicles based on an integrated artificial neural network and vehicle dynamics model

This paper presents a road vehicle emission model that integrates an artificial neural network (ANN) model with a vehicle dynamics model to predict the instantaneous carbon dioxide (CO₂), nitrogen oxides (NOx) and total hydrocarbon (THC) emissions of diesel light-duty vehicles. Real-world measurement data were used to train a multi-layer feed-forward ANN model. The optimal combination of the various experimental variables was selected as the ANN input through a parametric study considering both practicality and accuracy. For CO₂ prediction, two variables (engine speed and engine torque) are enough to develop an accurate ANN model. In order to achieve satisfactory accuracy for CO and NOx prediction, more variables were used for ANN training. The trained ANN model was used to predict road vehicle emissions by integrating the vehicle dynamics model, which was used as a supplementary tool to produce ANN input data. The integrated model is practical because it requires relatively simple data for input such as vehicle specifications, velocity, and road gradient. In the accuracy validation, the proposed model showed satisfactory prediction accuracy for road vehicle emissions.