Analyzing Temperature Distribution, Mass Transport, and Cell Performance in PEM Fuel Cells with Emphasis on GDL Face Permeability and Thermal Contact Resistance Parameters.

Temperature distribution, mass transport, and current density are crucial parameters to characterize the durability and output performance of proton exchange membrane fuel cell (PEMFC), which are affected by thermal contact resistance (TCR) and gas diffusion layer (GDL) face permeability within both cathode and anode GDL porous jumps. This study examined the effects of TCR and GDL face permeability on a single PEM fuel cell's temperature profiles, mass transport, and cell performance using a three-dimensional, nonisothermal computational model with an isotropic gas diffusion layer (GDL). This model calculates the ideal thermal contact resistance by comparing the expected plate-cathode electrode temperature difference to the numerical and experimental literature. The combined artificial neural network-genetic algorithm (ANN-GA) method is also applied to identify the optimum powers and their operating conditions in six cases. Theoretical findings demonstrate that TCR and suitable GDL face permeability must be considered to optimize the temperature distribution and cell efficiency. TCR and GDL face permeability lead to a 1.5 °C rise in maximum cell temperature at 0.4 V, with a "Λ" shape in temperature profiles. The TCR and GDL face permeability also significantly impacts electrode heat and mass transfer. Case 6 had 1.91, 6.58, and 8.72% higher velocity magnitudes, oxygen mass fractions, and cell performances than case 1, respectively. Besides, the combined ANN-GA method is suitable for predicting fuel cell performance and identifying operation parameters for optimum powers. Therefore, the findings can improve PEM fuel cell performance and give a reference for LT-PEMFC design.

NOx emissions prediction in diesel engines: a deep neural network approach.

The reduction of various nitrogen oxide (NOx) emissions from diesel engines is an important environmental issue due to their negative impact on air quality and public health. Selective catalytic reduction (SCR) has emerged as an effective technology to mitigate NOx emissions, but predicting the performance of SCR systems remains a challenge due to the complex chemistry involved. In this study, we propose using DNN models to predict NOx emission reductions in SCR systems. Four types of datasets were created; each consisted of five variables as inputs. We evaluated the models using experimental data collected from a diesel engine equipped with an SCR system. Our results indicated that the deep neural network (DNN) model produces precise estimates for exhaust gas temperature, NOx concentration, and De-NOx efficiency. Moreover, inclusion of additional input features, such as engine speed and temperature, improved the prediction accuracy of the DNN model. The mean absolute error (MAE) values for these parameters were 3.1 °C, 3.04 ppm, and 3.65%, respectively. Furthermore, the R-squared coefficient of determination values for the estimates were 0.912, 0.983, and 0.905, respectively. Overall, this study demonstrates the potential of using DNNs to accurately predict NOx emissions from diesel engines and provides insights into the impact of input features on the performance of the model.

A Study to Predict Ignition Delay of an Engine Using Diesel and Biodiesel Fuel Based on the ANN and SVM Machine Learning Methods.

Over time, machine learning methods have developed, but there have not been many studies comparing how well they predict ignition delays. In this study, a model that forecasts the ignition delay of a diesel engine utilizing diesel fuel and biodiesel fuel was developed using Artificial Neural Network (ANN) and Support Vector Machine (SVM) machine learning techniques. This work has clarified the problems in designing and training the model. The effectiveness of the ANN and SVM machine learning methods' ignition delay prediction models has been evaluated under various input variable conditions. The authors employed a data set of over 700 input data sets from diesel fuel and biodiesel in the B0 to B60 range for this purpose. To evaluate the accuracy of the models, the authors compared the average accuracy of the overall classification as well as the standard deviation. The results after training and verifying the accuracy of the models show that the SVM model has a better ability to predict the fire ignition delay than the ANN model. Specifically, with the test data set and the SVM model at compression ratio (ε) = 15, RMSE = 34.45 µs, MAPE = 1.30%, MAE = 28.33 µs, MAE = 28.33 µs, and R 2 = 0.967, respectively, and the SVM model can predict well. At compression ratio ε = 17, RMSE = 30.18 µs, MAPE = 1.30%, MAE = 23.48 µs, and R 2 = 0.908, respectively. With an ANN neural network model, the prediction error value at compression ratio ε = 15 is RMSE = 41.29 µs, MAPE = 1.35%, MAE = 29.68 µs, and R 2 = 0.952, respectively; at compression ratio ε = 17, it is RMSE = 30.28 µs, MAPE = 1.25%, MAE = 23.00 µs, and R 2 = 0.975, respectively. With this accuracy, the SVM model is fully capable of forecasting the ignition delay combustion time of diesel/biodiesel engines.

Influence of Combustion Duration on the Performance and Emission Characteristics of a Spark-Ignition Engine Fueled with Pure Methanol and Ethanol.

In this research, we estimated and summarized the effects of combustion duration on the performance and emission characteristics of a spark-ignition engine using pure methanol and ethanol as fuels, which have not been previously presented. From the results, we demonstrated that an increase in combustion duration causes a decrease in peak firing temperature and peak firing pressure and an increase in trapped residual gas. The level of trapped residual gas when using ethanol as fuel is higher than that of methanol fuel. The indicated mean effective pressure (IMEP) and brake mean effective pressure (BMEP) increase to maximum values and then decrease with increasing combustion duration, while the brake specific fuel consumption (BSFC) reaches a minimum value and then increases. The optimal BSFC improved to 33.31% when the engine used ethanol fuel instead of methanol. The increase in combustion duration helps to reduce NO x and HC emissions, but an increase in CO emissions is observed.

Dimethyl Ether as the Next Generation Fuel to Control Nitrogen Oxides and Particulate Matter Emissions from Internal Combustion Engines: A Review.

Dimethyl ether (DME) is a new generation fuel produced from natural gas and coal. This fuel can be used directly to a conventional internal combustion (IC) engine without any significant modifications. The main advantage of DME combustion in IC engines is the low NO x and particulate emissions compared with the fossil liquid fuel. Thus, the usage of DME in IC engines is potentially to improve engine efficiency and reduce emissions in the future with minimum attempts. This paper offers a comprehensive review of some topics related to DME as an alternative fuel for IC engines and efforts to increase its utilization to meet high efficiency and low emissions regulations in the future.

The role of black carbon as a catalyst for environmental redox transformation.

Black carbon (BC) is an important class of geosorbents that control the fate and transport of organic pollutants in soil and sediment. We previously demonstrated a new role of BC as an electron transfer mediator in the abiotic reduction of nitroaromatic and nitramine compounds by Oh and Chiu (Environ Sci Technol 43:6983-6988, 2009). We proposed that BC can catalyze the reduction of nitro compounds because it contains microscopic graphitic (graphene) domains, which facilitate both sorption and electron transfer. In this study, we assessed the ability of different types of BC--graphite, activated carbon, and diesel soot--to mediate the reduction of 2,4-dinitrotoluene (DNT) and 2,4-dibromophenol (DBP) by H(2)S. All three types of BC enhanced DNT and DBP reduction. H(2)S supported BC-mediated reduction, as was observed previously with a thiol reductant. The results suggest that BC may influence the fate of organic pollutants in reducing subsurface environments through redox transformation in addition to sorption.