• Energy Research

Abstract Heating, ventilating and air conditioning (HVAC) systems are used in buildings, industry and agriculture to provide thermal and humidity comfort. Modeling of HVAC system can help to design precise controlling systems. In this study, a HVAC system had been modeled using MATLAB simulation software that had been developed using a fuzzy controlling system and radial basis function (RBF) model of artificial neural network (ANN) as a predictive control system. Results of the modeled systems were extracted and compared with actual system. In order to compare results of the modeled and actual systems, comparing parameters, such as mean absolute error (MAE), root mean square error (RMSE), mean absolute percentage/relative error (MAPE) and coefficient of Pearson correlation (r) were applied. The results indicated that, the modeled systems was accurately controlling the system and the difference between real and modeled system was also close. In the results as a whole, the predictive controller (RBF network) has the best performance compared to fuzzy model.

Abstract In this study, a small-scale production of biogas was undertaken using spent mushroom compost (SMC). The carbon to nitrogen (C/N) ratio, temperature of the reactor (T), and retention time (RT) were the independent variables of the study. Maximum production of biogas is related to the C/N ratio of 20 at temperature of 35 °C (cumulative values of 40.5183 ml/g of VS) and C/N ratio of 30 at temperature of 55 °C (cumulative value of 44.1001 ml/g of VS). Logistic, ANFIS, and ANN models were employed in modeling the production process of biogas. Comparing the values of the results indicate that the total values of RMSE and r in case of mesophilic temperature (35 (°C)) for ANFIS network are 0.1940 and 0.9998, for MLP network are 0.780 and 0.9981, and for logistic model are 0.5111 and 0.9992, respectively. And also at the thermophilic temperature (55 (°C)), the total values of RMSE and R were calculated as 0.3033 and 0.9997 for ANFIS network, 0.3430 and 0.9992 for MLP network, and 0.5506 and 0.9991 for the logistic model, respectively. Therefore, it can be reported that the ANFIS network accurately predicted the output values of the both thermophilic and mesophilic situations.

Machine learning (ML) models have been widely used in the modeling, design and prediction in energy systems. During the past two decades, there has been a dramatic increase in the advancement and application of various types of ML models for energy systems. This paper presents the state of the art of ML models used in energy systems along with a novel taxonomy of models and applications. Through a novel methodology, ML models are identified and further classified according to the ML modeling technique, energy type, and application area. Furthermore, a comprehensive review of the literature leads to an assessment and performance evaluation of the ML models and their applications, and a discussion of the major challenges and opportunities for prospective research. This paper further concludes that there is an outstanding rise in the accuracy, robustness, precision and generalization ability of the ML models in energy systems using hybrid ML models. Hybridization is reported to be effective in the advancement of prediction models, particularly for renewable energy systems, e.g., solar energy, wind energy, and biofuels. Moreover, the energy demand prediction using hybrid models of ML have highly contributed to the energy efficiency and therefore energy governance and sustainability.

Diesel fuel (DF) is a significant power supply in agricultural, industrial, and transportation applications. Establishing sustainable and renewable fuel substitutes for diesel has become increasingly common due to the rising expense of petroleum resources and the pollution rate crises. A biodiesel-DF mixture in a dual-fuel (DuF) diesel engine (DE) can bring favorable environmental results. In the present study, three rates of ethanol (0, 2, and 4%), two rates of biodiesel (0 and 5%), and four rates of water (0, 0.3, 0.6, and 0.9%) were blended with DF. All these samples were considered pilot fuel (PF) in the DuF combustion process with an 80% natural gas (NG) replacement percentage. The combustion process was investigated from engine emissions and performance, power cost, and life cycle assessment (LCA) to obtain a sustainable fuel formulation. As a result, water, ethanol, and the combination of water-ethanol and NG can enhance the DE’s performance by rising the inside pressure of the cylinder. The presence of oxygen content in ethanol can improve the combustion process by pushing the combustion towards complete combustion. The optimum engine performance point at full load was obtained with a fuel sample containing 1.57% biodiesel, 4.38% ethanol, 1.1% water, and 80% NG. In optimum condition, the brake power (BP) was 24.16 kW, and the brake-specific fuel consumption (BSFC) was 60.64 g/kWh. This fuel sample produces 0.46, 364.08, 1.66, and 1088.29 g/kWh of BSCO, BSCO2, BSNOx, and BSO2, respectively. At this point, the energy production cost was $0.783/kWh. The environmental impacts of the combustion process at optimal fuel formulation were 0.34249, 1.00 E + 02 , 1.53 E + 00 , and 1.94 E − 06 , respectively, for ecosystem quality (EQ) (PDF ∗ m2 ∗ yr), resources (R) (MJ primary), climate change (CCh) (kg CO2 eq), and human health (HH) (DALY). Accordingly, the best fuel combination was selected to be NG+B1.5E4.3W1.1.

The present study is developed for considering the effect of thermochemical pre-treatment on the biogas production process from kitchen waste. Parameters controlled by the experimental setup include mechanical stirring and temperature. Thermochemical pre-treatment included chemical pre-treatment by 3 and 6% (based on TS) NaOH for 1 h and thermal pre-treatment at 60, 90 and 120 °C for 30 min. The data of the production process were imported to SPSS software using a factorial experiment in a completed randomized design (CRD) and were analyzed by developing the logistic model. Based on the results, the effect of thermochemical pre-treatment was significant at a level of 0.05 and the correlation coefficient of the logistic model, on average was R2 = 0.99. And also, according to the results of the logistic model the delay time ( μ ) in the acidification phase also decreases with the increasing of sodium hydroxide and temperature in the thermochemical pretreatment. For chemical pre-treatment, there was a significant difference in the effect of 3 and 6% of NaOH on biogas production such that increasing the NaOH amount from 3 to 6% (at 120 °C) increased the biogas and methane production as 21.39 and 20.74% respectively. For thermal pre-treatment, increasing the temperature from 60 to 120 °C (in NaOH 6%) increased the biogas and methane production by 13.2 and 11.6%, respectively. The maximum biogas and methane production was related to NaOH 6% and temperature 120 °C (206.16 and 121.42 ml/g VS).

The production of a desired product needs an effective use of the experimental model. The present study proposes an extreme learning machine (ELM) and a support vector machine (SVM) integrated with the response surface methodology (RSM) to solve the complexity in optimization and prediction of the ethyl ester and methyl ester production process. The novel hybrid models of ELM-RSM and ELM-SVM are further used as a case study to estimate the yield of methyl and ethyl esters through a trans-esterification process from waste cooking oil (WCO) based on American Society for Testing and Materials (ASTM) standards. The results of the prediction phase were also compared with artificial neural networks (ANNs) and adaptive neuro-fuzzy inference system (ANFIS), which were recently developed by the second author of this study. Based on the results, an ELM with a correlation coefficient of 0.9815 and 0.9863 for methyl and ethyl esters, respectively, had a high estimation capability compared with that for SVM, ANNs, and ANFIS. Accordingly, the maximum production yield was obtained in the case of using ELM-RSM of 96.86% for ethyl ester at a temperature of 68.48 °C, a catalyst value of 1.15 wt. %, mixing intensity of 650.07 rpm, and an alcohol to oil molar ratio (A/O) of 5.77; for methyl ester, the production yield was 98.46% at a temperature of 67.62 °C, a catalyst value of 1.1 wt. %, mixing intensity of 709.42 rpm, and an A/O of 6.09. Therefore, ELM-RSM increased the production yield by 3.6% for ethyl ester and 3.1% for methyl ester, compared with those for the experimental data.

Abstract Global application of biodiesel in the transport sector has rapidly expanded over the last decade, however, efforts to overcome its main shortcoming, i.e., increase in NOx emissions compared with diesel, are still underway. In light of that, parameters/strategies capable of mitigating biodiesel NOx emissions are of wide interest to further enhance the sustainability aspects of this green fuel. Among various options put to test, the use of fuel additives due to its simplicity and cost-effectiveness has attracted a great deal of attention. In this study, the mechanical shaft work produced by a diesel engine fueled with various diesel/biodiesel blends (B5 and B20) containing glycerol-derived triacetin was scrutinized from environmental viewpoint. Neat petro-diesel, B5, and B20 were also considered as control fuels. Two environmental evaluation methodologies, namely discrete emissions analysis and consolidated life cycle assessment (LCA) were considered to assess the impacts of fuel composition, engine speed, and engine load on the environmental burdens of the shaft work produced. According to the results obtained, the outcomes of both methods considered herein were profoundly affected by engine load and speed. Even though triacetin inclusion into both B5 and B20 profoundly affected the outcomes of emissions analysis, its application did not lead to any spectacular differences in the results of LCA method compared with petro-diesel. More specifically, triacetin incorporation into fuel blends neutralized the unfavorable impacts of biodiesel addition in terms of NOx emissions. However, incorporating triacetin into diesel/biodiesel blends in general did not profoundly mitigate the environmental impacts of the shaft work produced in terms of LCA damage categories as well as the total environmental impacts. Overall, using triacetin as combustion improving agent did appear to be an efficient strategy from the LCA viewpoint considering the current production technologies. In addition, LCA approach was found to be more a comprehensive decision-making approach compared with discrete emissions analysis for evaluating the environmental impacts of the shaft work produced by internal combustion engines.

The conventional machine learning (ML) algorithms are continuously advancing and evolving at a fast-paced by introducing the novel learning algorithms. ML models are continually improving using hybridization and ensemble techniques to empower computation, functionality, robustness, and accuracy aspects of modeling. Currently, numerous hybrid and ensemble ML models have been introduced. However, they have not been surveyed in a comprehensive manner. This paper presents the state of the art of novel ML models and their performance and application domains through a novel taxonomy.