Multi-objective optimization of the Atkinson cycle gasoline engine using NSGA Ⅲ coupled with support vector machine and back-propagation algorithm

Li, Yangyang; Shi, Zhou; Liu, Jingping; Tong, Ji Jun; Dang, Jian; Li, Fuyuan Yang; Ouyang, Minggao

doi:10.1016/j.energy.2022.125262

Cited by 26 publications

(11 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The results suggested that the ANN exhibits a significant degree of prediction accuracy. Li et al 42 proposed an approach that combines NSGA-III and SVM techniques for the optimization of the Atkinson cycle gasoline engine. The integration successfully tackled the problem and yielded a substantial reduction in time expenditure.…”

Section: Introductionmentioning

confidence: 99%

A Deep Learning Hybrid Framework Combining an Efficient Evolutionary Algorithm for Complex Many-Objective Optimization of Sustainable Triple CO₂ Feed Methanol Production

Cao,

Li,

Chang

et al. 2024

ACS Sustainable Chem. Eng.

View full text Add to dashboard Cite

Current mainstream technologies have exhibited limits in integrating global many-objective optimization methods with chemical production systems, resulting in subpar outcomes in terms of energy efficiency and environmental issues for methanol production systems. In this study, a novel deep learning hybrid framework is proposed, which involves the construction of a mechanism model with the ability to elucidate the underlying principles and interrelationships of chemistry on a macroscopic scale and a data-driven model to enhance the accuracy and dependability of predictions from available data. The efficiency and global search capability of the proposed framework are further improved through the integration of an advanced evolutionary algorithm, which incorporates many-criteria decision-making technology to provide a comprehensive set of trade-offs for the optimal solution sets. The results demonstrate that all four objective functions of carbon dioxide emissions, methane conversion rate, methanol production, and energy consumption in the triple CO 2 feed methanol production system are rapidly optimized, in which carbon dioxide emissions and energy consumption are reduced by 18.50% and 3.15%, respectively. Consequently, this considerably enhances the environment. This proposed framework holds significant potential in facilitating the efficient optimization and sustainable production of complex systems within process engineering.

show abstract

Section: Introductionmentioning

confidence: 99%

A Deep Learning Hybrid Framework Combining an Efficient Evolutionary Algorithm for Complex Many-Objective Optimization of Sustainable Triple CO₂ Feed Methanol Production

Cao,

Li,

Chang

et al. 2024

ACS Sustainable Chem. Eng.

View full text Add to dashboard Cite

show abstract

“…In this work, a secondorder response surface methodology (RSM) model is proposed to fit the radial flow path and spool region density of the radial MR valve using orthogonal experiments and response surface analysis, and the accuracy of the response surface function is also estimated for the entire design development. Finally, a geometric optimization problem was formulated for the constructed RSM using a genetic algorithm to find the global optimal geometric parameters of the radial MR valve, and the correctness of the algorithm and the effectiveness of the optimized design were effectively verified by experiments (Li et al, 2023b). Conducting experiments according to an orthogonal design method allows effective comparison of preselected parameters to determine their degree of influence on the experimental results.…”

Section: Introductionmentioning

confidence: 99%

The combustion and emission improvements for diesel–biodiesel hybrid engines based on response surface methodology

Zhong

Zhang

et al. 2023

Front. Energy Res.

View full text Add to dashboard Cite

With the rapid technological progress of society and increasingly stringent environmental regulations, further reduction of emissions has become an important issue for environmental protection. This study developed a response surface model with the biodiesel blending ratio (BBR), load, and exhaust gas recirculation (EGR) as independent variables and brake thermal efficiency (BTE), brake specific fuel consumption (BSFC), and NOx, and CO emission rates as dependent variables. Simulations were performed and calculated. The results of the response surface approach with the objectives of maximizing the BTE of the engine and minimizing BSFC, NOx emissions, and CO emissions show that when the BBR is 20%, the EGR rate is 15%, and the engine load is 74.52%, pollutant emissions are significantly reduced while the engine power’s performance is maximized.

show abstract

“…Finally, researchers used less data in the past and lacked a comparison of the impact of different input states on model predictions. 35 Based on the abovementioned limitations, this study considers engine speed, torque, NG substitution rate (NGSR), diesel injection pressure (DIP), and diesel injection timing (DIT) as input parameters of the model and heat release (CA50), brake-specific fuel consumption (BSFC), brake thermal efficiency (BTE), CO, CO 2 , total unburned hydrocarbon (THC), NO x , and soot as output parameters of the model. Subsequently, a coupled Gaussian process regression and feedback neural network (GPR-FNN) prediction model was built based on a six-cylinder heavy-duty diesel/NG dual-fuel engine to predict the performance and emission characteristics of the engine.…”

Section: Introductionmentioning

confidence: 99%

“…Second, the current modeling methods are mainly applied to light single cylinder engines, with relatively few applications in heavy dual fuel engines and even less in multicylinder heavy diesel/NG dual fuel engines. Finally, researchers used less data in the past and lacked a comparison of the impact of different input states on model predictions …”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Prediction and Verification of Performance and Emission Characteristics of Diesel/Natural Gas Dual-Fuel Engine Based on Intelligent Algorithm

Wan

Huang

et al. 2023

ACS Omega

View full text Add to dashboard Cite

With the development of computer application technologies, intelligent algorithm has been widely used in various fields. In this study, a coupled Gaussian process regression and feedback neural network (GPR-FNN) algorithm is proposed, and it is used to predict the performance and emission characteristics of a six-cylinder heavy-duty diesel/natural gas (NG) dual-fuel engine. Using the engine speed, torque, NG substitution rate, diesel injection pressure, and injection timing as inputs, an GPR-FNN model is established to predict the crank angle corresponding to 50% heat release, brake-specific fuel consumption, brake thermal efficiency, and carbon monoxide, carbon dioxide, total unburned hydrocarbon, nitrogen oxides, and soot emissions. Subsequently, its performance is evaluated using experimental results. The results show that the regression correlation coefficients of all output parameters are greater than 0.99, and the mean absolute percentage error is less than 5.9%. In addition, a contour plot is used to compare the experimental results with the GPR-FNN prediction data in detail, and the results show that the prediction model has high accuracy. The results of this study can provide new ideas for the research on diesel/natural gas dual-fuel engines.

show abstract

Multi-objective optimization of the Atkinson cycle gasoline engine using NSGA Ⅲ coupled with support vector machine and back-propagation algorithm

Cited by 26 publications

References 30 publications

A Deep Learning Hybrid Framework Combining an Efficient Evolutionary Algorithm for Complex Many-Objective Optimization of Sustainable Triple CO₂ Feed Methanol Production

A Deep Learning Hybrid Framework Combining an Efficient Evolutionary Algorithm for Complex Many-Objective Optimization of Sustainable Triple CO₂ Feed Methanol Production

The combustion and emission improvements for diesel–biodiesel hybrid engines based on response surface methodology

Prediction and Verification of Performance and Emission Characteristics of Diesel/Natural Gas Dual-Fuel Engine Based on Intelligent Algorithm

Contact Info

Product

Resources

About

Multi-objective optimization of the Atkinson cycle gasoline engine using NSGA Ⅲ coupled with support vector machine and back-propagation algorithm

Cited by 26 publications

References 30 publications

A Deep Learning Hybrid Framework Combining an Efficient Evolutionary Algorithm for Complex Many-Objective Optimization of Sustainable Triple CO2 Feed Methanol Production

A Deep Learning Hybrid Framework Combining an Efficient Evolutionary Algorithm for Complex Many-Objective Optimization of Sustainable Triple CO2 Feed Methanol Production

The combustion and emission improvements for diesel–biodiesel hybrid engines based on response surface methodology

Prediction and Verification of Performance and Emission Characteristics of Diesel/Natural Gas Dual-Fuel Engine Based on Intelligent Algorithm

Contact Info

Product

Resources

About

A Deep Learning Hybrid Framework Combining an Efficient Evolutionary Algorithm for Complex Many-Objective Optimization of Sustainable Triple CO₂ Feed Methanol Production

A Deep Learning Hybrid Framework Combining an Efficient Evolutionary Algorithm for Complex Many-Objective Optimization of Sustainable Triple CO₂ Feed Methanol Production