scholarly journals An artificial neural network developed for predicting of performance and emissions of a spark ignition engine fueled with butanol–gasoline blends

2018 ◽  
Vol 10 (1) ◽  
pp. 168781401774843 ◽  
Author(s):  
Zhiqiang Liu ◽  
Qingsong Zuo ◽  
Gang Wu ◽  
Yuelin Li
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Network Model ◽  
Neural Network Model ◽  
Artificial Neural Network Model ◽  
Equivalence Ratio ◽  
Engine Performance ◽  
Spark Ignition Engine ◽  
Performance And Emissions ◽  
Artificial Neural

The engine experiments require multiple tests that are hard, time-consuming, and high cost. Therefore, an artificial neural network model was developed in this study to successfully predict the engine performance and exhaust emissions when a port fuel injection spark ignition engine fueled with n-butanol–gasoline blends (0–60 vol.% n-butanol blended with gasoline referred as G100-B60) under various equivalence ratio. In the artificial neural network model, compression ratio, equivalence ratio, blend percentage, and engine load were used as the input parameters, while engine performance and emissions like brake thermal efficiency, brake-specific fuel consumption, carbon monoxide, unburned hydrocarbons, and nitrogen oxides were used as the output parameters. In comparison between experimental data and predicted results, a correlation coefficient ranging from 0.9929 to 0.9996 and a mean relative error ranging from 0.1943% to 9.9528% were obtained. It is indicated that the developed artificial neural network model was capable of predicting the combustion of n-butanol–gasoline blends due to a commendable accuracy.

Prediction of Efficient Operating Conditions Inside a Heavy-Duty Natural Gas Spark Ignition Engine Using Artificial Neural Networks

2020 ◽  
Author(s):  
Jinlong Liu ◽  
Christopher Ulishney ◽  
Cosmin E. Dumitrescu
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Network Model ◽  
Neural Network Model ◽  
Artificial Neural Network Model ◽  
Fused Silica ◽  
Operating Conditions ◽  
Spark Ignition Engine ◽  
Optical Engine ◽  
Artificial Neural

Abstract Research engines with optical access can assist traditional engine development and optimization by providing first-hand information of in-cylinder combustion process. However, the fragility of the optical engine components (e.g., the see-thru windows are usually made from fused silica) limit the engine operating conditions such as the maximum in-cylinder pressure and pressure rise rate. To make it easier to determine if a particular engine operating condition can be used for optical investigations, a back-propagation artificial neural network model was built to provide the values of pressure-based parameters of interest for engine safety. The training data came from steady-state engine experiments that changed spark timing, mixture equivalence ratio, and engine speed, but using the non-optical configuration of the engine to widen the testing conditions. The comparison between model predictions and experimental data indicated that the well-trained artificial neural network model can provide fast and consistent results, making it an easy-to-use tool for designing future optical engine investigations.

scholarly journals Using Artificial Neural Networks to Predict Influences of Heterogeneity on Rock Strength at Different Strain Rates

Materials ◽  
2021 ◽  
Vol 14 (11) ◽  
pp. 3042
Author(s):  
Sheng Jiang ◽  
Mansour Sharafisafa ◽  
Luming Shen
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Strain Rate ◽  
Network Model ◽  
Neural Network Model ◽  
Artificial Neural Network Model ◽  
Rock Strength ◽  
Strain Rates ◽  
Filling Material ◽  
Artificial Neural

Pre-existing cracks and associated filling materials cause the significant heterogeneity of natural rocks and rock masses. The induced heterogeneity changes the rock properties. This paper targets the gap in the existing literature regarding the adopting of artificial neural network approaches to efficiently and accurately predict the influences of heterogeneity on the strength of 3D-printed rocks at different strain rates. Herein, rock heterogeneity is reflected by different pre-existing crack and filling material configurations, quantitatively defined by the crack number, initial crack orientation with loading axis, crack tip distance, and crack offset distance. The artificial neural network model can be trained, validated, and tested by finite 42 quasi-static and 42 dynamic Brazilian disc experimental tests to establish the relationship between the rock strength and heterogeneous parameters at different strain rates. The artificial neural network architecture, including the hidden layer number and transfer functions, is optimized by the corresponding parametric study. Once trained, the proposed artificial neural network model generates an excellent prediction accuracy for influences of high dimensional heterogeneous parameters and strain rate on rock strength. The sensitivity analysis indicates that strain rate is the most important physical quantity affecting the strength of heterogeneous rock.

Sign in / Sign up

Export Citation Format

Share Document