Comparison of Artificial Neural Network and Fuzzy Logic Approaches for the Prediction of In-Cylinder Pressure in a Spark Ignition Engine

Abstract

In first stage, a machine learning (ML) was performed to predict in-cylinder pressure using both fuzzy logic (FL) and artificial neural networks (ANN) depending on the results of experimental studies in a spark ignition (SI) engine. In the ML phase, the experimental in-cylinder pressure data of SI engine was used. SI engine was operated at stoichiometric air–fuel mixture (φ = 1.0) at 1200, 1400, and 1600 rpm engine speeds. Six different ignition timings, ranging from 15 to 45 °CA, were used for each engine speed. Correlations (R2) between data from in-cylinder pressure obtained via FL and ANN models and data form experimental in-cylinder pressure were determined. R2 values over 0.995 were obtained at an ML stage of ANN model for all test conditions of the engine. However, R2 values were remained between range of 0.820–0.949 with the FL model for different engine speeds and ignition timings. In the second stage, in-cylinder pressure prediction was performed by using an ANN model for engine operating conditions where no experimental results were obtained. Furthermore, indicated mean effective pressure (IMEP) values were calculated by predicting in-cylinder pressure data for different engine operation conditions, and then compared with experimental IMEP values. The results show that the in-cylinder pressure and IMEP results estimated with the trained ANN model are fairly close to the experimental results. Moreover, it was found that using the trained ANN model, the ignition timing corresponding to the maximum brake torque (MBT) used in the engine management systems and engine studies could be determined with high accuracy.

A novel strategy for comprehensive optimization of structural and operational parameters in a supersonic separator using computational fluid dynamics modeling

“…Furthermore, to further investigate the accuracy of the developed CFD model, the root mean square ( R 2 ) was used, which is defined by Eq. (40) 48 , 49 . Figure 5 shows the results of comparison between numerical results and experimental data.…”

Optimisation study of a supersonic separator considering nonequilibrium condensation behaviour

“…To compare the numerical and experimental results, the root-mean-square (R 2 ) is employed to determine the error between them [43][44][45], which is defined in Eq. (7).…”

Steam ejector performance considering phase transition for multi-effect distillation with thermal vapour compression (MED-TVC) desalination system

“…The root-mean-square (R 2 ), which is defined in Eq. ( 7), is used to compare the numerical and experimental errors [44][45][46]. Figure 4 shows the computed and experimental pressure and droplet radius, as well as the relative errors.…”