Estimating pressure peak position and air-fuel ratio using the ionization current and artificial neural networks

Effects of engine parameters on ionization current and modeling of excess air coefficient by artificial neural network

“…The effects of the equivalence ratio, engine load, engine coolant temperature, and engine speed on the ionization current signal were investigated by Huang et al It was shown that the ionization current signal could be used with ANNs for the prediction of the equivalence ratio [5]. The estimation of the peak pressure position and AFR using the ionization current and ANNs was investigated by Wickstr€ om et al According to the results of this study, the estimation performance of the peak pressure position with ANN was two times better than a linear model and the estimation performance of the AFR with the ANN was 10 times better than the linear model [6]. The estimation of the AFR using the ionization current and neural networks was studied by Hellring et al For estimation with an un-normalized ionization current, a network with two hidden layer consisting of 20 neurons was selected and for a normalized ionization current, a network with two hidden layers with 10 neurons was selected.…”

A transient virtual-AFR sensor using the in-cylinder ion current signal

“…Using principal component analysis (PCA) on this window of the ion current signal between 101 and 451 after ignition can give inputs for a neural network (NN) that can predict averaged values of the AFR [13]. Further work using this methodology has seen the inputs to the NN increase in number to include engine speed (N), manifold absolute air pressure (MAP) and spark advance (SA) along with the PCA scores to predict AFR [14].…”

“…This use of NNs for AFR prediction has now been extensively researched [15,13,16,12,6,17]. Networks sizes and complexities have been determined through trial and error and estimation errors as low as 2% for 90% of test transients have been achieved [18].…”

Machine learning for nano-scale particulate matter distribution from gasoline direct injection engine

“…Their model was capable of predicting particle distribution with the absolute square mean error of 3-7%. Ample evidence could be found in the literature in relation to application of neural network for predicting the behaviours of diesel particulate filter [37], NOx and soot emissions in diesel engine [38], prediction of emission levels using cylinder pressure [39][40][41] from diesel engines, cylinder pressure, NOx and CO 2 from gasoline engine [42] and neural network for CI and SI engines for predicting mainly emissions [36][37][38][39][40][41][42][43][44][45][46][47][48][49][50]. This is not an exhaustive list but a few very studies relevant to current work.…”