Application of Neural Networks for Prediction and Optimization of Emissions and Performance in a Hydrogen Fuelled Direct Injection Engine Equipped With In Cylinder Water Injection

Gadallah, Aly H.; Elshenawy, Hanaa M.; Elzahaby, Aly M.; El-Salmawy, Hafez; Bawady, Ahmed H.

doi:10.4271/2009-01-2684

Cited by 2 publications

(2 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…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.…”

Section: Introductionmentioning

confidence: 99%

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

Reddy

Samuel

2017

Applied Thermal Engineering

View full text Add to dashboard Cite

Predicting the amount of combustion generated nano-scale particulate matter (PM) emitted by gasoline direct injection (GDI) is a challenging task, but immensely useful for engine calibration engineers in order to meet the stringent emission legislation norms. The present work aimed to link the in-cylinder combustion with engine-out nano-scale PM for the size range of 23.7 to 1000 nm diameter. Neural network with a single hidden layer using first 8 principal components of cylinder pressure was employed for training and predicting the number of nano-scale PM number count. Using a systematic computational approach and comparing its results with experimental data this work demonstrates that machine-learning approach based on neural network is sufficient for predicting engine out nano-scale PM count as a function of engine load and speed.

show abstract

Section: Introductionmentioning

confidence: 99%

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

Reddy

Samuel

2017

Applied Thermal Engineering

View full text Add to dashboard Cite

show abstract

“…The number of neurons in the hidden layer is user defined. The number of hidden layer neurons was iterated for accuracy within this study.Figure 3shows a diagram of the interaction of the three types of layers within the neural network[13].…”

mentioning

confidence: 99%

Investigation of a Neural Network Approach in Modeling and Diagnostics of an Engine-out NOx Sensor

Layhew¹

View full text Add to dashboard Cite

The objective of this study was to develop a method for fault detection of an engine-out oxides of nitrogen (NOx) sensor. The aim of the developed method was not only to isolate a fault with the NOx sensor, but to also diagnose faults in other engine subsystems that may result in higher engine-out NOx production. The developed fault diagnostics are aimed at providing reliable, accurate determinations of sensor output, in-lieu of physical sensors. The data for the development of numerical models in this study was derived from in-use emissions data of a 2014 Freightliner equipped with a 2013 Cummins ISX15 engine. Data included engine control unit (ECU) data from a variety of vehicle operation in southern California that included interstate, highway, regional, local, and near dock locations. For this method of fault detection, a virtual sensor was created using an artificial neural network (ANN) with an input configuration using 12 engine parameters, which provided the most accurate results in this study. These parameters included engine speed, engine torque, fuel rate, intake temperature, boost pressure, exhaust temperature, coolant temperature, oil pressure, the first derivative of engine speed, the first derivative of engine torque, the second derivative of engine speed, and the second derivative of engine torque. The neural network could then be used to predict expected NOx values. The ANN NOx model was trained on a subset of the data and later validated with another subset of the available ECU data. Two different sets of training data, and seven validation data sets were used for prediction evaluation. The study also included the insertion of fault data and run against the model to test for fault detection with the best performing data set. It was found that the network is able to predict NOx within 1-5% at highway operation, when trained with highway data, enabling the detection of NOx sensor faults as well as faults in engine subsystems that were included in the input parameters for the neural network. Three different types of sensor failures, including a step, ramp, and square function failure, were implemented in the validation data, which caused an increase in error between the actual and predicted NOx production to increase between 15-200%, creating the means of detection.

show abstract

Application of Neural Networks for Prediction and Optimization of Emissions and Performance in a Hydrogen Fuelled Direct Injection Engine Equipped With In Cylinder Water Injection

Cited by 2 publications

References 23 publications

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

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

Investigation of a Neural Network Approach in Modeling and Diagnostics of an Engine-out NOx Sensor

Contact Info

Product

Resources

About