The air hybrid engine absorbs the vehicle kinetic energy during braking, stores it in an air tank in the form of compressed air, and reuses it to start the engine and to propel a vehicle during cruising and acceleration. Capturing, storing and reusing this braking energy to achieve stop-start operation and to give additional power can therefore improve fuel economy, particularly in cities and urban areas where the traffic conditions involve many stops and starts. In order to reuse the residual kinetic energy, the vehicle operation consists of 3 basic modes, i.e. Compression Mode (CM), Expander Mode (EM) and normal firing mode, as well as stop-start operation through an air starter. A four-cylinder 2 litre diesel engine has been modelled to operate in four air hybrid engine configurations so that the braking and motoring performance of each configuration could be studied. These air hybrid systems can be constructed with production technologies and incur minimum changes to the existing engine design. The regenerative engine braking and starting capability is realised through the employment of an innovative simple one-way intake system and a production cam profile switching (CPS) mechanism. The hybrid systems will allow the engine to be cranked by the compressed air at moderate pressure without using addition starters or dedicated valves in the cylinder head. Therefore, the proposed air hybrid engine systems can be considered as a cost-effective regenerative hybrid powertrain and can be implemented in vehicles using existing production technologies. A novel cost-effective pneumatic regenerative stop-start hybrid system, Regenerative Engine Braking Device (RegenEBD), for buses and commercial vehicles is presented. RegenEBD is capable of converting kinetic energy into pneumatic energy in the compressed air saved in an air tank using a production engine braking device and other production type automotive components and a proprietary intake system design. The compressed air is then used to drive an air starter to achieve regenerative stop-start operations. The proposed hybrid system can work with the existing vehicle transmission system and can be implemented with the retro-fitted valve actuation device and a sandwich block mounted between the cylinder head and the production intake manifold. Compression mode operation is achieved by keeping the intake valves from fully closed throughout the four-strokes through a production type variable valve exhaust brake (VVEB) device on the intake valves. As a result, the induced air could be compressed through the opening gap of intake valves into the air tank through the intake system of proprietary design. The compressed air can then be used to crank the engine directly through the air expander operation or indirectly through the action of an air starter in production. A single cylinder camless engine has been set up and operated to evaluate the compression mode performance of two air hybrid concepts. The experimental results are then compared with the computational output with excellent agreement. In order to evaluate the potential of the air hybrid engine technologies, a new vehicle driving cycle simulation program has been developed using Matlab Simulink. An air hybrid engine sub-model and methodology for modelling the air hybrid engine’s performance have been proposed and implemented in the vehicle driving cycle simulation. The NEDC analysis of a Ford Mondeo vehicle shows that the vehicle can achieve regenerative stop-start operations throughout the driving cycle when it is powered by a 2.0litre diesel engine with air hybrid operation using a 40litre air tank of less than 10bar pressure. The regenerative stop-start operation can lead to 4.5% fuel saving during the NEDC. Finally, the Millbrook London Transport Bus (MLTB) driving cycle has been used to analyse the effectiveness of RegenEBD on a double deck bus powered by a Yuchai diesel engine. The results show that 90% stop-starts during the MLTB can be accomplished by RegenEBD and that a significant fuel saving of 6.5% can be obtained from the regenerative stop-start operations.

Indiana University-Purdue University Indianapolis (IUPUI) / This thesis proposes an artificial neural network (NN) model to predict fuel consumption in heavy vehicles. The model uses predictors derived from vehicle speed, mass, and road grade. These variables are readily available from telematics devices that are becoming an integral part of connected vehicles. The model predictors are aggregated over a fixed distance traveled (i.e., window) instead of fixed time interval. It was found that 1km windows is most appropriate for the vocations studied in this thesis. Two vocations were studied, refuse and delivery trucks. The proposed NN model was compared to two traditional models. The first is a parametric model similar to one found in the literature. The second is a linear regression model that uses the same features developed for the NN model. The confidence level of the models using these three methods were calculated in order to evaluate the models variances. It was found that the NN models produce lower point-wise error. However, the stability of the models are not as high as regression models. In order to improve the variance of the NN models, an ensemble based on the average of 5-fold models was created. Finally, the confidence level of each model is analyzed in order to understand how much error is expected from each model. The mean training error was used to correct the ensemble predictions for five K-Fold models. The ensemble K-fold model predictions are more reliable than the single NN and has lower confidence interval than both the parametric and regression models.