Search Results

The interest of the vehicle producers in fulfillment emission legislations without adopting after treatment systems is driving to the use of non-conventional energy sources for modern engines. A previous test campaign dealing with the use of blends of diesel and propane in a CI engine has pointed out the potential of this non-conventional fuel for diesel engines. The soft adaptation of the common rail injection system and the potential benefits, in terms of engine performances and pollutant emissions, encourage the use of propane-diesel blends if an optimization of the injection strategies is performed. In this work, the performances of a propane-diesel mixture in a research diesel engine have been investigated. The injection strategies of Euro 5 calibration have been used as reference for the development of optimized strategies. The aim of the optimization process was to ensure the same engine power output and reduce the pollutant emissions.

The management of multiple injections in compression ignition (CI) engines is one of the most common ways to increase engine performance by avoiding hardware modifications and after-treatment systems. Great attention is given to the profile of the injection rate since it controls the fuel delivery in the cylinder. The Injection Rate Shaping (IRS) is a technique that aims to manage the quantity of injected fuel during the injection process via a proper definition of the injection timing (injection duration and dwell time). In particular, it consists in closer and centered injection events and in a split main injection with a very small dwell time. From the experimental point of view, the performance of an IRS strategy has been studied in an optical CI engine. In particular, liquid and vapor phases of the injected fuel have been acquired via visible and infrared imaging, respectively. Injection parameters, like penetration and cone angle have been determined and analyzed.

This study aims at building an efficient and robust radial basis function (RBF) artificial neural network (ANN), to reconstruct the in-cylinder pressure of a diesel engine starting from the signal of a low-cost accelerometer placed on the engine block. The accelerometer is a perfect non-intrusive replacement for expensive probes and is prospectively suitable for production vehicles. The RBF network is trained using measurements from different engine operating conditions. Training data are composed of time series from the accelerometer and corresponding measured in-cylinder pressure signals. The RBF network is then validated using data not included in training and the results show good correspondence between measured and reconstructed pressure signal. Various network parameters are used to optimize the network quality.

This study aims at building efficient and robust artificial neural networks (ANN) able to reconstruct the in-cylinder pressure of Diesel engines and to identify engine conditions starting from the signal of a low-cost accelerometer placed on the engine block. The accelerometer is a perfect non-intrusive replacement for expensive probes and is prospectively suitable for production vehicles. In this view, the artificial neural network is meant to be efficient in terms of response time, i.e. fast enough for on-line use. In addition, robustness is sought in order to provide flexibility in terms of operation parameters. Here we consider a feed-forward neural network based on radial basis functions (RBF) for signal reconstruction, and a feed-forward multi-layer perceptron network with tan-sigmoid transfer function for signal classification. The networks are trained using measurements from a three-cylinder real engine for various operating conditions.