Search Results

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 work reports on the application of spectroscopic measurements coupled with data processing techniques in order to study, in terms of spectral emissions, the dynamic of the HCCI (Homogeneous charge compression ignition) combustion that occurs inside the combustion chamber of an optically accessible direct injection Diesel engine. A pre-processing of the recorded spectra is required for a correct analysis. The procedure of pre-processing consists of two main steps, that is: noise filtering with a technique based on the POD (Proper Orthogonal Decomposition); estimate and subtraction of the baseline. The analysis of the dynamics of the recorded spectra was carried out by the estimates of the synchronous and asynchronous 2D correlation spectra.

Flame luminosity fields can nowadays be collected from optically accessible engines, with high spatial and temporal resolution, and constitute a very powerful investigation means for the transient combustion phenomena taking place in the engine chamber. Interpretation of the impressive amount of collected data can be quite challenging, mainly due to the variety of coupled phenomena involved. Application of Independent Component Analysis (ICA) aims here at separating spatial structures related to different combustion events, and is coupled with the analysis of the statistics of the coefficients of the independent components, and of the measured in-cylinder parameters. This paper reports on the comparison of the application of ICA to 2D images of combustion-related luminosity collected from two different optically accessible engines: Diesel and spark ignition.

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.