Search Results

The paper focuses on the experimental identification and validation of recurrent neural networks (RNN) for virtual sensing of NO emissions in internal combustion engines (ICE). Suited training procedures and experimental tests are proposed to improve RNN precision and generalization in predicting NO formation dynamics. The reference Spark Ignition (SI) engine was tested by means of an integrated system of hardware and software tools for engine test automation and control strategies prototyping. A fast response analyzer was used to measure NO emissions at the exhaust valve. The accuracy of the developed RNN model is assessed by comparing simulated and experimental trajectories for a wide range of operating scenarios. The results evidence that RNN-based virtual NO sensor will offer significant opportunities for implementing on-board feedforward and feedback control strategies aimed at improving the performance of after-treatment devices.

The paper focuses on the experimental identification and validation of recurrent neural networks (RNN) for real-time prediction and control of air-fuel ratio (AFR) in spark-ignited engines. Suited training procedures and experimental tests are proposed to improve RNN precision and generalization in predicting both forward and inverse AFR dynamics for a wide range of operating scenarios. The reference engine has been tested by means of an integrated system of hardware and software tools for engine test automation and control strategies prototyping. The comparison between RNNs simulation and experimental trajectories showed the high accuracy and generalization capabilities guaranteed by RNNs in reproducing forward and inverse AFR dynamics. Then, a fast and easy-to-handle procedure was set-up to verify the potentialities of the inverse RNN to perform feed-forward control of AFR.

In the last few years, concern about the environmental impact of vehicles has increased, considering the growth of the dangerous effects on health of noxious exhaust emissions. For this reason, car manufacturers are moving towards more efficient combustion systems for Spark Ignition (SI) engines, aiming to comply with the increasingly stringent regulation imposed by EU and other legislators. Engine operation with very lean air/fuel ratios has demonstrated to be a viable solution to this problem. Stable ultra-lean combustion can be obtained with a Pre-Chamber (PC) ignition system, installed in place of the conventional spark plug. The efficiency of this configuration in terms of performance and emissions is due to its combustion process, that starts in the PC and propagates in the main chamber in the form of multiple hot turbulent jets.

The paper deals with the use of Recurrent Neural Networks (RNNs) for the Air-Fuel Ratio (AFR) control in Spark Ignition (SI) engines. Because of their features, Neural Networks can perform an adaptive control more efficiently than classical techniques. In the paper, a review of the most useful control schemes based on Neural Networks is presented and the potential use in the field of engine control is analyzed. A preliminary controller has been implemented making use of a Direct Inverse Modeling approach. The controller compensates for the wall wetting dynamics and estimates the right amount of fuel to be injected to meet the target AFR during engine transients. The Direct Inverse Controller has been tested within an engine/vehicle simulator. The simulation tests have been performed by imposing a set of throttle transients at different engine speeds. The results show that the Inverse Model can satisfactorily bound the AFR excursions around the target value.

The development of more affordable sensors together with the enhancement of computation features in current Engine Management Systems (EMS), makes the in-cylinder pressure sensing a suitable methodology for the on-board engine control and diagnosis. Since the 1960’s the in-cylinder pressure signal was employed to investigate the combustion process of the internal combustion engines for research purposes. Currently, the sensors cost reduction in addition to the need to comply with the strict emissions legislation has promoted a large-scale diffusion on production engines equipment. The in-cylinder pressure signal offers the opportunity to estimate with high dynamic response almost all the variables of interest for an effective engine combustion control even in case of non-conventional combustion processes (e.g. PCCI, HCCI, LTC).

The paper addresses the potentialities of Recurrent Neural Networks (RNN) for modeling and controlling Air-Fuel Ratio (AFR) excursions in Spark Ignited (SI) engines. Based on the indications provided by previous studies devoted to the definition of optimal training procedures, an RNN forward model has been identified and tested on a real system. The experiments have been conducted by altering the mapped injection time randomly, thus making the effect of fuel injection on AFR dynamics independent of the other operating variables, namely manifold pressure and engine speed. The reference engine has been tested by means of an integrated system of hardware and software tools for engine test automation and control strategies prototyping. The developed forward model has been used to generate a reference AFR signal to train another RNN model aimed at simulating the inverse AFR dynamics by evaluating the fuel injection time as function of AFR, manifold pressure and engine speed.

The computer code ODECS (Optimal Design of Engine Control Strategies) for the design of Spark Ignition engine control strategies is presented. This code has been developed starting from the author's activity in this field, availing of some original contributions about engine stochastic optimization and dynamical models. This code has a modular structure and is composed of a user interface for the definition, the execution and the analysis of different computations performed with 4 independent modules. These modules allow the following calculations: (i) definition of the engine mathematical model from steady-state experimental data; (ii) engine cycle test trajectory corresponding, to a vehicle transient simulation test such as ECE15 or FTP drive test schedule; (iii) evaluation of the optimal engine control maps with a steady-state approach.

In the last decades, NOx emissions legislations for Diesel engines are becoming more stringent than ever before and the selective catalytic reduction (SCR) is considered as the most suitable technology to comply with the upcoming constraints. Model-based control strategies are promising to meet the dual objective of maximizing NOx reduction and minimizing NH3 slip in urea-selective catalytic reduction. In this paper, a control oriented model of a Cu-zeolite urea-SCR system for automotive diesel engines is presented. The model is derived from a quasi-dimensional four-state model of the urea-SCR plant. To make it suitable for the real-time urea-SCR management, a reduced order one-state model has been developed, with the aim of capturing the essential behavior of the system with a low computational burden. Particularly, the model allows estimating the NH3 slip that is fundamental not only to minimize urea consumption but also to reduce this unregulated emission.

The wall-flow Diesel Particulate Filter (DPF) is currently the most common after-treatment system used to meet the particulate emission limits imposed by government regulations. Today’s technology shows the best balance between filtration efficiency and back-pressure in the engine exhaust pipe. Conventional filters consist in alternately plugged parallel square channels, so that the exhaust gases flow through the porous inner walls leading to particles trapping. During the accumulation phase the pressure drop across the filter increases, thus requiring periodic regeneration of the DPF through after and post fuel injection strategies. This paper deals with the experimental testing of a catalytic silicon carbide (SiC) wall flow DPFs with CuFe2O4 loading. The filter was built following an optimized procedure based on a preliminary controlled chemical erosion of the SiC porous structure.

1 The Selective Catalytic reduction (SCR) using urea as reducing agent is currently regarded as the most promising after-treatment technology in order to comply with strict RDE targets for NOX and particulate in Diesel application. Model-based control strategies are promising to satisfy the demands of high NOX conversion efficiency and low tailpipe ammonia slip. This paper deals with the development of a control oriented model of a Cu-zeolite urea-SCR system for automotive Diesel engines. The model is intended to be used for the real-time urea-SCR management, depending on engine NOX emissions and ammonia storage. In order to ensure suitable computational demand for the on-board implementation, a reduced order one-state model of ammonia storage has been derived from a quasi-dimensional four-state model of the urea-SCR plant.

Diesel engines are attractive thanks to good performance in terms of fuel consumption, drivability, power output and efficiency. Nevertheless in the last years, increasing restrictions have been imposed to particulate emissions, concerning both mass (PM) and number (PN). Different technologies have been proposed to meet emissions standards and the wall-flow Diesel Particulate Filter (DPF) is currently the most common after-treatment system used to trap PM from the exhaust gases. This technology exhibits good features such that it can be regenerated to remove any accumulation of PM. However, this process involves oxidation of the filtered PM at a high temperature through after and post fuel injection strategies, which results in an increase of fuel consumption and may lead to physical damages of the filter in the long term. This work deals with the experimental testing of a catalytic silicon carbide (SiC) wall flow DPF, aiming at decreasing the soot oxidation temperature.

1 The wall-flow Diesel Particulate Filter (DPF) is currently the most common after-treatment system used to meet the particulate emissions regulations for automotive engines. Today’s technology shows the best balance between filtration efficiency and back-pressure in the engine exhaust pipe. During the accumulation phase the pressure drop across the filter increases, thus requiring periodic regeneration of the DPF through after and post fuel injection strategies. This paper deals with the development of a control oriented model of a catalytic silicon carbide (SiC) wall flow DPFs with CuFe2O4 loading for automotive Diesel engines. The model is intended to be used for the real-time management of the regeneration process, depending on back-pressure and thermal state.