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.

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 paper deals with the application of two techniques for the selection of the training data set used for the identification of Neural Network black-box engine models; the research starts from previous studies on Sequential Experimental Design for regression based engine models. The implemented methodologies rely on the Active Learning approach (i.e. active selection of training data) and are oriented to drive the experiments for the Neural Network training. The methods allow to select the most significant examples leading to an improvement of model generalization with respect to a heuristic choice of the training data. The data selection is performed making use of two different formulation, originally proposed by MacKay and Cohn, based on the Shannon's Statistic Entropy and on the Mean Error Variance respectively.

A computer code oriented to S.I. engine control and powertrain simulation is presented. The model predicts engine and driveline states, taking into account the dynamics of air and fuel flows into the intake manifold and the transient response of crankshaft, clutch, transmission gearing and vehicle. The whole model is integrated in the code O.D.E.C.S., now in use at Magneti Marelli, and is based on a hierarchical structure composed of different classes of models, ranging from black-box Neural Network to grey-box mean value models. By adopting the proposed approach, a satisfactory accuracy is achieved with limited computational demand, which makes the model suitable for the optimization of engine control strategies. Furthermore, in order to simulate the driver behavior during the assigned vehicle mission profile, two drive controllers have been implemented for throttle and brakes actuation, based on classical PID and fuzzy-logic theory.

The paper describes suited methodologies for developing Recurrent Neural Networks (RNN) aimed at estimating NOx emissions at the exhaust of automotive Diesel engines. The proposed methodologies particularly aim at meeting the conflicting needs of feasible on-board implementation of advanced virtual sensors, such as neural network, and satisfactory prediction accuracy. Suited identification procedures and experimental tests were developed to improve RNN precision and generalization in predicting engine NOx emissions during transient operation. NOx measurements were accomplished by a fast response analyzer on a production automotive Diesel engine at the test bench. Proper post-processing of available experiments was performed to provide the identification procedure with the most exhaustive information content. The comparison between experimental results and predicted NOx values on several engine transients, exhibits high level of accuracy.

Due to the greater need to reduce exhaust emissions of harmful gases (GHG, NOx, PM, etc.), to promote the decarbonisation process and to overcome the drawbacks of electric vehicles (low range, high cost, impact of electricity production on CO2 emissions…), the hybrid-electric vehicles are still considered as the more feasible path through sustainable mobility. However, one of the main tasks to be accomplished to get maximum benefit from hybrid-electric powertrain is the management of the energy flows between the different power sources, namely internal combustion engine, electric machine(s) and battery pack. In this paper a methodology for the experimental testing of HEVs energy management strategies at the engine test bed is presented. The experimental set-up consists in an eddy-current dyno and a light-duty common-rail Diesel engine.

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.

A computer code oriented to S.I. engine control and powertrain simulation is presented. The model, developed in Matlab-Simulink® environment, predicts engine and driveline states, taking into account the dynamics of air and fuel flows into the intake manifold and the transient response of crankshaft, transmission gearing and vehicle. The model, derived from the code O.D.E.C.S. for the optimal design of engine control strategies now in use at Magneti Marelli, is suitable both for simulation analysis and to achieve optimal engine control strategies for minimum consumption with constraints on exhaust emissions and driveability via mathematical programming techniques. The model is structured as an object oriented modular framework and has been tested for simulating powertrain system and control performance with respect to any given transient and control strategy.

A set of models for the prediction of mechanical efficiency as function of the operating conditions for an automotive spark ignition engine is presented. The models are embedded in an integrated system of models with hierarchical structure for the analysis and the optimal design of engine control strategies. The validation analysis has been performed over a set of more than 400 steady-state operating conditions, where classical engine variables and pressure cycles were measured. Models with different functional structures have been tested; parameter values and indices of statistical significance have been determined via non-linear and step-wise regression techniques. The Neural Network approach (Multi Layer Perceptrons with Back-Propagation) has been also used to evaluate the feasibility of using such an approach for fast black-box modelization.

Conventional electric vehicles adopt either single-speed transmissions or direct drive architecture in order to reduce cost, losses and mass. However, the integration of optimized multiple-speed transmissions is considered as a feasible method to enhance EVs performances, (i.e. top speed, acceleration and grade climbing), improving powertrain efficiency, saving battery energy and reducing customer costs. Perfectly in line with these objectives, this paper presents a patented fully integrated electric traction system, as scalable solution for electrifying light duty passenger and commercial vehicles (1.5-4.2 tons), with a focus on minibuses (<20 seats). The adoption of high-speed motor coupled to multiple-speed transmission offers the possibility of a relevant efficiency improvement, a 50% volume reduction with respect to a traditional transmission, superior output torque and power density.

The last environmental regulations on passenger vehicles’ emissions harden constraints on designing powertrains. A promising solution consists in vehicle electrification leading to hybrid configurations: the tank-to-wheel pollutant emissions can be drastically reduced combining features of typical battery electric vehicles adding an Internal Combustion Engine (ICE) controlled as a Range Extender (REX). Furthermore, HC and CO/CO2 emissions can be avoided using green hydrogen as fuel for the ICE; moreover, in absence of a mechanical coupling between REX and wheels the best operating conditions in terms of maximum ICE efficiency may be easily achieved. In this work, a light quadricycle (EU L6e, classification) series hybrid vehicle with four in-wheel motors is studied for the application of a range extender system.

This article presents a novel approach for predicting fuel consumption in vehicles through a recurrent neural network (RNN) that uses only speed, acceleration, and road slope as input data. The model has been developed for real-time vehicle monitoring, route planning optimization, cost and emissions reduction and it is suitable for fleet-management purposes. To train and test the RNN, chosen after addressing several structures, experimental data have been measured on-board of a heavy-duty truck representative of a heavy-duty transportation company. Data have been acquired during typical daily missions, making use of an advanced connectivity platform, which features CANbus vehicle connection, GPS tracking, 4G/LTE - 5G connectivity, along with on-board data processing. The experimental data used for RNN train and test have been treated starting from on-board acquired raw data (e.g., speed, acceleration, fuel consumption, etc.) along with road slope downloaded from map providers.

To accurately evaluate the energy consumption benefits provided by connected and automated vehicles (CAV), it is necessary to establish a reasonable baseline virtual driver, against which the improvements are quantified before field testing. Virtual driver models have been developed that mimic the real-world driver, predicting a longitudinal vehicle speed profile based on the route information and the presence of a lead vehicle. The Intelligent Driver Model (IDM) is a well-known virtual driver model which is also used in the microscopic traffic simulator, SUMO. The Enhanced Driver Model (EDM) has emerged as a notable improvement of the IDM. The EDM has been shown to accurately forecast the driver response of a passenger vehicle to urban and highway driving conditions, including the special case of approaching a signalized intersection with varying signal phases and timing. However, most of the efforts in the literature to calibrate driver models have focused on passenger vehicles.

Water management in PEMFC power generation systems is a key point to guarantee optimal performances and durability. It is known that a poor water management has a direct impact on PEMFC voltage, both in drying and flooding conditions: furthermore, water management entails phenomena from micro-scale, i.e., formation and water transport within membrane, to meso-scale, i.e., water capillary transport inside the GDL, up to the macro-scale, i.e., water droplet formation and removal from the GFC. Water transport mechanisms through the membrane are well known in literature, but typically a high computational burden is requested for their proper simulation. To deal with this issue, the authors have developed an analytical model for the water membrane content simulation as function of stack temperature and current density, for fast on-board monitoring and control purposes, with good fit with literature data.