Search

In the last few years, car manufacturers are moving toward electrified powertrains, like Battery Electric Vehicles (BEV) and Hybrid Electric Vehicles (HEV), to reduce the levels of CO2 in the atmosphere. A promising alternative to BEVs to reduce CO2 emissions, while maintaining an existing and well-developed technology, could be the use of hydrogen for internal combustion engines (ICEs). Particularly, the zero-carbon content of hydrogen allows for guaranteeing very clean combustion and near-zero carbon footprint. Within this context, the present study aims to deeply investigate the effects of pure hydrogen fueling of Spark Ignition (SI) engines, especially on specific fuel consumption and NOx emissions. Particularly, the benefits of pure hydrogen fueling were assessed in a production small Direct Injection (DI) SI engine. The engine is intended to operate in steady state conditions as an Auxiliary Power Unit (APU) for a series hybrid powertrain. The effects of pure hydrogen fueling were investigated at two engine speeds, namely 2000 and 3000 rpm. All tests were carried out at unthrottled conditions and lean mixture. A 1-D engine model was developed within a commercial software. Combustion, heat transfer, and NOx emissions embedded sub-models were tuned based on the experimental data, to accurately reproduce the engine behavior in a wide range of operating conditions. Both experimental and simulation results demonstrated that hydrogen fueling, together with lean mixture operation, allow for significantly improving engine thermal efficiency. The results of 1-D model simulations supported the energy management strategies of the hybrid powertrain in selecting the most suitable ICE operating condition. Particularly, the best engine operating conditions in terms of fuel consumption are achieved at 2500 rpm, with λ = 2.0, while the lowest NOx emissions are reached when λ is increased up to 2.4.

During the last years, the sales of vehicles equipped with Spark-Ignition (SI) engines have increased, to the detriment of those powered by Compression-Ignition (CI) engines. However, SI engines provide lower efficiency than CI engines, due to the low compression ratio and stoichiometric mixture operation. A way to increase the efficiency of SI engines is lean combustion, as it allows to increase the specific heats ratio (γ) and reduces pumping losses at part loads. Nevertheless, the operation with extremely lean mixtures deals with ignition issues, promoting Cycle-to-Cycle Variability (CCV) and increasing the probability of misfire. The prechamber ignition concept, also known as Turbulent Jet Ignition (TJI), is a promising solution for enabling the implementation of lean combustion, without its drawback in SI engines. Such a concept can be implemented according to two approaches: In active TJI, there is an additional fuel supply system inside the prechamber, while in passive TJI there isn’t. Therefore, the main advantage of passive TJI is its simplicity, as the prechamber can be installed into a conventional spark plug body, with obvious benefits in terms of packaging and costs. In this work, the benefits of passive TJI on combustion and performance are assessed by simulation analyses. Particularly, a 1-D engine model was developed to simulate the TJI combustion and was validated versus experimental data. Afterward, a 0-D method was applied to assess the impact of the relative air-fuel ratio on CCV. The analysis was carried out in a high speed and load operating condition, namely 4500 rpm and 13 bar of IMEP, under both stoichiometric and lean mixture. Experimental and numerical results demonstrate the effectiveness of the passive TJI concept in promoting faster and more stable combustion also in lean-burn conditions.

The NOχ Storage Catalyst is currently envisaged to be implemented in light-duty passenger cars for nitrogen oxides reduction, in order to comply with strict emission legislation targets. Since robustness and durability of the engine and emission control system is the first priority in automotive application, to satisfy the need of robust on-board real time monitoring, diagnosis and control, computing efficient methods are needed. In this framework, a control oriented model that describes the dynamics of the main physical-chemical processes within the NSC catalyst, while still maintaining affordable computational burden, has been developed and validated. Model calibration has been performed, for light-duty application, along the NEDC test cycle, by using a statistical-based sub-optimal procedure, based on a parametric analysis which allows identifying the more suitable section of NeDC cycle for model identification, without the need to perform cost- and time- expensive experiments on the engine test bench. The procedure also accounts for missing information and sensors inaccuracies. The great potential of this methodology is the possibility to adopt not optimal designed tests for model parameters identification. The proposed methodology is proven to be effective for real time control strategy, directly embedded in ECU, and provide a sub-optimal but effective strategy for complex models calibration.

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. In this work, the benefits of the PC were assessed in a production small SI engine, fueled with gasoline, and equipped with a proper designed pre-chamber. The engine is intended to operate in steady state conditions as a range extender for a series hybrid powertrain. The effects of the PC on combustion process, engine performance and fuel consumption were experimentally analyzed at the engine test bed. Three different engine speeds were investigated, namely 2000, 3000 and 4000 rpm. All tests were carried out at full load, both in stoichiometric and lean conditions. A 1D model of the engine under study was developed by a commercial software. Combustion, heat transfer and emissions embedded sub-models were tuned based on experimental data, in order to accurately reproduce the engine behavior. Both numerical and experimental results demonstrated that lean engine operation allows to significantly improve thermal efficiency. The results of 1D model simulations are useful to support the energy management strategies of the hybrid powertrain in selecting the most suitable ICE operating condition, considering the trade-off between low fuel consumption and high power supplied to the battery charger.

A benchmark problem for fuel efficient control of a truck on a given road profile has been formulated and solved. Six different solution strategies utilizing varying degrees of off-line and on-line computations are described and compared. A vehicle model is used to benchmark the solutions on different driving missions. The vehicle model was presented at the IFAC AAC2016 symposium and is compiled from model components validated in previous research projects. The driving scenario is provided as a road slope profile and a desired trip time. The problem to solve is a combination of engine-, driveline- and vehicle-control while fulfilling demands on emissions, driving time, legislative speed, and engine protections. The strength of this publication is the collection of all six different solutions in one paper. This paper is intended to provide a starting point for practicing engineers or researchers who work with optimal and/or model based vehicle control. Funding Agencies|Vinnova Industrial Excellence Center "Linkoping Center for Sensor Informatics and Control" LINK-SIC

In the recent years, engine developer attention is focused on the application of advanced control strategies for the SCR system, considered as the leading technology for the abatement of NOX emissions in Diesel engines. The most challenging task in SCR control is the optimization of the urea dosing strategy while reaching the balance between high NOX reduction efficiency and low NH3 slip in the tailpipe, especially during transients. In order to accomplish this task, an Extended Kalman Filter (EKF) estimator is developed, to be integrated in the closed loop control of SCR urea dosing. The EKF estimator is applied to a one-state model, in which the ammonia coverage ratio θ is the only dynamic process taken into account. To improve the model accuracy, an additional dynamics, related to total ammonia adsorption capacity Ω, is considered while conceiving the EKF. The recursive EKF algorithm allows achieving enhanced estimation accuracy with a slight increase of the computational burden that is still suitable with on-board application.

The present study investigates the energy needs for the on-board generation of oxyhydrogen (HHO) used as fuel additive on vehicles. HHO production is performed through the use of an alkaline electrolyzer, directly taking energy from the equipped internal combustion engine. A longitudinal vehicle dynamic model is used to evaluate the driving power to be supplied by the engine for two reference speed profiles, NEDC and WLTC. The performed investigation determines the engine brake thermal efficiency gain required to ensure HHO production without increase in fuel consumption. The results can be used as guidelines for the development of on-board control strategies.

In this paper, a multi-level, comprehensive control technique for a heavy duty vehicle, capable of reducing fuel consumption while complying with engine constraints on both operating conditions and smoke emissions has been developed. The higher control layer, using road data, engine and vehicle parameters, computes the optimal speed and gear shifting profiles through an off-line, dual step dynamic programming algorithm. Since fuel consumption alone could be potentially decreased by driving at lower speeds and thus increasing travel time, this last aspect is also taken into account in the presented algorithm. The lower control layer, operating in real time, computes suitable powertrain control signals assuring the tracking of both reference speed and gear trajectories, while respecting the constraints imposed on engine operation. After the general description of the optimal control problem aimed at minimizing fuel consumption, an approach for its solution, implemented in the higher control layer, is presented. Afterwards, the lower control layer is described. In conclusion, the effectiveness of the developed control structure and the achievable improvement in terms of fuel consumption in comparison with a traditional fixed-point cruise controller are assessed through simulations in different driving scenarios.

To meet current Diesel engine pollutant legislation, it is important to manage after-treatment devices. The paper describes the development of Neural Network based virtual sensors used to estimate NOx emissions at the exhaust of automotive Diesel engines. Suitable identification methodologies and experimental tests were developed with the aim of meeting the conflicting needs of feasible on-board implementation and satisfactory prediction accuracy. In addition, since the prediction of control-oriented models is typically affected by engine aging and production spread as well as components drift, least square technique features were exploited in order to overcome these issues by adapting the virtual sensor output. The NOx adaptive virtual sensor was tested via comparison with experimental data, measured at the engine test bench on a turbocharged common-rail automotive Diesel engine. Furthermore, besides model validation, the experimental measurements were modified to simulate a sensor drift in order to enable full assessment of the proposed LS-based algorithm adaptation capabilities.

The present paper details a performance analysis made through model-based simulation of a dual stage multi-level control algorithm applied to heavy duty vehicles that accounts for traffic information. Such work exploits a control algorithm at different level of traffic congestion. In the two stages control, the first level entails a supervisory optimizer, which evaluates the optimal speed and gear shifting profile according to road and vehicle information to minimize fuel consumption; the second level is an actuator control that computes the powertrain signals to be applied to the engine actuators to comply with the indications given by the supervisory control. The advancement brought by the present work resides in the introduction of speed constraints related to different traffic levels: i) free flow, ii) free flow/conditioned, iii) conditioned and iv) congested. To each state, a maximum limiting speed is associated and several scenarios are investigated in simulated environment. All the results are compared to a conventional Cruise Controller to assess the achievements in terms of fuel consumption reduction, assessing that the proposed control strategy ensures an average reduction of about 3.5% over all the investigated conditions.

The introduction of actual and upcoming emission standards, move the industrial attentions from laboratory towards real-world emission performance, In-Service Conformity testing (ISC) and life-time periods. Besides advanced air management, fuel injection pattern optimization and aftertreatment systems, the goal to realize optimal and robust powertrain setting under varying operating conditions, while ensuring the proper operation of ATs is challenging and require a massive calibration effort. To accomplish this task, the present research deals with supervisory controller for the integrated engine-SCR system, also referred in literature as EGR-SCR balancing. The goal is to comply with NOx emissions limit and, at the same time, to minimize global costs over transient operating conditions. The potential of this IEM strategy is demonstrated for a typical type-approval test case. The optimization identifies the effective EGR actuation, based on the actual powertrain state, engine settings and ATs performances. The resulting control strategy optimizes the overall performance.

The use of efficient embedded control systems in the transportation industry and particularly in turbocharged Diesel engines requires the programming of elaborated nonlinear control and filtering methods. To this end, in this paper nonlinear control for turbocharged Diesel engines is developed with the use of Differential flatness theory and adaptive fuzzy control. It is shown that the dynamic model of the turbocharged Diesel engine is differentially flat and admits dynamic feedback linearization. It is also shown that the dynamic model can be written in the linear Brunovsky canonical form for which a state feedback controller can be easily designed. To compensate for modeling errors and external disturbances an adaptive fuzzy control scheme is implemented making use of the transformed dynamical system of the diesel engine that is obtained through the application of differential flatness theory. The control algorithm aims at satisfying the $$H_\infty $$ tracking performance criterion, which means that the influence of the modeling errors and the external disturbances on the tracking error is attenuated to an arbitrary desirable level. After transforming the MIMO diesel engine system into the canonical form, the resulting control inputs are shown to contain nonlinear elements which depend on the system’s parameters. The nonlinear terms which appear in the control inputs are approximated with the use of neuro-fuzzy networks. Moreover, since only the system’s output is measurable the complete state vector has to be reconstructed with the use of a state observer. It is shown that a suitable learning law can be defined for the aforementioned neuro-fuzzy approximators so as to preserve the closed-loop system stability. With the use of Lyapunov stability analysis it is proven that the proposed observer-based adaptive fuzzy control scheme results in $$H_{\infty }$$ tracking performance.

In spark-ignition engines, knock control represents one of the most critical issue to reach optimal thermal efficiency. The paper deals with the development of a methodology aimed at evaluating the most suited spark advance to achieve the right compromise between performance optimization and knocking occurrence (KLSA). The methodology is based on combustion simulation via a two-zone 0D model in which the cycle-by-cycle variation (CCV) is described by a model parameter that impacts on the turbulence level at inlet valve closing. The auto-ignition of the unburnt mixture is described by a thermodynamic equation derived from literature while knock intensity is evaluated by a stochastic approach. The method allows evaluating the percentage of knocking cycles, depending on the spark advance actuated. The validation has been carried out vs. experimental data collected at the engine test rig on a 4 cylinders turbocharged GDI engine, by comparing predicted and experimental MAPO.

The paper presents model-based scenario analyses of micro and mild tri-hybrid vehicle configurations, related to existing conventional vehicles equipped with small power proton exchange membrane (PEM) fuel cell (FC) systems and, eventually, additional battery pack. The analyses are intended to support short-to medium-term development of fuel cell powered Light Duty Vehicles (LDVs) technology and are useful for carmakers to quantitatively assess the potential advantages associated to the afore-mentioned opportunities in terms of short-term clean and cost-efficient production of hydrogen. The analyses are performed making use of a comprehensive vehicle model, based on a hybrid (black-box and lumped parameters) approach, of a medium passenger car equipped with a turbocharged SI engine. The model has been enhanced to account for the additional components of two different powertrain configurations, namely conventional powertrain with ICE and fuel cell Auxiliary Power Unit (APU) and hybrid powertrain ICE/FC. Simulations have been carried out vs. standard driving cycles for two energy management strategies. The results allow evaluating the impact of powertrain configuration on CO2 emissions, in case of both Tank-to-Wheel (TTW) and Well-to-Wheel (WTW) analyses.

The paper illustrates the design and verification of a model-based diagnostic algorithm for fault detection and isolation of a Diesel Particulate Filter (DPF). The algorithm relies on the Structural Analysis theory, which identifies proper fault indicators (i.e., residuals) upon the knowledge of the mathematical relationships within the system model. The main innovation of the proposed work consists in applying for the first time such theory to a Diesel after-treatment system. To check theoretical fault detectability and isolability, the approach requires only qualitative correlations among the physical variables and parameters representative of the faults that may occur into the system, without the need for quantitative information. Nevertheless, to build the residuals, the form of the equations needs to be defined and properly implemented. The mathematical model developed in this work is a lumped dynamic model that accounts for two main control volumes, one related to the Diesel Oxidation Catalyst (DOC) and the other to the DPF. Mass and energy balance equations are introduced in both volumes. Within the DPF, soot inlet flow is related to the engine exhaust flow, and its oxidation kinetics is modelled by means of Arrhenius-type equation. Four faulty states are introduced into this study with respect to: i) variation in fuel-post injection amount (i.e., injector malfunction), ii) partial or missed fuel combustion in the DOC, iii) partial or missed residual fuel combustion in the DPF, and iv) degradation of the substrate viscosity. Each faulty state is modelled through a dedicated parameter and the overall model is then used to perform faults isolability through Structural Analysis. The theoretical results show that the proposed diagnostic algorithm can detect and correctly isolate all the considered faults. Then, residuals are built and verified in simulated environment on specific cases, proving the capability of the algorithm to successfully detect and isolate the considered faults.

Nowadays the high competition reached by the automotive market forces original equipment manufacturers (OEMs) towards innovative solutions. Strict emission standards and fuel economy targets make the work hard to be accomplished. Therefore modern engines feature complex architecture and embed new devices for exhaust gas recirculation (EGR), turbocharging (e.g. multi-stage compressors), gas after-treatment (e.g. selective catalyst reduction (SCR)) and fuel injection (either high or low pressure). In this context the engine management system (EMS) plays a fundamental role to optimize engine operation. The paper deals with fuel spray and combustion simulation by a multi-zone phenomenological model aimed at the optimal tuning of the injection pattern. The fuel spray model simulates the injection process, the fuel-air mixture formation, the in-cylinder gas mixture evolution and accounts for the fuel-wall impingement that usually occurs in case of low-medium injection pressure or advanced injection timing. This feature is fundamental to investigate a wide range of injection pattern set-points, as those applied for advanced combustion concepts (i.e. Premixed Charge Compression Ignition (PCCI)). The impingement of the spray on cylinder walls is modeled by a zero-dimensional approach, simulating dynamics and evaporation of the fuel film with two different semi-empirical models. The numerical and experimental analyses have been performed with respect to an automotive Common-Rail Diesel engine, equipped with high pressure EGR and VGT turbocharger. The experimental measurements have been carried out at the engine test stand, investigating operating conditions with highly advanced injection timing and low rail pressure, in order to induce the fuel impingement process. Model validation against the experimental data exhibits satisfactory accuracy in predicting the impact of injection pattern control on impingement.

In order to face with the increasing EU restrictions on CO2 emissions from light-duty vehicles, concepts such as the engines downsizing, stop/start systems as well as more costly full hybrid solutions and Waste Heat Recovery (WHR) technologies have been proposed in the last years by OEMs. WHR technologies include Thermo-Electric Generator (TEG), Organic Rankine Cycle (ORC) and Electric Turbo-Compound (ETC) that have been practically implemented on few heavy-duty applications but have not been proved yet as effective and affordable solutions for passenger cars. The paper deals with the analysis of opportunities and challenges of TEG and ETC technologies for a compact car, powered by a turbocharged SI engine. Specifically, the benefits achievable by TEG and ETC have been investigated by simulation analyses carried out by a dynamic engine-vehicle model, validated against steady-state and transient experimental data. The in-cylinder processes and friction losses of the engine are modeled by a black-box scalable parametric approach while grey-box dynamic models are applied for intake/exhaust manifolds and turbocharger. The TEG model is based on existing and commercial thermoelectric materials, specifically Bi2Te3. The simulations have been carried out considering standard driving cycles (i.e. NEDC, WLTC) and the results evidence that significant improvement of fuel economy and CO2 reduction can be achieved by suitable management and configuration of the WHR systems, depending on engine speed and load and auxiliaries demand.

This paper deals with the development of an automotive hybridization kit (equipment, along with associated techniques and methodologies), aimed at converting conventional cars into hybrid solar vehicles (Mild-Solar-Hybrid). The main aspect of the projects consists into the integration of state-of-the-art components (in-wheel motors, photovoltaic panels, batteries), and into the development of an optimal controller for the power management. A prototype of the hybridizing equipment – patented by the University of Salerno (Italy)- is installed on a FIAT Grande Punto. A mild parallel hybrid structure is obtained by substituting/integrating the rear wheels with 7 kW in-wheel motors and adding a lithium battery to manage on-board energy. Thus, the vehicle can operate in electric mode (when ICE is switched off or disconnected by the front wheels) or in hybrid mode (when the ICE drives the front wheels and the rear in-wheel motors operate in traction mode or in generation mode, corresponding to a positive or negative torque). The battery can be recharged both by rear wheels, when operating in generation mode, and by photovoltaic panels. The vehicle is also equipped with an EOBD gate (On Board Diagnostics protocol), which allows accessing data such as pedal position, vehicle speed, engine speed, manifold pressure and other variables. The Vehicle Management Unit (VMU), which is part of the invention and implements control logics compatible with typical drive styles of conventional-car users, receives the data from OBD gate, from battery (SOC estimation) and drives in-wheel motors by properly acting on the electric node. The paper, focused on the main aspects of prototype design and realization, also provides insights on control issues related to the integration of the above-mentioned components, drivability and safety.

In the last decades the role of the engine control has became fundamental to improve fuel consumption and comply with the emissions standards. Particularly on automotive Diesel engines sophisticated control systems have been introduced, which are based on both large measurement data sets and complex controllers. Alternatives are needed to simplify and improve the Engine Management System (EMS). To this purpose the in-cylinder signal may be an effective measure to enhance EMS and its reliability, as well as to potentially reduce both costs and development time. The paper deals with the development of two techniques to estimate the Air-Fuel Ratio (AFR) and the in-cylinder mass from the in-cylinder pressure signal. These methodologies are intended to be implemented in real-time with the aim of replacing or working jointly with the existing air mass flow and lambda sensors. The techniques were validated vs. experimental data measured at the engine test bench on a Common Rail light-duty Diesel engine. The results show a good accuracy in predicting Air-Fuel Ratio and in-cylinder mass in a wide engine operating range.

Nowadays researchers and car-makers are working on autonomous vehicles related topics towards solutions that employ detailed road network information derived from 3D maps. In this context, Advanced Driver Assistance Systems (ADAS) are getting more and more widespread on automotive market. Information on the upcoming horizon is used to enhance vehicle drivability, comfort, energy efficiency and driver safety. This data extends vehicle's status knowledge beyond what on-board sensors can provide. An ADAS application towards energy consumption reduction, named “Eco-Tutor”, is presented. It provides a velocity reference to enhance the energy efficiency, and thus lowering fuel consumption, taking into account road gradients and speed limits of the upcoming road segments within a defined horizon length. This ADAS-based application has been designed to provide the optimal value of the target vehicle speed to be achieved by the driver. The application has been developed, tested through several simulations and implemented on rapid prototyping for in-vehicle testing. It is assessed in terms of energy savings and drivers experience.

Nowadays the high competition reached in the automotive market forces original equipment manufacturers (OEMs) towards the implementation of more and more innovative solutions. Strict emission standards and fuel economy targets make the work hard to be accomplished. Therefore modern engines feature complex architecture and embed new devices for exhaust gas recirculation (LP-HP EGR), turbocharging (e.g. multi-stage compressors), gas after-treatment (e.g. DPF, SCR, LNT) and fuel injection. This results in increased costs for engine and components as well as great complexity for the overall powertrain management. An alternative solution to comply with emissions and CO2 standards is to supply the engine with alternative fuel blends that allow reducing significantly engine pollutants thus lowering the complexity of the after-treatment path. The paper deals with the analysis of the impact of different fuel blends Diesel-Ethanol on the performance and NOx / Particulate emissions in a common-rail CI engine. The simulation analyses are performed by a multi-zone phenomenological model of fuel spray, combustion and emissions mechanisms, that takes into account the influence of the specific fuel blend on the fuel-air mixture formation and the in-cylinder gas mixture evolution. Model validation is carried out vs. experimental data collected on an automotive common-rail CI engine, fuelled by a E20 blend and operating at different working conditions. Afterwards simulations are performed by spanning the fuel blends and the combustion control parameters (i.e. injection pattern and EGR) with the aim of optimizing combustion tuning vs. fuel blend.

The paper focuses on the development of an adaptive NO x emissions model, whose intended deployment is to provide accurate estimation, throughout engine lifetime, in correspondence of the engine exhaust port of a Diesel propulsion system. Particularly, black-box modelling approach is proposed, which specifically in this paper takes advantage of an intake manifold oxygen estimator previously developed. The resulting multi-linear regression model was preliminary validated in steady-state conditions. Upon successful verification of model accuracy, the above NO x predictor was integrated within a least-square adaptation algorithm, which relies on the experimental NO x measurement performed downstream the selective catalytic reduction catalyst. Therefore, it was possible to perform further validation analyses, both to assess prediction reliability in transient conditions, as well as to verify the adaptation capability of the proposed least-square-based algorithm.

Hybrid electric vehicles (HEV) represent a good and feasible solution to reduce fuel consumption and related emissions. Furthermore, there is an increasing interest toward the integration of HEV's with photovoltaic (PV) panels, in order to enhance their benefits. But, despite the recent commercial success of HEVs, their market share is still insufficient to produce a significant impact on global energy consumption. Moreover, due to the present crisis, a substantial substitution of conventional vehicles with HEVs is unlikely, at least in short time. Consequently, a realistic strategy could consist in developing solutions able to achieve part of the benefits of hybrid and solar vehicles on conventional vehicles. A method for the mild solar hybridization of conventional vehicles is presented in this paper, based on use of in-wheel motors on rear wheels, of a PV panels, of an additional battery and of control system not interfering with the original ECU. A preliminary assessment of the benefits obtainable in terms of fuel consumption as a function of the degree of mild hybridization is performed by simulation analysis.

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 engine NO emissions in transient operation. 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 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 of NO emissions for a wide range of operating scenarios, with an estimation error lower than 2 % throughout the test transients. The results evidence that RNN-based virtual NO sensor offers significant opportunities for improving the performance of SCR after-treatment devices.

In the paper, the performances of a rule-based (RB) control strategy for a series Hybrid Solar Vehicle (HSV) are assessed via comparison with a batch genetic algorithm-based (GA) optimization. The RB strategy relies on heuristic rules defined by optimizing ICE start&stop strategy as function of average traction power and current solar irradiation. The comparison with the reference GA benchmark confirms the suitability of the proposed RB strategy for HSV on-board energy management. Extensive simulations were performed to test the influence of driving cycle features, power-prediction time-horizon and solar irradiation on HSV fuel economy. Such simulation analysis, beyond providing useful indications about correct implementation of the RB strategy, also demonstrates the potentialities offered by HSV powertrains in both urban and highway driving conditions.

The increasing competition among automotive OEMs together with the worsening of the environmental pollution has lead to the development of complex engine systems. Innovative control strategies are needed to simplify and improve the Engine Management System (EMS), moving towards energy saving and complying with the restrictions on emissions standards. In this scenario the application of methodologies based on the in-cylinder pressure measurement finds widespread applications. Indeed, the in-cylinder pressure signal provides direct in-cylinder information with a high dynamical potentiality that is fundamental for the control and diagnosis of the combustion process. Furthermore, the in-cylinder pressure measurement may also allow reducing the number of existing sensors on-board, thus lowering the equipment costs and the engine wiring complexity. The paper focuses on the estimation of the Air-Fuel ratio from the in-cylinder pressure signal. The methodology is based on the analysis of the statistical moments of the pressure cycle and was already presented by the authors and applied to a set of steady state engine operation conditions. In this paper the technique has been enhanced in order to be applied under the more critical engine transient operation. The results achieved show a satisfactory accuracy in predicting the Air-Fuel ratio during engine transients performed at the engine test bench on a Common-Rail turbocharged Diesel engine.