Cesare Pianese

On-line sensor fault detection, isolation, and accommodation in automotive engines

The paper describes the hybrid solution, based on Artificial Neural Networks, ANNs, and production rule adopted in the realization of an Instrument Fault Detection, Isolation, and Accommodation scheme for automotive applications. Details on the ANN architectures and training are given together with diagnostic and dynamic performance of the scheme.

Models for the Prediction of Performance and Emissions in a Spark Ignition Engine - A Sequentially Structured Approach

A thermodynamic model for the simulation of performance and emissions in a spark ignition engine is presented. The model is part of an integrated system of models with a hierarchical structure developed for the study and the optimal design of engine control strategies. In order to reduce the uncertainty due to the mutual interference during the validation phase, the model has been developed accordingly with a hierarchical and sequential structure. The main thermodynamic model is based on the classical two zone approach. A multi-zone model is then derived form the two zone calculation, for a proper evaluation of temperature gradients in the burned gas region. The emissions of HC, CO and NOx are then predicted by three sub-models. In order to make the precision of emission models suitable for engine control design, an identification technique based on decomposition approach has been developed, for the definition of optimal model structure with a minimum number of parameters. The results of the thermodynamic cycle model validation, performed over more than 300 engine operating conditions, show a satisfactory level of agreement between measured and predicted data cycles. Afterward, the two step identification procedure has been applied for the emission models parameters identification. From this analysis, it has been found that the model precision achieved can be comparable with that obtained via conventional mapping procedures using black-box models, but with a drastic reduction of the experimental effort. Moreover, the proposed approach allows substantial computational time saving with respect to conventional identification techniques.

A procedure to enhance identification of recurrent neural networks for simulating air-fuel ratio dynamics in SI engines

The paper deals with the identification of recurrent neural networks (RNNs) for simulating the air-fuel ratio (AFR) dynamics into the intake manifold of a spark ignition (SI) engine. RNN are derived from the well-established static multi layer perceptron feedforward neural networks (MLPFF), that have been largely adopted for steady-state mapping of SI engines. The main contribution of this work is the development of a procedure that allows identifying a RNN-based AFR simulator with high generalization and limited training data set. The procedure has been tested by comparing RNN simulations with AFR transients generated using a nonlinear-dynamic engine model. The results show how training the network making use of inputs that are uncorrelated and distributed over the entire engine operating domain allows improving model generalization and reducing the experimental burden. Potential areas of application of the procedure developed can be either the use of RNN as virtual AFR sensors (e.g. engine or individual AFR prediction) or the implementation of RNN in the framework of model-based control architectures. rchitectures.

An adaptive estimator of fuel film dynamics in the intake port of a spark ignition engine

In order to meet the limits imposed on automotive emissions, engine control systems are required to constrain air/fuel ratio (AFR) in a narrow band around the stoichiometric value, due to the strong decay of catalyst efficiency in case of rich or lean mixture. An adaptive estimator, based on an extended Kalman filter, is proposed for the fuel film dynamics in the intake port of a spark ignition engine. The observer is based on a two states mean value model which accounts for the impingement of the injected fuel on the manifold walls and the evaporation process. The observer has been tested on a set of experimental transient maneuvers, showing a good accuracy in predicting the AFR.

Control Oriented Modeling of Solid Oxide Fuel Cell Auxiliary Power Unit for Transportation Applications

This paper reports on the development of a control-oriented model for simulating a hybrid auxiliary power unit (APU) equipped with a solid oxide fuel cell (SOFC) stack. Such a work is motivated by the strong interest devoted to SOFC technology due to its highly appealing potentialities in terms of fuel savings, fuel flexibility, cogeneration, low-pollution and low-noise operation. In this context, the availability of a model with acceptable computational burden and satisfactory accuracy can significantly enhance both system and control strategy design phases for APUs destined to a wide application area (e.g., mild-hybrid cars, trains, ships, and airplanes). The core part of the model is the SOFC stack, surrounded by a number of ancillary devices: air compressor/blower, regulating pressure valves, heat exchangers, prereformer, and postburner. Since the thermal dynamics is clearly the slowest one, a lumped-capacity model is proposed to describe the response of SOFC and heat exchangers to load (i.e., operating current) variation. The stack model takes into account the dependence of stack voltage on operating temperature, thus adequately describing the typical voltage undershoot following a decrease in load demand. On the other hand, due to their faster dynamics the mass transfer and electrochemistry processes are assumed instantaneous. The hybridizing device, whose main purpose is to assist the SOFC system (i.e., stack and ancillaries) during transient conditions, consists of a lead-acid battery pack. Battery power dependence on current is modeled, taking into account the influence of actual state of charge on open circuit voltage and internal resistance. The developed APU model was tested by simulating typical auxiliary power demand profiles for a heavy-duty truck in parked-idling phases. Suited control strategies also were developed to avoid operating the SOFC stack under severe thermal transients and, at the same time, to guarantee a charge sustaining operation of the battery pack. In order to assess the benefits achievable by introducing the SOFC-APU on board of a commercial truck, the simulated fuel consumption was compared with the fuel consumed by idling the thermal engine. From the simulation carried out, it emerges how the SOFC-APU allows achieving a potential reduction in fuel consumption of up to 70%.

A Computer Code for S.I. Engine Control and Powertrain Simulation

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. The adoption of a hierarchical structure based on different classes of models, ranging from black-box Neural Network to grey-box mean value dynamic models, allows a satisfactory accuracy with limited computational demand which makes it suitable for the optimization of engine control strategies. In the paper the whole model framework is described together with simulation results obtained for different transient manouevres and control strategies.

Modeling and Analysis of Transient Behavior of Polymer Electrolyte Membrane Fuel Cell Hybrid Vehicles

The paper focuses on the simulation of a hybrid vehicle with proton exchange membrane fuel cell as the main energy conversion system. A modeling structure has been developed to perform accurate analysis for powertrain and control system design. The models simulate the dynamics of the main powertrain elements and fuel cell system to give a sufficient description of the complex interaction between each component under real operating conditions. A control system based on a multilevel scheme has also been introduced and the complexity of control issues for hybrid powertrains have been discussed. This study has been performed to analyze the energy flows among powertrain components. The results highlight that optimizing these systems is not a trivial task and the use of precise models can improve the powertrain development process. Furthermore, the behavior of system state variables and the influence of control actions on fuel cell operation have also been analysed. In particular, the effect of introducing a rate limiter on the stack power has been investigated, evidencing that a 2 kW/s rate limiter increased the system efficiency by 10% while reducing the dynamic performance of the powertrain in terms of speed error .

Information Based Selection of Neural Networks Training Data for S.I. Engine Mapping

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. These techniques have been applied to assist the training of artificial Neural Networks for the estimation of engine torque and exhaust emissions of an S.I. engine, to be embedded into a powertrain dynamic model for the optimal design of engine control strategies (O.D.E.C.S.), now in use at Magneti Marelli.

PEM Fuel Cells Control by means of the Perturb and Observe Technique

In this paper the use of an adaptive technique aimed at controlling a polymeric electrolyte membrane fuel cell is introduced. It is demonstrated that a hill climbing-based method acting on the compressor speed and/or the backpressure valve opening is able to improve the performance of the fuel cell system with respect to those ones obtained by means of classical feed forward control approaches. Moreover, the proposed technique is able to ensure better performances even if well known aging mechanisms deteriorate cell efficiency. Numerical results based on experimentally derived models confirm the potential of the proposed control method and its intrinsic reliability

A stochastic approach for the optimization of open-loop engine control systems

The operation of sensors and actuators in engine control systems is always affected by errors, which are stochastic in nature. In this paper it is shown that, because of the non-linear interactions between engine performance and control laws in an open-loop engine control system, these errors can give rise to unexpected deviations of control variables, fuel consumption and emissions from the optimal values, which are not predictable in an elementary way.A model for vehicle performance evaluation on a driving cycle is presented, which provides the expected values of fuel consumption and emissions in the case of stochastic errors in sensors and actuators, utilizing only steady-state engine data.The stochastic model is utilized to obtain the optimal control laws; the resultant non-linear constrained minimization problem is solved by an Augmented Lagrangian approach, using a Quasi-Newton technique. The results of the stochastic optimization analysis indicate that significant reductions in performance degradation may be achieved with respect to the solutions provided by the classical deterministic approach.