Search Results

In the last few years, several studies have proved the benefits of exploiting information about the road topography ahead of the vehicle to adapt vehicle cruising for fuel consumption reduction. Recent technologies have brought on-board more road information enabling the optimization of the driving profile for fuel economy improvement. In the present paper, a cruise controller able to lowering vehicle fuel consumption taking into account the characteristics of the road the vehicle is traveling through is presented. The velocity profile is obtained by minimizing via discrete dynamic programming the energy spent to move the vehicle. In order to further enhance vehicle fuel efficiency, also the gear shifting schedule is optimized, allowing to avoid useless gear shifts and choose the most suitable gear to match current road load and keeping the engine in its maximum efficiency range. Despite the optimality of the solution provided, dynamic programming entails high computational time.

Road topography has a remarkable impact on vehicle fuel consumption for both passenger and heavy duty vehicles. In addition, erroneous or non-optimized scheduling of both velocity set-point and gear shifting may be detrimental for fuel consumption and performance. Recent technologies have made road data, such as elevation or slope, either available or measurable on board, thus making possible the exploitation of this additional information in innovative controllers. The aim of this paper is the development of a smart, fuel-economy oriented controller adapting cruising speed and engaged gear to current road load (i.e. local slope). Unlike traditional cruise controllers, the velocity set-point is not constant, but it is set by applying a mathematical transformation of the current slope, accounting for the mission time duration as well.

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 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.