Search Results

The calibration of Engine Control Units (ECUs) for road vehicles is challenged by stringent legal and environmental regulations, coupled with short development cycles. The growing number of vehicle variants, although sharing similar engines and control algorithms, requires different calibrations. Additionally, modern engines feature increasingly number of adjustment variables, along with complex parallel and nested conditions within the software, demanding a significant amount of measurement data during development. The current state-of-the-art (White Box) model-based ECU calibration proves effective but involves considerable effort for model construction and validation. This is often hindered by limited function documentation, available measurements, and hardware representation capabilities. This article introduces a model-based calibration approach using Neural Networks (Black Box) for two distinct ECU functional structures with minimal software documentation.

The modern engine development process is characterized by shorter development cycles and a reduced number of prototypes. However, simultaneously exhaust after-treatment and emission testing is becoming increasingly more sophisticated. It is expected that predictive simulation tools that encompass the entire powertrain can potentially improve the efficiency of the calibration process. The testing of an ECU using a HiL system requires a real-time model. Additionally, if the initial parameters of the ECU are to be defined and tested, the model has to be more accurate than is typical for ECU functional testing. It is possible to enhance the generalization capability of the simulation, with neuronal network sub-models embedded into the architecture of a physical model, while still maintaining real-time execution. This paper emphasizes the experimental investigation and physical modeling of the port fuel injected SI engine.

Within a project of the Research Association for Combustion Engines e.V., different measures for rising the temperature of exhaust gas aftertreatment components of both a passenger car and an industrial/commercial vehicle engine were investigated on a test bench as well as in simulation. With the passenger car diesel engine and different catalyst configurations, the potential of internal and external heating measures was evaluated. The configuration consisting of a NOx storage catalyst (NSC) and a diesel particulate filter (DPF) illustrates the potential of an electrically heated NSC. The exhaust aftertreatment system consisting of a diesel oxidation catalyst (DOC) and a DPF shows in simulation how variable valve timing in combination with electric heated DOC can be used to increase the exhaust gas temperature and thus fulfill the EU6 emission limits.

Modern combustion engines must meet increasingly higher requirements concerning emission standards, fuel economy, performance characteristics and comfort. Especially fuel consumption and the related CO2 emissions were moved into public focus within the last years. One possibility to meet those requirements is downsizing. Engine downsizing is intended to achieve a reduction of fuel consumption through measures that allow reducing displacement while simultaneously keeping or increasing power and torque output. However, to reach that goal, downsized engines need high brake mean effective pressure levels which are well in excess of 20bar. When targeting these high output levels at low engine speeds, undesired combustion events with high cylinder peak pressures can occur that can severely damage the engine. These phenomena, typically called low speed pre-ignition (LSPI), set currently an undesired limit to downsizing.

A main focus of development in modern SI engine technology is variable valve timing, which implies a high potential of improvement regarding fuel consumption and emissions. Variable opening, period and lift of inlet and outlet valves enable numerous possibilities to alter gas exchange and combustion. However, this additional variability generates special demands on the calibration process of specific engine control devices, particularly under cold start and warm-up conditions. This paper presents procedures, based on Hardware-in-the-Loop (HiL) simulation, to support the classical calibration task efficiently. An existing approach is extended, such that a virtual combustion engine is available including additional valve timing variability. Engine models based purely on physical first principles are often not capable of real time execution. However, the definition of initial parameters for the ECU requires a model with both real time capability and sufficient accuracy.

The modern engine design process is characterized by shorter development cycles and a reduced number of prototypes. However, simultaneously exhaust after-treatment and emission testing is becoming increasingly more sophisticated. The introduction of predictive real-time simulation tools that represent the entire powertrain can likely contribute to improving the efficiency of the calibration process. Engine models, which are purely based on physical first principles, are usually not capable of real-time applications, especially if the simulation is focused on cold start and warm-up behavior. However, the initial data definition for the ECU using a Hardware-in-the-Loop (HiL)-Simulator requires a model with both real-time capability and sufficient accuracy. The use of artificial intelligence systems becomes necessary, e.g. neural networks. Methods, structures and the realization of a hybrid real-time model are presented in this paper, which combines physical and neural network models.

Gasoline Controlled Auto-Ignition (GCAI) combustion, which can be categorized under Homogeneous Charge Compression Ignition (HCCI), is a low-temperature combustion process with promising benefits such as ultra-low cylinder-out NOx emissions and reduced brake-specific fuel consumption, which are the critical parameters in any modern engine. Since this technology is based on uncontrolled auto-ignition of a premixed charge, it is very sensitive to any change in boundary conditions during engine operation. Adopting real time valve timing and fuel-injection strategies can enable improved control over GCAI combustion. This work discusses the outcome of collaborative experimental research by the partnering institutes in this direction. Experiments were performed in a single cylinder GCAI engine with variable valve timing and Gasoline Direct Injection (GDI) at constant indicated mean effective pressure (IMEP). In the first phase intake and exhaust valve timing sweeps were investigated.

The global push towards reducing green-house gas and criteria pollutant emissions is leading to tighter emission standards for heavy-duty engines. Among the most stringent of these standards are the California Air Resource Board (CARB) 2024+ HD Omnibus regulations adopted by the agency in August 2020. The CARB 2024+ HD Omnibus regulations require up to 90% reduction in NOx emissions along with updated compliance testing methods for on-road heavy-duty engines. Subsequently, the agency announced development of new Tier 5 standards for off-road engines in November 2021. The Tier 5 standards aim to reduce NOx/PM emissions by 90%/75% respectively from Tier 4 final levels, along with introduction of greenhouse gas emission standards for CO2/CH4/N2O/NH3. Furthermore, CARB is also considering similar updates on compliance testing as those implemented in 2024+ HD Omnibus regulations including, low-load cycle, idle emissions and 3-bin moving average in-use testing.

Modeling thermal systems in Battery Electric Vehicles (BEVs) is crucial for enhancing energy efficiency through predictive control strategies, thereby extending vehicle range. A major obstacle in this modeling is the often limited availability of detailed system information. This research introduces a methodology using neural networks for system identification, a powerful technique capable of approximating the physical behavior of thermal systems with minimal data requirements. By employing black-box models, this approach supports the creation of optimization-based operational strategies, such as Model Predictive Control (MPC) and Reinforcement Learning-based Control (RL). The system identification process is executed using MATLAB Simulink, with virtual training data produced by validated Simulink models to establish the method's feasibility. The neural networks utilized for system identification are implemented in MATLAB code.

The application of technologies such as direct injection, turbo charging and variable valve timing has caused a significant evolution of the gasoline engine with positive effects on fuel consumption and emissions. The current developments are primarily focused on the realization of improved full load characteristics and fuel consumption reduction with stoichiometric operation, following the downsizing approach in combination with turbo charging and high specific power. The requirements of high specific power in a relatively small cylinder displacement and a wide range of DI injection specifications lead to competing development targets and to a high number of degrees of freedom during engine layout and optimization. One of the major targets is to assess the stability of the combustion system in the early development phase.

Vehicle OEM’s for MHD applications are facing significant challenges in meeting the stringent 2027 low-NOx and GHG emissions regulations. To meet such challenges, advanced engine and aftertreatment technologies along with powertrain electrification are being applied to achieve robust solutions. FEV has previously conducted model-based assessments to show the potential of 48V engine and aftertreatment technologies to simultaneously meet GHG and low NOx emission standards. This study focuses on evaluating the full potential of 48V electrification technology through addition of 48V P3 hybrid system to the previously developed 48V advanced engine and aftertreatment technology package. Previously, a model-based approach was utilized for selection and sizing of a 48V system-enabled engine and aftertreatment package for class 6-7 MHD application.

With the advent of advanced diesel after-treatment technologies, sophisticated sensors are becoming a critical cost challenge to OEMs. This paper describes an approach for replacing the engine out NOx sensor with an artificial neural network (ANN) based virtual sensor. The technique centers around inferring NOx concentration from readily available engine operating parameters, eliminating the need for physical sensing and the cost associated with it. A multi-layer perceptron network was trained to estimate NOx concentration from engine speed, load, exhaust gas recirculation, and air-fuel ratio information. This supervised learning was conducted with measured engine data. The network was validated against measured data that was excluded from the training data set. The paper details application of this technique to both a heavy duty and light duty diesel engine. Results show good agreement between predictions and measured data under the steady state conditions studied.

Advanced technologies such as direct injection DI, turbocharging and variable valve timing, have lead to a significant evolution of the gasoline engine with positive effects on driving pleasure, fuel consumption and emissions. Today's developments are primarily focused on the implementation of improved full load characteristics for driving performance and fuel consumption reduction with stoichiometric operation, following the downsizing approach in combination with turbocharging and high specific power. The requirements of a relatively small cylinder displacement with high specific power and a wide flexibility of DI injection specifications lead to competing development targets and additionally to a high number of degrees of freedom during optimization. In order to successfully approach an optimum solution, FEV has evolved an advanced development methodology, which is based on the combination of simulation, optical diagnostics and engine thermodynamics testing.

In a gasoline engine, the cycle-by-cycle fresh trapped charge, and corresponding unswept residual gas fraction (RGF) are critical parameters of interest for maintaining the desired air-fuel ratio (AFR). Accurate fueling is a key precursor to improved engine fuel economy, and reduced engine out emissions. Asymmetric flow paths to cylinders in certain engines can cause differences in the gas exchange process, which in turn cause imbalances in trapped fresh charge and RGF. Variable cam timing (VCT) can make the gas exchange process even more complex. Due to the reasons stated above, simplified models can result in significant estimation errors for fresh trapped charge and RGF if they are not gas dynamics-based or detailed enough to handle features such as variable valve timing, duration, or lift. In this paper, a new air flow and RGF measurement tool is introduced.