Search Results

The SAE AutoDrive Challenge II is a four-year collegiate competition dedicated to developing a Level 4 autonomous vehicle by 2025. In January 2023, the participating teams each received a Chevy Bolt EUV. Within a span of five months, the second phase of the competition took place in Ann Arbor, MI. The authors of this contribution, who participated in this event as team Wisconsin Autonomous representing the University of Wisconsin–Madison, secured second place in static events and third place in dynamic events. This has been accomplished by reducing reliance on the actual vehicle platform and instead leveraging physical analogs and simulation. This paper outlines the software and hardware infrastructure of the competing vehicle, touching on issues pertaining sensors, hardware, and the software architecture employed on the autonomous vehicle. We discuss the LiDAR-camera fusion approach for object detection and the three-tier route planning and following systems.

Lithium-ion and Lithium polymer batteries are fast becoming ubiquitous in high-discharge rate applications for military and non-military systems. Applications such as small aerial vehicles and energy transfer systems can often function at C-rates greater than 1. To maximize system endurance and battery health, there is a need for models capable of precisely estimating the battery state-of-charge (SoC) under all temperature and loading conditions. However, the ability to perform state estimation consistently and accurately to within 1% error has remained unsolved. Doing so can offer enhanced endurance, safety, reliability, and planning, and additionally, simplify energy management. Therefore, the work presented in this paper aims to study and develop experimentally validated mathematical models capable of high-accuracy battery SoC estimation.

Identifying edge cases for designed algorithms is critical for functional safety in autonomous driving deployment. In order to find the feasible boundary of designed algorithms, simulations are heavily used. However, simulations for autonomous driving validation are expensive due to the requirement of visual rendering, physical simulation, and AI agents. In this case, common sampling techniques, such as Monte Carlo Sampling, become computationally expensive due to their sample inefficiency. To improve sample efficiency and minimize the number of simulations, we propose a tailored active learning approach combining the Support Vector Machine (SVM) and the Gaussian Process Regressor (GPR). The SVM learns the feasible boundary iteratively with a new sampling point via active learning. Active Learning is achieved by using the information of the decision boundary of the current SVM and the uncertainty metric calculated by the GPR.

Traffic state identification is a key problem in intelligent transportation system. As a new technology, connected and automated vehicle can play a role of identifying traffic state with the installation of onboard sensors. However, research of lane level traffic state identification is relatively lacked. Identifying lane level traffic state is helpful to lane selection in the process of driving and trajectory planning. In addition, traffic state identification precision with low penetration of connected and automated vehicles is relatively low. To fill this gap, this paper proposes a novel method of identifying traffic state in the presence of connected and automated vehicles with low penetration rate. Assuming connected and automated vehicles can obtain information of surrounding vehicles’, we use the perceptible information to estimate imperceptible information, then traffic state of road section can be inferred.

In-cylinder thermal barrier coatings (TBCs) have the capability to reduce fuel consumption by reducing wall heat transfer and to increase exhaust enthalpy. Low thermal conductivity, low volumetric heat capacity thermal barrier coatings tend to reduce the gas-wall temperature difference, the driving potential for heat transfer from the gas to the combustion chamber surfaces. This paper presents a coupling between an analytical methodology for multi-layer coated wall surface temperature prediction with a fully calibrated production model in a commercial system-level simulation software package (GT-Power). The wall surface temperature at each time step was calculated efficiently by convolving the engine wall response function with the time-varying surface boundary condition, i. e., in-cylinder heat flux and coolant temperature. This tool allows the wall to be treated either as spatially uniform with one set of properties, or with independent head/piston/liner components.

Appropriate spray modeling in multidimensional simulations of diesel engines is well known to affect the overall accuracy of the results. More and more accurate models are being developed to deal with drop dynamics, breakup, collisions, and vaporization/multiphase processes; the latter ones being the most computationally demanding. In fact, in parallel calculations, the droplets occupy a physical region of the in-cylinder domain, which is generally very different than the topology-driven finite-volume mesh decomposition. This makes the CPU decomposition of the spray cloud severely uneven when many CPUs are employed, yielding poor parallel performance of the spray computation. Furthermore, mesh-independent models such as collision calculations require checking of each possible droplet pair, which leads to a practically intractable O(np2/2) computational cost, np being the total number of droplets in the spray cloud, and additional overhead for parallel communications.

Although turbocharging can extend the high load limit of low temperature combustion (LTC) strategies such as reactivity controlled compression ignition (RCCI), the low exhaust enthalpy prevalent in these strategies necessitates the use of high exhaust pressures for improving turbocharger efficiency, causing high pumping losses and poor fuel economy. To mitigate these pumping losses, the divided exhaust period (DEP) concept is proposed. In this concept, the exhaust gas is directed to two separate manifolds: the blowdown manifold which is connected to the turbocharger and the scavenging manifold that bypasses the turbocharger. By separately actuating the exhaust valves using variable valve actuation, the exhaust flow is split between two manifolds, thereby reducing the overall engine backpressure and lowering pumping losses. In this paper, results from zero-dimensional and one-dimensional simulations of a multicylinder RCCI light-duty engine equipped with DEP are presented.

We present an approach in which an open-source software infrastructure is used for testing the behavior of autonomous vehicles through computer simulation. This software infrastructure is called CAVE, from Connected Autonomous Vehicle Emulator. As a software platform that allows rapid, low-cost and risk-free testing of novel designs, methods and software components, CAVE accelerates and democratizes research and development activities in the field of autonomous navigation.

The paper describes a methodology to co-simulate, with high fidelity, simultaneously and in one computational framework, all of the main vehicle subsystems for improved engineering design. The co-simulation based approach integrates in MATLAB/Simulink a physics-based tire model with high fidelity vehicle dynamics model and an accurate powertrain model allowing insights into 1) how the dynamics of a vehicle affect fuel consumption, quality of emission and vehicle control strategies and 2) how the choice of powertrain systems influence the dynamics of the vehicle; for instance how the variations in drive shaft torque affects vehicle handling, the maximum achievable acceleration of the vehicle, etc. The goal of developing this co-simulation framework is to capture the interaction between powertrain and rest of the vehicle in order to better predict, through simulation, the overall dynamics of the vehicle.

A study of partially premixed combustion (PPC) with non-oxygenated 91 pump octane number1 (PON) commercially available gasoline was performed using a heavy-duty (HD) compression-ignition (CI) 2.44 l Caterpillar 3401E single-cylinder oil test engine (SCOTE). The experimental conditions selected were a net indicated mean effective pressure (IMEP) of 11.5 bar, an engine speed of 1300 rev/min, an intake temperature of 40°C with intake and exhaust pressures of 200 and 207 kPa, respectively. The baseline case for all studies presented had 0% exhaust gas recirculation (EGR), used a dual injection strategy a -137 deg ATDC pilot SOI and a -6 deg ATDC main start-of-injection (SOI) timing with a 30/70% pilot/main fuel split for a total of 5.3 kg/h fueling (equating to approximately 50% load). Combustion and emissions characteristics were explored relative to the baseline case by sweeping main and pilot SOI timings, injection split fuel percentage, intake pressure, load and EGR levels.

Optimal fuel injection strategies are obtained with a micro-genetic algorithm and an adaptive gradient method for a nonroad, medium-speed DI diesel engine equipped with a multi-orifice, asynchronous fuel injection system. The gradient optimization utilizes a fast-converging backtracking algorithm and an adaptive cost function which is based on the penalty method, where the penalty coefficient is increased after every line search. The micro-genetic algorithm uses parameter combinations of the best two individuals in each generation until a local convergence is achieved, and then generates a random population to continue the global search. The optimizations have been performed for a two pulse fuel injection strategy where the optimization parameters are the injection timings and the nozzle orifice diameters.

A previously developed CFD-based optimization tool is utilized to find optimal engine operating conditions with respect to fuel consumption and emissions. The optimization algorithm employed is based on the steepest descent method where an adaptive cost function is minimized along each line search using an effective backtracking strategy. The adaptive cost function is based on the penalty method, where the penalty coefficient is increased after every line search. The parameter space is normalized and, thus, the optimization occurs over the unit cube in higher-dimensional space. The application of this optimization tool is demonstrated for the Sulzer S20, a central-injection, non-road DI diesel engine. The optimization parameters are the start of injection of the two pulses of a split injection system, the duration of each pulse, the exhaust gas recirculation rate, the boost pressure and the compression ratio.

A global optimization method has been developed for an engine simulation code and utilized in the search of optimal fuel injection strategies. This method uses a Lagrange interpolation function which interpolates engine output data generated at the vertices and the intermediate points of the input parameters. This interpolation function is then used to find a global minimum over the entire parameter set, which in turn becomes the starting point of a CFD-based optimization. The CFD optimization is based on a steepest descent method with an adaptive cost function, where the line searches are performed with a fast-converging backtracking algorithm. The adaptive cost function is based on the penalty method, where the penalty coefficient is increased after every line search. The parameter space is normalized and, thus, the optimization occurs over the unit cube in higher-dimensional space.

Engine-out CO emission and fuel conversion efficiency were measured in a highly-dilute, low-temperature diesel combustion regime over a swirl ratio range of 1.44-7.12 and a wide range of injection timing. At fixed injection timing, an optimal swirl ratio for minimum CO emission and fuel consumption was found. At fixed swirl ratio, CO emission and fuel consumption generally decreased as injection timing was advanced. Moreover, a sudden decrease in CO emission was observed at early injection timings. Multi-dimensional numerical simulations, pressure-based measurements of ignition delay and apparent heat release, estimates of peak flame temperature, imaging of natural combustion luminosity and spray/wall interactions, and Laser Doppler Velocimeter (LDV) measurements of in-cylinder turbulence levels are employed to clarify the sources of the observed behavior.

A numerical simulation and optimization study was conducted for a medium speed direct injection diesel engine. The engine's operating characteristics were first matched to available experimental data to test the validity of the numerical model. The KIVA-3V ERC CFD code was then modified to allow independent spray events from two rows of nozzle holes. The angular alignment, nozzle hole size, and injection pressure of each set of nozzle holes were optimized using a micro-genetic algorithm. The design fitness criteria were based on a multi-variable merit function with inputs of emissions of soot, NOx, unburned hydrocarbons, and fuel consumption targets. Penalties to the merit function value were used to limit the maximum in-cylinder pressure and the burned gas temperature at exhaust valve opening. The optimization produced a 28.4% decrease in NOx and a 40% decrease in soot from the baseline case, while giving a 3.1% improvement in fuel economy.

The University of Wisconsin - Madison hybrid vehicle team has designed and constructed a four-wheel drive, charge sustaining, parallel hybrid-electric sport utility vehicle for entry into the FutureTruck 2003 competition. This is a multi-year project utilizing a 2002 4.0 liter Ford Explorer as the base vehicle. Wisconsin's FutureTruck, nicknamed the ‘Moolander’, weighs 2000 kg and includes a prototype aluminum frame. The Moolander uses a high efficiency, 1.8 liter, common rail, turbo-charged, compression ignition direct injection (CIDI) engine supplying 85 kW of peak power and an AC induction motor that provides an additional 60 kW of peak power. The 145 kW hybrid drivetrain will out-accelerate the stock V6 powertrain while producing similar emissions and drastically reducing fuel consumption. The PNGV Systems Analysis Toolkit (PSAT) model predicts a Federal Testing Procedure (FTP) combined driving cycle fuel economy of 16.05 km/L (37.8 mpg).

Neural networks are useful tools for optimization studies since they are very fast, so that while capturing the accuracy of multi-dimensional CFD calculations or experimental data, they can be run numerous times as required by many optimization techniques. This paper describes how a set of neural networks trained on a multi-dimensional CFD code to predict pressure, temperature, heat flux, torque and emissions, have been used by a genetic algorithm in combination with a hill-climbing type algorithm to optimize operating parameters of a diesel engine over the entire speed-torque map of the engine. The optimized parameters are mass of fuel injected per cycle, shape of the injection profile for dual split injection, start of injection, EGR level and boost pressure. These have been optimized for minimum emissions. Another set of neural networks have been trained to predict the optimized parameters, based on the speed-torque point of the engine.

Neural networks have been used for engine computations in the recent past. One reason for using neural networks is to capture the accuracy of multi-dimensional CFD calculations or experimental data while saving computational time, so that system simulations can be performed within a reasonable time frame. This paper describes three methods to improve upon neural network predictions. Improvement is demonstrated for in-cylinder pressure predictions in particular. The first method incorporates a physical combustion model within the transfer function of the neural network, so that the network predictions incorporate physical relationships as well as mathematical models to fit the data. The second method shows how partitioning the data into different regimes based on different physical processes, and training different networks for different regimes, improves the accuracy of predictions.

The University of Wisconsin - Madison FutureTruck Team has designed and built a four-wheel drive, charge sustaining, parallel hybrid-electric sport utility vehicle for entry into the FutureTruck 2002 competition. This is a two-year project with tiered goals; the base vehicle for both years is a 2002 Ford Explorer. Wisconsin's FutureTruck, nicknamed the ‘Moolander’, weighs approximately 2050 kg. The vehicle uses a high efficiency, 2.5 liter, turbo-charged, compression ignition common rail, direct-injection engine supplying approximately 100 kW of peak power and a AC induction motor that provides an additional 33 kW of peak power. This hybrid drivetrain is an attractive alternative to the large displacement V6 drivetrain, as it provides comparable performance with similar emissions and drastically reduced fuel consumption.

Combustion under stratified operating conditions in a direct-injection spark-ignition engine was investigated using simultaneous planar laser-induced fluorescence imaging of the fuel distribution (via 3-pentanone doped into the fuel) and the combustion products (via OH, which occurs naturally). The simultaneous images allow direct determination of the flame front location under highly stratified conditions where the flame, or product, location is not uniquely identified by the absence of fuel. The 3-pentanone images were quantified, and an edge detection algorithm was developed and applied to the OH data to identify the flame front position. The result was the compilation of local flame-front equivalence ratio probability density functions (PDFs) for engine operating conditions at 600 and 1200 rpm and engine loads varying from equivalence ratios of 0.89 to 0.32 with an unthrottled intake. Homogeneous conditions were used to verify the integrity of the method.