Search Results

Engineering design-decisions often involve many attributes which can differ in the levels of their importance to the decision maker (DM), while also exhibiting complex statistical relationships. Learning a decision-making policy which accurately represents the DM’s actions has long been the goal of decision analysts. To circumvent elicitation and modeling issues, this process is often oversimplified in how many factors are considered and how complicated the relationships considered between them are. Without these simplifications, the classical lottery-based preference elicitation is overly expensive, and the responses degrade rapidly in quality as the number of attributes increase. In this paper, we investigate the ability of deep preference machine learning to model high-dimensional decision-making policies utilizing rankings elicited from decision makers.

The Lane Change Task (LCT) provides a simple, scorable simulation of driving, and serves as a primary task in studies of driver distraction. It is widely accepted, but somewhat limited in functionality, a problem this project partially overcomes. In the Lane Change Task, subjects drive along a road with 3 lanes in the same direction. Periodically, signs appear, indicating in which of the 3 lanes the subject should drive, which changes from sign to sign. The software is plug-and-play for a current Windows computer with a Logitech steering/pedal assembly, even though the software was written 18 years ago. For each timestamp in a trial, the software records the steering wheel angle, speed, and x and y coordinates of the subject. A limitation of the LCT is that few characteristics of this useful software can be readily modified as only the executable code is available (on the ISO 26022 website), not the source code.

Making manned and remotely-controlled wheeled and tracked vehicles easier to drive, especially off-road, is of great interest to the U.S. Army. If vehicles are easier to drive (especially closed hatch) or if they are driven autonomously, then drivers could perform additional tasks (e.g., operating weapons or communication systems), leading to reduced crew sizes. Further, poorly driven vehicles are more likely to get stuck, roll over, or encounter mines or improvised explosive devices, whereby the vehicle can no longer perform its mission and crew member safety is jeopardized. HMI technology and systems to support human drivers (e.g., autonomous driving systems, in-vehicle monitors or head-mounted displays, various control devices (including game controllers), navigation and route-planning systems) need to be evaluated, which traditionally occurs in mission-specific (and incomparable) evaluations.

Automated vehicles (AVs)—and the automated driving systems (ADSs) that enable them—are increasing in prevalence but remain far from ubiquitous. Progress has occurred in spurts, followed by lulls, while the motor transportation system learns to design, deploy, and regulate AVs. Automated Vehicles: A Human/Machine Co-learning Experience focuses on how engineers, regulators, and road users are all learning about a technology that has the potential to transform society. Those engaged in the design of ADSs and AVs may find it useful to consider that the spurts and lulls and stakeholder tussles are a normal part of technology transformations; however, this report will provide suggestions for effective stakeholder engagement. Click here to access the full SAE EDGETM Research Report portfolio.

Tanker trucks are commonly used for transporting liquid material including chemical and petroleum products. On the one hand, tanker trucks are susceptible to rollover accidents due to the high center of gravity when they are loaded and due to the liquid sloshing effects when the tank is partially filled. On the other hand, tanker truck rollover accidents are among the most dangerous vehicle crashes, frequently resulting in serious to fatal driver injuries and significant property damage, because the liquid cargo is often hazardous and flammable. Therefore, effective schemes for tanker truck rollover avoidance are highly desirable and can bring a considerable amount of societal benefit. Yet, the development of such schemes is challenging, as tanker trucks can operate in various environments and be affected by manufacturing variability, aging, degradation, etc. This paper considers the use of Learning Reference Governor (LRG) for tanker truck rollover avoidance.

The need for transient thermal simulations in vehicle packaging studies has grown rapidly in recent years. To date, the computational costs associated with the transient simulation of 3D conjugate heat transfer phenomena has prohibited the widespread use of full vehicle transient simulations. This paper presents results from a recent study that explored a method to circumvent the computational costs associated with long transient conjugate heat transfer simulations. The proposed method first segregates the thermal structural and fluid physics domains to take advantage of time scale differences. The two domains are then re-coupled to calculate a series of steady state conjugate heat transfer simulations at various vehicle speeds. The local convection terms are then used to construct a set of surrogate models dependent on vehicle speed, that predict the local heat transfer coefficients and the local near wall fluid temperatures.

Springback is a common phenomenon in automotive manufacturing processes, caused by the elastic recovery of the internal stresses during unloading. A thorough understanding of springback is essential for the design of tools used in sheet metal forming operations. A DBS (Draw-bead Simulator) has been used to simulate the forming process for two different sheet metals: aluminum and steel. Two levels of pulling force and two die radii have been enforced to the experimental process to get different springback. Also, the Digital Image Correlation (DIC) system has been adopted to capture the sheet contour and measure the amount of side-wall-curl (sheet springback) after deformation. This paper presents the influence of the material properties, force, and die radius on the deformation and springback after forming. A thorough understanding of this phenomenon is essential, seeing that any curvature in the part wall can affect quality and sustainability.

This study uses full drive cycle simulation to compare the fuel consumption of a vehicle with a turbocharged (TC) engine to the same vehicle with an alternative boosting technology, namely, a hybrid supercharger, in which a planetary gear mechanism governs the power split to the supercharger between the crankshaft and a 48 V 5 kW electric motor. Conventional mechanically driven superchargers or electric superchargers have been proposed to improve the dynamic response of boosted engines, but their projected fuel efficiency benefit depends heavily on the engine transient response and driver/cycle aggressiveness. The fuel consumption benefits depend on the closed-loop engine responsiveness, the control tuning, and the torque reserve needed for each technology. To perform drive cycle analyses, a control strategy is designed that minimizes the boost reserve and employs high rates of combustion dilution via exhaust gas recirculation (EGR).

This paper presents a simple method of using Voronoi partitions for estimating vehicle fuel economy from a limited set of engine operating conditions. While one of the overarching goals of engine research is to continually improve vehicle fuel economy, evaluating the impact of a change in engine operating efficiency on the resulting fuel economy is a non-trivial task and typically requires drive cycle simulations with experimental data or engine model predictions and a full suite of engine controllers over a wide range of engine speeds and loads. To avoid the cost of collecting such extensive data, proprietary methods exist to estimate fuel economy from a limited set of engine operating conditions. This study demonstrates the use of Voronoi partitions to cluster and quantize the fuel consumed along a complex trajectory in speed and load to generate fuel consumption estimates based on limited simulation or experimental results.

Selecting the right transportation platform is challenging, whether it is at a personal level or at an organizational level. In settings where predominantly the functional aspects rule the decision making process, defining the mobility of a vehicle is critical for comparing different offerings and making acquisition decisions. With the advent of intelligent vehicles, exhibiting partial to full autonomy, this challenge is exacerbated. The same vehicle may traverse independently and with greater tolerance for acceleration than human occupied vehicles, while, at the same time struggle with obstacle avoidance. The problem presents itself at the individual vehicle sensing level and also at the vehicle/fleet level. At the sensing and information level, one can be looking at issues of latency, bandwidth and optimal information fusion from multiple sources including privileged sensing. At the overall vehicle level, one focuses more on the ability to complete missions.

The coefficient of friction between surfaces is an important criterion for predicting metal behavior during sheet metal stamping processes. This research introduces an innovative technique to find the coefficient of friction on a lubricated aluminum sheet metal surface by simulating the industrial manufacturing stamping process while using 3D digital image correlation (3D-DIC) to track the deformation. During testing, a 5000 series aluminum specimen is placed inside a Stretch-Bend-Draw Simulator (SBDS), which operates with a tensile machine to create a stretch and bend effect. The friction coefficient at the contact point between an alloy sheet metal and a punch tool is calculated using an empirical equation previously developed. In order to solve for the unknown friction coefficient, the load force and the drawback force are both required. The tensile machine software only provides the load force applied on the specimen by the load cell.

As part of its midterm evaluation of the 2022-2025 light-duty greenhouse gas (GHG) standards, the Environmental Protection Agency (EPA) has been acquiring fuel efficiency data from testing of recent engines and vehicles. The benchmarking data are used as inputs to EPA’s Advanced Light Duty Powertrain and Hybrid Analysis (ALPHA) vehicle simulation model created to estimate GHG emissions from light-duty vehicles. For complete powertrain modeling, ALPHA needs both detailed engine fuel consumption maps and transmission efficiency maps. EPA’s National Vehicle and Fuels Emissions Laboratory has previously relied on contractors to provide full characterization of transmission efficiency maps. To add to its benchmarking resources, EPA developed a streamlined more cost-effective in-house method of transmission testing, capable of gathering a dataset sufficient to broadly characterize transmissions within ALPHA.

The U.S. Environmental Protection Agency’s (EPA’s) Advanced Light-Duty Powertrain and Hybrid Analysis (ALPHA) tool was created to estimate greenhouse gas (GHG) emissions from light-duty vehicles. ALPHA is a physics-based, forward-looking, full vehicle computer simulation capable of analyzing various vehicle types with different powertrain technologies, showing realistic vehicle behavior, and auditing of all energy flows in the model. In preparation for the midterm evaluation (MTE) of the 2017-2025 light-duty GHG emissions rule, ALPHA has been refined and revalidated using newly acquired data from model year 2013-2016 engines and vehicles. The robustness of EPA’s vehicle and engine testing for the MTE coupled with further validation of the ALPHA model has highlighted some areas where additional data can be used to add fidelity to the engine model within ALPHA.

Mcity at the University of Michigan in Ann Arbor provides a realistic off-roadway environment in which to test vehicles and drivers in complex traffic situations. It is intended for testing of various levels of vehicle automation, from advanced driver assistance systems (ADAS) to fully self-driving vehicles. In a recent human factors study of interfaces for teen drivers, we performed parallel experiments in a driving simulator and Mcity. We implemented driving scenarios of moderate complexity (e.g., passing a vehicle parked on the right side of the road just before a pedestrian crosswalk, with the parked vehicle partially blocking the view of the crosswalk) in both the simulator and at Mcity.

A GT-SUITE vehicle-aftertreatment model has been developed to examine the cold-start emissions reduction capabilities of a Vacuum Insulated Catalytic Converter (VICC). This converter features a thermal management system to maintain the catalyst monolith above its light-off temperature between trips so that most of a vehicle’s cold-start exhaust emissions are avoided. The VICC thermal management system uses vacuum insulation around the monoliths. To further boost its heat retention capacity, a metal phase-change material (PCM) is packaged between the monoliths and vacuum insulation. To prevent overheating of the converter during periods of long, heavy engine use, a few grams of metal hydride charged with hydrogen are attached to the hot side of the vacuum insulation. The GT-SUITE model successfully incorporated the transient heat transfer effects of the PCM using the effective heat capacity method.

Combatting the modification of automotive control systems is a current and future challenge for OEMs and suppliers. ‘Chip-tuning’ is a manifestation of manipulation of a vehicle's original setup and calibration. With the increase in automotive functions implemented in software and corresponding business models, chip tuning will become a major concern. Recognizing and reporting of tuned control units in a vehicle is required for technical as well as legal reasons. This work approaches the problem by capturing the behavior of relevant control units within a machine learning system called a recognition module. The recognition module continuously monitors vehicle's sensor data. It comprises a set of classifiers that have been trained on the intended behavior of a control unit before the vehicle is delivered. When the vehicle is on the road, the recognition module uses the classifier together with current data to ascertain that the behavior of the vehicle is as intended.

Driving simulators offer a safe alternative to on-road driving for the evaluation of performance. In addition, simulated drives allow for controlled manipulations of traffic situations producing a more consistent and objective assessment experience and outcome measure of crash risk. Yet, few simulator protocols have been validated for their ability to assess driving performance under conditions that result in actual collisions. This paper presents results from a new Simulated Driving Assessment (SDA), a 35- to-40-minute simulated assessment delivered on a Real-Time® simulator. The SDA was developed to represent typical scenarios in which teens crash, based on analyses from the National Motor Vehicle Crash Causation Survey (NMVCCS). A new metric, failure to brake, was calculated for the 7 potential rear-end scenarios included in the SDA and examined according two constructs: experience and skill.

The fidelity of the hybrid electric vehicle simulation is increased with the integration of a computationally-efficient finite-element based electric machine model, in order to address optimization of component design for system level goals. In-wheel electric motors are considered because of the off-road military application which differs significantly from commercial HEV applications. Optimization framework is setup by coupling the vehicle simulation to the constrained optimization solver. Utilizing the increased design flexibility afforded by the model, the solver is able to reshape the electric machine's efficiency map to better match the vehicle operation points. As the result, the favorable design of the e-machine is selected to improve vehicle fuel economy and reduce cost, while satisfying performance constraints.

An application of variation simulation for predicting vehicle interior driveline vibration is presented. The model, based on a “Monte Carlo”-style approach, predicts the noise, vibration and harshness (NVH) response of the vehicle driveline based on distributions of imbalance and runout derived from manufacturing production variation (the forcing function) and the vehicle's sensitivity to the forcing function. The model is used to illustrate the change in vehicle interior vibration that results when changes are made to production variation for runout and imbalance of driveline components, and how those same changes result in different responses based on vehicle sensitivity.

The cooling system of Series Hybrid Electric Vehicles (SHEVs) is more complicated than that of conventional vehicles due to additional components and various cooling requirements of different components. In this study, a numerical model of the cooling system for a SHEV is developed to investigate the thermal responses and power consumptions of the cooling system. The model is created for a virtual heavy duty tracked SHEV. The powertrain system of the vehicle is also modeled with Vehicle-Engine SIMulation (VESIM) previously developed by the Automotive Research Center at the University of Michigan. VESIM is used for the simulation of powertrain system behaviors under three severe driving conditions and during a realistic driving cycle. The output data from VESIM are fed into the cooling system simulation to provide the operating conditions of powertrain components.