Search Results

Forecasting the motion of the leading vehicle is a critical task for connected autonomous vehicles as it provides an efficient way to model the leading-following vehicle behavior and analyze the interactions. In this study, a personalized time-series modeling approach for leading vehicle trajectory prediction considering different driving styles is proposed. The method enables a precise, personalized trajectory prediction for leading vehicles with limited inter-vehicle communication signals, such as vehicle speed, acceleration, space headway, and time headway of the front vehicles. Based on the learning nature of human beings that a human always tries to solve problems based on grouping and similar experience, three different driving styles are first recognized based on an unsupervised clustering with a Gaussian Mixture Model (GMM).

The vision for the future automotive chassis is to interconnect the lateral, longitudinal, and vertical dynamics by separately controlling driving, braking, steering, and damping of each individual wheel. A major advantage of all wheel drive electric vehicles with four in-wheel motors is the possibility to control the torque and speed at each wheel independently. This paper proposes a traction controller for such a vehicle. It estimates the road's adhesion potential at each wheel and adjusts each motor voltage, such that the longitudinal slip is kept in an optimal range. For development and validation, a full vehicle model is designed in ADAMS/View software, in co-simulation with motor and control elements, modeled in MATLAB/Simulink.

A serpentine flow channel is one of the most common and practical channel layouts for a PEM fuel cell since it ensures the removal of water produced in a cell. While the reactant flows along the flow channel, it can also leak or cross to neighboring channels via the porous gas diffusion layer due to a high pressure gradient. Such a cross flow leads to effective water removal in a gas diffusion layer thus enlarging the active area for reaction although this cross flow has largely been ignored in previous studies. In this study, neutron radiography is applied to investigate the liquid water accumulation and its effect on the performance of a PEM fuel cell. Liquid water tends to accumulate in the gas diffusion layer adjacent to the flow channel area while the liquid water formed in the gas diffusion layer next to the channel land area seems to be effectively removed by the cross leakage flow between the adjacent flow channels.

A fuel cell hybrid powertrain design is implemented and optimized by the University of Waterloo Alternative Fuels Team for the ChallengeX competition. A comprehensive set of bench-top and in-vehicle validation results are used to generate accurate fuel cell vehicle models for SIL/HIL control strategy testing and tuning. The vehicle is brought to a “99% buy-off” level of production readiness, and a detailed crashworthiness analysis is performed. The vehicle performance is compared to Vehicle Technical Specifications (VTS).

A serpentine flow channel can be considered as neighboring channels connected in series, and is one of the most common and practical channel layouts for PEM fuel cells since it ensures the removal of liquid water produced in a cell with excellent performance and acceptable parasitic load. During the reactant flows along the flow channel, it can also leak or cross directly to the neighboring channel via the porous gas diffusion layer due to the high pressure gradient caused by the short distance. Such a cross flow leads to a larger effective flow area resulting in a substantially lower amount of pressure drop in an actual PEM fuel cell compared to the case without cross flow. In this work, an analytical solution is obtained for the cross flow in a PEM fuel cell with a serpentine flow channel based on the assumption that the velocity of cross flow is linearly distributed in the gas diffusion layer between two successive U-turns.

In this work, a new air hybrid engine is introduced in which two throttles are used to manage the engine load in three modes of operation i.e. braking, air motor, and conventional mode. The concept includes an air tank to store pressurized air during braking and rather than a fully variable valve timing (VVT) system, two throttles are utilized. Use of throttles can significantly reduce the complexity of air hybrid engines. The valves need three fixed timing schedules for the three modes of operation. To study this concept, for each mode, the results of engine simulations using GT-Power software are used to generate the operating maps. These maps show the maximum braking torque as well as maximum air motor torque in terms of air tank pressure and engine speed. Moreover, the resulting maps indicate the operating conditions under which each mode is more effective. Based on these maps, a power management strategy is developed to achieve improved fuel economy.

Robust lane marking detection remains a challenge, particularly in temperate climates where markings degrade rapidly due to winter conditions and snow removal efforts. In previous work, dynamic Bayesian networks with heuristic features were used with the feature distributions trained using semi-supervised expectation maximization, which greatly reduced sensitivity to initialization. This work has been extended in three important respects. First, the tracking formulation used in previous work has been corrected to prevent false positives in situations where only poor RANSAC hypotheses were generated. Second, the null hypothesis is reformulated to guarantee that detected hypotheses satisfy a minimum likelihood. Third, the computational requirements have been greatly reduced by computing an upper bound on the marginal likelihood of all part hypotheses upon generation and rejecting parts with an upper bound less likely than the null hypothesis.

Recently, the development of braking assistance system has largely benefit the safety of both driver and pedestrians. A robust prediction and detection of driver braking intention will enable driving assistance system response to traffic situation correctly and improve the driving experience of intelligent vehicles. In this paper, two types unsupervised clustering methods are used to build a driver braking intention predictor. Unsupervised machine learning algorithms has been widely used in clustering and pattern mining in previous researches. The proposed unsupervised learning algorithms can accurately recognize the braking maneuver based on vehicle data captured with CAN bus. The braking maneuver along with other driving maneuvers such as normal driving will be clustered and the results from different algorithms which are K-means and Gaussian mixture model (GMM) will be compared.

The automobile industry has been undergoing a transition from fossil fuels to a low emission platform due to stricter environmental policies and energy security considerations. Electric vehicles, powered by lithium-ion batteries, have started to attain a noticeable market share recently due to their stable performance and maturity as a technology. However, electric vehicles continue to suffer from two disadvantages that have limited widespread adoption: charging time and energy density. To mitigate these challenges, vehicle Original Equipment Manufacturers (OEMs) have developed different vehicle architectures to extend the vehicle range. This work seeks to compare various powertrains, including: combined power battery electric vehicles (BEV) (zinc-air and lithium-ion battery), zero emission fuel cell vehicles (FCV)), conventional gasoline powered vehicles (baseline internal combustion vehicle), and ICE engine extended range hybrid electric vehicle.

Dynamic modelling of the contact between the tires of automobiles and the road surface is crucial for accurate and effective vehicle dynamic simulation and the development of various driving controllers. Furthermore, an accurate prediction of the rolling resistance is needed for powertrain controllers and controllers designed to reduce fuel consumption and engine emissions. Existing models of tires include physics-based analytical models, finite element based models, black box models, and data driven empirical models. The main issue with these approaches is that none of these models offer the balance between accuracy of simulation and computational cost that is required for the model-based development cycle. To address this issue, we present a volumetric approach to model the forces/moments between the tire and the road for vehicle dynamic simulations.

Proton exchange membrane fuel cell (PEMFC) is considered to be one of the best clean power sources for transportation application. Water management is a critical issue, conventionally achieved by coating the cell components with the hydrophobic materials. In this work, the effects of one surface-coated cathode gas diffusion layer (GDL) on water removal rate, droplet dynamics, and the cell performance have been studied. The coated GDL is fabricated by coating one side of raw GDL (SpectraCarb 2050-A) with 15 wt. % of polytetrafluoroethylene (PTFE) solution but the other side remains uncoated. The raw GDL is commercial one and made of carbon fiber. The contact angles (θ) on both sides of the coated and raw GDL are measured. The pore size distribution, and capillary pressure are measured for the GDL, studied using the method of standard porosimetry (MSP). Water removal rate is measured by using a 20 ml syringe barrel, wherein a 13 mm diameter GDL token is stuck on the barrel opening.

In this paper, gear ratios of a two-speed transmission system are optimized for an electric passenger car. Quasi static system models, including the vehicle model, the motor, the battery, the transmission system, and drive cycles are established in MATLAB/Simulink at first. Specifically, since the regenerative braking capability of the motor is affected by the SoC of battery and motors torque limitation in real time, the dynamical variation of the regenerative brake efficiency is considered in this study. To obtain the optimal gear ratios, iterations are carried out through Nelder-Mead algorithm under constraints in MATLAB/Simulink. During the optimization process, the motor efficiency is observed along with the drive cycle, and the gear shift strategy is determined based on the vehicle velocity and acceleration demand. Simulation results show that the electric motor works in a relative high efficiency range during the whole drive cycle.

The development of a comprehensive battery simulator is essential for future improvements in the durability, performance and service life of lithium-ion batteries. Although simulations can never replace actual experimental data, they can still be used to provide valuable insights into the performance of the battery, especially under different operating conditions. In addition, a single-cell model can be easily extended to the pack level and can be used in the optimization of a battery pack. The first step in building a simulator is to create a model that can effectively capture both the voltage response and thermal behavior of the battery. Since these effects are coupled together, creating a robust simulator requires modeling both components. This paper will develop a battery simulator, where the entire battery model will be composed of four smaller submodels: a heat generation model, a thermal model, a battery parameter model and a voltage response model.

Supervisory control strategies for a hybrid fuel cell powertrain are developed and simulated using Simulink models and the Powertrain Systems Analysis Toolkit (PSAT). The control strategy selects the power splitting ratio between a 65kW Hydrogenics fuel cell power module and a 70kW Cobasys Nickel Metal Hydride (NiMH) battery pack. Simple control algorithms targeting a battery pack State of Charge (SOC), or maximizing the instantaneous powertrain efficiency are initially considered and analyzed. A comprehensive control strategy optimizing powertrain efficiency, vehicle performance, emissions, and long-term reliability is then developed and simulated. The simulated vehicle using the comprehensive control strategy with reliability considerations exhibits a 21% mileage improvement as compared to a simple rule-based control algorithm.

A fuel cell-battery hybrid powertrain SUV vehicle is designed using an optimized model-based design process. Powertrain and fuel storage components selected include a 65 kW Polymer Electrolyte Membrane Fuel Cell (PEMFC) power module, two 67 kW electric traction motors, a 35 MPa compressed hydrogen storage tank, a 70 kW nickel metal hydride battery pack, and a University of Waterloo in-house DC/DC converter design. Hardware control uses two controllers, a main supervisory controller and a subsystem controller in addition to any embedded component control modules. Two key innovations of this work include the hybrid control strategy and the DC/DC converter. The final powertrain characteristics are expected to meet a set of Vehicle Technical Specifications (VTS).

With the widespread development of automated driving systems (ADS), it is imperative that standardized testing methodologies be developed to assure safety and functionality. Scenario testing evaluates the behavior of an ADS-equipped subject vehicle (SV) in predefined driving scenarios. This paper compares four modes of performing such tests: closed-course testing with real actors, closed-course testing with surrogate actors, simulation testing, and closed-course testing with mixed reality. In a collaboration between the Waterloo Intelligent Systems Engineering (WISE) Lab and AAA, six automated driving scenario tests were executed on a closed course, in simulation, and in mixed reality. These tests involved the University of Waterloo’s automated vehicle, dubbed the “UW Moose”, as the SV, as well as pedestrians, other vehicles, and road debris.

Modern electrified vehicles rely on drivers to manually adjust control parameters to modify the vehicle's powertrain, such as regenerative braking strength selection or drive mode selection. However, this reliance on infrequent driver input may lead to a mismatch between the selected powertrain control modifiers and the true driving environment. It is therefore advantageous for an electric vehicle's powertrain controller to make online identifications of the current driving conditions. This paper proposes an online driving condition identification scheme that labels drive cycle intervals collected in real-time based on a clustering model, with the objective of informing adaptive powertrain control strategies. HDBSCAN and K-means clustering models are fitted to a data set of drive cycle intervals representing a full range of characteristic driving conditions.

An electric vehicle model has been developed with four direct-drive in-wheel motors. A high-level vehicle stability controller is proposed, which uses the principles of fuzzy logic to determine the corrective yaw moment required to minimize the vehicle sideslip and yaw rate errors. A genetic algorithm has been used to optimize the parameters of the fuzzy controller. The performance of the controller is evaluated as the vehicle is driven through a double-lane-change maneuver. Preliminary results indicate that the proposed control system has the ability to improve the performance of the vehicle considerably.