Search Results

Connected and automated vehicles (CAVs) promise to reshape two areas of the mobility industry: the transportation and driving experience. The connected feature of the vehicle uses communication protocols to provide awareness of the surrounding world while the automated feature uses technology to minimize driver dependency. Constituting a subset of connected technologies, vehicle-to-infrastructure (V2I) technologies provide vehicles with real-time traffic light information, or Signal Phase and Timing (SPaT) data. In this paper, the vehicle and SPaT data are combined with a reinforcement learning (RL) method as an effort to minimize the vehicle’s energy consumption. Specifically, this paper explores the implementation of the deep deterministic policy gradient (DDPG) algorithm. As an off-policy approach, DDPG utilizes the maximum Q-value for the state regardless of the previous action performed.

As the automotive industry faces tighter fuel economy and emission regulations, it is becoming increasingly important to improve powertrain system efficiency. One of the areas to improve powertrain efficiency is the thermal management system. By controlling how to distribute the heat rejected by the engine, especially during the warm-up stage under cold temperatures, an engine thermal management system can improve the overall energy efficiency of the powertrain system. Conventionally, engine thermal management systems have been operated by a mechanical water pump and a thermostat. However, the recent introduction of electric water pumps and electrically-controlled flow valves allow for more sophisticated control of the thermal management system. In this study, these two different thermal management system architectures are investigated by conducting simulations.

As a viable alternative to the conventional hybrid electric vehicles, so called “mild” hybrid drivetrains are currently being implemented in production vehicles. These mild hybrid electric vehicles use an Integrated Starter Generator (ISG) to simply assist the internal combustion (IC) engine rather than drive the vehicle independently of the IC engine. Some of the production mild hybrid vehicles have been shown to achieve over a10 % increase in fuel efficiency with minimal additional costs. In this paper, we present a lookup table-based control scheme for the optimal control of the ISG and the IC engine on a mild hybrid vehicle. The developed control logic is implemented in Matlab/Simulink along with a mild hybrid vehicle model, which is based on an EPA light-duty vehicle model. The simulation results show that the optimally controlled mild hybrid vehicle has better fuel efficiency with comparable drivability when compared to a simple intuitive rule-based control strategy.

A neural network-based computer vision system is developed to estimate position of an excavator manipulator in real time. A camera is used to capture images of a manipulator, and the images are down-sampled and used to train a neural network. Then, the trained neural network can estimate the position of the excavator manipulator in real time. To study the feasibility of the proposed system, a webcam is used to capture images of an excavator simulation model and the captured images are used to train a neural network. The simulation results show that the developed neural network-based computer vision system can estimate the position of the excavator manipulator with an acceptable accuracy.

Due to the high demand of fuel efficient construction equipment, significant research effort has been dedicated to improving excavator efficiency. Among various possibilities, methods to recuperate energy during cab swing motion have been widely examined. Electric and hydraulic hybrids designs have shown to greatly improve fuel efficiency but require drastic design changes. The redesigned systems thus require many hours of operation to offset the manufacturing costs with fuel savings. In this research, a relatively simple swing energy recuperation system is presented using an additional accumulator, fixed displacement hydraulic motor, and control valves. With the system, hydraulic fluid is stored in an accumulator, and a simple controller opens a valve to allow the stored energy to assist the engine in running the main pumps.

Hydraulic excavators perform numerous tasks in the construction and mining industry. Although ground grading is a common task, proper grading cannot easily be achieved. Grading requires an experienced operator to control the boom, arm, and bucket cylinders in a rapid and coordinated manner. Due to this reason, automated grade control is being considered as an effective alternative to conventional human-operated ground grading. In this paper, a path-planning method based on a 2D kinematic model and inverse kinematics is used to determine the desired trajectory of an excavator's boom, arm, and bucket cylinders. Then, the developed path planning method and PI control algorithms for the three cylinders are verified by a simple excavator model developed in Simulink®. The simulation results show that the automated grade control algorithm can grade level or with reduced operation time and error.