Search Results

Electrochemical models of lithium ion batteries are today a standard tool in the automotive industry for activities related to the computer-aided engineering design, analysis, and optimization of energy storage systems for electrified vehicles. One of the challenges in the development or use of such models is the need of detailed information on the cell and electrode geometry or properties of the electrode and electrolyte materials, which are typically unavailable or difficult to retrieve by end-users. This forces engineers to resort to “hand-tuning” of many physical and geometrical parameters, using standard cell-level characterization tests. This paper proposes a method to provide information and data on individual electrode performance that can be used to simplify the calibration process for electrochemical models.

Engine control units (ECUs) on heavy trucks have been capable of storing “last stop” or “hard stop” data for some years. These data provide useful information to accident reconstruction personnel. In past studies, these data have been analyzed and compared to higher-resolution on-vehicle data for several heavy trucks and several makes of passenger cars. Previous published studies have been quite helpful in understanding the limitations and/or anomalies associated with these data. This study was designed and executed to add to the technical understanding of heavy truck event data recorders (EDR), specifically data associated with a modern Cummins power plant ECU. Emergency “full-treadle” stops were performed at many combinations of load-speed-surface coefficient conditions. In addition, brake-in-curve tests were performed on wet Jennite for various conditions of disablement of the braking system.

Over the years numerous researchers have suggested that the ionization current signal carries within it combustion relevant information. The possibility of using this signal for diagnostics and control provides motivation for continued research in this area. To be able to use the ion current signal for feedback control a reliable estimate of some combustion related parameter is necessary and therein lies the difficulty. Given the nature of the ion current signal this is not a trivial task. Fei An et al. [1] employed PCA for feature extraction and then used these feature vectors to design a neural network based classifier for the estimation of air to fuel ratio (AFR). Although the classifier predicted AFR with sufficient reliability, a major draw back was that the ion current signals used for prediction were averaged signals thus precluding a cycle to cycle estimate of AFR.

This paper describes the design and development of the hardware, electronics, and software components of a state-of-the-art automated steering controller, the SEA, Ltd. ASC. The function of the ASC is to input to a vehicle virtually any steering profile with both high accuracy and repeatability. The ASC is designed to input profiles having steering rates and timing that are in excess of the limits of a human driver. The ASC software allows the user to specify steering profiles and select controller settings, including motor controller gains, through user-interface windows. This makes it possible for the test driver to change steering profiles and settings immediately after running any test maneuver. The motor controller used in the ASC offers self-contained signal input, output, and data storage capabilities. Thus, the ASC can operate as a standalone steering machine or it can be incorporated into typical existing, on-vehicle data acquisition systems.

Automated driving has become a very promising research direction with many successful deployments and the potential to reduce car accidents caused by human error. Automated driving requires automated path planning and tracking with the ability to avoid collisions as its fundamental requirement. Thus, plenty of research has been performed to achieve safe and time efficient path planning and to develop reliable collision avoidance algorithms. This paper uses a data-driven approach to solve the abovementioned fundamental requirement. Consequently, the aim of this paper is to develop Deep Reinforcement Learning (DRL) training pipelines which train end-to-end automated driving agents by utilizing raw sensor data. The raw sensor data is obtained from the Carla autonomous vehicle simulation environment here. The proposed automated driving agent learns how to follow a pre-defined path with reasonable speed automatically.