Li, Zhijian | Search NASA

DOE OSTI2024

A real-time energy and cost efficient vehicle route assignment neural recommender system

Here, this paper presents a neural network recommender system algorithm for assigning vehicles to routes based on energy and cost criteria. In this work, we applied this new approach to efficiently identify the most cost-effective medium and heavy duty truck (MDHDT) powertrain technology, from a total cost of ownership (TCO) perspective, for given trips. We employ a machine learning based approach to efficiently estimate the energy consumption of various candidate vehicles over given routes, defined as sequences of links (road segments), with little information known about internal dynamics, i.e. using high level macroscopic route information. A complete recommendation logic is then developed to allow for real-time optimum assignment for each route, subject to the operational constraints of the fleet. We show how this framework can be used to (1) efficiently provide a single trip recommendation with a top-k vehicles star ranking system, and (2) engage in more general assignment problems where n vehicles need to be deployed over m (m ≤ n) trips. This new assignment system has been deployed and integrated into the POLARIS. Transportation System Simulation Tool for use in research conducted by the Department of Energy's Systems and Modeling for Accelerated Research in Transportation (SMART) Mobility Consortium (SMART, 2024).

Energy consumption↗

DOE OSTI2021

Interlayer reinforcement of 3D printed concrete by the in-process deposition of U-nails

Highlights: • An in-process interlayer reinforcement approach for 3D concrete printing was proposed through the concurrent deposition of U-nails. • Significant strength and toughness improvement was achieved for U-nail reinforced 3D-printed concrete. • The bridge linking effect and dowel action of U-nails were analysed. • Response surface method were utilised to quantify the effects of U-nails on the interlayer bonding behaviour. 3D concrete printing has tremendous potential for construction manufacturing; however, weak interface bonding between adjacent layers remains a well-known issue that affects the mechanical properties of printed structures. The layers introduce anisotropy and reduce the capacity to resist tensile and shear loads. Reinforcements, inserted perpendicular to the printed layers to traverse the interfaces, can improve these limitations, but the insertion of reinforcements is difficult to achieve in practice, and there are few published studies exploring appropriate methods. This study presents a promising approach using U-shaped nails inserted into concrete during the printing process. The bridging effect and dowel action of the applied U-nails are visualised and analysed to elucidate the toughness improvement. The ultimate tensile strength and shear strength of 3D printed concrete are significantly increased by 145.0% and 220.0%, respectively. U-nails with a filament thickness of 2–2.5 mm are recommended to yield optimal improvement in the interlayer strength.

36 MATERIALS SCIENCE↗