Thermal And Mechanical Properties Of Demolition Wastes In Geothermal Pavements By Experimental And Machine Learning Techniques
CONSTRUCTION AND BUILDING MATERIALS(2021)
Abstract
Despite the growing interest in using construction and demolition (C&D) waste materials in geotechnical engineering projects, there is limited knowledge of their thermo-mechanical properties, which is essential for the design of energy geostructures, such as geothermal pavements. The pavement unbound layers can be integrated with heat exchangers to form a novel pavement concept, namely geothermal pavements. This study focuses on recycled concrete aggregate (RCA), crushed brick (CB), waste rock (WR), and reclaimed asphalt pavement (RAP), and aims to investigate the thermal conductivity of these C&D materials as well as their response to combined dynamic loads and temperature. Thermal conductivity was measured using a prototype divided bar equipment. Temperature-controlled repeated loading triaxial (RLT) tests were undertaken to evaluate the effect of temperature on deformation properties of the C&D materials. RLT tests were conducted at 5 degrees C, 20 degrees C, 35 degrees C, and 50 degrees C. Deformation behavior of the C&D materials at different temperatures was characterized using the shakedown concept. Thermal conductivity measurements indicated that CB and RCA had higher thermal conductivity compared to WR and RAP. RLT results showed that RCA exhibited plastic shakedown (Range A) behavior in all temperatures, while CB and WR demonstrated plastic creep (Range B) behavior. RAP exhibited plastic creep behavior at 20 degrees C and 5 degrees C, and incremental collapse (Range C) behavior at 35 degrees C and 50 degrees C. An artificial neural network (ANN) model was developed considering the physical properties and test variables as input parameters. Sensitivity analysis was then performed on the proposed ANN model. Results of the ANN modeling provided new insight into the deformation behavior of C&D materials at different temperatures and agreed with the experimental results. (C) 2021 Elsevier Ltd. All rights reserved.
MoreTranslated text
Key words
Thermal conductivity, Geothermal pavement, Demolition wastes, Pavement geotechnics, Ground Improvement, Repeated load triaxial, Artificial neural network, Recycled materials
AI Read Science
Must-Reading Tree
Example
![](https://originalfileserver.aminer.cn/sys/aminer/pubs/mrt_preview.jpeg)
Generate MRT to find the research sequence of this paper
Chat Paper
Summary is being generated by the instructions you defined