Prediction Air Temperature in Geothermal Heat Exchangers Using Pseudorandom Numbers: The New DARL Model

TL;DR

This paper introduces the DARL model, which predicts air temperature distribution in geothermal heat exchangers using pseudo-random numbers, reducing sensor dependence and computational costs while maintaining high accuracy.

Contribution

The novel DARL model combines experimental boundary data with pseudo-random number simulations to accurately estimate thermal air distribution in heat exchangers.

Findings

Predicts air temperature with less than 6.2% relative error.

Reduces sensor dependency in thermal distribution measurements.

Demonstrates high predictive capacity and efficiency.

Abstract

The use of Earth-Air-Water Heat Exchangers (EAWHE) for sustainable air conditioning has not been widely studied. Due to their experimental nature, methods of characterizing internal thermal air distribution impose high dependence on instrumentation by sensors and entail data acquisition and computational costs. This document presents an alternative method that estimates air temperature distribution while minimizing the need for a dense network of sensors in the experimental system. The proposed model, DARL (Data of Air and Random Length), can predict the temperature of air circulating inside EAWHEs. DARL is a significant methodological advance that integrates experimental data from boundary conditions with simulations based on pseudo-random numbers (PRNs). These PRNs are generated using Fermat's prime numbers as seeds to initialize the generator. Ordinary linear regressions and robust statistical validations, including the Shapiro-Wilk test and root mean square error, have demonstrated that the model can estimate the thermal distribution of air at different lengths with a relative error of less than 6.2%. These results demonstrate the model's efficiency, predictive capacity, and potential to reduce dependence on sensors.