Calibrating numerical model by neural networks: A case study for the simulation of the indoor temperature of a building

Xiaoshu Lü, Tao Lu, Martti Viljanen

Research output: Contribution to journalArticleScientificpeer-review

5 Citations (Scopus)
125 Downloads (Pure)

Abstract

This paper proposes a method using neural networks to calibrate numerical models. The approach passes the output of numerical model to a neural network for calibration. An experimental study was conducted using a simulation of unheated and uncooled indoor temperature of a sports hall. The proposed neural network-based model improves the results and produces more accurate calibrated indoor temperature. Furthermore, the developed calibration method requires only measurements of indoor temperatures as the necessary inputs, thus significantly simplifying the calibration procedure needed to model the building performances.
Original languageEnglish
Pages (from-to)1366-1372
JournalEnergy Procedia
Volume75
Issue numberAugust
DOIs
Publication statusPublished - 2015
MoE publication typeA1 Journal article-refereed
EventInternational Conference on Applied Energy - Abu Dhabi, United Arab Emirates
Duration: 28 Mar 201531 Mar 2015
Conference number: 7

Keywords

  • Numerical model
  • Neural networks
  • Model calibration
  • Generalization
  • Unheated and uncooled indoor temperature simulation

Fingerprint Dive into the research topics of 'Calibrating numerical model by neural networks: A case study for the simulation of the indoor temperature of a building'. Together they form a unique fingerprint.

Cite this