<abstract xmlns="http://www.w3.org/1999/xhtml">

<p>The paper presents an innovative concept of digital aggregation of data related to mandatory in-situ load tests of bridge structures. The proposed approach allows to manage various types of information regarding those experiments, in a way which is consistent with current good practises in BIM technology and digitalisation of construction industry. The proposed web platform will allow for vast improvements in decision-making process regarding admission of a given bridge for service, in proper analyses and even predictions of bridges mechanical response. Initial architecture of the system is introduced along with an appropriate literature review and the identification of key actors and their roles in the described information management process. To highlight the potential of the solution, two examples are shown. In both cases key advantages of digital aggregation are emphasised: the possibility to learn from previous analogical in-situ experiments, and the possibility to utilise modern machine learning algorithms and state-of-the-art open-source solutions.</p>
</abstract>

The paper presents an innovative concept of digital aggregation of data related to mandatory in-situ load tests of bridge structures. The proposed approach allows to manage various types of information regarding those experiments, in a way which is consistent with current good practises in BIM technology and digitalisation of construction industry. The proposed web platform will allow for vast improvements in decision-making process regarding admission of a given bridge for service, in proper analyses and even predictions of bridges mechanical response. Initial architecture of the system is introduced along with an appropriate literature review and the identification of key actors and their roles in the described information management process. To highlight the potential of the solution, two examples are shown. In both cases key advantages of digital aggregation are emphasised: the possibility to learn from previous analogical in-situ experiments, and the possibility to utilise modern machine learning algorithms and state-of-the-art open-source solutions.

A Proposal to Facilitate Mandatory Bridge Load Tests with Artificial Neural Network Analyses Using a Digital Data Aggregation Platform

Architecture, Civil Engineering, Environment

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

The paper presents an innovative concept of digital aggregation of data related to mandatory in-situ load tests of bridge structures. The proposed approach...

A Proposal to Facilitate Mandatory Bridge Load Tests with Artificial Neural Network Analyses Using a Digital Data Aggregation Platform

Published Online: Oct 08, 2021

Page range: 69 - 78

Received: May 21, 2021

Accepted: Jul 03, 2021

DOI: https://doi.org/10.21307/acee-2021-023

Keywords
Bridge load tests, TensorFlow, Neural networks, API, BIM, Digitalization

© 2021 Piotr Owerko et al., published by Sciendo

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

A Proposal to Facilitate Mandatory Bridge Load Tests with Artificial Neural Network Analyses Using a Digital Data Aggregation Platform

Published Online: Oct 08, 2021

Page range: 69 - 78

Received: May 21, 2021

Accepted: Jul 03, 2021

DOI: https://doi.org/10.21307/acee-2021-023

KeywordsBridge load tests, TensorFlow, Neural networks, API, BIM, Digitalization

© 2021 Piotr Owerko et al., published by Sciendo

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Keywords
Bridge load tests, TensorFlow, Neural networks, API, BIM, Digitalization