Sensor Data Interpretation in Bridge Monitoring—A Case Study

Raphael, Benny; Harichandran, Aparna

doi:10.3389/fbuil.2019.00148

Cited by 2 publications

(2 citation statements)

References 48 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Classification algorithms such as ANN (Lashkari et al, 2015), deep belief networks (Shao et al, 2017), sparse autoencoder (Sun et al, 2016), and CNN (Janssens et al, 2018) were implemented for this problem. Data-driven fault detection methods are widely adopted in construction for structural health monitoring (Rafiei & Adeli, 2017b;Raphael & Harichandran, 2020). The existing fault detection studies for construction equipment are limited and confined to equipment such as tower cranes, excavators, and dump trucks.…”

Section: Data-driven Fault Detection Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Equipment activity recognition and early fault detection in automated construction through a hybrid machine learning framework

Harichandran

Raphael

Mukherjee

2022

Computer aided Civil Eng

Self Cite

View full text Add to dashboard Cite

Existing studies on automated construction equipment monitoring have focused mainly on activity recognition rather than fault detection. This paper proposes a novel equipment activity recognition and fault detection framework called hybrid unsupervised and supervised machine learning (HUS‐ML). HUS‐ML first identifies normal operations and known faulty conditions through supervised learning. Then, an anomaly detection algorithm is applied to spot any unseen faulty conditions. The framework is tested using acceleration measurements from a low‐rise automated construction system prototype. HUS‐ML outperformed the conventional machine learning approach in activity recognition and fault detection with an average F1 score of 86.6%. The conventional approach failed to detect unseen faulty operations. HUS‐ML identified known faulty operations and unseen faulty operations with F1 scores of 98.11% and 76.19%, respectively. The generalizability of the framework is demonstrated by validating it on an independent benchmark dataset with good results.

show abstract

Section: Data-driven Fault Detection Methodsmentioning

confidence: 99%

“…Data‐driven fault detection methods are widely adopted in construction for structural health monitoring (Rafiei & Adeli, 2017b; Raphael & Harichandran, 2020). The existing fault detection studies for construction equipment are limited and confined to equipment such as tower cranes, excavators, and dump trucks.…”

Section: Related Workmentioning

confidence: 99%

Equipment activity recognition and early fault detection in automated construction through a hybrid machine learning framework

Harichandran

Raphael

Mukherjee

2022

Computer aided Civil Eng

Self Cite

View full text Add to dashboard Cite

show abstract

Digital Twin of Artifact Systems: Models Assimilated with Monitoring Data from Material Microstructures to Social Systems

Okita

Kawabata

Murayama

et al. 2020

IJAT

View full text Add to dashboard Cite

In contemporary society, where changes in the environment surrounding artifacts as well as changes in the purpose and operating conditions of artifacts occur frequently, it is necessary to equip artifacts with resilience and plasticity, and to incorporate this knowledge in the succeeding generation of artifacts. For this purpose, we propose digital twin of artifact systems (DTAS) that focuses on structural materials, from their microstructure to the environment and social systems in which the artifacts are used. The realization of DTAS requires the development of modelling and monitoring technologies from the atomic scale to the social system, the development of technologies to operate these technologies in multiscale in an integrated way, and the development of technologies for model uncertainty assessment. In the future, the information on models and monitoring of artifact systems stored in DTAS is expected to be shared and utilized not only by designers but also among various stakeholders, contributing to the realization of a framework for co-creative development and consensus building through interaction between designers and users.

show abstract

Sensor Data Interpretation in Bridge Monitoring—A Case Study

Cited by 2 publications

References 48 publications

Equipment activity recognition and early fault detection in automated construction through a hybrid machine learning framework

Equipment activity recognition and early fault detection in automated construction through a hybrid machine learning framework

Digital Twin of Artifact Systems: Models Assimilated with Monitoring Data from Material Microstructures to Social Systems

Contact Info

Product

Resources

About