Application of unsupervised anomaly detection techniques to moisture content data from wood constructions

Álvaro García Faura (Avtor), Dejan Štepec (Avtor), Matija Cankar (Avtor), Miha Humar (Avtor)

Povzetek

Wood is considered one of the most important construction materials, as well as a natural material prone to degradation, with fungi being the main reason for wood failure in a temperate climate. Visual inspection of wood or other approaches for monitoring are time-consuming, and the incipient stages of decay are not always visible. Thus, visual decay detection and such manual monitoring could be replaced by automated real-time monitoring systems. The capabilities of such systems can range from simple monitoring, periodically reporting data, to the automatic detection of anomalous measurements that may happen due to various environmental or technical reasons. In this paper, we explore the application of Unsupervised Anomaly Detection (UAD) techniques to wood Moisture Content (MC) data. Specifically, data were obtained from a wood construction that was monitored for four years using sensors at different positions. Our experimental results prove the validity of these techniques to detect both artificial and real anomalies in MC signals, encouraging further research to enable their deployment in real use cases.

Ključne besede

vlažnost lesa;monitoring vlažnosti lesa;lesena okna;lesena fasada;enadzorovano odkrivanje nepravilnosti;wood moisture monitoring;Unsupervised Anomaly Detection;moisture content data;wooden facade;wooden windows;

Podatki

Jezik:	Angleški jezik
Leto izida:	2021
Tipologija:	1.01 - Izvirni znanstveni članek
Organizacija:	UL BF - Biotehniška fakulteta
UDK:	630*8
COBISS:	50590467
ISSN:	1999-4907
Št. ogledov:	140
Št. prenosov:	44
Ocena:	0 (0 glasov)
Metapodatki:

Ostali podatki

Sekundarni jezik:	Slovenski jezik
Sekundarne ključne besede:	vlažnost lesa;monitoring vlažnosti lesa;lesena okna;lesena fasada;nenadzorovano odkrivanje nepravilnosti;
Vrsta dela (COBISS):	Članek v reviji
Strani:	1-19 str.
Letnik:	ǂVol. ǂ12
Zvezek:	ǂiss. ǂ2
Čas izdaje:	2021
DOI:	10.3390/f12020194
ID:	14562755