Application of Unsupervised Anomaly Detection techniques to Moisture Content data from wood constructions

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

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.

• Language: English
• Keywords: wood moisture monitoring, Unsupervised Anomaly Detection (UAD), Moisture Content (MC) data, wooden facade, wooden windows
• Work type: Article
• Typology: 1.01 - Original Scientific Article
• Organization: BF - Biotechnical Faculty
• Publication status: Published
• Publication version: Version of Record
• Year: 2021
• Number of pages: 19 str.
• Numbering: Vol. 12, iss. 2, art. 194
• PID: 20.500.12556/RUL-135050
• UDC: 630*8
• ISSN on article: 1999-4907
• DOI: 10.3390/f12020194
• COBISS.SI-ID: 50590467
• Publication date in RUL: 18.02.2022

Record is a part of a journal

• Title: Forests
• Shortened title: Forests
• Publisher: MDPI
• ISSN: 1999-4907
• COBISS.SI-ID: 3872166

Licences

• License: CC BY 4.0, Creative Commons Attribution 4.0 International
• Link: http://creativecommons.org/licenses/by/4.0/
• Description: This is the standard Creative Commons license that gives others maximum freedom to do what they want with the work as long as they credit the author.
• Licensing start date: 08.02.2021

Secondary language

• Language: Slovenian
• Keywords: vlažnost lesa, monitoring vlažnosti lesa, lesena okna, lesena fasada, nenadzorovano odkrivanje nepravilnosti

Projects

• Funder: Other - Other funder or multiple funders
• Funding programme: Republic of Slovenia, Ministry of Education, Science, and Sport
• Project number: 5441-2/2017/241
• Acronym: WOOLF

• Funder: EC - European Commission
• Funding programme: European Regional Development Fund
• Acronym: WOOLF