Outlier detection with ontology-driven fault contextualization in the Industry 4.0

  • Dionei Miodutzki Universidade Tecnológica Federal do Paraná (UTFPR)
  • Cesar Tacla Universidade Tecnológica Federal do Paraná (UTFPR)
  • Luiz Gomes-Jr Universidade Tecnológica Federal do Paraná (UTFPR)

Resumo


In the industrial sector, outlier detection makes it possible to quickly identify equipment failures. The evolution of Industry 4.0 is bringing challenges previously uncommon in the area. The large number of data constantly generated represents a processing challenge and can lead to the identification of a large number of outliers simultaneously. This scenario slows the troubleshooting process, delaying the identification of the source of the fault. This work presents a solution to support decision-making in a widespread failure scenario. Dependencies are represented using ontologies, to provide a clear and user-facilitated interpretation. An inference engine is used to identify the most probable causes of the failure. Performance tests demonstrate its scalability.

Palavras-chave: Outlier, Industry 4.0, Ontology

Referências

Varun Chandola, Arindam Banerjee, and Vipin Kumar. Anomaly detection: a survey. ACM Computing Surveys, 2009.

Haibo Cheng, Peng Zeng, Lingling Xue, Zhao Shi, Peng Wang, and Haibin Yu. Manufacturing ontology development based on industry 4.0 demonstration production line. Third International Conference on Trustworthy Systems and Their Applications, 2016.

Lei Duan, Guanting Tang, Jian Pei, James Bailey, Akiko Campbell, and Changjie Tang. Mining outlying aspects on numeric data. Data Mining and Knowledge Discovery, 2015.

Daniel Fleischhacker, Heiko Paulheim, Volha Bryl, Johanna Völker, and Christian Bizer. Detecting errors in numerical linked data using cross-checked outlier detection. The Semantic Web - ISWC 2014, 2014.

Anuroop Gaddam, Tim Wilkin, Maia Angelova, and Jyotheesh Gaddam. Detecting sensor faults, anomalies and outliers in the internet of things: A survey on the challenges and solutions. Electronics, 2020.

W3C OWL Working Group. Owl 2 web ontology language document overview (second edition), 2012. URL https://www.w3.org/TR/owl2-overview/.

N. Guarino. Formal Ontology in Information Systems. IOS Press, 1998.

D. Hawkins. Identification of Outliers. Chapman and Hall, 1980.

Gustavo H. Orair, Carlos H. C. Teixeira, Wagner Meira, Ye Wang, and Srinivasan Parthasarathy. Distance-based outlier detection: consolidation and renewed bearing. Proceedings of the VLDB Endowment, 2010.

Ali Ahmadian Ramaki, Reza Asgari, and Reza Ebrahimi Atani. Credit card fraud detection based on ontology graph. International Journal of Security, Privacy and Trust Management, 2012.

Theodoros Toliopoulos, Christos Bellas, Anastasios Gounaris, and Apostolos Papadopoulos. Proud: Parallel outlier detection for streams. SIGMOD Record, 2020.

Jianxin Wang, Ming K. Lim, Chao Wang, and Ming-Lang Tseng. The evolution of the internet of things (iot) over the past 20 years. Computers and Industrial Engineering, 2022.

Yufeng Yu, Yuelong Zhu, Shijin Li, and Dingsheng Wan. Time series outlier detection based on sliding window prediction. Mathematical problems in engineering, 2014.
Publicado
19/09/2022
MIODUTZKI, Dionei; TACLA, Cesar; GOMES-JR, Luiz. Outlier detection with ontology-driven fault contextualization in the Industry 4.0. In: SIMPÓSIO BRASILEIRO DE BANCO DE DADOS (SBBD), 37. , 2022, Búzios. Anais [...]. Porto Alegre: Sociedade Brasileira de Computação, 2022 . p. 267-278. ISSN 2763-8979. DOI: https://doi.org/10.5753/sbbd.2022.224309.