Three-layer approach to detect anomalies in industrial environments based on machine learning

Daniel Gutierrez-Rojas, Mehar Ullah, Ioannis T Christou, Gustavo Almeida, Pedro Nardelli, Dick Carrillo, Jean M Sant’Ana, Hirley Alves, Merim Dzaferagic, Alessandro Chiumento

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

Abstract

This paper introduces a general approach to design a tailored solution to detect rare events in different industrial applications based on Internet of Things (IoT) networks and machine learning algorithms. We propose a general framework based on three layers (physical, data and decision) that defines the possible designing options so that the rare events/anomalies can be detected ultra-reliably. This general framework is then applied in a well-known benchmark scenario, namely Tennessee Eastman Process. We then analyze this benchmark under three threads related to data processes: acquisition, fusion and analytics. Our numerical results indicate that: (i) event-driven data acquisition can significantly decrease the number of samples while filtering measurement noise, (ii) mutual information data fusion method can significantly decrease the variable spaces and (iii) quantitative association rule mining method for data analytics is effective for the rare event detection, identification and diagnosis. These results indicates the benefits of an integrated solution that jointly considers the different levels of data processing following the proposed general three layer framework, including details of the communication network and computing platform to be employed.
Original languageEnglish
Title of host publication2020 IEEE Conference on Industrial Cyberphysical Systems (ICPS)
Pages250-256
Number of pages7
Volume1
ISBN (Electronic)978-1-7281-6389-5
DOIs
Publication statusPublished - 2020
Externally publishedYes
Event3rd IEEE International Conference on Industrial Cyber-Physical Systems, ICPS 2020 - Virtual Conference, Virtual Event
Duration: 10 Jun 202012 Jun 2020
Conference number: 3
https://events.tuni.fi/icps2020/

Conference

Conference3rd IEEE International Conference on Industrial Cyber-Physical Systems, ICPS 2020
Abbreviated titleICPS 2020
CityVirtual Event
Period10/06/2012/06/20
Internet address

Fingerprint Dive into the research topics of 'Three-layer approach to detect anomalies in industrial environments based on machine learning'. Together they form a unique fingerprint.

Cite this