Industrial Data-Driven Monitoring Based on Incremental Learning Applied to the Detection of Novel Faults

• Published in: IEEE transactions on industrial informatics Vol. 16; no. 9; pp. 5985 - 5995
• Main Authors: Saucedo-Dorantes, Juan Jose, Delgado-Prieto, Miguel, Osornio-Rios, Roque Alfredo, Romero-Troncoso, Rene de Jesus
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 01.09.2020; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Condition monitoring; Data integration; Discriminant analysis; Fault detection; feature extraction; incremental learning; Industrial applications; Inspection; Machine learning; novelty detection; Self organizing maps

The detection of uncharacterized events during electromechanical systems operation represents one of the most critical data challenges dealing with condition-based monitoring under the Industry 4.0 framework. Thus, the detection of novelty conditions and the learning of new patterns are considered a...