One-Shot Fault Diagnosis of Three-Dimensional Printers Through Improved Feature Space Learning
| Autor: | José Valente de Oliveira, Mariela Cerrada, Diego Cabrera, Chuan Li, Fernando Sancho, René-Vinicio Sánchez |
|---|---|
| Rok vydání: | 2021 |
| Předmět: |
Computer science
business.industry Deep learning Feature vector 020208 electrical & electronic engineering Supervised learning Feature extraction Pattern recognition 02 engineering and technology Fault (power engineering) One-shot learning Multiclass classification Transformation (function) Control and Systems Engineering 0202 electrical engineering electronic engineering information engineering Artificial intelligence Electrical and Electronic Engineering business |
| Zdroj: | IEEE Transactions on Industrial Electronics. 68:8768-8776 |
| ISSN: | 1557-9948 0278-0046 |
| DOI: | 10.1109/tie.2020.3013546 |
| Popis: | Signal acquisition from mechanical systems working in faulty conditions is normally expensive. As a consequence, supervised learning-based approaches are hardly applicable. To address this problem, a one-shot learning-based approach is proposed for multiclass classification of signals coming from a feature space created only from healthy condition signals and one single sample for each faulty class. First, a transformation mapping between the input signal space and a feature space is learned through a bidirectional generative adversarial network. Next, the identification of different health condition regions in this feature space is carried out by means of a single input signal per fault. The method is applied to three fault diagnosis problems of a three-dimensional printer and outperforms other methods in the literature. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|