Industrial process monitoring by means of recurrent neural networks and Self Organizing Maps
| Autor: | Jesus A. Carino, Enric Sala, M. Delgado, Juan Antonio Ortega, Daniel Zurita |
|---|---|
| Přispěvatelé: | Universitat Politècnica de Catalunya. Departament d'Enginyeria Electrònica, Universitat Politècnica de Catalunya. MCIA - Motion Control and Industrial Applications Research Group |
| Rok vydání: | 2016 |
| Předmět: |
Self-organizing map
Artificial intelligence Engineering Informàtica::Automàtica i control [Àrees temàtiques de la UPC] Process (engineering) condition monitoring Reliability (computer networking) knowledge extraction production engineering computing 02 engineering and technology computer.software_genre Machine learning self-organizing map copper rod industrial plant process monitoring industrial manufacturing plant Knowledge extraction recurrent neural nets Machinery--Monitoring 0202 electrical engineering electronic engineering information engineering self-organising feature maps Maquinària -- Monitoratge day-to-day operation Operating point business.industry critical industrial signal time-series forecasting Intel·ligència artificial 020208 electrical & electronic engineering Condition monitoring productive process Knowledge acquisition industrial condition monitoring approach knowledge acquisition operating point codification Recurrent neural network reliability problem internal dynamics critical signal modeling recurrent neural network 020201 artificial intelligence & image processing Data mining industrial process monitoring Informàtica::Robòtica [Àrees temàtiques de la UPC] business computer |
| Zdroj: | ETFA Recercat. Dipósit de la Recerca de Catalunya instname UPCommons. Portal del coneixement obert de la UPC Universitat Politècnica de Catalunya (UPC) |
| DOI: | 10.1109/etfa.2016.7733534 |
| Popis: | Industrial manufacturing plants often suffer from reliability problems during their day-to-day operations which have the potential for causing a great impact on the effectiveness and performance of the overall process and the sub-processes involved. Time-series forecasting of critical industrial signals presents itself as a way to reduce this impact by extracting knowledge regarding the internal dynamics of the process and advice any process deviations before it affects the productive process. In this paper, a novel industrial condition monitoring approach based on the combination of Self Organizing Maps for operating point codification and Recurrent Neural Networks for critical signal modeling is proposed. The combination of both methods presents a strong synergy, the information of the operating condition given by the interpretation of the maps helps the model to improve generalization, one of the drawbacks of recurrent networks, while assuring high accuracy and precision rates. Finally, the complete methodology, in terms of performance and effectiveness is validated experimentally with real data from a copper rod industrial plant. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|