Abstract | ||
---|---|---|
Graphical abstractDisplay Omitted HighlightsA new data-driven fault detection and isolation scheme is presented.The fuzzy/Bayesian approach is used to indicate a possible fault event.The faults classification is performed using a new immune/neural approach. This study presents a data-based methodology for fault detection and isolation in dynamic systems based on fuzzy/Bayesian approach for change point detection associated with a hybrid immune/neural formulation for pattern classification applied to the Tennessee Eastman benchmark process. The fault is detected when a change occurs in the signals from the sensors and classified into one of the classes by the immune/neural formulation. The change point detection system is based on fuzzy set theory associated with the MetropolisHastings algorithm and the classification system, the main contribution of this paper is based on a representation which combines the ClonALG algorithm with the Kohonen neural network. |
Year | DOI | Venue |
---|---|---|
2016 | 10.1016/j.asoc.2016.08.040 | Appl. Soft Comput. |
Keywords | Field | DocType |
Fault detection and isolation,Fuzzy/Bayesian approach,Immune/neural formulation,Tennessee Eastman benchmark process | Data mining,Change detection,Fault detection and isolation,Fuzzy logic,Fuzzy set,Kohonen neural network,Artificial intelligence,Mathematics,Dynamical system,Machine learning,Bayesian probability | Journal |
Volume | Issue | ISSN |
49 | C | 1568-4946 |
Citations | PageRank | References |
2 | 0.38 | 0 |
Authors | ||
6 |
Name | Order | Citations | PageRank |
---|---|---|---|
m f s v dangelo | 1 | 4 | 0.78 |
Reinaldo M. Palhares | 2 | 467 | 41.12 |
Murilo C. O. Camargos Filho | 3 | 2 | 0.38 |
Renato D. Maia | 4 | 2 | 0.38 |
João B. Mendes | 5 | 2 | 0.38 |
Petr Ekel | 6 | 130 | 7.13 |