Dynamic Bayesian Network Factors from Possible Conflicts for Continuous System Diagnosis

Alonso-González, Carlos J.; Moya, Noemi; Biswas, Gautam

doi:10.1007/978-3-642-25274-7_23

Cited by 9 publications

(31 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Además aparece otro objetivo que permitirá validar las técnicas desarrolladas utilizando un sistema híbrido real. 1. Factorizar de manera eficiente Redes Bayesianas Dinámicas mediante Posibles Conflictos y aplicarlas a la diagnosis de fallos de sistemas continuos.…”

Section: Objetivosunclassified

“…Los Posibles Conflictos son estructuralmente observables por definición [39] lo que permite que su modelo computacional se pueda implementar satisfactoriamente como DBNs. La detección y el aislamiento de fallos de sistemas continuos se puede realizar mediante PCs de manera eficiente. Como se ha dicho anteriormente, cada PC se corresponde con un residuo 1 . Un PC se confirma como conflicto cuando se activa, esto es, cuando el residuo correspondiente deja de ser cero.…”

Section: Posibles Conflictos (Pcs)unclassified

“…Como extensión de la HFSM se ha definido la Hybrid Qualitative Fault Signature Matrix (HQFSM), esta incluye información cualitativa sobre la variación del residuo 1 . Con esta información adicional, lo que se consigue es reducir aún más el conjunto de candidatos de fallo discretos, permitiendo que el proceso de identificación de estos fallos se haga de manera más eficiente.…”

Section: Hbg − Pc1 Hbg − Pc2 Hbg − Pc3 Hbgunclassified

“…There is another objective which will be helpful to validate the techniques developed using a real complex hybrid system. 1. Factorize efficiently Dynamic Bayesian Networks using Possible Conflicts for fault diagnosis in continuous systems.…”

Section: Main Goalsmentioning

confidence: 99%

“…In those works, the authors talk about the concept of observability [14,112] and they explain its importance to estimate the state of a system from the inputs and the measurements. [14], a necessary and sufficient condition for a system to be structurally observable is that, under derivative causality: 1. All the unknown variables are reachable from the known ones.…”

Section: Observability and System Factorizationmentioning

confidence: 99%

See 4 more Smart Citations

Fault Diagnosis of Hybrid Systems with Dynamic Bayesian Networks and Hybrid Possible Conficts

Alonso¹

View full text Add to dashboard Cite

Here it is, my dissertation. It's me who is going to become a PhD, true, but it has been possible thanks to many people supporting me and working with me during all these years. First of all I want to thank from the bottom of my heart my supervisors, Dr. Carlos Alonso and Dr. Belarmino Pulido for all the work they have devoted to guide me along those years. They have worked by my side, they have taught me how to face the challenges we have found in our way and they have prepared me to become a PhD. If I'm writing these lines, it is thank to all their work during the last four years. I would also want to thank Dr. Gautam Biswas. Thank you for letting me work in ISIS for a period of time, this has been a very fruitful period for my training. I want to thank also Dr. Xenofon Koutsoukos for helping me improve my work with all the meetings and discussions. Regarding my research stay in Vanderbilt University, I have to thank Kristy, Tonya, Jaclyn and Michelle for helping me with all the paper work, it would have been much more difficult without your help.

show abstract

Section: Objetivosunclassified

Section: Posibles Conflictos (Pcs)unclassified

Section: Hbg − Pc1 Hbg − Pc2 Hbg − Pc3 Hbgunclassified

Section: Main Goalsmentioning

confidence: 99%

Section: Observability and System Factorizationmentioning

confidence: 99%

See 3 more Smart Citations

Fault Diagnosis of Hybrid Systems with Dynamic Bayesian Networks and Hybrid Possible Conficts

Alonso¹

View full text Add to dashboard Cite

show abstract

Integration of Simulation and State Observers for Online Fault Detection of Nonlinear Continuous Systems

Bregón

Alonso-González

Pulido

2014

IEEE Trans. Syst. Man Cybern, Syst.

View full text Add to dashboard Cite

A Parameter-Optimized DBN Using GOA and Its Application in Fault Diagnosis of Gearbox

Gai

Shen

Wang

et al. 2020

Shock and Vibration

View full text Add to dashboard Cite

Aiming at the problems of poor self-adaptive ability in traditional feature extraction methods and weak generalization ability in single classifier under big data, an internal parameter-optimized Deep Belief Network (DBN) method based on grasshopper optimization algorithm (GOA) is proposed. First, the minimum Root Mean Square Error (RMSE) in the network training is taken as the fitness function, in which GOA is used to search for the optimal parameter combination of DBN. After that the learning rate and the number of batch learning in DBN which have great influence on the training error would be properly selected. At the same time, the optimal structure distribution of DBN is given through comparison. Then, FFT and linear normalization are introduced to process the original vibration signal of the gearbox, preprocess the data from multiple sensors and construct the input samples for DBN. Finally, combining with deep learning featured by powerful self-adaptive feature extraction and nonlinear mapping capabilities, the obtained samples are input into DBN for training, and the fault diagnosis model for gearbox based on DBN would be established. After several tests with the remaining samples, the diagnosis rate of the model could reach over 99.5%, which is far better than the traditional fault diagnosis method based on feature extraction and pattern recognition. The experimental results show that this method could effectively improve the self-adaptive feature extraction ability of the model as well as its accuracy of fault diagnosis, which has better generalization performance.

show abstract

Dynamic Bayesian Network Factors from Possible Conflicts for Continuous System Diagnosis

Cited by 9 publications

References 3 publications

Fault Diagnosis of Hybrid Systems with Dynamic Bayesian Networks and Hybrid Possible Conficts

Fault Diagnosis of Hybrid Systems with Dynamic Bayesian Networks and Hybrid Possible Conficts

Integration of Simulation and State Observers for Online Fault Detection of Nonlinear Continuous Systems

A Parameter-Optimized DBN Using GOA and Its Application in Fault Diagnosis of Gearbox

Contact Info

Product

Resources

About