Supervision, Fault-Detection and Fault-Diagnosis Methods

Isermann, Rolf; Füssel, Dominik

doi:10.1007/978-1-4615-4601-6_3

Cited by 23 publications

(13 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Encontra-se, nos diferentes trabalhos, o termo fault associado tanto ao primeiro "objeto" (p.e. : ISO e IEC, 1993;Frank, 1990;Isermann, 1984 quanto ao segundo "objeto" (p.e. : IEC, 1990), o mesmo ocorrendo com o termo failure, que é associado ao primeiro "objeto" por Venkatasubramanian et alii (2003a), e ao segundo "objeto" por IEC (1990), ISO e IEC (1993) e Isermann e Ballé (1997).…”

Section: Condição De Falha (Fault) Versus Evento De Falha (Failure) unclassified

See 1 more Smart Citation

Detecção, diagnóstico e correções de falhas: Uma proposição consistente de definições e terminologias

Sartori¹,

Amaro²,

Júnior

et al. 2017

Cieng

View full text Add to dashboard Cite

RESUMOA crescente complexidade dos sistemas industriais e o consequente aumento da automação e instrumentação dos processos têm tornado os sistemas de detecção, diagnóstico e correção de falhas (Fault Detection, Diagnosis and Correction, FDDC) cada vez mais importantes. Neste trabalho é feita uma reflexão sobre a pesquisa em detecção, diagnóstico e correção de falhas, a partir de uma análise crítica das definições e terminologias utilizadas. Dessa forma, são propostas as terminologias e definições que parecem mais apropriadas para a área, suas atividades básicas e seus objetos de estudo, a partir do confronto das visões de diversos autores, já que isto não foi feito até o momento por nenhum trabalho da literatura. Também são apontados os principais sistemas industriais investigados nos últimos anos para a resolução de problemas de FDDC, e são averiguadas quais são as técnicas mais aplicadas na resolução destes problemas. Palavras-chave: Detecção, diagnóstico e correção de falhas; processos industriais; definições; terminologia. ABSTRACTThe increasing complexity of industrial systems and the consequent growth in instrumentation and process automation have given FDDC -Fault Detection, Diagnosis and Correction -systems an increasingly important role. This paper reflects on research into fault detection, diagnosis and correction through a critical analysis of the definitions and terminology used. The terminology and definitions that seem most appropriate for the research field, for its activities and for its object of study are proposed to conciliate the clash of visions of various authors, since this was not done yet by any work of literature. Furthermore, the most commonly studied industrial systems are highlighted as well as the most commonly used techniques in recent works with applications in these industrial problems.

show abstract

Section: Condição De Falha (Fault) Versus Evento De Falha (Failure) unclassified

“…Dificilmente irá se determinar a ocorrência da falha sem que se possa conhecer o tempo em que foi realizada esta determinação. Esta etapa também é chamada de monitoramento/monitoração por alguns autores (Isermann, 1984;Teixeira, 2000). Além deste termo, IEC (1990) usa também o termo "supervisão" com o mesmo sentido.…”

Section: Detecção De Falhasunclassified

Detecção, diagnóstico e correções de falhas: Uma proposição consistente de definições e terminologias

Sartori¹,

Amaro²,

Júnior

et al. 2017

Cieng

View full text Add to dashboard Cite

show abstract

“…In contrast, MMs, including e.g. parameter estimation methods [2,3] and state estimation methods [4,5], take both input and output signals into account. But an accurate model for each specific motor type is needed.…”

Section: Introductionmentioning

confidence: 99%

Automated fault detection using deep belief networks for the quality inspection of electromotors

Sun

Wyss²,

Steinecker³

et al. 2014

Tm - Technisches Messen

View full text Add to dashboard Cite

Vibration inspection of electro-mechanical components and systems is an important tool for automated reliable online as well as post-process production quality assurance. Considering that bad electromotor samples are very rare in the production line, we propose a novel automated fault detection method named "Tilear", based on Deep Belief Networks (DBNs) training only with good electromotor samples. Tilear consctructs an auto-encoder with DBNs, aiming to reconstruct the inputs as closely as possible. Tilear is structured in two parts: training and decision-making. During training, Tilear is trained only with informative features extracted from preprocessed vibration signals of good electromotors, which enables the trained Tilear only to know how to reconstruct good electromotor vibration signal features. In the decision-making part, comparing the recorded signal from test electromotor and the Tilear reconstructed signal, allows to measure how well a recording from a test electromotor matches the Tilear model learned from good electromotors. A reliable decision can be made. Keywords

show abstract

“…The basic idea of model-based fault diagnosis is to generate signals that reflect inconsistencies between nominal and faulty system operation conditions. Such signals, called residuals, are usually calculated by using analytical methods such as observers (Chen and Patton, 1999), parameter estimation methods (Isermann, 1994) or parity equations (Gertler, 1999). Unfortunately, the common draw-back of these approaches is that an accurate mathematical model of the diagnosed plant is required, so their application is limited.…”

Section: Introductionmentioning

confidence: 99%

Robust Fault Diagnosis in Catalytic Cracking Converter Using Artificial Neural Networks

Patan

2005

IFAC Proceedings Volumes

View full text Add to dashboard Cite

The paper presents designing of a robust fault diagnosis system for a catalytic cracking process using artificial neural networks. Identification of the considered process is carried out by using recurrent neural networks. To achieve a robust fault diagnosis system, an uncertainty associated with the model is also taken into account. Neural version of the Model Error Modelling is used to deal with two main uncertainty sources: unmodelled dynamics and noise corrupting the data. The proposed approach is tested on the example of catalytic cracking converter at the nominal operations condition as well as in the case of faults.

show abstract

Supervision, Fault-Detection and Fault-Diagnosis Methods

Cited by 23 publications

References 30 publications

Detecção, diagnóstico e correções de falhas: Uma proposição consistente de definições e terminologias

Detecção, diagnóstico e correções de falhas: Uma proposição consistente de definições e terminologias

Automated fault detection using deep belief networks for the quality inspection of electromotors

Robust Fault Diagnosis in Catalytic Cracking Converter Using Artificial Neural Networks

Contact Info

Product

Resources

About