Soft Computing Approaches to Fault Diagnosis for Dynamic Systems

Calado, João Manuel Ferreira; Korbicz, Józef; Patan, Krzysztof; Patton, R.J.; Costa, J.M.G. Sá da

doi:10.3166/ejc.7.248-286

Cited by 87 publications

(44 citation statements)

References 67 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…in order to secure the process or re-configure the structure of the control system. The bond-graphs are the The methods of detection making use of the models of the systems play fundamental role in the diagnostics of processes, whereas these are models built for the normal state of the process [3][4][5][6][7][8][9][10][11][12][13][14][15][16]. Such methods allow for early detection of the small size faults, before they reveal their negative effects.…”

Section: Process Diagnostics With the Use Of Qualitative Modelsmentioning

confidence: 99%

“…This limits the application, of this method to processes, which are described by relatively simple relations. Linear models in the form of state equations, operator transmittances, state observers or Kalman filters [3,10,11] have limited applicability in the diagnostics of industrial processes due to non-linearity of the processes and variable operating point. In the case of such models, the residuals are specified as a difference between the measured and modeled values of the output signals (Fig.…”

Section: Fault Detectionmentioning

confidence: 99%

“…The most detailed description of these methods can be found in the books [1][2][3][4][5][6][7][8][9][10]. There had also been written a lot of survey papers on the methods of fault diagnostics [11][12][13][14][15][16][17][18]. As a valuable source of information may serve proceedings from IFAC Symposium on Fault Detection, Supervision and Safety for Technical Processes -SafeProcess, which has been organized every 3 years, since 1991.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Application properties of methods for fault detection and isolation in the diagnosis of complex large-scale processes

Kościelny¹,

Syfert²

2014

Bulletin of the Polish Academy of Sciences Technical Sciences

View full text Add to dashboard Cite

Abstract. The survey presents a selection of the methods of the fault detection and isolation suitable to be useful for the diagnostics of the complex, large scale industrial processes. The paper focuses on these methods that have appropriately high level of potential applicability in industrial practice. The novelty of the paper relies on the discussion of the dependency of the level of knowledge about diagnosed process and recommended diagnostic approaches. Appropriate recommendations were given in the convenient form of the table.

show abstract

Section: Process Diagnostics With the Use Of Qualitative Modelsmentioning

confidence: 99%

Section: Fault Detectionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Application properties of methods for fault detection and isolation in the diagnosis of complex large-scale processes

Kościelny¹,

Syfert²

2014

Bulletin of the Polish Academy of Sciences Technical Sciences

View full text Add to dashboard Cite

show abstract

“…It is difficult to accurately predict their behavior, especially with corrupted measures, and unreliable sensors. Therefore, a number of researchers have perceived artificial neural networks as an alternative way to represent knowledge about faults (Sorsa et al 1992, Himmelblau 1992, Patton et al 1994, Frank 1997, Calado et al 2001, Korbicz et al 2004). …”

Section: Introductionmentioning

confidence: 99%

Nerual Networks with Decision Trees for Diagnosis Issues

Kourd

Lefebvre

Guersi

2013

Computer Science &Amp; Information Technology ( CS &Amp; IT )

View full text Add to dashboard Cite

This paper presents a new idea for fault detection and isolation (FDI) technique which is applied to industrial system. This technique is based on Neural Networks fault-free and Faulty behaviours Models (NNFMs). NNFMs are used for residual generation, while decision tree architecture is used for residual evaluation. The decision tree is realized with data collected from the NNFM's outputs and is used to isolate detectable faults depending on computed threshold. Each part of the tree corresponds to specific residual. With the decision tree, it becomes possible to take the appropriate decision regarding the actual process behaviour by evaluating few numbers of residuals. In comparison to usual systematic evaluation of all residuals, the proposed technique requires less computational effort and can be used for on linediagnosis. An application example is presented to illustrate and confirm the effectiveness and the accuracy of the proposed approach.

show abstract

“…An alternative solution can be obtained through artificial intelligence, e.g. neural networks (Frank and Köppen-Seliger, 1997;Calado et al, 2001).…”

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

Soft Computing Approaches to Fault Diagnosis for Dynamic Systems

Cited by 87 publications

References 67 publications

Application properties of methods for fault detection and isolation in the diagnosis of complex large-scale processes

Application properties of methods for fault detection and isolation in the diagnosis of complex large-scale processes

Nerual Networks with Decision Trees for Diagnosis Issues

Robust Fault Diagnosis in Catalytic Cracking Converter Using Artificial Neural Networks

Contact Info

Product

Resources

About