Soft computing tools for transient classification

Roverso, Davide

doi:10.1016/s0020-0255(00)00035-9

Cited by 41 publications

(19 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…[Roverso, 2000], [Roverso, 2003] and [Baraldi et al, 2012a] have shown the improved performance of transient classification algorithms when they are fed by wavelet features instead of the direct signal values. In the present work, the Haar wavelet transform [Ogden, 1997] is applied on a sliding window of the signal timeseries.…”

Section: Wavelet Transform Pre-processingmentioning

confidence: 99%

Unsupervised Clustering for Fault Diagnosis in Nuclear Power Plant Components

Baraldi¹,

Maio²,

Zio³

2013

IJCIS

View full text Add to dashboard Cite

The development of empirical classification models for fault diagnosis usually requires a process of training based on a set of examples. In practice, data collected during plant operation contain signals measured in faulty conditions, but they are 'unlabeled', i.e., the indication of the type of fault is usually not available. Then, the objective of the present work is to develop a methodology for the identification of transients of similar characteristics, under the conjecture that faults of the same type lead to similar behavior in the measured signals. The proposed methodology is based on the combined use of Haar wavelet transform, fuzzy similarity, spectral clustering and the Fuzzy C-Means algorithm. A procedure for interpreting the fault cause originating the similar transients is proposed, based on the identification of prototypical behaviors. Its performance is tested with respect to an artificial case study and then applied on transients originated by different faults in the pressurizer of a nuclear power reactor.

show abstract

Section: Wavelet Transform Pre-processingmentioning

confidence: 99%

Unsupervised Clustering for Fault Diagnosis in Nuclear Power Plant Components

Baraldi¹,

Maio²,

Zio³

2013

IJCIS

View full text Add to dashboard Cite

show abstract

“…Compact wavelet features are then extracted from the 123 measured signals by Haar wavelet decomposition from a sliding window on the actual-signal time series. 32 The selected wavelet features are 70 the mean residual signal taken at the highest, that is, coarsest, scale, and the minimum and maximum wavelet coefficients over all the scales. The rationale behind this choice is that the first wavelet feature captures the general trend of the signal across the windows in a compact way, being very much related to the average signal value within the analysis window, while the minimum and maximum wavelet coefficients capture important variations in the signal within a single window that would otherwise be severely smoothed out by the compression process.…”

Section: Results Of the Application Of The Npga On The Case Study Of mentioning

confidence: 99%

“…Because of its ability of continuously applying the wavelet transform on a sliding window, and since the transform is used as a preprocessing step for the final transient classification, this technique has been named Wavelet Online Preprocessing (WOLP). 70 Thus, the application of the WOLP preprocessing on the 123 original plant measured signals generates 369 wavelet coefficients, increasing from 2 123 to 2 369 the dimension of the search space from which the optimal subset of features relevant for the fault classification task is to be selected. For completeness of the paper, a detailed description of the WOLP technique is given in Appendix B.…”

Section: Results Of the Application Of The Npga On The Case Study Of mentioning

confidence: 99%

Application of a niched Pareto genetic algorithm for selecting features for nuclear transients classification

Baraldi

Pedroni

Zio

2009

Int. J. Intell. Syst.

View full text Add to dashboard Cite

Feature selection for transient classification is the problem of choosing among several monitored parameters (i.e., the features) to be used for efficiently recognizing the developing transient patterns. It is a critical issue for the application of "on condition" diagnostic techniques in complex systems, such as the nuclear power plants, where hundreds of parameters are measured. Indeed, irrelevant and noisy features have been shown to unnecessarily increase the complexity of the classification problem and degrade the diagnostic performance. In this paper, the problem of selecting the features to be used for efficient transient classification is tackled by means of multiobjective genetic algorithms. The approach leads to the identification of a family of equivalently optimal subsets of features, in the Pareto sense. However, difficulties in the convergence of the standard Pareto-based multiobjective genetic algorithm search in large feature spaces may arise in terms of representativeness of the identified Pareto front whose elements may turn out to be unevenly distributed in the objective functions space, thus not providing a full picture of the potential Pareto-optimal solutions. To overcome this problem, a niched Pareto genetic algorithm is embraced in this work. The performance of the feature subsets examined during the search is evaluated in terms of two optimization objectives: the classification accuracy of a Fuzzy K-Nearest Neighbors classifier and the number of features in the subsets. During the genetic search, the algorithm applies a controlled "niching pressure" to spread out the population in the search space so that convergence is shared on different niches of the Pareto front, which is thus evenly covered. The method is tested on a diagnostic problem characterized by a very large number of process features available for the classification of simulated transients in the feedwater system of a boiling water reactor. The dynamics of the transient signals is captured by wavelet decomposition, which actually increases the complexity of the search for the optimal feature subsets by triplicating the number of features to be considered. C 2008 Wiley Periodicals, Inc.

show abstract

“…For completeness, similar tests were performed with the other three neural models described in Ref. 13, that is, the RBF classifier, the cascade-RBF classifier, and the SOM classifier. The results obtained were in line with the ones from the first case study on the Forsmark 2 data, once more confirming the superior performance of the recurrent ANNs.…”

Section: Neural Network Ensemblesmentioning

confidence: 99%

“…In the case of event classification, the occurrence of a new event, which was not included in the design of the classifier, could lead to a misleading classification. In previous versions of ALADDIN, 13 this problem was solved through the introduction of a validation module based on the concept of possibilistic fuzzy clustering. 41 The main property of possibilistic fuzzy clustering is that the membership values of points falling in areas of the input space not covered by the constructed clusters will all be zero.…”

Section: Conclusion and Further Workmentioning

confidence: 99%

Plant diagnostics by transient classification: The ALADDIN approach

Roverso¹

2002

Int. J. Intell. Syst.

Self Cite

View full text Add to dashboard Cite

Any action taken on a plant, for example in response to an abnormal situation or in reaction to unsafe conditions, relies on the ability to identify the state and dynamics of operation of the plant. Although there might be hundreds or even thousands of measurements in a plant, there are generally few events occurring. The data from these measurements must be mapped into appropriate descriptions of the occurring event(s), which in most cases is a difficult task. The realtime history of scores of variables can be displayed and monitored in most computerized plant monitoring and control systems. However, whereas a simple visual inspection of displayed trends is generally sufficient to allow the operator to confirm the plant status during normal, steady-state operations, when the plant is subject to deviations due to anomalies or faults, the displayed trends of interacting variables can be very difficult to interpret, either because the changes are too subtle, or because the changes are too fast.In this article we describe the ALADDIN methodology for dynamic event recognition and fault diagnosis, which combines techniques such as recurrent neural network ensembles, wavelet on-line pre-processing (WOLP), and autonomous recursive task decomposition (ARTD), in an attempt to improve the practical applicability and scalability of this type of system to real processes and machinery.

show abstract

Soft computing tools for transient classification

Cited by 41 publications

References 12 publications

Unsupervised Clustering for Fault Diagnosis in Nuclear Power Plant Components

Unsupervised Clustering for Fault Diagnosis in Nuclear Power Plant Components

Application of a niched Pareto genetic algorithm for selecting features for nuclear transients classification

Plant diagnostics by transient classification: The ALADDIN approach

Contact Info

Product

Resources

About