Signal reconstruction by a GA-optimized ensemble of PCA models

Baraldi, Piero; Zio, Enrico; Gola, Giulio; Roverso, Davide; Hoffmann, Mario

doi:10.1016/j.nucengdes.2010.10.012

Cited by 7 publications

(4 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Artificial Neural Networks (ANNs) and Recurrent ANNs [2]- [9], Principal Component Analysis (PCA) and Independent Component Analysis (ICA) [10]- [12], Multivariate State Estimation Technique (MSET) [13]- [14], and Support Vector Machines (SVMs) [15]- [16]. The model considered in this work for reconstructing the component behavior in normal conditions is based on the Auto-Associative Kernel Regression (AAKR) method [17]- [20].…”

Section: Different Empirical Models Have Been Developed For Signal Rementioning

confidence: 99%

“…with overlapping, i.e., the same signal can belong to more than one group [12], [22]- [25], and without overlapping [26]- [28]. In practical applications, the latter strategy tends to be preferred because it allows for a smaller number of models to be developed, at a lower computational effort [28].…”

Section: Different Empirical Models Have Been Developed For Signal Rementioning

confidence: 99%

See 1 more Smart Citation

Fault Detection in Nuclear Power Plants Components by a Combination of Statistical Methods

et al. 2013

View full text Add to dashboard Cite

-In this paper, we investigate the feasibility of a strategy of fault detection capable of controlling misclassification probabilities, i.e., balancing false and missed alarms. The novelty of the proposed strategy consists of i) a signal grouping technique and signal reconstruction modeling technique (one model for each subgroup), and ii) a statistical method for defining the fault alarm level. We consider a real case study concerning 46 signals of the Reactor Coolant Pump (RCP) of a typical Pressurized Water Reactor (PWR). In the application, the reconstructions are provided by a set of Auto-Associative Kernel Regression (AAKR) models, whose input signals have been selected by a hybrid approach based on Correlation Analysis (CA) and Genetic Algorithm (GA) for the identification of the groups. Sequential Probability Ratio Test (SPRT) is used to define the alarm level for a given expected classification performance. A practical guideline is provided for optimally setting the SPRT parameters' values.

show abstract

Section: Different Empirical Models Have Been Developed For Signal Rementioning

confidence: 99%

Section: Different Empirical Models Have Been Developed For Signal Rementioning

confidence: 99%

Fault Detection in Nuclear Power Plants Components by a Combination of Statistical Methods

et al. 2013

View full text Add to dashboard Cite

show abstract

“…Different empirical models have been used with success to estimate (reconstruct) the expected values of the signals in normal conditions. Typical examples include Artificial Neural Networks (ANNs) (Hines, Wrest & Uhrig, 1997;Safty, Ashour, Dessouki & Sawaf, 2004;Rahman, 2010), Auto-Associative Kernel Regression (AAKR) (Chevalier, Provost & Seraoui, 2009;Baraldi, Canesi, Zio, Seraoui & Chevalier, 2010;Baraldi, Di Maio, Pappaglione, Zio & Seraoui, 2012), Evolving Clustering Method (ECM) (Zhao, , Principal Component Analysis (PCA) (Garcıa-Alvarez, 2009;Baraldi, Zio, Gola, Roverso & Hoffmann, 2011), Independent Principal Component Analysis (Ding, Hines & Rasmussen, 2003), Support Vector Machines (SVMs) (Zavaljevski & Gross, 2000;Batur, Zhou & Chan, 2002;Laouti, Sheibat-Othman & Othman, 2011) and Fuzzy Similarity (Baraldi, Di Maio, Genini & Zio, 2013).…”

Section: Introductionmentioning

confidence: 99%

Quantification of Signal Reconstruction Uncertainty in Fault Detection Systems

Al-Dahidi,

Baraldi,

Maio

et al. 2014

PHME_CONF

View full text Add to dashboard Cite

In Condition-Based Maintenance (CBM), Fault Detection (FD) systems monitor the health state of the components and aid the operator to decide whether a maintenance intervention is necessary. A FD system is a decision-aid tool typically based on i) a reconstruction model that estimates (reconstructs) the values of measurable signals in normal conditions, and ii) an analyzer of the differences (residuals) between the measured and reconstructed values: abnormal conditions are detected when residuals are statistically significant. The performance of the reconstruction model is influenced by several sources of uncertainty which can influence the operator decision: 1) measurement errors, 2) intrinsic stochasticity of the physical process, 3) uncertainty on the settings of the model parameters, and 4) uncertainty on the model output due to incompleteness of the training data. The objective of the present work is the quantification of the overall uncertainty affecting the model reconstructions. The proposed novel approach for uncertainty quantification relies on the estimation of Prediction Intervals (PIs) by using Order Statistics (OS) fora pre-defined confidence level. The proposed approach is verified with respect to an artificial case study; the obtained results show that the approach is able to guarantee the desired level of confidence on the correctness of the detection and provide the decision maker with the required information for establishing whether a maintenance intervention is necessary.

show abstract

“…Alternatively, grouping techniques based on overlapping groups (i.e. the same signal can belong to more than one group) have been proposed in [8][9][10][11]. In these approaches, the number of groups and the number of signals in each group are a priori fixed according to the user needs and a feature subset selection algorithm is developed to provide the optimal grouping.…”

Section: Introductionmentioning

confidence: 99%

Genetic algorithm-based wrapper approach for grouping condition monitoring signals of nuclear power plant components

Baraldi

Canesi

Zio

et al. 2011

ICA

View full text Add to dashboard Cite

Equipment condition monitoring of nuclear power plants requires to optimally group the usually very large number of signals and to develop for each identified group a separate condition monitoring model. In this paper we propose an approach to optimally group the signals. We use a Genetic Algorithm (GA) for the optimization of the groups; the decision variables of the optimization problem relate to the composition of the groups (i.e., which signals they contain) and the objective function (fitness) driving the search for the optimal grouping is constructed in terms of quantitative indicators of the performances of the condition monitoring models themselves: in this sense, the GA search engine is a wrapper around the condition monitoring models. A real case study is considered, concerning the condition monitoring of the Reactor Coolant Pump (RCP) of a Pressurized Water Reactor (PWR). The optimization results are evaluated with respect to the accuracy and robustness of the monitored signals estimates. The condition monitoring models built on the groups found by the proposed approach outperform the model which uses all available signals, whereas they perform similarly to the models built on groups based on signal correlation. However, these latter do not guarantee the robustness of the reconstruction in case of abnormal conditions and require to a priori fix characteristics of the groups, such as the desired minimum correlation value in a group.

show abstract

Signal reconstruction by a GA-optimized ensemble of PCA models

Cited by 7 publications

References 16 publications

Fault Detection in Nuclear Power Plants Components by a Combination of Statistical Methods

Fault Detection in Nuclear Power Plants Components by a Combination of Statistical Methods

Quantification of Signal Reconstruction Uncertainty in Fault Detection Systems

Genetic algorithm-based wrapper approach for grouping condition monitoring signals of nuclear power plant components

Contact Info

Product

Resources

About