Reconstruction of Faulty Signals by an Ensemble of Principal Component Analysis Models Optimized by a Multi-Objective Genetic Algorithm

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

doi:10.1142/9789812799470_0153

Cited by 6 publications

(13 citation statements)

References 5 publications

(7 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The procedure is tailored for realistic applications where the number of measured signals is too large to be handled effectively by a single reconstruction model [2,[10][11][12]. The approach is based on the subdivision of the set of signals into overlapping groups, the development of a reconstruction model for each group of signals and the combination of the outcomes of the models within an ensemble approach [13][14][15][16][17][18][19][20][21][22] (Figure 1). …”

Section: Introductionmentioning

confidence: 99%

“…An additional advantage of adopting ensembles of diverse models is an increased robustness of the ensemble-aggregated output [17,[21][22][23][24][25][26]. Indeed, the conjecture is that, when performing the ensemble signal reconstruction, if the signal predictions obtained by the individual models are diverse (e.g.…”

Section: Introductionmentioning

confidence: 99%

“…(i) the groups size: groups made of a reasonably small number of signals are both more accurate and easier to handle [10][11][12][16][17][18];…”

Section: Introductionmentioning

confidence: 99%

“…(iii) the diversity of the groups and of the associated models: ensembles based on diverse models are generally more reliable and robust [17,19,21,[23][24][25][26].…”

Section: Introductionmentioning

confidence: 99%

“…Regarding the integration of the outcomes of the individual models, many techniques can be adopted ranging from the simple arithmetic average to weighted average [17], local fusion [32] and dynamic integration techniques [19,20], with increasing computational costs. In practice, there is no single combination rule that is universally recognized better than the others and it is still not clear that more sophisticated and complicated aggregation techniques are actually beneficial to the ensemble performance; then, for the same reason stated above and in absence of any other prior information, the simple arithmetic average is used as a valid choice for combining the models predictions [24,33,34].…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

A randomized model ensemble approach for reconstructing signals from faulty sensors

Baraldi¹,

Gola²,

Zio³

et al. 2011

Expert Systems with Applications

Self Cite

View full text Add to dashboard Cite

On-line sensor monitoring aims at detecting anomalies in sensors and reconstructing their correct signals during operation. The techniques used for signal reconstruction are commonly based on auto-associative regression models. In full scale implementations however, the number of sensors to be monitored is often too large to be handled effectively by a single reconstruction model. In this paper we propose to tackle the problem by resorting to a pool (ensemble) of reconstruction models, each one handling an individual group of signals. This approach involves two main technical steps: firstly, a procedure for constructing signal groups, and secondly a procedure for combining the outputs of the reconstruction models associated to the groups. For the signal grouping step, a wrapper optimization search is proposed to identify the optimal number of groups in the ensemble and the size of the groups. For the model output aggregation step, a simple arithmetic average is adopted. Ensemble accuracy and robustness is achieved by promoting diversity between the signal groups through the use of the Random Feature Selection Ensemble (RFSE) technique in combination with the Bootstrapping AGGregatING (BAGGING) technique for training data selection. The individual reconstruction models are based on Principal Components Analysis (PCA). The proposed approach has been applied to a real case study concerning 215 signals monitored at a Finnish nuclear pressurized water reactor. The results obtained have been compared with those achieved by an equivalent ensemble of models based on a grouping directly optimized by a Multi-Objective Genetic Algorithm (MOGA).

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

“…(i) the groups size: groups made of a reasonably small number of signals are both more accurate and easier to handle [10][11][12][16][17][18];…”

Section: Introductionmentioning

confidence: 99%

“…(iii) the diversity of the groups and of the associated models: ensembles based on diverse models are generally more reliable and robust [17,19,21,[23][24][25][26].…”

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

A randomized model ensemble approach for reconstructing signals from faulty sensors

Baraldi¹,

Gola²,

Zio³

et al. 2011

Expert Systems with Applications

Self Cite

View full text Add to dashboard Cite

show abstract

Two novel procedures for aggregating randomized model ensemble outcomes for robust signal reconstruction in nuclear power plants monitoring systems

Baraldi

Zio

Gola

et al. 2011

Annals of Nuclear Energy

Self Cite

View full text Add to dashboard Cite

International audienceDetecting anomalies in sensors and reconstructing the correct values of the measured signals is of paramount importance for the safe and reliable operation of nuclear power plants. Auto-associative regression models can be used for the signal reconstruction task but in real applications the number of sensors signals may be too large to be handled effectively by one single model. In these cases, one may resort to an ensemble of reconstruction models, each one handling a small group of sensor signals; the outcomes of the individual models are then combined to produce the final reconstruction. In this work, three methods for aggregating the outcomes of a feature-randomized ensemble of Principal Components Analysis (PCA)-based regression models are analyzed and applied to two case studies concerning the reconstruction of 215 signals monitored at a Finnish nuclear Pressurized Water Reactor (PWR) and 920 simulated signals of the Swedish Forsmark-3 Boiling Water Reactor (BWR). Based on the insights gained, two novel aggregation procedures are developed for optimal signal reconstruction

show abstract

Aggregation of randomized model ensemble outcomes for reconstructing nuclear signals from faulty sensors

Baraldi¹,

Zio²,

Gola³

et al. 2009

Reliability, Risk, and Safety, Three Volume Set

View full text Add to dashboard Cite

Reconstruction of Faulty Signals by an Ensemble of Principal Component Analysis Models Optimized by a Multi-Objective Genetic Algorithm

Cited by 6 publications

References 5 publications

A randomized model ensemble approach for reconstructing signals from faulty sensors

A randomized model ensemble approach for reconstructing signals from faulty sensors

Two novel procedures for aggregating randomized model ensemble outcomes for robust signal reconstruction in nuclear power plants monitoring systems

Aggregation of randomized model ensemble outcomes for reconstructing nuclear signals from faulty sensors

Contact Info

Product

Resources

About