A Coevolutionary Optimization Approach with Deep Sparse Autoencoder for the Extraction of Equipment Degradation Indicators

Milani, Ali Eftekhari; Antonello, Federico; Baraldi, Piero; Zio, Enrico

doi:10.3850/978-981-14-8593-0_5858-cd

Cited by 2 publications

(6 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The complexity of the input-space containing 10 signals, which have to be considered at different time steps to catch the dynamics of the degradation process, has been properly treated by the deep-learning method in Milani et al 33 This is due to the capability of the complex, multi-layer hierarchical architecture of extracting information from large-dimensional datasets. Also, the degradation indicator obtained by projecting the multi-dimensional data in the innermost layer of the stacked autoencoders has been shown to be robust to the evolving environments, given its high-level of abstraction.…”

Section: Results and Commentsmentioning

confidence: 99%

“…The detailed description of the methods can be found in Refs. 30–33 It is interesting to notice that three groups of participants have developed ensemble of models 30–32 and two groups have used deep-learning based methods. 32,33…”

Section: Methods Proposed To Solve the Challenge And Their Performancesmentioning

confidence: 99%

“…Deep learning methods have been employed also in Milani et al, 33 where sparse autoencoders are stacked to obtain a high-level representation of the system state in the encoder innermost layer. The authors have shown that one of the features extracted by the neurons of the innermost layer is directly related to the component degradation and is robust to the evolving environments.…”

Section: Methods Proposed To Solve the Challenge And Their Performancesmentioning

confidence: 99%

“…The detailed description of the methods can be found in Refs. [30][31][32][33] It is interesting to notice that three groups of participants have developed ensemble of models [30][31][32] and two groups have used deep-learning based methods. 32,33 The individual models of the ensemble in Altarabichi et al 30 are classifiers created using different algorithms, such as Random Forest, LightGbm, and Artificial Neural Networks, to guarantee diversity in the classifications.…”

Section: Methods Proposed To Solve the Challenge And Their Performancesmentioning

confidence: 99%

“…[30][31][32][33] It is interesting to notice that three groups of participants have developed ensemble of models [30][31][32] and two groups have used deep-learning based methods. 32,33 The individual models of the ensemble in Altarabichi et al 30 are classifiers created using different algorithms, such as Random Forest, LightGbm, and Artificial Neural Networks, to guarantee diversity in the classifications. The predictions of the individual models are aggregated using a method based on stacked generalization, 34 where a second-level meta-model is developed to optimally combine the outcomes of the individual classifiers.…”

Section: Methods Proposed To Solve the Challenge And Their Performancesmentioning

confidence: 99%

See 4 more Smart Citations

The Aramis Data Challenge to prognostics and health management methods for application in evolving environments

Baraldi

Bellani²,

Zio

et al. 2022

Proceedings of the Institution of Mechanical Engineers, Part O:

Self Cite

View full text Add to dashboard Cite

A recurrent difficulty for the effective application of Prognostics and Health Management (PHM) methods is related to the “evolving environments” in which industrial components typically operate. Several factors render the operational environments evolving, including deterioration of components, effects of maintenance activities and changes in working conditions. The issue of evolving environments is even more complicated for multi-component systems, where the degradation of one component can affect the degradation processes of other components, thus modifying their lifetime distributions and the statistical properties of the monitored signals. In an effort to convey research toward practical PHM solutions capable of dealing with evolving environments, the “Aramis challenge on degradation state assessment in evolving environments,” has been launched for the ESREL2020-PSAM15 conference. This work describes the Aramis Data Challenge and associated public dataset, illustrates the methods proposed for its solution and the related results obtained. For the evaluation of the goodness of the fault detection methods, an original metric is introduced, which is a variant of the timeliness metric that has been used in the PHM08 data challenge.

show abstract

Section: Results and Commentsmentioning

confidence: 99%

Section: Methods Proposed To Solve the Challenge And Their Performancesmentioning

confidence: 99%

Section: Methods Proposed To Solve the Challenge And Their Performancesmentioning

confidence: 99%

Section: Methods Proposed To Solve the Challenge And Their Performancesmentioning

confidence: 99%

Section: Methods Proposed To Solve the Challenge And Their Performancesmentioning

confidence: 99%

See 3 more Smart Citations

The Aramis Data Challenge to prognostics and health management methods for application in evolving environments

Baraldi

Bellani²,

Zio

et al. 2022

Proceedings of the Institution of Mechanical Engineers, Part O:

Self Cite

View full text Add to dashboard Cite

show abstract

Advanced Semi-Automatic Approach for Identifying Damaged Surfaces in Cultural Heritage Sites: Integrating UAVs, Photogrammetry, and 3D Data Analysis

Caciora,

Ilieș,

Herman

et al. 2024

Remote Sensing

View full text Add to dashboard Cite

The analysis and preservation of the cultural heritage sites are critical for maintaining their historical and architectural integrity, as they can be damaged by various factors, including climatic, geological, geomorphological, and human actions. Based on this, the present study proposes a semi-automatic and non-learning-based method for detecting degraded surfaces within cultural heritage sites by integrating UAV, photogrammetry, and 3D data analysis. A 20th-century fortification from Romania was chosen as the case study due to its physical characteristics and state of degradation, making it ideal for testing the methodology. Images were collected using UAV and terrestrial sensors and processed to create a detailed 3D point cloud of the site. The developed pipeline effectively identified degraded areas, including cracks and material loss, with high accuracy. The classification and segmentation algorithms, including K-means clustering, geometrical features, RANSAC, and FACETS, improved the detection of destructured areas. The combined use of these algorithms facilitated a detailed assessment of the structural condition. This integrated approach demonstrated that the algorithms have the potential to support each other in minimizing individual limitations and accurately identifying degraded surfaces. Even though some limitations were observed, such as the potential for the overestimation of false negatives and positives areas, the damaged surfaces were extracted with high precision. The methodology proved to be a practical and economical solution for cultural heritage monitoring and conservation, offering high accuracy and flexibility. One of the greatest advantages of the method is its ease of implementation, its execution speed, and the potential of using entirely open-source software. This approach can be easily adapted to various heritage sites, significantly contributing to their protection and valorization.

show abstract

A Coevolutionary Optimization Approach with Deep Sparse Autoencoder for the Extraction of Equipment Degradation Indicators

Cited by 2 publications

References 8 publications

The Aramis Data Challenge to prognostics and health management methods for application in evolving environments

The Aramis Data Challenge to prognostics and health management methods for application in evolving environments

Advanced Semi-Automatic Approach for Identifying Damaged Surfaces in Cultural Heritage Sites: Integrating UAVs, Photogrammetry, and 3D Data Analysis

Contact Info

Product

Resources

About