2014
DOI: 10.1177/1475090214540874
|View full text |Cite
|
Sign up to set email alerts
|

Abstract: Availability, reliability and economic sustainability of naval propulsion plants are key elements to cope with because maintenance costs represent a large slice of total operational expenses. Depending on the adopted strategy, impact of maintenance on overall expenses can remarkably vary; for example, letting an asset running up until breakdown can lead to unaffordable costs. As a matter of fact, a desideratum is to progress maintenance technology of ship propulsion systems from breakdown or preventive mainten… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

3
123
0
5

Year Published

2015
2015
2022
2022

Publication Types

Select...
5
2
1

Relationship

1
7

Authors

Journals

citations
Cited by 90 publications
(131 citation statements)
references
References 54 publications
3
123
0
5
Order By: Relevance
“…Regression Problems: NADINE is capable of handling the regression problem equally well as the classification problem because it is developed under the MLP-like structure. NADINE's performance for regression problem is numerically validated in three data stream regression problems with non-stationary characteristics, household electricity prediction, SP 500 time series index prediction and condition monitoring problems [30] where their characteristics are summarized in Table 1 and detailed in the supplemental document. Minor modification is performed in NADINE where the drift detection module checks the prequential error rather than classification error.…”
Section: Proof Of Conceptsmentioning
confidence: 99%
“…Regression Problems: NADINE is capable of handling the regression problem equally well as the classification problem because it is developed under the MLP-like structure. NADINE's performance for regression problem is numerically validated in three data stream regression problems with non-stationary characteristics, household electricity prediction, SP 500 time series index prediction and condition monitoring problems [30] where their characteristics are summarized in Table 1 and detailed in the supplemental document. Minor modification is performed in NADINE where the drift detection module checks the prequential error rather than classification error.…”
Section: Proof Of Conceptsmentioning
confidence: 99%
“…Because these data sets come from a wide variety of application areas, these results indicate that low-rank structure exists and is pervasive in a wide variety of regimes. Coraddu et al [2014]. HP denotes high-pressure and GT denotes gas turbine.…”
Section: Real-data Performancementioning
confidence: 99%
“…In this section we consider a simulation of a gas turbine propulsion engine mounted on a naval Frigate as detailed in Coraddu et al [2014], and for which simulation data is made openly available through the UCI Machine Learning Repository [Lichman, 2013]. The goal of the UQ problem is to predict the degradation of the gas turbine based on certain parameters of its operation.…”
Section: Application: Modeling a Propulsion Plant On A Naval Vesselmentioning
confidence: 99%
See 1 more Smart Citation
“…Among other fields of applications, Condition Based Maintenance (CBM) is one of the most challenging problems for SDA of BDS [14,15,16]. The general principle guiding optimal Maintenance is to make all the necessary actions that guarantee that an asset continues to perform the required functions in the proper way [17,18].…”
Section: Introductionmentioning
confidence: 99%