2020
DOI: 10.2172/1661211
|View full text |Cite
|
Sign up to set email alerts
|

Development of Prognostic Models Using Plant Asset Data

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
21
0

Year Published

2021
2021
2022
2022

Publication Types

Select...
5
1

Relationship

5
1

Authors

Journals

citations
Cited by 11 publications
(21 citation statements)
references
References 23 publications
0
21
0
Order By: Relevance
“…In datadriven methods, no mechanism or input-output relationship needs to be known a priori to produce acceptable results, and the method development/implementation cost is relatively low (Diez-Olivan et al, 2019). Therefore, these methods are highly flexible and can be deployed at any level (component, subsystem, or system level) of the physical asset, which is of particular interest to large, complex systems (Ramuhalli et al, 2020;Sun et al, 2010). As shown in Figure 4, statistical-based and ML/DLbased data-driven methods have attracted most of the research attention in machinery prognostics.…”
Section: Data-driven Methodsmentioning
confidence: 99%
See 2 more Smart Citations
“…In datadriven methods, no mechanism or input-output relationship needs to be known a priori to produce acceptable results, and the method development/implementation cost is relatively low (Diez-Olivan et al, 2019). Therefore, these methods are highly flexible and can be deployed at any level (component, subsystem, or system level) of the physical asset, which is of particular interest to large, complex systems (Ramuhalli et al, 2020;Sun et al, 2010). As shown in Figure 4, statistical-based and ML/DLbased data-driven methods have attracted most of the research attention in machinery prognostics.…”
Section: Data-driven Methodsmentioning
confidence: 99%
“…Prognostic calculations cannot be done in isolation and depend largely on the stages of monitoring, detection, and diagnostics: the accuracy of these stages will all affect RUL estimation. It is desirable to develop generalizable prognostic methods that can accurately predict the future equipment state given a set of measurements correlated to the equipment's current state (Ramuhalli et al, 2020). An appropriate estimate of the equipment's RUL can improve overall plant performance and reduce costs by optimizing O&M activities.…”
Section: Prognosticsmentioning
confidence: 99%
See 1 more Smart Citation
“…This report is the last in a series of documents detailing online monitoring, wireless communication networks, and the development of diagnostic and prognostic models using heterogenous data regarding critical balance of plant equipment in NPPs [5][6][7][8][9]. The previous documents in this series evaluated potential wireless technologies and communication networks inside NPPs, based on their performance and economics [5][6][7]; assessed vibration sensors with wireless capabilities [8]; and developed formal methodologies for cleaning data and objectively comparing ML prognostic models [9].…”
Section: Scope Of This Reportmentioning
confidence: 99%
“…A milestone report was issued in September 2020 [14] documented achievement of the objective to create a prognostic model to estimate predictions of future measurements of the FWCS. This milestone used three different ML methods, long short-term memory (LSTM) networks, SVMs, and a nonlinear autoregressive neural network (NAR) to estimate three different forecast horizons: 1 hour, 1 day, and 1 week.…”
Section: Development Of Prognostic Models Using Plant Asset Datamentioning
confidence: 99%