Logo: to the web site of Uppsala University

uu.sePublications from Uppsala University
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Neural network survivability approach of a wave energy converter considering uncertainties in the prediction of future knowledge
(Wave energy group)ORCID iD: 0000-0002-1165-5569
(Wave energy group)
(Wave energy group)
2024 (English)In: Article in journal (Refereed) Submitted
Abstract [en]

To tune the wave energy converter (WEC) controller parameters such as damping to reduce the line force during extreme wave conditions, future knowledge of the line force is required.To achieve this, the incoming wave and system state should be predicted for a few seconds in the future. It is rather an arduous task to predict the future knowledge of waves and the system's dynamic when dealing with breaking and steep waves, and the system is subject to various nonlinear forces. The classical model-based control strategies often rely on linear assumptions to estimate the WEC dynamics for the sake of simplicity. Unlike the model-based, the data-driven approaches are free from modeling errors and the algorithms are trained over the true and noisy data to predict non-linear system behaviors.Using data-driven approaches, we are able to model nonlinear dynamics. However, new questions emerge on the accuracy of the future wave and system state predictions, and how this uncertainty propagates into the final prediction of the line force. As incorrect damping may lead to excessive line force and detrimental damage to the system, these are the knowledge gaps that need to be addressed.The main purpose of this paper is to answer these questions through a survivability strategy for wave energy converters by providing a realistic perspective on the implementation of the neural network approaches by accounting for the errors in the input data. For this purpose, a series of neural networks is designed that first predicts the surface elevation for 0.36 s ahead, i.e. corresponding to 2 s in the full-scale WEC. This future knowledge of the wave elevation is then used to predict the system state (i.e. power take-off (PTO) translator position) for the same prediction horizon based on the PTO damping. This information is then fed to a convolutional neural network (CNN) that predicts the peak line force 0.36 s ahead. Further, the sensitivity of the peak line force prediction to the uncertainties in the input data and the prediction horizon is analyzed. The neural network models are trained over the experimental data subjected to the extreme sea states for a point absorber wave energy converter. The results present a thorough analysis of the NN models’ performance.The results suggest that the accuracy of the surface elevation prediction has an insignificant independent effect on the peak force prediction model. However, these uncertainties reflect in the PTO translator position prediction, and the model is considerably sensitive to the accuracy of this prediction. This sensitivity nonetheless is less notable for higher PTO damping values. The prediction accuracy of the peak forces dropped by only about 7\% when the predicted input was used in the lower damping cases here, whereas, a larger drop was seen for the higher damping case.  

Place, publisher, year, edition, pages
2024.
Keywords [en]
Wave energy converters, Survivability, Neural networks, Prediction of system dynamics, Extreme sea state, Wave tank experiment
National Category
Marine Engineering Ocean and River Engineering Control Engineering Energy Engineering Reliability and Maintenance
Identifiers
URN: urn:nbn:se:uu:diva-521361OAI: oai:DiVA.org:uu-521361DiVA, id: diva2:1830519
Available from: 2024-01-23 Created: 2024-01-23 Last updated: 2024-04-04
In thesis
1. Survivability control using data-driven approaches and reliability analysis for wave energy converters
Open this publication in new window or tab >>Survivability control using data-driven approaches and reliability analysis for wave energy converters
2024 (English)Doctoral thesis, comprehensive summary (Other academic)
Abstract [en]

Wave energy, with five times the energy density of wind and ten times the power density of solar, offers a compelling carbon-free electricity solution. Despite its advantages, ongoing debates surround the reliability and economic feasibility of wave energy converters (WECs). To address these challenges, this doctoral thesis is divided into four integral parts, focusing on optimizing the prediction horizon for power maximization, analyzing extreme waves' impact on system dynamics, ensuring reliability, and enhancing survivability in WECs.

Part I emphasizes the critical importance of the prediction horizon for maximal power absorption in wave energy conversion. Using generic body shapes and modes, it explores the effect of dissipative losses, noise, filtering, amplitude constraints, and real-world wave parameters on the prediction horizon. Findings suggest achieving optimal power output may be possible with a relatively short prediction horizon, challenging traditional assumptions.

Part II shifts focus to WEC system dynamics, analyzing extreme load scenarios. Based on a 1:30 scaled wave tank experiment, it establishes a robust experimental foundation, extending into numerical assessment of the WEC. Results underscore the importance of damping to alleviate peak forces. Investigating various wave representations highlights conservative characteristics of irregular waves, crucial for WEC design in extreme sea conditions.

Part III explores the computational intricacies of environmental design load cases and fatigue analyses for critical mechanical components of the WEC. The analysis is conducted for hourly sea state damage and equivalent two-million-cycle loads. Finally, a comparison of safety factors between the ultimate limit state and fatigue limit state unfolds, illustrating the predominant influence of the ultimate limit state on point-absorber WEC design.

Part IV, centers on elevating survivability strategies for WECs in extreme wave conditions. Three distinct controller system approaches leverage neural networks to predict and minimize the line force. Distinct variations emerge in each approach, spanning from rapid detection of optimal damping to integrating advanced neural network architectures into the control system with feedback. The incorporation of a controller system, refined through experimental data, showcases decreases in the line force, providing a practical mechanism for real-time force alleviation.

This thesis aims to contribute uniquely to the goal of advancing wave energy conversion technology through extensive exploration.

Place, publisher, year, edition, pages
Uppsala: Acta Universitatis Upsaliensis, 2024. p. 169
Series
Digital Comprehensive Summaries of Uppsala Dissertations from the Faculty of Science and Technology, ISSN 1651-6214 ; 2377
Keywords
power maximization, prediction horizon, extreme wave conditions, wave tank experiment, numerical WEC-Sim analysis, reliability analysis, statistical methods, environmental design load, fatigue analysis, statistical methods, survivability analysis, neural network methods
National Category
Control Engineering Energy Systems Ocean and River Engineering Other Electrical Engineering, Electronic Engineering, Information Engineering Marine Engineering Reliability and Maintenance Energy Engineering
Identifiers
urn:nbn:se:uu:diva-524903 (URN)978-91-513-2077-9 (ISBN)
Public defence
2024-05-17, Häggsalen (10132), Ångströmlaboratoriet, Uppsala, 09:00 (English)
Opponent
Supervisors
Available from: 2024-04-22 Created: 2024-03-12 Last updated: 2024-04-22

Open Access in DiVA

No full text in DiVA

Search in DiVA

By author/editor
Shahroozi, ZahraGöteman, MalinEngström, Jens
Marine EngineeringOcean and River EngineeringControl EngineeringEnergy EngineeringReliability and Maintenance

Search outside of DiVA

GoogleGoogle Scholar

urn-nbn

Altmetric score

urn-nbn
Total: 33 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf