One-dimensional convolutional neural network for damage detection of jacket-type offshore platforms

Bao, Xingxian; Fan, T. Y.; Shi, Chen; Yang, Guangwu

doi:10.1016/j.oceaneng.2020.108293

Cited by 43 publications

(14 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recently, Bao et al (2020) evaluated a combination of finite element method (FE) and 1D CNN for localizing damage for a jacket-type offshore structure. However, the data was generated synthetically using a finite element model, which might not resemble the actual real-world data with operational and environmental noise contamination.…”

Section: Recent Development Of 1d Cnn-based Shmmentioning

confidence: 99%

Multiclass Damage Identification in a Full-Scale Bridge Using Optimally Tuned One-Dimensional Convolutional Neural Network

Sony

Gamage

Sadhu

et al. 2022

J. Comput. Civ. Eng.

View full text Add to dashboard Cite

In this paper, a novel method is proposed based on a windowed one-dimensional convolutional neural network (1D CNN) for multiclass damage identification using vibration responses of a full-scale bridge. The measured data is first augmented by extracting samples of windows of raw acceleration time-series to alleviate the problem of a limited training dataset. 1D CNN is developed to classify the windowed time-series into multiple damage classes. The damage is quantified using the predicted class probabilities, and the damage is localized if the predicted class is equal to the assigned damage class, exceeding a threshold associated with majority voting. The proposed network is optimally tuned with respect to various hyper-parameters such as window size, random initialization of weights, etc., to achieve the best classification performance using a global 1D CNN model. The proposed method is validated using the Z24 bridge benchmark data for multiclass classification for two different damage scenarios, namely, pier settlement and rupture of tendons, 1Sony, September 22, 2021 under the various extent of the damage. The damage identification is carried out on various bridge components to collectively identify the structural component with a damaged signature. The resultsshow that the proposed windowed 1D CNN method achieves an accuracy of 97%, and performs well with different types of damage.

show abstract

Section: Recent Development Of 1d Cnn-based Shmmentioning

confidence: 99%

Multiclass Damage Identification in a Full-Scale Bridge Using Optimally Tuned One-Dimensional Convolutional Neural Network

Sony

Gamage

Sadhu

et al. 2022

J. Comput. Civ. Eng.

View full text Add to dashboard Cite

show abstract

“… [116] used the neural network in the time domain to reduce the variance to predict the damage. [117] proposed a damage detection of offshore structures based on the vibration response; this was used as a damage indicator to get the location and its severity.…”

Section: Fatiguementioning

confidence: 99%

“…Convolutional Neural Network used convolutional kernels to convolute the local area of the input [117] , [130] . For time series value,

is the output of the convolutional layer i , which can be expressed as

where

is the output of the convolutional layer

1

.…”

Section: Fatiguementioning

confidence: 99%

Harbor and coastal structures: A review of mechanical fatigue under random wave loading

Jimenez-Martinez

2021

Heliyon

View full text Add to dashboard Cite

Harbor and coastal structures are essential in maritime connections. Additionally, some offshore structures near the coast are important for supplying energy as a material or transforming the natural resources into energy, as in wind turbines. One of the main issues that needs to be overcome in terms of these structures is mechanical fatigue due to the loads of the structure by its function and waves, wind, the current seawater level, and ice. Structural design has to meet high target loads to ensure that structures can endure extreme marine conditions under the assumption of the probability of loads and based on marine conditions, can mask damage where component immersions are not available for inspection. In this work, the wave loads and fatigue damage under random processes are reviewed.

show abstract

“…By extending this work, one could make assumptions on the fatigue life of an offshore wind turbine. Bao et al [1] utilise a one-dimensional convolutional neural network to determine the occurrence of damage to the support structure of an offshore wind turbine. In this example, the examination looks at localised damage to a jacket support structure under regular waves with an incredibly high accuracy of 98.4%.…”

Section: Introductionmentioning

confidence: 99%

Deep Neural Network Hard Parameter Multi-Task Learning for Condition Monitoring of an Offshore Wind Turbine

Black

Cevasco

Kolios

2022

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

Breaking the curse of small datasets in machine learning is but one of the major challenges that cause several real-life prediction problems. In offshore wind application, for instance, this issue presents when monitoring an asset in an attempt to reduce its infant mortality failures. Another challenge could emerge when reducing the number of sensors installed in order to limit the investment in monitoring systems. To tackle these issues, the aim of this article is to investigate the impact of small data-set on conventional machine learning methods, and to outline the improvement achievable by the implementation of transfer learning approach. It provides a solution to mitigate this issue by applying a hard parameter multi-task learning approach to the supervisory control and data acquisition data from an operational wind turbine, allowing for smaller datasets to efficiently predict the status of the gearbox’s vibration data. Two experiments are carried out in this paper. The first is to envisage the possibility of using hard parameter transfer on the operational data from two wind turbines. The second is to compare the results of this model to the findings from a conventional deep neural network model trained on the data from a single turbine.

show abstract

One-dimensional convolutional neural network for damage detection of jacket-type offshore platforms

Cited by 43 publications

References 37 publications

Multiclass Damage Identification in a Full-Scale Bridge Using Optimally Tuned One-Dimensional Convolutional Neural Network

Multiclass Damage Identification in a Full-Scale Bridge Using Optimally Tuned One-Dimensional Convolutional Neural Network

Harbor and coastal structures: A review of mechanical fatigue under random wave loading

Deep Neural Network Hard Parameter Multi-Task Learning for Condition Monitoring of an Offshore Wind Turbine

Contact Info

Product

Resources

About