Damage detection for offshore structures using long and short-term memory networks and random decrement technique

Bao, Xingxian; Wang, Zhichao; Iglesias, G.

doi:10.1016/j.oceaneng.2021.109388

Cited by 26 publications

(6 citation statements)

References 53 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In addition, the LSTM with memory function has been applied to the damage localization and quantification for engineering structures. Bao et al 56 input the natural frequencies and vibration modes of a 3D parametric FE model of a jacket structure into a LSTM model to detect the structure damages, and the RDT is used to quantify the damage degree. Yao et al 67 establish an anomaly detection framework combining the statistical analysis and neural network to locate and quantify the structural damage of offshore structures.…”

Section: Structure Health Monitoring Of Offshore Jacket Structuresmentioning

confidence: 99%

Condition-based structural health monitoring of offshore wind jacket structures: Opportunities, challenges, and perspectives

Leng

Gardoni

Wang

et al. 2023

Structural Health Monitoring

View full text Add to dashboard Cite

Structural health monitoring (SHM) has been recognized as a useful tool for safety management and risk reduction of offshore wind farms. In complex offshore environment, jacket structures of offshore wind turbines are prone to damages due to corrosion and fatigue. Effective SHM on jacket structures can substantially reduce their operation risk and costs. This work reviews the latest progress on the SHM of offshore wind jacket structures. The achievements in the structural damage identification, location, quantification, and remaining useful life (RUL) estimation are respectively introduced in detail, and existing challenges are discussed. Possible solutions to the challenges using the Digital Twin (DT) technology are put forward. The DT is able to mirror a real jacket structure into a virtual model, and Bayesian updating can refresh the virtual model parameters in real-time to keep consistency between virtual model and physical structure; then, just-in-time SHM can be carried out for jacket structures by performing damage detection, location, quantification, and RUL estimation using the virtual model. As a result, the DT may provide engineers and researchers a practicable tool for safety monitoring and risk reduction of fixed foundation offshore wind structures.

show abstract

Section: Structure Health Monitoring Of Offshore Jacket Structuresmentioning

confidence: 99%

Condition-based structural health monitoring of offshore wind jacket structures: Opportunities, challenges, and perspectives

Leng

Gardoni

Wang

et al. 2023

Structural Health Monitoring

View full text Add to dashboard Cite

show abstract

“…In recent years, researchers of RNN have obtained many results in sequence tasks such as speech recognition and translation. The standard structure of RNN consists of three components: the input layer, the hidden layer, and the output layer [18]. The structure of the LSTM model includes cell states as well as gating structures, as shown in Figure 5 below:…”

Section: Long and Short Term Memory Networkmentioning

confidence: 99%

Exploring English-Chinese Translation Skills Based on Big Data Technology

2023

Applied Mathematics and Nonlinear Sciences

View full text Add to dashboard Cite

This paper first explores and evaluates English-Chinese translation skills through deep learning in machine learning based on big data technology, focusing on applying convolutional neural networks and long and short-term memory network models in English-Chinese translation. Then it is to construct a deep learning evaluation model based on the dataset with text-level labels of English-Chinese translation. The structure of the deep learning evaluation model consists of three categories: data representation of text, feature extraction of text, and text classifier. Finally, the research object is determined from the purpose of the study, and the data analysis is performed on the experimental and control groups using the deep learning model to characterize the fluency by the continuous convergence of the data. The results showed that the continuous convergence of the experimental group remained in the range of 76.95% to 82.6%, and its average value was 79.76%. The continuous convergence of the control group remained in the range of 60.15% to 71.92%, with a mean value of 67.02%. The average convergence value of the experimental group was 12.74% higher than that of the control group, and the experimental group outperformed the control group. This study should learn and cultivate English-Chinese translation skills while improving the efficiency and accuracy of English-Chinese translation, which is a guiding reference value for the progress of translation talents.

show abstract

“…Long and short-term memory network can solve the problem of memory forgetting over long distances [ 23 , 24 ]. The main difference lies in that the processing of information in neural network becomes more precise.…”

Section: Estimation Algorithm Of Artificial Intelligence Modelmentioning

confidence: 99%

Feasibility Analysis and Countermeasures of Psychological Health Training Methods for Volleyball Players Based on Artificial Intelligence Technology

Jin

2022

Journal of Environmental and Public Health

View full text Add to dashboard Cite

In the process of volleyball players’ mental health training, there exists the problem of low parameter accuracy. In order to further improve the accuracy of mental health training methods, based on artificial intelligence calculation, the neural network and long and short-term memory network were used to analyze the model. Estimation algorithm was used to describe the data, and finally, the optimization model was obtained to describe the feasibility study of mental health. In addition, the relevant data were used to verify and analyze the model. The research shows that in the time update curve, with the increase of the model state, the corresponding curve on the whole first presents a fluctuating trend of different degrees. The increase of model state will make the corresponding time value gradually tend to flat. The fluctuation of the corresponding time index is obvious. Indicators corresponding to the status update curve show an obvious linear change trend with the increase in time, and the overall linear characteristics are obvious. This shows that when time is constant, the relationship between the corresponding parameter and the state value conforms to the linear law. The corresponding state index gradually increases and eventually tends to be stable. Through the analysis, it can be seen that the proportion of different indicators under the effect of artificial intelligence and the calculation results are different. The parameters show an obvious linear variation trend, indicating that the corresponding model parameters can well reflect the data changes. Finally, the accuracy of the model is verified by the method of experimental comparison. The relevant research results can provide a new model and a method for volleyball players’ mental health training.

show abstract

Damage detection for offshore structures using long and short-term memory networks and random decrement technique

Cited by 26 publications

References 53 publications

Condition-based structural health monitoring of offshore wind jacket structures: Opportunities, challenges, and perspectives

Condition-based structural health monitoring of offshore wind jacket structures: Opportunities, challenges, and perspectives

Exploring English-Chinese Translation Skills Based on Big Data Technology

Feasibility Analysis and Countermeasures of Psychological Health Training Methods for Volleyball Players Based on Artificial Intelligence Technology

Contact Info

Product

Resources

About