Fatigue damage prediction of top tensioned riser subjected to vortex-induced vibrations using artificial neural networks

Sivaprasad, Harishankar; Lekkala, Malakonda Reddy; Mohamed, L.; Seo, Junhyeon; Yoo, Kwangkyu; Jin, Chungkuk; Kim, Do Kyun

doi:10.1016/j.oceaneng.2022.113393

Cited by 24 publications

(3 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Due to the low cost of numerical simulation and easy extraction and analysis of large quantities of data, the vibration-based damage detection method is increasingly applied to marine risers [17][18][19]. For instance, Zhou et al [20] used transfer matrix techniques to extract patterns and detect damage in marine risers, then identified cracks incurred during riser deployment and retrieval [21].…”

Section: Introductionmentioning

confidence: 99%

Subsea jumper damage detection based on fractal analysis and modal characteristics

2024

Brodogradnja

View full text Add to dashboard Cite

Subsea jumpers play a critical role in subsea oil and gas production. Structural damage such as cracks is inevitable in subsea jumpers due to the harsh marine environment (internal fluid flow corrosion, high temperature and pressure, etc.). However, the current research on damage detection and evaluation of subsea jumpers is limited, particularly in cases of slight damage. This study thus proposes a method to identify cracks in subsea jumpers based on the modal characteristics and fractal theory. The accuracy of the method is verified by comparing the finite element simulation method via APDL and the analytical method via MATLAB. In addition, the sensitivity of the method to noise is investigated. The results indicate that the method accurately identifies cracks (single and multiple) with a minimum depth of 0.2 mm in various locations on subsea jumpers. This study may hold significant reference value for improving the safety and reliability of subsea jumpers.

show abstract

Section: Introductionmentioning

confidence: 99%

Subsea jumper damage detection based on fractal analysis and modal characteristics

2024

Brodogradnja

View full text Add to dashboard Cite

show abstract

“…This method forms the core of deep learning algorithms and is a subset of machine learning. One of the main benefits of ANN over other models is its ability to represent a multivariable problem based on the complex interactions between the variables and extract implicit nonlinear correlations among them [20][21][22]. This model-optimization method is widely used across various fields due to its impressive performance [23][24][25][26][27].…”

Section: Introductionmentioning

confidence: 99%

Modeling and Optimization of Hydraulic and Thermal Performance of a Tesla Valve Using a Numerical Method and Artificial Neural Network

Vaferi,

Vajdi,

Shadian

et al. 2023

Entropy

View full text Add to dashboard Cite

The Tesla valve is a non-moving check valve used in various industries to control fluid flow. It is a passive flow control device that does not require external power to operate. Due to its unique geometry, it causes more pressure drop in the reverse direction than in the forward direction. This device’s optimal performance in heat transfer applications has led to the use of Tesla valve designs in heat sinks and heat exchangers. This study investigated a Tesla valve with unconventional geometry through numerical analysis. Two geometrical parameters and inlet velocity were selected as input variables. Also, the pressure drop ratio (PDR) and temperature difference ratio (TDR) parameters were chosen as the investigated responses. By leveraging numerical data, artificial neural networks were trained to construct precise prediction models for responses. The optimal designs of the Tesla valve for different conditions were then reported using the genetic algorithm method and prediction models. The results indicated that the coefficient of determination for both prediction models was above 0.99, demonstrating high accuracy. The most optimal PDR value was 4.581, indicating that the pressure drop in the reverse flow direction is 358.1% higher than in the forward flow direction. The best TDR response value was found to be 1.862.

show abstract

“…Pipelines during offshore installations endure external pressure, bending, and axial load from various environmental forces [16,17], impacting their fatigue life over operational phases [18][19][20][21]. Hence, ensuring pipelines perform as designed without compromising integrity is paramount.…”

Section: Introductionmentioning

confidence: 99%

A Simplified Approach for Predicting Bend Radius in HDPE Pipelines during Offshore Installation

Jiwa,

Kim,

Mustaffa

et al. 2023

JMSE

Self Cite

View full text Add to dashboard Cite

Traditionally, subsea pipelines designed for the transportation of oil, gas, and water are constructed using carbon steel due to its strength, toughness, and ability to operate at temperatures up to 427 °C. However, polyethylene (PE), especially its high-density variant (HDPE), presents advantages such as reduced installation costs, diminished water leakage, and superior corrosion resistance. As research endeavours to enhance PE properties, its adoption for subsea applications is anticipated to rise. This study first delineates the mechanical behaviour of HDPE pipelines for offshore installation, identifying pulling tension, dimension ratio, water depth, and air fill ratio as the paramount lay parameters. Subsequently, a theoretical bend radius equation was derived from pipelaying mechanics using a purely geometric approach. Within this equation, two determinants, parameter X and parameter Y, dictate the sagbend bend radius. Regression analysis elucidated the relationships of lay parameters with both X and Y, yielding a general equation for X in terms of pull tension, water depth, and air fill ratio and another for Y as a function of water depth. Together, these geometric determinants underpin the sagbend bend radius estimation model. For overbend bend radius prediction, a lay index (IL) was fashioned from the aforementioned three parameters. Correlation assessments between the lay index and overbend bend radius revealed R2 values of 0.940, 0.836, and 0.712 for pipes with diameters of 2.0, 2.5, and 3.0 metres, respectively. This underscores the model’s proficiency in predicting the bend radius, albeit with decreasing precision for larger-diameter pipelines.

show abstract

Fatigue damage prediction of top tensioned riser subjected to vortex-induced vibrations using artificial neural networks

Cited by 24 publications

References 35 publications

Subsea jumper damage detection based on fractal analysis and modal characteristics

Subsea jumper damage detection based on fractal analysis and modal characteristics

Modeling and Optimization of Hydraulic and Thermal Performance of a Tesla Valve Using a Numerical Method and Artificial Neural Network

A Simplified Approach for Predicting Bend Radius in HDPE Pipelines during Offshore Installation

Contact Info

Product

Resources

About