An AI-Based Detection System for Mooring Line Failure

2021 ◽  
Author(s):  
Djoni Eka Sidarta ◽  
Nicolas Tcherniguin ◽  
Philippe Bouchard ◽  
Ho-Joon Lim ◽  
Mengchen Kang ◽  
...  
Keyword(s):  
Environmental Conditions ◽  
Computational Time ◽  
Mooring Line ◽  
Ann Model ◽  
Mooring Lines ◽  
Hydrodynamic Simulations ◽  
Alternative Method ◽  
Detection Program ◽  
Artificial Neural ◽  
Fully Coupled

Abstract Safe and productive offshore operations are of utmost importance, with monitoring the integrity of mooring lines on floating offshore platforms being one of the key factors. The conventional method uses sensors installed on mooring components, which may fail over time and can be costly to replace. Alternative methods using dry and non-intrusive monitoring systems offer a lot of potentials to the industry. An alternative method that uses only Differential Global Positioning System (DGPS) data has been proposed by Sidarta et al. (2018, 2019), and it does not require any information on environmental conditions. This alternative method is based on monitoring shifts in the low-frequency periods and mean yaw angles as a function of vessel positions, mass and added mass. The method utilizes Artificial Intelligence, specifically Artificial Neural Network (ANN), for the detection of mooring line failure, which is a pattern recognition and classification problem. The ANN model learns to recognize and classify patterns of intact mooring lines and those of a broken line. One of the proposed models is a group identification model, in which the model identifies the mooring group that has a broken line. This paper shows that an ANN model can be quite robust and tolerant in dealing with conditions that are somewhat different from its training. As an example, an ANN model for detecting mooring line failure on a spread moored FPSO has been trained using MLTSIM hydrodynamic simulations with quasi static model of the mooring lines and risers to significantly reduce the computational time to generate the ANN training data. The trained ANN model can properly function when tested using fully coupled OrcaFlex hydrodynamic simulations with environmental conditions that are not included in the training. Moreover, although the ANN model has been trained using simulations with a completely removed line, the trained model can still function for a line broken at the bottom. This ANN model is an ANN-based status detection model, which is one of the key components in the ALANN (Anchor Lines monitoring using Artificial Neural Networks) System. The system also composes of an ANN-based system evaluation model, an algorithm-based status detection program and an event detection program. A series of fully coupled dynamic simulations have been used to test the ALANN System. Most of the simulations have a single mooring line failure that occurs randomly during simulation, and the failed line varies for different simulations. Each simulation lasts for six hours. The ALANN System uses a two-hour time window at a time and moves every 20 minutes. The tests demonstrate how each component of the ALANN System contributes to and improves the robustness of the overall solution.

An Adaptive Method to Further Improve the Tolerance of an ANN-Based Detection System for Mooring Line Failure

2021 ◽  
Author(s):  
Djoni E. Sidarta ◽  
Nicolas Tcherniguin ◽  
Ho-Joon Lim ◽  
Philippe Bouchard ◽  
Mengchen Kang ◽  
...  
Keyword(s):  
Time Series ◽  
Adaptive Method ◽  
Training Data ◽  
Computational Time ◽  
Mooring Line ◽  
Ann Model ◽  
Hydrodynamic Simulations ◽  
Sensitivity Tests ◽  
Fully Coupled ◽  
And Training

Abstract The use of an Artificial Neural Network (ANN) for detection of mooring line failure has been a growing subject of discussion over the past several years. Sidarta et al. [6, 8, 12] have presented papers on the detection of mooring line failure of a moored vessel by monitoring shifts in the low frequency periods, mean yaw angles as a function of vessel positions, mass and added mass. An ANN model has been trained using MLTSIM hydrodynamic simulations based on information from the early stages of the project. The restoring forces and moments from mooring lines, risers and umbilicals have been solved using catenary equations to significantly reduce the computational time to generate the ANN training data. This paper presents the evaluation of this ANN model using fully coupled OrcaFlex hydrodynamic simulations, based on the latest information of the project. The results of this evaluation demonstrate the tolerance of the trained ANN model as it can properly function when tested using time series of vessel motions from the fully coupled OrcaFlex hydrodynamic simulations. Furthermore, although the ANN model has been trained using simulations with a completely removed line, the trained model can still function when tested with simulations of a line broken at the bottom. These give affirmation that the ANN model can tolerate the differences that exist between the test and training data. Sensitivity of the polyester line stiffness has also been performed using fully coupled OrcaFlex hydrodynamic simulations, and the computed time series of vessel motions have been used to test the ANN model. The ANN model can deal with some level of differences between the sensitivity tests and training data. However, sensitivity tests of the polyester line stiffness to model aging lines has posed a real challenge to the ANN model as its prediction accuracy has decreased significantly. This paper presents an adaptive method that can be implemented such that the ANN model can adapt to relatively new conditions that are quite different from the training data and maintain the accuracy of its prediction. With this approach, an existing ANN model that has been trained under certain assumptions of the system can still function although the behavior of the system has drifted away from those assumptions. This phenomenon may have similarity with a possible reality that measured behavior in the field can be somewhat different from numerical simulations. This adaptive method has a potential for addressing this issue such that a simulation trained ANN model can maintain its expected accuracy although dealing with different conditions from the training data. If successful, this is a good cost saving scenario that an ANN model adapts to some degree to relatively new and different conditions before the differences become too much to handle and the only solution is to retrain the model.

Damage Detection of Offshore Platform Mooring Line Using Artificial Neural Network

2018 ◽  
Author(s):  
Djoni E. Sidarta ◽  
Jim O’Sullivan ◽  
Ho-Joon Lim
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Damage Detection ◽  
Total Mass ◽  
Offshore Platform ◽  
Mooring Line ◽  
Ann Model ◽  
Station Keeping ◽  
Mooring Lines ◽  
Artificial Neural

Station-keeping using mooring lines is an important part of the design of floating offshore platforms, and has been used on most types of floating platforms, such as Spar, Semi-submersible, and FPSO. It is of great interest to monitor the integrity of the mooring lines to detect any damaged and/or failures. This paper presents a method to train an Artificial Neural Network (ANN) model for damage detection of mooring lines based on a patented methodology that uses detection of subtle shifts in the long drift period of a moored floating vessel as an indicator of mooring line failure, using only GPS monitoring. In case of an FPSO, the total mass or weight of the vessel is also used as a variable. The training of the ANN model employs a back-propagation learning algorithm and an automatic method for determination of ANN architecture. The input variables of the ANN model can be derived from the monitored motion of the platform by GPS (plus vessel’s total mass in case of an FPSO), and the output of the model is the identification of a specific damaged mooring line. The training and testing of the ANN model use the results of numerical analyses for a semi-submersible offshore platform with twenty mooring lines for a range of metocean conditions. The training data cover the cases of intact mooring lines and a damaged line for two selected adjacent lines. As an illustration, the evolution of the model at various training stages is presented in terms of its accuracy to detect and identify a damaged mooring line. After successful training, the trained model can detect with great fidelity and speed the damaged mooring line. In addition, it can detect accurately the damaged mooring line for sea states that are not included in the training. This demonstrates that the model can recognize and classify patterns associated with a damaged mooring line and separate them from patterns of intact mooring lines for sea states that are and are not included in the training. This study demonstrates a great potential for the use of a more general and comprehensive ANN model to help monitor the station keeping integrity of a floating offshore platform and the dynamic behavior of floating systems in order to forecast problems before they occur by detecting deviations in historical patterns.

Detection of Mooring Line Failure of a Spread-Moored FPSO: Part 1 — Development of an Artificial Neural Network Based Model

2019 ◽  
Author(s):  
Djoni E. Sidarta ◽  
Ho-Joon Lim ◽  
Johyun Kyoung ◽  
Nicolas Tcherniguin ◽  
Timothee Lefebvre ◽  
...  
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Numerical Simulations ◽  
Learning Algorithm ◽  
Offshore Platform ◽  
Training Data ◽  
Mooring Line ◽  
Ann Model ◽  
Mooring Lines ◽  
Artificial Neural

Abstract Artificial Intelligence (AI) has gained popularity in recent years for offshore engineering applications, and one such challenging application is detection of mooring line failure of a floating offshore platform. For most types of floating offshore platforms, accurately detecting any mooring line damage and/or failures is of great interest to their operators. This paper demonstrates the use of an Artificial Neural Network (ANN) model for detecting mooring line failure for a spread-moored FPSO. The ANN model representation, in terms of its input variables, is based on assessing when changes in a platform’s motion characteristics are in-fact indicators of a mooring line failure. The output of the ANN model indicates the status condition for the mooring lines (intact or failed). This ANN model only requires GPS / DGPS monitoring data and does not require data on the environmental conditions at the platform. Since the mass of an FPSO changes with the stored volume of oil, the vessel’s mass is also an input variable. The ANN training uses the results from numerical simulations of a spread-moored FPSO with fourteen mooring lines. The numerical simulations create the FPSO’s response to a range of metocean conditions for 360-degree directions, and they cover several levels of vessel draft (mass). Furthermore, the simulations cover both the intact mooring configuration and the full permutation where each of the fourteen mooring lines is modeled as broken at the top. The global performance analysis of the FPSO is presented in a different paper (Part 2 of these paper series). The training of the ANN model employs a back-propagation learning algorithm and an automatic method for determining the size of ANN hidden layers. The trained ANN model can detect mooring line failure, even for vessel draft (mass), sea states and environmental directions that are not included in the training data. This demonstrates that the ANN model can recognize and classify patterns associated with mooring line failure and separate such patterns from those associated with intact mooring lines under conditions not included in the original training data. This study reveals a great potential for using an ANN model to monitor the station keeping integrity of a floating offshore platform with changing storage, or mass status, and to detect mooring line failure using only the vessel’s mass and deviations in the platform’s motions derived from GPS / DGPS data.

Cazacu and Barlat Criterion Identification Using the Cylindrical Cup Deep Drawing Test and the Coupled Artificial Neural Networks – Genetic Algorithm Method

2012 ◽  
Vol 504-506 ◽  
pp. 637-642 ◽  
Author(s):  
Hamdi Aguir ◽  
J.L. Alves ◽  
M.C. Oliveira ◽  
L.F. Menezes ◽  
Hedi BelHadjSalah
Keyword(s):  
Genetic Algorithm ◽  
Finite Element ◽  
Deep Drawing ◽  
Inverse Analysis ◽  
Computational Time ◽  
Ann Model ◽  
Drawing Test ◽  
Artificial Neural ◽  
Deep Drawing Test ◽  
Cylindrical Cup

This paper deals with the identification of the anisotropic parameters using an inverse strategy. In the classical inverse methods, the inverse analysis is generally coupled with a finite element code, which leads to a long computational time. In this work an inverse analysis strategy coupled with an artificial neural network (ANN) model is proposed. This method has the advantage of being faster than the classical one. To test and validate the proposed approach an experimental cylindrical cup deep drawing test is used in order to identify the orthotropic material behaviour. The ANN model is trained by finite element simulations of this experimental test. To reduce the gap between the experimental responses and the numerical ones, the proposed method is coupled with an optimization procedure based on the genetic algorithm (GA) to identify the Cazacu and Barlat’2001 material parameters of a standard mild steel DC06.

scholarly journals Application of artificial neural network for predicting the performance of CO2 enhanced oil recovery and storage in residual oil zones

2020 ◽  
Vol 10 (1) ◽  
Author(s):  
Hung Vo Thanh ◽  
Yuichi Sugai ◽  
Kyuro Sasaki
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Oil Recovery ◽  
Early Stage ◽  
Computational Time ◽  
Residual Oil ◽  
Ann Model ◽  
Ann Models ◽  
Artificial Neural ◽  
And Storage

Abstract Residual Oil Zones (ROZs) become potential formations for Carbon Capture, Utilization, and Storage (CCUS). Although the growing attention in ROZs, there is a lack of studies to propose the fast tool for evaluating the performance of a CO2 injection process. In this paper, we introduce the application of artificial neural network (ANN) for predicting the oil recovery and CO2 storage capacity in ROZs. The uncertainties parameters, including the geological factors and well operations, were used for generating the training database. Then, a total of 351 numerical samples were simulated and created the Cumulative oil production, Cumulative CO2 storage, and Cumulative CO2 retained. The results indicated that the developed ANN model had an excellent prediction performance with a high correlation coefficient (R2) was over 0.98 on comparing with objective values, and the total root mean square error of less than 2%. Also, the accuracy and stability of ANN models were validated for five real ROZs in the Permian Basin. The predictive results were an excellent agreement between ANN predictions and field report data. These results indicated that the ANN model could predict the CO2 storage and oil recovery with high accuracy, and it can be applied as a robust tool to determine the feasibility in the early stage of CCUS in ROZs. Finally, the prospective application of the developed ANN model was assessed by optimization CO2-EOR and storage projects. The developed ANN models reduced the computational time for the optimization process in ROZs.

scholarly journals STRUCTURAL BEHAVIOUR OF FULLY COUPLED SPAR–MOORING SYSTEM UNDER EXTREME WAVE LOADING

2014 ◽  
Vol 19 (Supplement_1) ◽  
pp. S69-S77 ◽  
Author(s):  
A. B. M. Saiful Islam ◽  
Mohammed Jameel ◽  
Suhail Ahmad ◽  
Mohd Zamin Jumaat ◽  
V. John Kurian
Keyword(s):  
Response Time ◽  
Deep Water ◽  
Mooring Line ◽  
Mooring System ◽  
Wave Loading ◽  
Extreme Wave ◽  
Spar Platform ◽  
Mooring Lines ◽  
Time Histories ◽  
Fully Coupled

Floating spar platform has been proven to be an economical and efficient type of offshore oil and gas exploration structure in deep and ultra-deep seas. Associated nonlinearities, coupled action, damping effect and extreme sea environments may modify its structural responses. In this study, fully coupled spar–mooring system is modelled integrating mooring lines with the cylindrical spar hull. Rigid beam element simulates large cylindrical spar hull and catenary mooring lines are configured by hybrid beam elements. Nonlinear finite element analysis is performed under extreme wave loading at severe deep sea. Morison's equation has been used to calculate the wave forces. Spar responses and mooring line tensions have been evaluated. Though the maximum mooring line tensions are larger at severe sea-state, it becomes regular after one hour of wave loading. The response time histories in surge, heave, pitch and the maximum mooring tension gradually decreases even after attaining steady state. It is because of damping due to heavier and longer mooring lines in coupled spar–mooring system under deep water conditions. The relatively lesser values of response time histories in surge, heave, pitch and the maximum mooring tension under extreme wave loading shows the suitability of a spar platform for deep water harsh and uncertain environmental conditions.

Sensitivity Analysis of an ANN-Based System for Detection of Mooring Line Failure

2020 ◽  
Author(s):  
Djoni E. Sidarta ◽  
Nicolas Tcherniguin ◽  
Philippe Bouchard ◽  
Ho-Joon Lim
Keyword(s):  
Numerical Simulations ◽  
Compressive Load ◽  
Low Frequency ◽  
Mooring Line ◽  
Offshore Platforms ◽  
Ann Model ◽  
Monitoring Equipment ◽  
Mooring Lines ◽  
Inclination Angles ◽  
Noise Tolerant

Abstract Monitoring the integrity of mooring lines on floating offshore platforms is one of the key factors in ensuring safe and productive offshore operations. Sensors, such as inclinometers, compressive load cells or strain sensors, can be used to monitor the inclination angles or tensions on mooring lines. An alternative method using only dry monitoring systems, such as DGPS (Differential Global Positioning System), Gyrocompass and/or IMU (Inertial Measurement / Motion Unit), can also be used to monitor the integrity of mooring lines. This method uses the measured motions and positions of a vessel without any information on the environmental conditions to detect mooring line failure. The detection of mooring line failure is based on detecting shifts in low-frequency periods and mean yaw angles as a function of vessel position, mass and added mass. The proposed method utilizes Artificial Neural Network (ANN) to recognize and classify patterns. The training of an ANN model requires examples/data associated with intact mooring lines and broken mooring line(s). Examples/data of broken mooring line(s) are practically available only from numerical simulations. Therefore, it is important to address these two key topics: (1) Is the real behavior of the floating offshore platform sufficiently aligned with numerical simulations? and (2) The effect of the accuracy of monitoring equipment on the performance of an ANN-based system. The first topic is reviewed briefly with its possible solution including some sensitivity tests, and this paper focuses on addressing the second topic. A system architecture is discussed in this paper along with the accuracy of the monitoring equipment. As an example, an ANN model has been trained to detect a broken mooring line of a spread-moored FPSO. This ANN model has been tested on its performance in dealing with a range of possible errors associated with the monitoring equipment. Furthermore, the tests have been carried out for a combination of variables that are not included in the ANN training, such as: vessel draft (mass), sea state conditions and directions. This paper presents the results of the tests for various variable sensitivities, which cover vessel positions, mean yaw angles and vessel drafts. These are essentially testing the tolerance of a trained ANN model against error or noise in the data. The results show that a trained ANN model can be error/noise tolerant.

Detecting SIM Box Fraud by Using Support Vector Machine and Artificial Neural Network

2015 ◽  
Vol 74 (1) ◽  
Author(s):  
Roselina Sallehuddin ◽  
Subariah Ibrahim ◽  
Azlan Mohd Zain ◽  
Abdikarim Hussein Elmi
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Support Vector Machine ◽  
Model Building ◽  
Computational Time ◽  
Support Vector ◽  
Ann Model ◽  
Svm Model ◽  
Artificial Neural ◽  
Artificial Neural Network Ann

Fraud in communication has been increasing dramatically due to the new modern technologies and the global superhighways of communication, resulting in loss of revenues and quality of service in telecommunication providers especially in Africa and Asia.  One of the dominant types of fraud is SIM box bypass fraud whereby SIM cards are used to channel national and multinational calls away from mobile operators and deliver as local calls. Therefore it is important to find techniques that can detect this type of fraud efficiently. In this paper, two classification techniques, Artificial Neural Network (ANN) and Support Vector Machine (SVM) were developed to detect this type of fraud.   The classification uses nine selected features of data extracted from Customer Database Record.  The performance of ANN is compared with SVM to find which model gives the best performance. From the experiments, it is found that SVM model gives higher accuracy compared to ANN by giving the classification accuracy of 99.06% compared with ANN model, 98.71% accuracy. Besides, better accuracy performance, SVM also requires less computational time compared to ANN since it takes lesser amount of time in model building and training.

scholarly journals Comparison between Artificial Neural Network and Rigorous Mathematical Model in Simulation of Industrial Heavy Naphtha Reforming Process

Catalysts ◽  
2021 ◽  
Vol 11 (9) ◽  
pp. 1034
Author(s):  
Ali Al-Shathr ◽  
Zaidoon M. Shakor ◽  
Hasan Sh. Majdi ◽  
Adnan A. AbdulRazak ◽  
Talib M. Albayati
Keyword(s):  
Neural Network ◽  
Mathematical Model ◽  
Artificial Neural Network ◽  
Coefficient Of Determination ◽  
Computational Time ◽  
Ann Model ◽  
Naphtha Reforming ◽  
Artificial Neural ◽  
Following Error ◽  
Rigorous Mathematical Model

In this study, an artificial neural network (ANN) model was developed and compared with a rigorous mathematical model (RMM) to estimate the performance of an industrial heavy naphtha reforming process. The ANN model, represented by a multilayer feed forward neural network (MFFNN), had (36-10-10-10-34) topology, while the RMM involved solving 34 ordinary differential equations (ODEs) (32 mass balance, 1 heat balance and 1 momentum balance) to predict compositions, temperature, and pressure distributions within the reforming process. All computations and predictions were performed using MATLAB® software version 2015a. The ANN topology had minimum MSE when the number of hidden layers, number of neurons in the hidden layer, and the number of training epochs were 3, 10, and 100,000, respectively. Extensive error analysis between the experimental data and the predicted values were conducted using the following error functions: coefficient of determination (R2), mean absolute error (MAE), mean relative error (MRE), and mean square error (MSE). The results revealed that the ANN (R2 = 0.9403, MAE = 0.0062) simulated the industrial heavy naphtha reforming process slightly better than the rigorous mathematical model (R2 = 0.9318, MAE = 0.007). Moreover, the computational time was obviously reduced from 120 s for the RMM to 18.3 s for the ANN. However, one disadvantage of the ANN model is that it cannot be used to predict the process performance in the internal points of reactors, while the RMM predicted the internal temperatures, pressures and weight fractions very well.

Computational Systems for Offshore Pipeline Launching Simulations

2003 ◽  
Author(s):  
Isai´as Q. Masetti ◽  
Joa˜o Vicente Sparano ◽  
Breno Pinheiro Jacob ◽  
Carl Horst Albrecht ◽  
Claudio R. Mansur Barros
Keyword(s):  
Environmental Conditions ◽  
Real Case ◽  
Mooring Line ◽  
Mooring Lines ◽  
Validation Test ◽  
Offshore Pipeline ◽  
Two Systems ◽  
Case Validation ◽  
Computational Systems ◽  
Good Agreement

Computational systems have been developed to help the BGL-1 crew to perform safe mooring procedures. They calculate the deformed catenary configuration of all mooring lines, and simulate the pipeline launching operation itself, regarding the subsea interferences and the local environmental conditions. An onboard real case validation test was carried out and a comparison between the two systems was evaluated, with good agreement between the results of several mooring line parameters.

Sign in / Sign up

Export Citation Format

Share Document