Upload
others
View
4
Download
0
Embed Size (px)
Citation preview
TECHNICAL PAPER
Emerging Solutions for Offshore
Asset Integrity Challenges
R. Thethi
SPE Workshop September 2020
SPE WORKSHOP
Emerging Solutions for Offshore Asset Integrity Challenges
10 – 11 February 2020Hilton Kota Kinabalu, Malaysia
Learn more at www.2hoffshore.com
SPE WORKSHOPEmerging Solutions for Offshore Asset Integrity Challenges
Implementation of Advanced Digital Technologies in Subsea Asset Life Extension
Ricky Thethi
Global Director
2H Offshore Engineering
Learn more at www.2hoffshore.com
3
Introduction
• Riser structural monitoring is a proven method for early detection of anomalies allowing Operators to address ahead of time and reduce remediation costs.
• Structural monitoring can also be used to accurately determine remaining life and justify life extension beyond the original service life
• Instrumenting the riser with sensors can be costly activity requiring interface data from and access to the host vessel
• An alternative lower cost approach is to use Machine Learning technology to develop a real time structural digital twin of the risers using the finite element model to provide training data
Learn more at www.2hoffshore.com
www.acteon.com4
Physical asset Real Time Digital Twin
• Wave, current and vessel motion stimuli
• Riser incurring fatigue damage over time
• Any corrosion will accelerate fatigue damage and reduce remaining life
• Bend stiffener region is the fatigue hotspot
• Steel tensile and pressure armour layers within flexible x-section are critical areas
Input• Vessel motions• Vessel GPS and heading• Environmental loads• Riser internal pressure
Response Model• Hot spot loads and stresses• Tensile and pressure layers• Wire stresses• Fatigue damage accumulation
Output Visualisation• Fatigue tracking GUI• Dashboard and alerts• Remaining life status• Impact of changing operational
parameters• Hosted on cloud• Web accessible
Learn more at www.2hoffshore.com
5
Key Benefits• Significant lower cost versus instrumented system
• Can be applied to all risers for life of field monitoring
• Proactive and continuous approach
• Early anomaly detection to minimize RISKEX
• Eliminates conservatisms in design from assumptions and simplifications
• Data used to justify and enable life extension
• Data used to justify integrity decisions such as a costly remediation or no remediationLearn more at www.2hoffshore.com
6
Cost Benefit Potential
• $20MM+ to avoid replacement cost of risers or mooring systems by demonstrating sufficient fatigue life for life extension target
• $50MM++ to rapidly detect and mitigate a structural issue that would have led to significant production downtime (i.e. > 6 months)
• Actual operating condition worse than design
• Excessive corrosion and interaction with structural strength and fatigue margins
• Gaps in maintenance during operating life
Learn more at www.2hoffshore.com
8
Hang-off(Bend Stiffner)
Bottom ofSag Bend
Top of Hog Bend (Buoyancy)
Touch Down Zone
Input Data6 DOF 1st and
2nd Order Vessel Motion & GPS Position Data
Output DataTensile and
pressure armourlayer stresses and fatigue damage
Field Inputs and Desired outputs
Learn more at www.2hoffshore.com
9Twin (using ML) the conventional FEA process as it is too slow to use real time with measured field data
www.acteon.com9
BFLEX Model of Flexible Cross Section
BFLEX Hysteresis Loop
Global Response Calculation
BFLEX Flexible Layer Stress Calculation
API-17J Strength Check
Armor Fatigue Lives
2HBFlexRain SN Curve Application
Learn more at www.2hoffshore.com
11
300
400
500
600
700
800
900
1,000
800 900 1000 1100 1200 1300 1400
Te
nsil
e A
rmo
ur
La
ye
r S
tre
ss (
MP
a)
Time (seconds)
Tullow - Jubilee Flexible Riser Eng Support
TARGET Vs OUTPUT TIMETRACES COMPARISON
Tensile Armour Layer Stress, Fatigue Seastate 4 (High Damage,
Low Error), 10, 10 Delays, 10 Hidden Layers
Target Output
Error in Maxima=0.20%Error in Minima=3.89%Error in Mean=0.76%Error in StDev=0.02%
ML Algorithm Excellent Amplitude and Phasing PredictionLearn more at www.2hoffshore.com
12ML Algorithm within +/-10% Fatigue Damage Accuracy Across Majority of Seastates
0
0.5
1
1.5
2
2.5
3
3.5
4
4.5
5
0 0.5 1 1.5 2 2.5 3 3.5 4 4.5 5
Pre
dic
ted
Fa
tig
ue
Da
ma
ge
Ra
te (
1/
Ye
ar)
FEA Fatigue Damage (1/Year)
Flexible Riser Fatigue Tracker
MACHINE LEARNING - STRESS TIME TRACEENARX/LM, Exponent 6 - 251 Seastates, Rainflow Counting
Over-Prediction
Under-Prediction
Learn more at www.2hoffshore.com
14
Integrate Computer Vision with Structural Digital Twin
• Use past anomalies to train using ML so computer can detect:• Excessive marine growth• Missing strakes or fairings• Missing buoyancy modules• Coating damage or disbondment• Deep trenches at touch down• Spans on seabed
• Use trained anomaly algorithm with ROV/AUV inspection video
• Feed into digital twin to check strength and fatigue integrityLearn more at www.2hoffshore.com
15
Summary
• Current approach to subsea integrity inspection and monitoring can benefit from digital technologies to improve efficiencies and unlock performance for extending life
• Machine learning digital twin algorithms can be used to better track dynamic structures in service using existing measured data (sensor data and inspection video footage)
• Structural digital twin demonstrated for risers – can be replicated for dynamic flowlines, subsea jumpers and moorings
Learn more at www.2hoffshore.com