The document proposes a condition monitoring architecture to reduce the total cost of ownership through lower hardware costs, improved software and support, and optimized IT infrastructure. It suggests using lower-cost MEMS accelerometers with embedded processing and digital signaling. Advanced signal processing like time synchronous averaging would extract fault indicators without spectra. A health indicator mapping would automate fusion of fault modes into a single metric requiring little interpretation. Cloud computing could replace local servers for simplified maintenance and data pooling across similar assets.

1. Condition Monitoring Architecture
To Reduce Total Cost of Ownership
Eric Bechhoefer, NRG Systems
Brogan Morton, NRG Systems

2. Barriers to Sales of PHM Systems
• CBM/PHM System are Proven to Work
– Low Penetration into Commercial Markets
– Example: 3% of Wind Turbines
• Why? - Business Case is Hard to Make
– Safety not the primary concern, cost avoidance is
– Hard to Quantify Benefit
• Change Architecture to Improve Value
– Lower “Costs” and Better Information

3. Current System Architecture
• System Hardware
– 6 to 8 PZT Accelerometers
• 5% Accuracy, .5 to 10,000 Hz
– Tachometer
– Signal Conditioning
• 6 to 12 channels
• Sample Rate: 60 to 80 KSPS
• Support/Monitoring Services
– Human in the loop to turn data into a diagnosis
– $1,000 to $1,500 per year per turbine
• IT Infrastructure
– Data hosting on local server
– Data also shipped to centralized analysis center

4. System Layout: Wind Turbines

5. From a System Perspective…
• How to Lower Total Ownership Cost
– Hardware Considerations
• Costs driven by accelerometer
– Software/Support Considerations
• Costs driven by knowledge creation (data to diagnosis)
– IT Infrastructure Considerations
• Cost driven by local data storage and associated
maintenance

6. Accelerometers – MEMS vs. PZT
MEMS Advantages MEMS Disadvantages
• Cost • Needs to be Packaged
– $6 to $30 vs. $100’s – No Trivial Task
• Bandwidth • Noisier
– 0 to 32,000 Hz vs. 0.5 to – PDS is 2 to 40x higher
10,000 Hz System Issues
• Accuracy • 4 Wire?
– Typically 1% vs. 5% or 10%
– Power/Signal
Error
• Local Conversion?
• Self Test
– ADC, then Microcontroller
– Can Enable BIT vs. No BIT
and RT

7. Sensor System Considerations
• Low cost target – move to MEMS
– Analog vs. Digital Sensing
• If Digital
– Local ADC,
• EMI is Reduced
– Microcontroller, RAM, Receiver/Transmitter
• If Multi-Drop: RS-485
– If Microcontroller: Local Processing?
• Many Smaller, Cheap Processors vs. One Larger Processor
• Low cost packaging
– Alternative to Stainless Steel or Titanium
– Transfer Function – Has to Be Stiff/Light

8. MEMS: A Sensor Solutions
• Noise Was Not An Issue
– After Signal Processing,
Noise was Negligible
• Conductive Plastic
Package
– 40% Mass of Stainless
– Similar Stiffness
1000 mv/g vs. 70 mv/g
– 12% of Cost of Stainless MEMS Accel, 0.25 Hz
– 6.5KHz Resonance, Flat Within 2% of Low G Accel
Response to 17 KHz

9. Embedded PHM
• Micro with FPU Support
– 32MB RAM
– 24 Bit ADC
– Sample @ 300-100,000 kbps
– R/T > 500 KB/S
• Local Vibe Processing
– Time Synchronous Average
(TSA)
– FFT/IFFT
– Hilbert Transform
• Total Cost: Similar to
PZT Accel

10. Software & Support Considerations
• Algorithmic
– Digital signal processing of the vibration signals for
fault detection
• Knowledge Creation
– Goal: Actionable information requiring little
interpretation

11. Typical Drivetrain Configuration
Generator
High Speed Shaft
3-stage Gearbox
Main
Bearing Int. Speed Shaft
Main Shaft Low Speed Shaft •17 Bearings
•9 Gears
•8 Shaft

12. Algorithmic
• Process vibration signal into indications of
faults
– Data reduction without loss of information
• No Spectrums/Order Analysis
– Configurable Analysis for Shafts, Gears and
Bearings,
– Several Condition Indicators for Each Component
• Use Time Synchronous Average (TSA)

13. Why This Approach
• Large Variation in Wind
Speeds Cause Large
Changes in Rotor Speed
• 3/Rev Torque/Speed
Ripple From Tower
Shadow/Wind Shear
• Gearbox has many gear
meshes; isolate gears of
interest

14. Example of Spectrum Vs. TSA
• Due to Changes
in Rotor Speed,
Order Analysis
or the PSD
Cause Smearing
of Frequency
Content
• Example Main
Rotor Shaft
1st, 2nd, and 3rd Harmonics of Ring Gear
Frequency

15. The TSA
•Use Tachometer as Phase Reference on Shaft
•Reduces Non-Synchronous Noise 1/sqrt(revolutions)
•For Each Revolution (From Tach)
•Resample length m = 2^Ceiling(log2(number of points in Rev))

16. Gear Fault Indicators
• No Single CI Works With All Fault Modes
– Surface Disturbance, Scuffing, Deformation,
Surface Fatigue, Cracks, Tooth Breakage,
Eccentricity
• Use a Number of Analysis to Cover All Fault
Modes
– Residual Analysis, Energy Operator, Narrow Band
Analysis, Amplitude Modulation Analysis,
Frequency Modulation Analysis.

17. Gear Analysis

18. Knowledge Creation
• Recall Goal: Create actionable
information requiring little
interpretation
– Convey what to fix and when
• Single Health Indicator for Each
Component
– Fusion of different condition
indicators
– Common scale for every
component (0-1)

19. Health as a Function of Distributions
• HI Paradigm: Map the CIs into an HI
– HI Ranges from 0 to 1, Where the Probability of
the HI exceeding 0.5 is the PFA
– HI in Warning when between 0.75 and 1
– HI is Alarm when Greater than 1.0
– Continued Operations with HI > 1 could Cause
Collateral Damage

20. Controlling Correlation Between CIs
• All CIs have PDFs
CI 1 CI 2 CI 3 CI 4 CI 5 CI 6
• Any Operation on the CI to
ij
CI 1 1 0.84 0.79 0.66 -0.47 0.74
form an HI is a Function of CI 2 1 0.46 0.27 -0.59 0.36
Distributions CI 3 1 0.96 -0.03 0.97
– Max of n CI (an Order Statistics) CI 4 1 0.11 0.98
– Sum of n CI CI 5 1 0.05
– Norm of n CI CI 6 1
• Function of Distribution
– PFA Correct if Distribution are IID
– Need to Whiten

21. CI to HI Mapping
• Six CIs used in HI
Calculation
– Residual RMS
– Energy Operator RMS
– FM0
– Narrowband Kurtosis
– AM Kurtosis
– FM RMS
• Statistics Generated from
4 test articles: 100
samples prior to fault
propagation

22. IT Infrastructure
Alternate to Local Server: Cloud Computing
For Owner/Operator For CMS Developer
• No Seat License of the CMS • Simplifies Software Maintenance
Database Cost
• No Local Servers to Host – Only one Platform to Develop
and Test to,
Data
– Only one Platform to Deploy
• Management of Software Software Updates/Patches to,
Maintenance. • Reduces the Cost of Certification
• Allows Pooling of Dataset of – Configuration Management is
Similar Type/Model Greatly Simplified
Turbines without Risk of • Scalability
Exposing Proprietary
Information

23. Conclusion
• Significant value can be created by redesigning
system architecture
– Vibration sensing
• Non-traditional sensor, new packaging and design methods
– Advanced signal processing techniques
• Increased sensitivity to faults under dynamic conditions
– Knowledge Creation
• Automated fusion of fault modes
• Actionable information with diagnostic support
– IT Infrastructure
• Economy of scale using cloud services