Pipeline integrity and leak detection Swimbot Robot Development

Pipeline integrity and leak detection Swimbot Robot Development

Enbridge, Edmonton, 2018

Created: 2018-12-05 Wed 19:12

Pipeline Big Data Analysis - Leak Localization

Agenda: Blue Sky swimming robot design for pipeline monitoring and integrity

  • Development of in-pipe monitoring device (swimming robot)
    1. passive driven (flow) and propulsion driven design
    2. acoustic signals - leak signatures detection (deep neural net)
    3. Internal measurement unit (IMU) - accurate positioning, magnetic field (Oil pipeline systems with inertial dominated features)
    4. Propulsion driven design - stagnant flows
  • Developments:
    1. local pressure recordings and viscosity measurements
    2. Big data mining - pipeline integrity historical data and fusion with in-pipe swimming robot data
    3. Real-time online monitoring and fusion with swimming robot inline inspection data

Pipeline network in North America (Source Enbridge Inc)

Pipeline.jpg

Pipeline Energy and Environmental Economics

  • 55,377 km of gas pipelines
  • 28,181 km of liquid pipelines
  • Move 28% of crude oil produced North America and 23% of natural gas consumed in the United States
  • Workforce of 15,400 people
  • $27B+ in secured capital projects for growth
  • No.12 on the 2016 Newsweek Green Rankings
  • Environmental issues
  • Insurance and leak prevention (pipeline integrity)

Pipeline inspection

  • Inertial Measurement Unit
  • External signal sink-source communication

Leak position localization

  • Measurements of IMU unit
    • Gyroscopes rotation angles \(\omega_1,\omega_2,\omega_3\) - Euler angles
    • Linear translation motion \(a_x, a_y, a_z\)-acceleration
    • Magnetometer
  • Error of integration prevents accurate localisation (known problem in aerospace engineering) \[a_{x}=\frac{d^2x}{dt^2}\] the meassurement error is accumulated by double integration of \(a_x\) signal \[x(t)=\int \int a_{x}d\tau\]
  • Practical solution is dead-reckoning
  • The IMU chip is designed to be placed in the geometric center of the ball in order to prevent the error during rotation.
  • The position of the battery is designed to keep the mass balance of the robot.

Swimbot Design I

swim-bot-fig.jpg

  • Cheaper swimbot (87$)
  • Large number of swimbot deployments (every batch of transfered fluid should have 2-3 swimbots)
  • Large number of data for statistical processing and mining
    • Deep Neural Network
  • Pipeline integrity and leak prevention

Swimbot Design II

new-swimbot.jpg

  • Cheaper swimbot (87$)
  • Large number of swimbot deployments (every batch of transfered fluid should have 2-3 swimbots)
  • Large number of data for statistical processing and mining
    • Deep Neural Network

Big Data Processing

  • Problem of integration drift is the main issue in all IMUs
  • Algorithm is applied to fuse acceleration and and angular velocity to generate accurate positioning

    Fig2.png

    • Quaternions
    • Euler angels
    • Rotation Matrix
    • Fusion algorithm and Madgwick library
  • Artificial Neural Network and Deep Neural Network

Model of Deep Neural Network

1.jpg

Experimental Test Environment

Ball.jpg

Experimental Test Environment

IMG_3740.jpg

Experimental Results

Gyro.jpg

The experimental run takes 4-5 seconds in the recorded interval between 31 sec and 36 sec

Experimental Results

Acc.jpg

The experimental run takes 4-5 seconds in the recorded interval between 31 sec and 36 sec

Experimental Results

Position Calculated

Pos.jpg

Pipe length is 3.22 m and relative error is 5.3%

Acustic data

sound.jpg

Summary

  • Leak localization is explored
    • Issues of drift associated with IMU are addressed
    • Fusioon algorithm
    • Deep Neural Network
  • Data exploration for large number of deployed swimbots

Future work:

  • Bayesian inference
  • Several agent swimbots with communication protocol