Created: 2018-12-05 Wed 19:12

- Development of in-pipe monitoring device (swimming robot)
- passive driven (flow) and propulsion driven design
- acoustic signals - leak signatures detection (deep neural net)
- Internal measurement unit (IMU) - accurate positioning, magnetic field (Oil pipeline systems with inertial dominated features)
- Propulsion driven design - stagnant flows

- Developments:
- local pressure recordings and viscosity measurements
- Big data mining - pipeline integrity historical data and fusion with in-pipe swimming robot data
- Real-time online monitoring and fusion with swimming robot inline inspection data

- 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)

- Inertial Measurement Unit
- External signal sink-source communication

- 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.

- 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

- 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

- 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

- Quaternions
- Euler angels
- Rotation Matrix
- Fusion algorithm and Madgwick library

- Artificial Neural Network and Deep Neural Network

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

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

Position Calculated

Pipe length is 3.22 m and relative error is 5.3%

- 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