Postgraduate Course: O&M Robotics and Sensors (IDCORE) (PGEE11235)
Course Outline
| School | School of Engineering |
College | College of Science and Engineering |
| Credit level (Normal year taken) | SCQF Level 11 (Postgraduate) |
Availability | Not available to visiting students |
| SCQF Credits | 10 |
ECTS Credits | 5 |
| Summary | The course will reflect on the critical impact operations and maintenance scheduling and planning has on the OPEX costs of an energy farm. During the first week of the course, building on outputs from the EPSRC funded ORCA Hub (EP/R026173/1), we will discuss operations and maintenance (O&M), and the use of robotics and autonomous vehicles for inspection and maintenance tasks. Industrialists and consulting engineers will be invited to discuss how O&M has been optimised in recent projects. During the second week at the course will focus on digital twinning, machine learning, and sensor data obtained from equipment being operated in hostile environments. An remote experimental lab will give insight into remote operations and interpretation of real-sensor data, showing how autonomous systems can enable the safe, reliable, and cost-effective operation of a marine energy asset. |
| Course description |
This course will begin with a broad overview of the impact that operations and maintenance scheduling has on the operational expenditure cost of an energy farm.
There are then five modules: Operations and Maintenance; Robotics and Systems Engineering; Digital Twins and Cyber Physical Fabric; Machine Learning and Data Analysis; and Sensing for Asset Integrity Management.
Each of these modules will consist of two lectures which will be delivered by academic sector experts.
Specific topics to be covered are:
Operations and Maintenance:
Understanding the major facets of operations and maintenance, the relationships between asset owners, inspectors, and third party subcontractors. Understanding the challenging operating environment and the types of vessels and weather windows in which they can operate. Understanding O&M scheduling and certification.
Robotics and Systems Engineering:
Based upon the learning from the O&M module students will be able to appreciate the difficulty, and projected benefits, of deploying remotely operated vehicles and sensors, and understand the drivers for autonomous operations and resident robotic systems. The students will be introduced to currently available robotic systems and the software-stack used to operate them.
Digital Twins and Cyber Physical Fabric:
Students will be introduced to digital twinning both of assets and of robotic systems. They will understand the flow of data and appreciate the role of Cyber Physical Fabric in, for example, Asset Integrity Management.
The first assessment in this course will be a video-report of the future potential for robotics and the cyber physical fabric in the offshore energy sector.
Machine Learning and Data Analysis:
The students will be introduced to machine learning as a tool for understanding and interpreting noisy real-world sensor data. They will be introduced to classifier models for time-series data, and they will understand the appropriate tools and methods used to interpret data.
Sensing for Asset Integrity Management:
The students will be introduced to the role of sensors and electronics for transducing information about an asset, e.g.: temperature, humidity, visual, and vibration. The challenges of data management and communications will be discussed.
The second assessment in this course will be a laboratory exercise where students will access a remote-asset to collect representative time-series data, which they will then analyse using skills gained from the machine learning course. This will involve implementing classifier algorithms in python to interpret no-fault vs fault data.
|
Entry Requirements (not applicable to Visiting Students)
| Pre-requisites |
|
Co-requisites | |
| Prohibited Combinations | |
Other requirements | None |
Course Delivery Information
|
| Academic year 2021/22, Not available to visiting students (SS1)
|
Quota: None |
| Course Start |
Flexible |
Timetable |
Timetable |
| Learning and Teaching activities (Further Info) |
Total Hours:
100
(
Lecture Hours 21,
Formative Assessment Hours 1,
Other Study Hours 76,
Programme Level Learning and Teaching Hours 2,
Directed Learning and Independent Learning Hours
0 )
|
| Additional Information (Learning and Teaching) |
Self study
|
| Assessment (Further Info) |
Written Exam
0 %,
Coursework
100 %,
Practical Exam
0 %
|
| Additional Information (Assessment) |
100% Coursework |
| Feedback |
Not entered |
| No Exam Information |
Learning Outcomes
On completion of this course, the student will be able to:
- Understand the main factors, their roles, their hardware and their contractual relationships that deliver operations and maintenance in the offshore renewable energy industry
- Appreciate the difficulty, and projected benefits, of deploying remotely operated vehicles and sensors e.g.: poor communication networks, and understand the drivers for autonomous operations and resident robotic systems.
- Be introduced to digital twinning both of assets and of robotic systems. They will understand the flow of data and appreciate the role of Cyber Physical Fabric in, for example, Asset Integrity Management.
- Be introduced to machine learning as a tool for understanding and interpreting noisy real-world sensor data. They will be introduced to classifier models for time-series data, and they will understand the appropriate tools and methods used to interpret data.
- Be introduced to the role of sensors and electronics for transducing information about an asset, e.g.: temperature, humidity, visual, and vibration as well as the inherent challenges of data management.
|
Additional Information
| Graduate Attributes and Skills |
Not entered |
| Keywords | Offshore energy,robotics,autonomous systems,asset integrity management,sensors,industrial IOT |
Contacts
| Course organiser | Dr Adam Stokes
Tel: (0131 6)50 5611
Email: Adam.Stokes@ed.ac.uk |
Course secretary | Dr Katrina Tait
Tel: (0131 6)51 9023
Email: k.tait@ed.ac.uk |
|
|
University Homepage