Next generation monitoring for enhanced asset management
Lead Research Organisation:
Newcastle University
Department Name: Electrical, Electronic & Computer Eng
Abstract
New sensor substation technologies coupled with real-time condition monitoring represents a large opportunity for transmission and distribution network operators to optimise their asset management and maintenance programs. These strategies monitor the condition of the equipment by intelligently monitoring substation parameters to recommend optimum maintenance and replacement activities. This is becoming more important in light of the increased challenges to resilience of power systems from more frequent and severe weather events, constraints on access to capital and planning permission and increased requirements on these assets due to the anticipated migration of the transport and heat sectors to electrical infrastructure. This necessitates assets closer to their operational limits while simultaneously ensuring system security and operator safety.
To enable this real-time condition monitoring and asset management capability a number of developments within the power systems and ICT industries have occurred:
Increased interoperability and data gathering capability due to the adoption of IEC61850 within substations;
Increased computational capabilities due to Cloud computing techniques;
Greater visibility of upstream and downstream grid systems through additional smart enabled monitoring systems;
Availability of load, generation and weather forecasting techniques and data;
New novel smart sensor technologies.
This PhD research project will investigate the application of these advances to condition monitoring and diagnostics for current and future substations across a range of voltage levels. The research will consider the technical feasibility of the latest and next generation substation sensor technologies and complementary analytic techniques including machine learning and other AI techniques to provide useful information to operators and planners. This advances will enable:
Improve safety
Higher utilisation
Extended plant lifetime
Reduce plant failures
Replace the plant that needs replacing
Reduce customer minutes lost
More cost effective O&M regimes
This work will consider individual substations as well as approaches for managing systems of substations within a broader network. The research will consider using state-of-the-art analysis techniques, such as machine learning, to deliver information that can reduce plant failures and enable revaluation of current asset management and replacement approaches.
The project will use data from existing Siemens transmission to run in parallel with the data from the Northern PowerGrid data that is already available at Newcastle University. A version of Siemens RCAM will be made available to Newcastle University.
To enable this real-time condition monitoring and asset management capability a number of developments within the power systems and ICT industries have occurred:
Increased interoperability and data gathering capability due to the adoption of IEC61850 within substations;
Increased computational capabilities due to Cloud computing techniques;
Greater visibility of upstream and downstream grid systems through additional smart enabled monitoring systems;
Availability of load, generation and weather forecasting techniques and data;
New novel smart sensor technologies.
This PhD research project will investigate the application of these advances to condition monitoring and diagnostics for current and future substations across a range of voltage levels. The research will consider the technical feasibility of the latest and next generation substation sensor technologies and complementary analytic techniques including machine learning and other AI techniques to provide useful information to operators and planners. This advances will enable:
Improve safety
Higher utilisation
Extended plant lifetime
Reduce plant failures
Replace the plant that needs replacing
Reduce customer minutes lost
More cost effective O&M regimes
This work will consider individual substations as well as approaches for managing systems of substations within a broader network. The research will consider using state-of-the-art analysis techniques, such as machine learning, to deliver information that can reduce plant failures and enable revaluation of current asset management and replacement approaches.
The project will use data from existing Siemens transmission to run in parallel with the data from the Northern PowerGrid data that is already available at Newcastle University. A version of Siemens RCAM will be made available to Newcastle University.
Organisations
People |
ORCID iD |
Damian Giaouris (Primary Supervisor) | |
Luke Burl (Student) |
Studentship Projects
Project Reference | Relationship | Related To | Start | End | Student Name |
---|---|---|---|---|---|
EP/N509292/1 | 30/09/2015 | 29/03/2021 | |||
1788973 | Studentship | EP/N509292/1 | 30/09/2016 | 30/03/2021 | Luke Burl |