Project Summary

SSEN-T previously delivered the NIA AIM High Project which introduced an autonomous robot within an inaccessible HVDC valve hall to perform monitoring tasks. Currently, data gathered from the robot and the related operational data is managed manually and is labour-intensive with no trend analysis or data management package available.

This SIF Discovery ODIN Project will investigate automated interpretation and diagnostics of data collected from continuous monitoring from robots operating in these halls. This will use modern analytic techniques including machine learning and artificial intelligence (AI). The use of modern condition-monitoring techniques will allow us to improve on the system availability and manage outage periods more efficiently with informed asset management decisions. This will become important moving forward as we benchmark the current performance of the system before expected load increases. ODIN will prove a novel solution that can be adopted in existing and future asset designs reducing the need for unplanned maintenance and cost to customers.

Innovation Justification

Challenge

The Project addresses Challenge 4 – Accelerating Towards Net Zero Energy Networks.

Innovation

SSEN-T is the first UK Network to integrate robotics into live fully operational HVDC converter stations to conduct autonomous inspections. The Ross Robotics’ robot is currently the only robotic solution suitable for harsh HVDC environments. This Project can maximise the use of the gathered data to reduce operational expenditure and prevent unexpected outages. This will apply advanced analytical techniques to CBM and data insight techniques, such as AI, to detect incipient fault conditions, predict potential failures and provide insights to prevent equipment failure. Since SSEN-T have implemented the UK’s first monitoring robot, analytical techniques maximising the use of the data are yet to be developed.

Developing these techniques now will enable benchmarking of the system's current performance before anticipated load increases add further thermal stress to the equipment.

Readiness

Please see attached Table 1 document.

Size & Scale

An agile approach is taken over 3 months to gain an understanding of how current processes could be improved to support the integration, management and operation of data analytics with existing data. At the end of Discovery Phase understanding will be sufficient to decide whether an Alpha Phase offers value for money and is feasible. Alpha will include further development of the solution enabling automated interpretation of data to facilitate operational decision making.

Funding

This new solution is innovative but unproven, requiring development and validation before it can be introduced as BAU. There are risks associated with implementation, including the effectiveness of the proposed technology and techniques within the Project scope. These must be tested to determine their viability. Additionally, there is a risk that the trialled solution may not be adopted into BAU therefore is best suited to be funded via SIF Discovery funding.

Counterfactual Solutions

If no action is taken, SSEN-T will continue to operate under the current status quo, unable to gain a complete picture of the condition of critical assets inside HVDC halls. The counterfactual solution is to manually interpret data to identify faults, without the advantages of data analytics. This approach increases the risk of missing faults, makes hall inspections inefficient, and limits data integration, making it difficult to develop new fault diagnosis methods. Ultimately, it restricts opportunities for a more intelligent and effective approach to operational maintenance.

Impacts and Benefits

Financial - future reductions in cost of operating network

Currently, the maintenance of HVDC assets relies heavily on scheduled inspections and reactive repairs, leading to higher operational costs, increased risk of forced outages, and constraints on renewable generation integration. The existing approach lacks predictive analytics, resulting in inefficient resource allocation and potential asset failures. Key baseline metrics include system availability, frequency of forced outages, maintenance costs, and renewable generation curtailment due to asset constraints.

This innovation introduces condition-based maintenance (CBM) techniques enabled by advanced data analytics. By implementing CBM, we expect to significantly reduce forced outages, lower maintenance costs, and enhance system availability. Initial forecasts suggest that, at a network partner level, these improvements could result in cumulative net benefits through reduced downtime, extended asset lifespan, and optimised operational efficiency. These benefits will be measured using key indicators: outage frequency, maintenance expenditures, and asset performance over time.

Additionally, if commercialised, robotic inspection technologies would generate vast amounts of data, posing a challenge for operations teams. A dedicated data platform will be essential for collecting, storing, processing, and analysing this data efficiently. By streamlining data management, Partners anticipate cost savings in manpower hours, improved fault detection accuracy, and more targeted maintenance interventions.

New to market – services

Developing an industry-wide standardised methodology for assessing performance and operational behaviour in HVDC applications is essential. Using robotics as a sensor platform, will enable CBM in HVDC halls, including those that are otherwise inaccessible. Since HVDC halls are widely used, there is a significant opportunity for a UK company (Ross Robotics), to lead the market. By scaling up and commercialising this technology, they can position themselves as a first mover and serve a growing global market. The Project will enable efficient collation, analysis and visualisation of asset conditions within the halls supporting an effective asset management strategy.

Others that are not SIF specific

ODIN offers qualitative benefits including an enhanced reliability, efficiency, safety, and sustainability while reducing costs and improving overall operation and maintenance of HVDC systems. The use of modern condition-monitoring techniques will enable improvement of system availability and manage outage periods more efficiently with informed asset management strategies. Ultimately this supports acceleration towards a net zero energy network.

Completion of the Discovery Phase is likely to discover additional benefits and opportunities to address wider development and adoption within the industry. One of the outputs of Discovery is a quantitative cost benefit analysis (CBA).