Trafisense is a real-time monitoring and early-warning service for high-risk situations in dry-type distribution and power transformers based on proprietary machine-learning technology.

Project Information

Trafisense

Grant agreement ID: 762676

DOI 10.3030/762676

Project closed

EC signature date 22 January 2017

Start date 1 February 2017

End date 31 July 2017

Funded under

• SOCIETAL CHALLENGES - Secure, clean and efficient energy

Total cost € 71 429,00

EU contribution € 50 000,00

Coordinated by

TRAFISENSE MONOPROSOPI IDIOTIKI KEFALAIOUCHIKI ETAIREIA
Greece

Periodic Reporting for period 1 - Trafisense (Trafisense is a real-time monitoring and early-warning service for high-risk situations in dry-typedistribution and power transformers based on proprietary machine-learning technology.)

Reporting period: 2017-02-01 to 2017-07-31

Summary of the context and overall objectives of the project

Dry-type power transformers are part of every modern critical and non-critical energy infrastructure. They constitute some of the most critical components for electricity distribution as their failure results to power cut-off and black out.
Many electricity distribution companies and operators will be replacing oil-insulated transformers with dry-type ones. The global growing focus on safety and environment protection is driving the demand for dry-type transformers. Trafisense therefore sees a large market need for monitoring that is currently undeveloped.
Dry state transformers have strong advantages for example:
• They do not explode when they fail
• They are inflammable
• They are far more environmentally friendly

In 2014 they represented 18% of the annual sales (in MUSD) of distribution transformers and in 2020 they are expected to represent around 19% of the annual sales The current (2014) estimated global stock of distribution transformers is 118 million units with a share of 7-10% for the dry-type ones .

Minimal insights lead to downtime or catastrophic hardware failures: Currently only 5% of dry-type power transformers are monitored online beyond a very basic set of properties, namely winding temperature and the current flow. As a result, owners cannot predict the condition of the transformers accurately and face hardware failures and downtime. Even worse, the lack of monitoring usually prevents identifying the original cause of failure, while it does not allow taking actions to minimise the downtime, resulting in additional associated costs. The issue is more critical for the case of off shore and rural installations and especially for off-shore wind farms, where the costs are by far higher than the typical cases.

Dry-type power transformer are currently over-maintained but not protected neither monitored: Only 60% of the maintenance performed on power transformers is actually needed. The remaining 40% is redundant or misguided. The unreliable or out-dated view of a transformer’s state leads to over-maintenance in many cases, while the lack of monitoring leads to unexpected failures. Poor technical knowledge and lack of expertise lead to inaccurate maintenance. The result is a costly and ineffective process that reflects to the deteriorating state of the transformers and to a large number of unresolved failures.

Trafisense Private Company has been founded by Prof. Konstantinos Psomopoulos (CTO) and Dr. Ioannis Georgiadis (CEO) in May 2016. Trafisense develops and markets monitoring solutions especially for dry-type power transformers. . Trafisense introduces major business innovations to the field of dry-type transformers:
1. Predictive and prescriptive analytics to provide an estimation of the required maintenance plan and thus allow customers to schedule downtime and maintenance ahead of time by generating focused condition-based maintenance actions.
2. Differencing from the main competitors Trafisense are dedicated only to the development and sales of monitoring solutions and thus not to the sale of the transformer hardware.

With the scheduling of the condition-based maintenance plans long before actual failures occur and the formulation of specific maintenance actions timely, Trafisense can reduce the maintenance cost, the number and duration of unexpected downtime due to failures, thus effectively reducing the TCO of dry-type transformers and optimizing their operational efficiency. This impact is amplified in remote (desert solar parks or wind turbines on mountains) and offshore installations. Consequently dry-type transformers become an even more viable alternative to far less environmentally friendly oil-insulated transformers.

Work performed from the beginning of the project to the end of the period covered by the report and main results achieved so far

The competition has been analyzed and the potential competitors along and their corresponding products have been compared with the Trafisense dry-type transformer monitoring solution. The major features that distinguish Trafisense from the competition are the following:
• The support for long-term maintenance schedule.
• The automated creation of a maintenance action plan using prescriptive analytics techiques.
• The monitoring of high and ultra-high frequency harmonics that significantly contribute to the deterioration of electronic equipment.

During this project, Trafisense has developed an ambitious business and growth plan in order to build a profitable and successful company. It is estimated that the business development and technical development will have a total cost of ½ million euros until break even. The cost will be financed through a mix of public/EU grants, loans and private equity. Trafisense is now looking for an investor that is willing to invest 450.000 euros in a combination of equity and loans. The long-term strategy for Trafisense is to develop the company and the markets making Trafisense a serious international player.

During the execution of this project, we have also identified a set of subscription packages for our monitoring service. The packages are based on potential customer interviews and the competition analysis and seem to be aligned with the corresponding classes of monitoring that customers require.

Progress beyond the state of the art and expected potential impact (including the socio-economic impact and the wider societal implications of the project so far)

During the project, Trafisense has completed the design and implementation/manufacturing of 2 revisions of its main dry-type transformer monitoring hardware. The 1st revision resulted to a device that is one third (65% reduction) of the cost and half (50% reduction) the size of the initial hardware version. This revision has been installed at a customer pilot site since June 2017. The 2nd revision has retained the hardware cost to 35% of the prototype version (i.e. same cost as the 1st revision) and has reduced the size to 65% of the original.

In addition, an initial version of a network harmonics monitoring device that supports a much higher frequency measurement range than any comparable device in the market has been designed.

Trafisense Console Web Application