Analyzing the operation of a turbine generator at a thermal power plant

To develop a predictive analysis model for the turbine generator and to demonstrate the potential for predictive analysis to improve the performance of energy equipment, reduce operating and capital costs, and reduce.


The use of F5 PMM — a system for diagnosing and predicting the technical condition of equipment.

The initial data: certificate and operating instructions, data on failures, telemetry data for two years of turbine generator operation.

Sequencing of actions

  • analyzed the turbine generator’s historical data
  • identified the relevant parameters characterizing the state of the turbine generator
  • analyzed the values of stator current variation up to the time of the failure
  • built a linear regression based on the temperature data of the stator winding (one month of normal operation) and the total power of the turbine generator
  • compared the actual and calculated temperatures for the entire sample provided

A systematic excess of the actual temperature of the stator winding over the nominal temperature in specific grooves and temperature peaks was detected.

Turbogenerator eng 2.jpg
The graph shows the change in the calculated and actual temperatures of the stator winding through the example of two grooves.
The designed predictive analysis model makes it possible to detect abnormal temperatures in the stator winding of a turbine generator 1.5 years before failure.
The model can predict the onset of failure in different grooves in advance based on the actual data.
Остались вопросы по продуктам? Узнайте больше о возможностях искусственного интеллекта для вашего предприятия
Thank you!
A Clover Group specialist will contact you during business hours.
We use cookies for your convenience on the website.
By clicking on the link to the website or using the website, you consent to the collection of data through cookies.
Learn more about our use of cookies and about changing your settings.