General Electric (GE) announced new machine learning software aimed at providing continuous tuning for gas turbines.
The company’s Autonomous Tuning software uses artificial intelligence (AI) to build a digital twin model of a gas turbine to find optimal flame temperatures and fuel splits. GE said the technology will help reduce emissions and fuel consumption.
The software is designed to sense changes in ambient temperature, gas fuel properties and degradation before sending adjustments to the controls every two seconds. The goal is to allow tracking of the turbine’s “sweet spot” with low emissions and acoustics in response to environmental conditions or physical degradation.
Have you read?
Wärtsilä to supply 110MW of flexible thermal balancing power to Italy
Valmet delivers automation to biogas plant in the Baltics
Gas turbines require seasonal adjustments to their flame temperature and fuel splits, generally performed manually after an outage and expected to take a few days to finish. With the new software, GE said this work would be done automatically.
The software applies to any original equipment manufacturer gas turbine and also is bounded by the turbine control system’s safety-critical programming” to help ensure it does not harm the turbine. GE said that power generators that might benefit most from the technology are in highly regulated regions or those with constrained emissions, such as Europe, the United States and Canada, or in any location that does not have consistent weather patterns.
GE said plants using the software have recorded carbon dioxide reductions between 0.5%-1.0%, carbon monoxide reductions of 14% and nitrous oxide reductions of 10%-14%.
The company said it expects software users to have a lower total cost of ownership, and more operational flexibility with their turbines. It said that added improved productivity from the turbines can result in payback in under one year.
“With Autonomous Tuning, GE Digital has introduced a practical industrial example of the use of machine learning in closed loop supervisory control, and all running at the Edge,” according to Joe Perino, Principal Analyst at LNS Research.
“This is a real-world application of AI for decarbonization with tangible reductions in emissions and fuel for gas turbine operators. This, and other building block sub-systems, are a step toward autonomous operations.”
Originally published by Kevin Clark on power-eng.com
