Gas Turbine Operating Point Selection via Kriging Interpolation

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

The manual selection of operating points for gas turbines is time-consuming, requires significant experience, and is inefficient in reacting to variations due to different environmental conditions and customer requirements, leading to inconsistent performance across identical gas turbines.

Innovation Solution

An automated method using the kriging interpolation method to select operating points based on known parameter combinations, balancing exploration and information utilization to efficiently find optimized settings for manipulated variables such as fuel flow and burner distribution, while considering disturbance variables like ambient conditions.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If manual selection of operating points is used, then experienced operators can select suitable points, but the process is extremely time-consuming and requires great experience

Engineering Contradiction:
Improveselection accuracyVSAvoidselection time
Core Design Contradiction:
ReliabilityVSLoss of time

Solution Approach 1:

The system performs automatic self-optimization by using the gas turbine itself to evaluate operating points through automated measurement of controlled variables, eliminating the need for manual expert intervention while maintaining reliable selection accuracy

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The manual expert system is replaced by an automated computer-based optimization system that uses algorithms to evaluate operating points and select optimal settings, substituting human expertise with automated computational methods

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

2Manufacturing precision

If manual selection of operating points is used, then detailed adjustments can be made, but it is difficult to react to unforeseen deviations in controlled variables

Engineering Contradiction:
Improveparameter setting precisionVSAvoidresponse to deviations
Core Design Contradiction:
Manufacturing precisionVSAdaptability or versatility

Solution Approach 1:

The system automatically measures controlled variables during gas turbine operation and uses this feedback to evaluate operating points and adjust settings, enabling real-time adaptation to deviations while maintaining precise parameter control

Inventive Principle:
Principle #23Feedback

Solution Approach 2:

The operating points are not fixed but dynamically adjusted based on automated evaluation of controlled variables and environmental conditions, allowing the system to adapt to changing conditions while maintaining precision

Inventive Principle:
Principle #15Dynamics

3Adaptability or versatility

If operating points are selected separately for each gas turbine, then customized settings can be achieved, but the process is extremely time-consuming

Engineering Contradiction:
Improvecustomization capabilityVSAvoidselection efficiency
Core Design Contradiction:
Adaptability or versatilityVSProductivity

Solution Approach 1:

Each gas turbine automatically determines its own optimal operating points through automated evaluation, eliminating the need for time-consuming manual customization while maintaining tailored settings for each unit

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The system efficiently explores the parameter space by systematically varying manipulated variables and evaluating their impact on controlled variables, enabling quick customization for each gas turbine without extensive time investment

Inventive Principle:
Principle #35Parameter changes

Data Source

PatentEP3140534B1Method for selecting operating points of a gas turbine
Publication Date: 2018.06.06 SIEMENS AG
  • EP3140534B1 patent drawing
  • EP3140534B1 patent drawing

AI summary

The invention relates to a method for selecting operating points of a gas turbine while taking into consideration at least one controlled variable, the operating points being defined at least by parameter combinations of manipulated variables, characterized in that the operating points are automatically selected on the basis of already known parameter combinations by using an interpolation method, the Kriging interpolation method being used as the interpolation method.