Gas Turbine Component Quality Estimation via Virtual Sensor Comparison

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Current methods for gas turbine engines lack the ability to continuously estimate and track the quality of individual components, such as fans, compressors, and turbines, making it difficult to predict remaining engine life and detect damage or faults effectively.

Innovation Solution

A method involving an engine model with virtual sensor values and quality parameters, which compares actual sensor values to virtual values, amplifies differences, and iteratively updates the model to recalculate sensor values, allowing for the estimation of component quality and detection of damage or faults.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If traditional sensor monitoring and trending methods are used to estimate engine performance, then overall engine performance can be inferred, but individual component quality cannot be estimated or tracked

Engineering Contradiction:

Improvecomponent quality estimationVSAvoidindividual component quality data

Core Design Contradiction:

Measurement precisionVSLoss of information

Solution Approach 1:

The patent divides the engine system into individual component models (compressor, turbine, condenser, etc.), each with its own quality parameters. This segmentation allows separate estimation and tracking of each component's quality rather than treating the engine as a single integrated system, directly resolving the inability to obtain individual component quality data.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The patent introduces a data processing system as an intermediary between sensor data and component quality assessment. This system uses sensor measurements combined with component-specific models and algorithms to compute quality parameters, acting as a mediator that transforms raw sensor data into actionable component-level quality information.

Inventive Principle:

Principle #24Intermediary (Mediator)

2Reliability

If conservative pre-selected maintenance schedules are used based on hours or cycles, then component failure risk is managed, but maintenance efficiency is reduced due to unnecessary overhauls

Engineering Contradiction:

Improvecomponent failure preventionVSAvoidmaintenance efficiency

Core Design Contradiction:

ReliabilityVSProductivity

Solution Approach 1:

The patent implements continuous feedback loops where sensor data is constantly monitored, component quality is estimated in real-time, and this information feeds back into maintenance decision-making. This allows dynamic adjustment of maintenance schedules based on actual component condition rather than fixed conservative intervals, improving maintenance efficiency while maintaining reliability.

Inventive Principle:

Principle #23Feedback

Solution Approach 2:

The patent transitions from static, pre-determined maintenance schedules to dynamic, condition-based maintenance planning. Component quality parameters are continuously updated based on operating conditions and sensor data, allowing maintenance timing to adapt dynamically to actual component degradation rates, thereby optimizing maintenance efficiency.

Inventive Principle:

Principle #15Dynamics

3Ease of repair

If predetermined diagnosis routines are followed after component failure, then failed components can be identified and replaced, but the ability to forecast remaining engine life and detect damage early is lost

Engineering Contradiction:

Improvecomponent identification and replacementVSAvoidremaining engine life forecasting capability

Core Design Contradiction:

Ease of repairVSLoss of time

Solution Approach 1:

The patent performs preliminary assessment of component quality and forecasts remaining engine life before actual failure occurs. By continuously monitoring quality parameters and predicting degradation trends, the system enables proactive maintenance planning and early damage detection, preventing the need for reactive diagnosis after failure.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The patent replaces traditional mechanical diagnosis routines (performed after failure) with a computational modeling and data analysis system. This system uses sensor data, component models, and algorithms to diagnose component condition and predict failures, substituting post-failure mechanical inspection with continuous predictive analytics.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Data Source

PatentUS7505844B2Model-based iterative estimation of gas turbine engine component qualities

Publication Date: 2009.03.17 GENERAL ELECTRIC CO

AI summary

A method of estimating quality parameters for a plurality of engine components of a gas turbine engine is provided. The engine components have at least one sensor responsive to the engine component operation. The method includes providing an engine model having virtual sensor values and quality parameters corresponding to the plurality of sensors of the engine components; comparing the virtual sensor values to actual sensor values of the plurality of sensors of the engine components to determine the difference between the actual and virtual sensor values; amplifying the difference by a predetermined gain; generating a plurality of quality parameter deltas in response to the sensed difference; iteratively updating the embedded engine model by inputting a predetermined portion of the generated quality parameter deltas into the embedded engine model; adjusting the embedded engine model for engine operating conditions; and recalculating the virtual sensor values.