Compressor Blade Corrosion Prediction Using a Digital Twin

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Turbomachinery compressors in commercial aircraft and land-based gas turbines suffer from significant corrosion and degradation due to varying environmental conditions, leading to pitting and fatigue, which increases the probability of cracking and results in costly downtime and unplanned outages, with current modeling techniques being insufficient in predicting fatigue-based failures.

Innovation Solution

A control system and method that utilizes sensors to monitor environmental and operational parameters, processes data through mathematical models, and creates a digital twin to predict corrosion damage by simulating the degradation of turbomachinery components, allowing for real-time decision-making on maintenance and repair schedules.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If current modeling techniques are used to predict fatigue, then the complexity of the system is low, but the prediction accuracy is insufficient

Engineering Contradiction:
Improveprediction accuracyVSAvoidsystem complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The system segments the corrosion prediction problem into multiple independent modules: environmental condition monitoring, operational parameter tracking, corrosion model selection, and fatigue analysis. Each module processes specific data types and can be independently configured, allowing high prediction accuracy through specialized models while managing system complexity through modular architecture.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The system dynamically adapts the corrosion prediction model based on operating conditions. Different corrosion models are selected and adjusted in real-time according to the specific environmental and operational parameters detected, enabling accurate predictions across varying conditions without requiring a single overly complex universal model.

Inventive Principle:
Principle #15Dynamics

2Reliability

If comprehensive environmental and operational monitoring is implemented, then corrosion prediction accuracy improves, but the cost and complexity of the system increases

Engineering Contradiction:
Improvecorrosion prediction reliabilityVSAvoidmonitoring system complexity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The monitoring system uses multi-functional sensors and data processing capabilities that serve multiple purposes. The same sensor data is used for both real-time corrosion prediction and historical trend analysis, and the system can adapt to monitor different types of corrosive environments using the same hardware platform, reducing overall system complexity while maintaining high reliability.

Inventive Principle:
Principle #6Universality (Multi-functionality)

Solution Approach 2:

The system implements feedback loops where corrosion predictions are continuously refined based on actual inspection results and operational data. This feedback mechanism improves prediction reliability over time without requiring proportional increases in system complexity, as the same hardware infrastructure is leveraged for both monitoring and validation.

Inventive Principle:
Principle #23Feedback

3Productivity

If real-time corrosion prediction is performed, then maintenance timing can be optimized, but the computational resources and system complexity increase

Engineering Contradiction:
Improvemaintenance efficiencyVSAvoidcomputational system complexity
Core Design Contradiction:
ProductivityVSDevice complexity

Solution Approach 1:

The system performs corrosion predictions at optimized intervals based on operational conditions and risk assessments rather than continuously. High-risk periods trigger more frequent predictions, while low-risk periods use reduced monitoring frequency, improving maintenance efficiency while managing computational resources effectively without requiring continuous high-power processing.

Inventive Principle:
Principle #19Periodic action

Solution Approach 2:

The system performs preliminary corrosion assessments using available data to identify high-risk scenarios before they develop into critical conditions. This preliminary action allows maintenance to be scheduled proactively based on predicted corrosion trends rather than reacting to actual damage, improving maintenance efficiency while using computationally efficient prediction algorithms.

Inventive Principle:
Principle #10Preliminary action

Applied Scientific Principles

This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.

Function Achieved in This Case

The system effectively predicts corrosion damage by calculating pit sizes and fatigue debit, enabling proactive maintenance and reducing downtime by scheduling inspections and repairs based on predicted corrosion risk, thereby minimizing costs and ensuring turbomachinery reliability.

Implementation Method 1

A control system and method that utilizes sensors to monitor environmental and operational parameters

Methodology Applied
Scientific EffectSensor detection:

Implementation Method 2

processes data through mathematical models, and creates a digital twin to predict corrosion damage by simulating the degradation of turbomachinery components

Methodology Applied
Scientific EffectMathematical modeling:

Data Source

PatentEP3410092B1Control system and method
Publication Date: 2025.12.24 GENERAL ELECTRIC TECH GMBH
  • EP3410092B1 patent drawingFigure 1
  • EP3410092B1 patent drawingFigure 2
  • EP3410092B1 patent drawingFigure 3~4

AI summary

A control system (100) and method utilizing one or more processors (110) that are configured to determine contaminant loading of blades (106) of a turbomachinery compressor (102) based on one or more environmental conditions to which the turbomachinery compressor (102) is exposed and one or more atmospheric air inlet conditions of the turbomachinery compressor (102). The one or more processors (110) then determine a corrosion contaminant concentration on the blades (106) of the turbomachinery compressor (102) based on the contaminant loading that is determined and determine an upper limit on or a distribution of potential corrosion of the blades (106) of the turbomachinery (102) based on the corrosion contaminant concentration, at least one of the environmental conditions to which the turbomachinery compressor (102) is exposed, and the corrosion contaminant concentration that is determined.