Mechanical Part Wear Prediction Under Variable Aircraft Use Profiles
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods fail to accurately predict the wear of mechanical parts, such as aircraft turbomachines, and estimate operational risks associated with their ageing, leading to inadequate profitability estimation and risk assessment in aircraft contracts.
Innovation Solution
A method for predicting wear and uncertainty of mechanical parts by considering usage profiles and environmental conditions, using operational data to develop weighted models and statistical dispersion analysis, enabling precise maintenance cost estimation and risk assessment.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If macroscopic estimation methods are used for maintenance costs and risk indicators, then the estimation process is simple, but the accuracy and reliability of profitability assessment deteriorates
Solution Approach 1:
The patent segments the mechanical part into multiple elements (e.g., turbine blades, compressor blades, disks) and creates separate wear prediction models for each element. This segmentation allows for more precise tracking of wear in critical components while maintaining manageable complexity through modular modeling approaches.
Solution Approach 2:
The patent applies local quality by creating element-specific wear models that account for local environmental conditions and usage patterns. Each mechanical element has its own weighting coefficients and wear parameters tailored to its specific operational context, enabling precise cost estimation for maintenance activities targeting specific worn components.
2Measurement precision
If environmental conditions and usage profiles are considered in wear prediction, then the accuracy of wear prediction improves, but the complexity of data processing and model development increases
Solution Approach 1:
The patent changes parameters by introducing environmental condition parameters (temperature, humidity, contamination levels) and usage profile parameters (flight hours, cycle counts, load factors) into the wear prediction models. These parameter changes enable the system to adapt wear predictions to specific operational contexts without requiring complete model redesign for each scenario.
Solution Approach 2:
The patent implements dynamics by making wear prediction models adaptive to changing environmental conditions and usage patterns. The weighting coefficients and model parameters are dynamically adjusted based on real-time or historical operational data, allowing the system to maintain high prediction accuracy across varying operational scenarios without static rigidity.
3Reliability
If multiple element-specific models are developed for mechanical parts, then the reliability of wear prediction improves, but the time and resources required for model development and maintenance increase
Solution Approach 1:
The patent applies preliminary action by developing a library of pre-configured wear prediction models for common mechanical elements (blades, disks, bearings) that can be selected and adapted for specific applications. This preliminary model development reduces the time required for new project setup while maintaining reliability through proven modeling approaches that have been validated across multiple applications.
Solution Approach 2:
The patent implements universality by creating a framework where a single set of modeling principles and computational methods can be applied across multiple mechanical elements and different aircraft types. The element-specific models use consistent mathematical formulations and data structures, allowing the system to handle diverse components through a unified approach that reduces development overhead.
Data Source
AI summary
A method for predicting the wear of a mechanical part and uncertainty of this prediction in a profile of use, the profile of use taking into account environmental conditions associated with environmental data and the time of use of the mechanical part under each of these environmental conditions, the method including determining operational data associated with a plurality of mechanical parts of the same type as the mechanical part; on the basis of the operational data determined, determining a plurality of predictive models of the wear of the part, the mechanical part being able to be divided into a plurality of elements, each element being modelled using at least one model of the plurality of models; and, for each model, determining a weighting coefficient, determining a wear prediction of the mechanical part, and determining a statistical quantity representative of dispersion of the predictions of the plurality of models.