Performance Estimation Modeling for Device Degradation Factors
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional prediction methods for power generation plants cannot accurately estimate the factors contributing to performance changes in devices over time, as they treat performance changes as a whole rather than isolating individual factors.
Innovation Solution
An apparatus and method that generate a performance estimation model by superposing individual performance functions, each representing the impact of specific change factors on performance indices, to closely approximate an overall performance function, allowing for quantitative estimation of performance changes and identification of underlying factors.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional prediction methods are used to predict performance changes of the plant or devices as a whole, then performance prediction can be obtained, but the factors of performance changes cannot be estimated
Solution Approach 1:
The patent segments the overall performance function into multiple individual performance functions, each representing a specific change factor (e.g., blade roughness, clearance, erosion). By dividing the composite performance degradation into separable components, the system can estimate both the overall performance change and the contributing factors independently.
Solution Approach 2:
The patent introduces individual performance functions as intermediary models that link specific physical change factors to performance degradation. These intermediary functions serve as bridges between observable performance changes and underlying physical causes, enabling factor estimation without direct measurement of each factor.
2Loss of information
If multiple individual performance functions are superposed to estimate performance changes, then factor estimation becomes possible, but model complexity increases
Solution Approach 1:
The patent merges multiple individual performance functions into a unified performance estimation model through superposition. Each individual function represents a specific factor's contribution, and their combined effect is calculated by summing their respective performance changes, creating a comprehensive model that maintains interpretability while capturing multiple degradation mechanisms.
Solution Approach 2:
The patent uses parameter changes in individual performance functions to represent different change factors (e.g., blade roughness parameter, clearance parameter). By monitoring how these parameters evolve over time and their impact on performance, the system can estimate factor contributions without requiring complex physical models of each degradation mechanism.
Data Source
AI summary
An apparatus for evaluating performance of a device includes: an overall performance function acquisition part configured to obtain an overall performance function which indicates a change over time in performance index of an evaluation target device, based on data acquired during operation of the evaluation target device; an individual performance function definition part configured to define a plurality of individual performance functions each of which indicates a change over time in the performance index caused by a plurality of change factors of the performance index, respectively; and a model generation part configured to generate a performance estimation model for the evaluation target device by performing superposition of the plurality of individual performance functions. The model generation part determines a coefficient of each of the plurality of individual performance functions in the superposition so the superposition of the plurality of individual performance functions becomes close to the overall performance function.