Asset Health Analysis for Multi-Mode RUL Estimation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In power systems, estimating the remaining useful life (RUL) of assets is challenging when they operate in different modes, leading to discontinuities in monitored data, which skews feature significance and results in unreliable RUL estimations, affecting maintenance planning and decision-making.
Innovation Solution
A method involving signal segmentation, metric determination, and selection based on correspondence with mathematical functions to assess asset health, allowing for accurate RUL estimation across varying operating modes, and optimizing sensor configurations for improved monitoring.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If features are selected based on significance at a single operating mode, then the estimation is accurate for that mode, but the estimation becomes unreliable when multiple operating modes are considered
Solution Approach 1:
The patent segments the operational data into multiple feature segments corresponding to different operating modes. For each segment, separate metric sets are determined to evaluate feature significance. This segmentation allows the system to capture mode-specific characteristics while maintaining overall reliability across all modes by treating each mode's features independently rather than averaging them.
2Adaptability or versatility
If transitions in monitored data are handled by averaging features across operating modes, then all modes are considered, but the significance of features is skewed leading to less accurate estimations
Solution Approach 1:
The patent applies local quality by determining metric sets specifically for each feature segment corresponding to different operating modes. Each metric set evaluates feature significance locally within its specific operating context rather than using a global average. This allows the system to maintain high measurement precision for each mode while still providing comprehensive multi-mode coverage through the aggregation of segment-specific results.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
The present disclosure relates to a method of performing a prognostic health analysis for an asset, in particular for determining a remaining useful life, RUL, of a power system asset or industrial asset, the method comprising: obtaining signals of at least one operational data; segmenting the signals of at least one operational data into a plurality of feature segments; determining a plurality of metric sets for each of the plurality of feature segments based on the signals of the at least one operational data in the respective plurality of feature segments, wherein each of the plurality of metric sets comprises at least one metric indicating a degree of correspondence between the signals of at least one operational data in the respective plurality of feature segments and a mathematical function; selecting the signals in at least one of the plurality of feature segments based on the plurality of metric sets; determining a prognostic asset health state based on the selected signals in at least one of the plurality of feature segments; and generating output based on the prognostic asset health state. The present disclosure also relates to a corresponding method of operating and/or maintaining an asset, a determining system operative to perform a prognostic health analysis for an asset and an industrial power system.