Adaptive RUL Estimation for Load-Bearing Structures
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional methods for predicting the remaining useful life (RUL) of load-bearing structures lack reliable threshold values and probabilistic quantification, leading to potential premature shutdowns or failures due to unreliable degradation measurements.
Innovation Solution
A system utilizing a constraint convex regression model to estimate total useful life (TUL) and remaining useful life (RUL) based on degradation data, with the option to recalibrate measurements and employ particle-filtering techniques for probabilistic RUL distribution estimation, incorporating sensors for electrical, thermal, or magnetic resistance measurements.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If conventional degradation measurement with predetermined threshold is used, then system operation can be monitored, but reliable threshold value cannot be determined leading to premature shutdown or system failure
Solution Approach 1:
The patent transforms the fixed threshold approach into a dynamic parameter estimation problem. Instead of using a predetermined threshold, the system continuously estimates the total useful life (TUL) parameter through convex regression analysis of degradation data, allowing the effective threshold to adapt as the system ages and degradation patterns evolve.
Solution Approach 2:
The patent replaces the simple mechanical threshold comparison mechanism with a sophisticated computational model. The convex regression framework substitutes basic threshold checking with continuous probabilistic estimation, using mathematical optimization to infer TUL from degradation measurements rather than relying on fixed cutoff values.
2Reliability
If conventional degradation measurement is used, then degradation can be tracked, but probabilistic quantification of system RUL cannot be provided
Solution Approach 1:
The patent introduces dynamic probabilistic estimation into the RUL prediction process. The convex regression model continuously updates the TUL estimate and associated uncertainty as new degradation data arrives, transforming static threshold monitoring into a dynamic Bayesian inference process that quantifies prediction confidence.
Solution Approach 2:
The patent introduces the TUL estimate as an intermediary variable between raw degradation measurements and final RUL prediction. This intermediate parameter, along with its uncertainty bounds, serves as a bridge that enables probabilistic quantification, allowing the system to express RUL as a distribution rather than a single deterministic value.
3Reliability
If continuous degradation measurement is performed, then RUL can be predicted, but system downtime increases due to frequent monitoring
Solution Approach 1:
The patent applies partial monitoring by focusing computational resources on the most informative aspects of degradation data. Rather than continuously processing all possible measurements, the convex regression framework selectively utilizes degradation features that provide maximum information about TUL, reducing monitoring overhead while maintaining prediction accuracy.
Solution Approach 2:
The patent performs preliminary analysis of degradation patterns to establish the convex regression model structure before full RUL prediction is needed. By pre-characterizing the degradation trajectory and uncertainty relationships, the system reduces real-time computational burden, allowing faster RUL updates without requiring continuous full-scale analysis.
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
This approach provides adaptive and accurate RUL predictions, reducing the risk of system failure by continuously updating TUL and RUL estimates, ensuring timely maintenance and minimizing downtime.
Implementation Method 1
measuring an electrical resistance
Implementation Method 2
measuring a thermal resistance
Implementation Method 3
measuring a magnetic resistance
Data Source
Figure 1
Figure 2
Figure 3A
AI summary
System, method and computer-implemented invention for estimating useful life of a load-bearing structure. During operation, the system can perform a degradation measurement on the structure to obtain degradation data for a predetermined time interval, apply a constraint convex regression model to the degradation data, estimate a total useful life (TUL) of the structure based on outputs of the constraint convex regression model, and predicting a remaining useful life (RUL) based on the TUL and a current time.