Equipment Remaining Life Estimation Using Severity-Class Time Series
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current Health-Monitoring processes face challenges in accurately estimating the Remaining Useful Life (RUL) of equipment, particularly in the aeronautical field, due to limitations in data processing and classification methods that fail to provide reliable and consistent predictions of equipment degradation.
Innovation Solution
A method involving a preliminary phase of acquiring and processing test data from similar equipment to learn diagnosis and prediction models, followed by an operational phase where real-time observations are used to extrapolate and classify signatures, employing a Fuzzy C-Mean algorithm and non-linear SVR regression for accurate RUL estimation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional data processing and classification methods are used in Health-Monitoring processes, then the implementation is simpler, but the accuracy and reliability of RUL estimation deteriorates
Solution Approach 1:
The method segments the RUL estimation process into distinct phases: data acquisition from multiple sources, data preprocessing and filtering, feature extraction to identify degradation signatures, severity classification into multiple levels, and final RUL prediction. This segmentation allows each step to be optimized independently, improving overall accuracy while managing complexity through structured processing stages
Solution Approach 2:
The method performs preliminary actions by acquiring and processing data from test equipment devices before actual RUL estimation is needed. Historical data is collected, severity classes are predefined, and degradation patterns are established in advance, enabling more accurate and reliable RUL predictions when the method is applied to subject equipment
2Stability of the object's composition
If traditional classification methods are used, then the implementation is simpler, but the temporal consistency of severity classification deteriorates
Solution Approach 1:
The classification model is designed to be dynamic and adaptive, automatically adjusting severity thresholds and classification criteria based on the specific degradation patterns observed in the data. The model evolves with the equipment's actual behavior rather than relying on fixed, pre-defined thresholds, ensuring temporal consistency across different operational phases
Solution Approach 2:
The method incorporates feedback mechanisms where classification results are continuously evaluated and used to refine the diagnosis model. The system learns from past classifications and adjusts its parameters to improve temporal consistency, creating a closed-loop system that enhances reliability over time
Data Source
AI summary
A method for estimating a Remaining Useful Life of a subject equipment, with a preliminary phase including the following steps: acquire test observations (step 10) and produce test time series (Sx) of at least one signature; partition the test time series to obtain severity classes corresponding to the ageing phases of the test equipment devices (step 14); carry out an initial learning of a diagnosis model on the test equipment devices (step 45); perform a second learning of a signature prediction model (step 51). There is also an operational phase including the following steps: acquire observations when in operation on the subject equipment and produce an extrapolated time series using the prediction model; classify the extrapolated time series using the diagnosis model and derive the remaining useful life of the subject equipment.