Method and system for failure prediction using lubricating fluid analysis
AssigneePratt & Whitney Canada Corp.
InventorsMaurice JEAN, Daniel MEILLEUR
Life of this patent
Estimating the term…
Abstract
Methods and systems for failure prediction using analysis of oil or other lubricant. Raw data about feature(s) of each of a plurality of particles filtered from a fluid sample are used to categorize each particle into one of a plurality of categories, each category being defined by one or more of: chemical composition, size and morphology. Particle physical characteristics in each category are quantified to obtain a set of categorized data. The categorized data are compared with historical data. Results of the comparing are evaluated to generate a prediction of any failure or mechanism of failure.
Claims19
-20. (canceled)
A method for generating a failure prediction for an engine of an engine type, the method comprising:
- receiving a sample of lubricating fluid of the engine, the sample of the lubricating fluid having particles therein;
- filtering out the particles from the sample of the lubricating fluid, the filtered particles including non-metallic particles;
- using X-ray spectroscopy, analyzing the filtered particles and producing raw data relating to the filtered particles, the raw data including chemical compositions of individual filtered particles, the raw data including data relating to the non-metallic particles;
- using one or more processors and the raw data:
- categorizing the filtered particles into categories to generate categorized data, at least one of the categories being a non-metallic category;
- comparing the categorized data with historical data associated with the engine type;
- generating the failure prediction based on the comparison, the failure prediction being indicative of one or both of the following:
- when the engine is expected to fail and a mechanism of failure of the engine;
- and
- generating an output indicative of the failure prediction.
Dependencies are inferred from the claim text.