US 12,638,843 B2 · System and method of predicting failures

Abstract

A system and method for prediction of failures and optimization, that can provide solution available for unsupervised learning models based on limited data that can predict different types of failure and pre-failure instances. The solution provides improvement upon previous methods of labelling by marking certain days data ahead of failure as belonging to failure data which will result in reduction of noisy data and improves good working condition data. The present invention helps with improved data quality due to labelling as the proposed method models complex distributions of feature vectors accurately and are better at finding deviations from normal data distribution which is used for detecting failures. The novel solution help to analyse and categorise the type of failures for PC Pumps currently deployed in CBM Fields for which failure days in advance can be predicted.

Claims11

Dependent claims

A system for facilitating prediction of wear and tear and future failure of components associated with gas extraction in a mining well, said system comprising:

one or more user equipment communicatively coupled to Coal Bed Methane (CBM) wells for gas extraction;
one or more sensors coupled to one or more pumpsin the mining well;
wherein the one or more user equipment comprises of one or more processors that execute a set of executable instructions that are stored in a memory, upon which execution, the processor causes the system to:
acquire a set of data packets from one or more sensors, by a data acquisition engine, wherein the set of data packets are received at synchronous and asynchronous instances of time;
extract a set of attributes, by a feature generation engine, from the synchronised data packets, wherein the feature generation engine is configured to generate features from the extracted set of attributes associated with interpolation of the received data packets;
evaluate, by a generative adaptive network (GAN) engine, a set of model parameters based on the generated features of the extracted set of attributes;
and
predict, by a prediction engine, failures associated with the received set of data packets based on the evaluation of the set of model parameters.

5 more elements

Dependencies are inferred from the claim text.

System and method of predicting failures

Life of this patent

System and method of predicting failures

Life of this patent

Abstract

Claims11