Relation Discovery for Diagnostics Using Machine Learning Technique
Author(s):
Mrs. Karthika P, Dr.P. Prabhusundhar
Keywords:
Fault detection, diagnostics, Machine learning, Signal Processing, Algorithms and Reliability.
Abstract
Warranty prediction is a most important task in reliability engineering. It needs to estimate the expected number of product failures in any given time period during the length of the warranty contract, Since the sensor capabilities and engineering effort available for diagnostic purposes is limited. It is, in practice, impossible to develop diagnostic algorithms capable of detecting many different kinds of faults that would be applicable to a wide range of product configurations and usage patterns. However, it is now becoming feasible to obtain and analyse on board data on products as they are being used. It makes automatic data-mining methods an attractive alternative, since they are capable of adapting themselves to specific product configurations and usage. In order to be though, useful, such methods need to be able to detect interesting relations between huge number of available signal. This method unsupervised for discovering useful relations between measured signals in a product, both during normal operations and when a fault has occurred. The interesting relationships are found in a two-step procedure. In the first step, identify a set of “good” models, by establishing a mean square error threshold over the complete data set. In the second step, estimate model parameters over time, in order to capture the dynamic behaviour of the system. use two different approaches here, the Least Absolute Shrinkage and Selection Operator method and the Recursive Least Squares filter. The usefulness of obtained relations is then evaluated using supervised learning to separate different classes of faults.
Article Details
Unique Paper ID: 166488

Publication Volume & Issue: Volume 11, Issue 2

Page(s): 614 - 619
Article Preview & Download


Share This Article

Join our RMS

Conference Alert

NCSEM 2024

National Conference on Sustainable Engineering and Management - 2024

Last Date: 15th March 2024

Call For Paper

Volume 11 Issue 1

Last Date for paper submitting for Latest Issue is 25 June 2024

About Us

IJIRT.org enables door in research by providing high quality research articles in open access market.

Send us any query related to your research on editor@ijirt.org

Social Media

Google Verified Reviews