Machines Condition Monitoring and Oil Life Remaining Forecasting through Artificial Intelligence Techniques- a Survey

  • Nazzal Salem, G. Grebenişan
Keywords: Condition Monitoring, Oil Life Remaining Forecasting, Artificial Intelligence, Principal Components Analysis, Neural Network.

Abstract

The present study intends to bring to the reader interested three methods of estimation and prediction, using Artificial Intelligence characteristic techniques, used to predict the life of the lubricating oil based on data collected directly from the mechanical or hydraulic system. The collected data is part of a complex data set with 19 lubricating oil status parameters as a result of online measurements on an experiment stand built and operated under conditions similar to those in a mechanical machining company. The data set was collected for six months, continuously, validating the data in several 258646 instances, for 19 operating parameters. In order to predict the values of the next steps of a sequence, three Principal Components Analysis (PCA), Classification Learner Technics, have been approached by support vector machines (SVM) models, in which the PCA approach was considered to be favorable experiment, and Neural Network Training (kernel Neural Network-kNN) models respectively. The answers obtained characterize and equate the training sequences with values changed by a step of the time, and this means that at each step of the input sequence, the data structure learns to predict the output value at the next time step. To prevent situations of divergence of the forecast were necessary to standardize the training data so that it has zero mean and unit variance. Also, the test data set has been standardized in the same way as training data.

Published
2021-10-05
How to Cite
G. Grebenişan, N. S. (2021). Machines Condition Monitoring and Oil Life Remaining Forecasting through Artificial Intelligence Techniques- a Survey. Design Engineering, 1958-2003. Retrieved from http://www.thedesignengineering.com/index.php/DE/article/view/5096
Section
Articles