Oil Condition Monitoring and Remaining Life Prediction using Classification Learner Technique, an AI Application


Based on data obtained directly from the hydraulic system of a mechanical processing machine, this study applies an estimation and prediction approach employing typical methodologies to anticipate the remaining life of the lubricating oil. The measured values of the 19 lubricating oil condition parameters are represented by the data gathered. The measurements were taken online on an experimental stand that was created and operated in comparable conditions to those seen in a mechanical processing plant. For all 19 operational parameters, data was collected for six months in 258646 courts. Support vector machines (SVM) models have tackled the Classification Learner Techniques to forecast the values of the future steps in a sequence. At each stage of the input sequence, the generated output values describe and equate the training sequences with values updated by a step of time, suggesting that the data structure learns to predict the output value at the following time step. The training data must be normalised to achieve a zero mean and unit variance in order to prevent the forecast from deviating. Furthermore, the test data set was normalised in the same manner as the training data.

Author(s) Details:

Gavril Grebenisan,
University of Oradea, Romania.

Nazzal Salem,
Zarqa University, Jordan.

Sanda Bogdan,
University of Oradea, Romania.

Dan Claudiu Negrau,
University of Oradea, Romania.

Please see the link here: https://stm.bookpi.org/RDST-V7/article/view/7101

Leave A Comment