Comparative Analysis of Multiple Linear Regression and Artificial Neural Network for Predicting Friction and Wear of Automotive Brake Pads Produced from Palm Kernel Shell

Journal Title: Tribology in Industry - Year 2018, Vol 40, Issue 4

Abstract

In this study, comparative analysis of multiple linear regression (MLR) and artificial neural network (ANN) for prediction of wear rate and coefficient of friction brake pad produced from palm kernel shell was carried out. The inputs parameters used for the two models generated using inertia dynamometer were the percentages of palm kernel shell, aluminium oxide, graphite, calcium carbonate, epoxy resin, interface temperature of the brake pad, and work done by brake application. Two model equations were developed using MLR model for predicting wear rate and coefficient of friction while the neural network architecture BR 7 [5-3] 2 was used to predict wear rate and coefficient of friction. The predicted wear rate and coefficient of friction by MLR model were compared with ANN model along with the measured values using statistical tools such as means square absolute error (MAE), root means square error (RMSE), and Nash-Scutcliffe efficiency (NSE). The results revealed that the MLR model outsmarts the ANN model with the values of MAE and RMSE reasonably low and NSE reasonably higher. The best MAE and RMSE values of 0.000 were observed at the three values of measured wear rates and coefficient of friction that matched with the predicted values using MLR compared to -0.0300 and 0.0740 for ANN model. However, the ANN model was equally found suitable for the prediction of wear rate and coefficient of friction of brake pads developed. The implication of these results is that the two models have the capabilities of being used simultaneously when estimating the wear and coefficient of friction of brake pads.

Authors and Affiliations

K. K. Ikpambese, E. A. Lawrence

Keywords

Related Articles

Softening Resistance, Dimensional Stability and Corrosion Behaviour of Alumina and Rice Husk Ash Reinforced Aluminium Matrix Composites Subjected to Thermal Cycling

The softening resistance, dimensional stability and corrosion behaviour of stir cast alumina and rice husk ash reinforced aluminium matrix composites subjected to thermal cycling has been investigated. Aluminium hybrid...

Comparison of Mechanical Properties in Compacted and Spheroidal Graphite Irons

Mechanical properties of cast irons are governed by the size, distribution and shape of the incorporated graphite particles. In a set of experiments, two groups of cast alloys, Compacted Graphite Iron (CGI) and Spheroida...

Wear Resistance Increase of Samples Tribomating in Oil Composite with Geo Modifier КGМF-1

Increase of wear resistance of different types of tribomating which are functioning in fluid lubrication is possible due to: choosing more expensive and high quality material of samples that is not always sensible; apply...

A Comparative Study on Wear Properties of As Cast, Cast Aged and Forge Aged A356 Alloy with Addition of Grain Refiner and/or Modifier

In the present work, a comparative wear behavior study of three categories of materials viz, as cast, cast aged (casting followed by T6) and forge aged (forging followed by T6) has been investigated. Neither melt treatme...

Wear Analysis of Top Piston Ring to Reduce Top Ring Reversal Bore Wear

The piston rings are the most important part in engine which controls the lubricating oil consumption and blowby of the gases. The lubricating film of oil is provided to seal of gases towards crankcase and also to give s...

Download PDF file
  • EP ID EP460334
  • DOI 10.24874/ti.2018.40.04.05
  • Views 72
  • Downloads 0

How To Cite

K. K. Ikpambese, E. A. Lawrence (2018). Comparative Analysis of Multiple Linear Regression and Artificial Neural Network for Predicting Friction and Wear of Automotive Brake Pads Produced from Palm Kernel Shell. Tribology in Industry, 40(4), 565-573. https://europub.co.uk/articles/-A-460334