Abstract

The wind turbine and helicopter rotor blades when exposed to dust borne environment are subjected to leading edge erosion because of the impact of dust particles. These blades are manufactured from fiber reinforced polymer (FRP) composites and therefore, it is important to predict the erosion rate of FRP composites. In this paper, the main aim is to accurately predict the erosion rate of uni-directional FRP composites using machine-learning algorithms like artificial neural networks (ANNs) and extreme gradient boosting (XGB) and compare between the algorithms. The model uses input parameters like erodent impact angle, velocity of erodent particle, fiber orientation, and fiber volume fraction as the input and erosion rate as the output variable. The total dataset considered for training and testing the model is obtained from two parts. The first part of the dataset is obtained from the literature and the other part is collected from performing in-house experiments on uni-directional glass fiber reinforced polymer (GFRP) composites. The crater profiles of the tested specimens are characterized using 3D Alicona imaging microscopy. The machine-learning models considered in this study provide accurate results on the dataset. However, the XGB method is more robust, reliable, and faster to train and more accurate than the ANN model in the case of an unknown dataset (dataset not used for training). The feature importance from the XGB model suggests that impact particle velocity, impact angle, and fiber orientation are the most important input features. The model predictions by taking into account the three input features provide accurate results without affecting the accuracy of the model.

References

1.
Barkoula
,
N. M.
, and
Karger-Kocsis
,
J.
,
2002
, “
Effects of Fibre Content and Relative Fibre-Orientation on the Solid Particle Erosion of GF/PP Composites
,”
Wear
,
252
(
1–2
), pp.
80
87
.
2.
Pool
,
K. V.
,
Dharan
,
C. K. H.
, and
Finnie
,
I.
,
1986
, “
Erosive Wear of Composite Materials
,”
Wear
,
107
(
1
), pp.
1
12
.
3.
Mathias
,
P. J. J.
,
Wu
,
W.
,
Goretta
,
K. C. C.
,
Routbort
,
J. L. L.
,
Groppi
,
D. P. P.
, and
Karasek
,
K. R. R.
,
1989
, “
Solid Particle Erosion of a Graphite-Fiber-Reinforced Bismaleimide Polymer Composite
,”
Wear
,
135
(
1
), pp.
161
169
.
4.
Deliwala
,
A. A.
,
Peter
,
M. R.
, and
Yerramalli
,
C. S.
,
2018
, “
A Multiple Particle Impact Model for Prediction of Erosion in Carbon-Fiber Reinforced Composites
,”
Wear
,
406–407
, pp.
185
193
.
5.
Deliwala
,
A. A.
, and
Yerramalli
,
C. S.
,
2020
, “
Computational Micromechanical Modelling of the Material Removal Process in a Carbon Fibre Composite Under Single-Erodent Particle Impact
,”
Proc. Inst. Mech. Eng. Part J J. Eng. Tribol.
,
234
(
10
), pp.
1605
1617
.
6.
Ahmed
,
D. A.
, and
Yerramalli
,
C. S.
,
2020
, “
Experimental and Computational Analysis of the Erosion Behaviour of Unidirectional Glass Fiber Epoxy Composites
,”
Wear
,
462–463
, p.
203525
.
7.
Biswas
,
S.
, and
Satapathy
,
A.
,
2009
, “
Tribo-Performance Analysis of Red Mud Filled Glass-Epoxy Composites Using Taguchi Experimental Design
,”
Mater. Des.
,
30
(
8
), pp.
2841
2853
.
8.
Velten
,
K.
,
Reinicke
,
R.
, and
Friedrich
,
K.
,
2000
, “
Wear Volume Prediction With Artificial Neural Networks
,”
Tribol. Int.
,
33
(
10
), pp.
731
736
.
9.
Zhang
,
Z.
,
Barkoula
,
N. M.
,
Karger-Kocsis
,
J.
, and
Friedrich
,
K.
,
2003
, “
Artificial Neural Network Predictions on Erosive Wear of Polymers
,”
Wear
,
255
(
1–6
), pp.
708
713
.
10.
Zhang
,
Z.
,
Friedrich
,
K.
, and
Velten
,
K.
,
2002
, “
Prediction on Tribological Properties of Short Fibre Composites Using Artificial Neural Networks
,”
Wear
,
252
(
7–8
), pp.
668
675
.
11.
Jiang
,
Z.
,
Zhang
,
Z.
, and
Friedrich
,
K.
,
2007
, “
Prediction on Wear Properties of Polymer Composites With Artificial Neural Networks
,”
Compos. Sci. Technol.
,
67
(
2
), pp.
168
176
.
12.
Harsha
,
A. P.
, and
Nagesh
,
D. S.
,
2007
, “
Prediction of Weight Loss of Various Polyaryletherketones and Their Composites in Three-Body Abrasive Wear Situation Using Artificial Neural Networks
,”
J. Reinf. Plast. Compos.
,
26
(
13
), pp.
1367
1377
.
13.
Suresh
,
A.
,
Harsha
,
A. P.
, and
Ghosh
,
M. K.
,
2009
, “
Solid Particle Erosion Studies on Polyphenylene Sulfide Composites and Prediction on Erosion Data Using Artificial Neural Networks
,”
Wear
,
266
(
1–2
), pp.
184
193
.
14.
Mishra
,
A.
,
Pradhan
,
D.
,
Behera
,
C. K.
,
Mohan
,
S.
, and
Mohan
,
A.
,
2019
, “
Modeling and Optimization of Parameters for High-Temperature Solid Particle Erosion of the AISI 446SS Using RSM and ANN
,”
Mater. Res. Exp.
,
6
(
2
), p.
026513
.
15.
Zahedi
,
P.
,
Parvandeh
,
S.
,
Asgharpour
,
A.
,
McLaury
,
B. S.
,
Shirazi
,
S. A.
, and
McKinney
,
B. A.
,
2018
, “
Random Forest Regression Prediction of Solid Particle Erosion in Elbows
,”
Powder Technol.
,
338
, pp.
983
992
.
16.
Bahrainian
,
S. S.
,
Bakhshesh
,
M.
,
Hajidavalloo
,
E.
, and
Parsi
,
M.
,
2021
, “
A Novel Approach for Solid Particle Erosion Prediction Based on Gaussian Process Regression
,”
Wear
,
466–467
, p.
203549
.
17.
Chen
,
T.
, and
Guestrin
,
C.
,
2016
, “
XGBoost: A Scalable Tree Boosting System
,”
Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining
,
San Francisco, CA
,
Aug. 13–17
, pp.
785
794
.
18.
Friedman
,
J. H.
,
2001
, “
Greedy Function Approximation: A Gradient Boosting Machine
,”
Ann. Stat.
,
29
(
5
), pp.
1189
1232
.
19.
Nguyen-Sy
,
T.
,
Wakim
,
J.
,
To
,
Q. D.
,
Vu
,
M. N.
,
Nguyen
,
T. D.
, and
Nguyen
,
T. T.
,
2020
, “
Predicting the Compressive Strength of Concrete From Its Compositions and Age Using the Extreme Gradient Boosting Method
,”
Constr. Build. Mater.
,
260
, p.
119757
.
20.
Zhang
,
J.
,
Li
,
D.
, and
Wang
,
Y.
,
2020
, “
Toward Intelligent Construction: Prediction of Mechanical Properties of Manufactured-Sand Concrete Using Tree-Based Models
,”
J. Clean. Prod.
,
258
, p.
120665
.
21.
Ferreño
,
D.
,
Sainz-Aja
,
J. A.
,
Carrascal
,
I. A.
,
Cuartas
,
M.
,
Pombo
,
J.
,
Casado
,
J. A.
, and
Diego
,
S.
,
2021
, “
Prediction of Mechanical Properties of Rail Pads Under In-Service Conditions Through Machine Learning Algorithms
,”
Adv. Eng. Softw.
,
151
, p.
102927
.
22.
Miyazaki
,
N.
, and
Hamao
,
T.
,
1996
, “
Effect of Interfacial Strength on Erosion Behavior of FRPs
,”
J. Compos. Mater.
,
30
(
1
), pp.
35
50
.
23.
Barkoula
,
N. M.
, and
Karger-Kocsis
,
J.
,
2002
, “
Solid Particle Erosion of Unidirectional GF Reinforced EP Composites With Different Fiber/Matrix Adhesion
,”
J. Reinf. Plast. Compos.
,
21
(
15
), pp.
1377
1388
.
24.
Tewari
,
U. S.
,
Harsha
,
A. P.
,
Häger
,
A. M.
, and
Friedrich
,
K.
,
2002
, “
Solid Particle Erosion of Unidirectional Carbon Fibre Reinforced Polyetheretherketone Composites
,”
Wear
,
252
(
11–12
), pp.
992
1000
.
25.
Tewari
,
U. S.
,
Harsha
,
A. P.
,
Häger
,
A. M.
, and
Friedrich
,
K.
,
2003
, “
Solid Particle Erosion of Carbon Fibre- and Glass Fibre-Epoxy Composites
,”
Compos. Sci. Technol.
,
63
(
3
), pp.
549
557
.
26.
Minsky
,
M.
,
Papert
,
S. A.
, and
Bottou
,
L.
,
2017
,
An Introduction to Computational Geometry
,
L.
Bottou
, ed.,
MIT Press
,
Cambridge, MA
, pp.
501
522
.
27.
Müller
,
A. C.
, and
Guido
,
S.
,
2016
,
Introduction to Machine Learning With Python: A Guide for Data Scientists
,
O’Reilly Media
,
CA, USA
.
28.
Chollet
,
F.
,
2021
,
Deep Learning With Python
, 2nd ed.,
Manning
,
New York
.
29.
Friedrich
,
K.
,
1986
, “
Erosive Wear of Polymer Surfaces by Steel Ball Blasting
,”
J. Mater. Sci.
,
21
(
9
), pp.
3317
3332
.
30.
Roy
,
M.
,
Vishwanathan
,
B.
, and
Sundararajan
,
G.
,
1994
, “
The Solid Particle Erosion of Polymer Matrix Composites
,”
Wear
,
171
(
1–2
), pp.
149
161
.
You do not currently have access to this content.