Abstract

Cylinder bore honing is a finishing process that generates a crosshatch pattern with alternate valleys and plateaus responsible for enhancing lubrication and preventing gas and oil leakage in the engine cylinder bore. The required functional surface in the cylinder bore is generated by a sequential honing process and is characterized by Rk roughness parameters (Rk, Rvk, Rpk, Mr1, Mr2). Predicting the desired surface roughness relies primarily on two techniques: (i) analytical models (AM) and (ii) machine learning (ML) models. Both of these techniques offer certain advantages and limitations. AM's are interpretable as they indicate distinct mapping relation between input variables and honed surface texture. However, AM's are usually based on simplified assumptions to ensure the traceability of multiple variables. Consequently, their prediction accuracy is adversely impacted when these assumptions are not satisfied. However, ML models accurately predict the surface texture but their prediction mechanism is challenging to interpret. Furthermore, the ML models' performance relies heavily on the representativeness of data employed in developing them. Thus, either prediction accuracy or model interpretability suffers when AM and ML models are implemented independently. This study proposes a hybrid model framework to incorporate the benefits of AM and ML simultaneously. In the hybrid model, an artificial neural network (ANN) compensates the AM by correcting its error. This retains the physical understanding built into the model while simultaneously enhancing the prediction accuracy. The proposed approach resulted in a hybrid model that significantly improved the prediction accuracy of the AM and additionally provided superior performance compared to independent ANN.

References

1.
Grabon
,
W.
,
Pawlus
,
P.
,
Wos
,
S.
,
Koszela
,
W.
, and
Wieczorowski
,
M.
,
2017
, “
Effects of Honed Cylinder Liner Surface Texture on Tribological Properties of Piston Ring-Liner Assembly in Short Time Tests
,”
Tribol. Int.
,
113
(
7
), pp.
137
148
.
2.
Holmberg
,
K.
,
Andersson
,
P.
, and
Erdemir
,
A.
,
2012
, “
Global Energy Consumption Due to Friction in Passenger Cars
,”
Tribol. Int.
,
47
(
3
), pp.
221
234
.
3.
Sabri
,
L.
,
Mezghani
,
S.
,
El Mansori
,
M.
, and
Zahouani
,
H.
,
2011
, “
Multiscale Study of Finish-Honing Process in Mass Production of Cylinder Liner
,”
Wear
,
271
(
3–4
), pp.
509
513
.
4.
ISO, ISO 13565–2:
,
1996
, “
Geometrical Product Specifications (GPS)—Surface Texture: Profile Method; Surfaces Having Stratified Functional Properties—Part 2: Height Characterization Using the Linear Material Ratio Curve
”, pp.
1
6
,
ISO 13565-21996. Geom. Prod. Specif. (GPS)—Surface Texture Profile Method; surfaces having Stratification Function Property. Part 2 Height Character Using Linear Material Ratio Curve, 1996, pp. 1–6, 2
.
5.
Stout
,
K. J.
, and
Blunt
,
L.
,
2000
,
Three Dimensional Surface Topography
,
Elsevier
,
New York
.
6.
Feng
,
C.-X.
,
Wang
,
X.
, and
Yu
,
Z.
,
2002
, “
Neural Networks Modeling of Honing Surface Roughness Parameters Defined by ISO 13565
,”
J. Manuf. Syst.
,
21
(
5
), pp.
395
408
.
7.
Lawrence
,
K. D.
, and
Ramamoorthy
,
B.
,
2016
, “
Multi-Surface Topography Targeted Plateau Honing for the Processing of Cylinder Liner Surfaces of Automotive Engines
,”
Appl. Surf. Sci.
,
365
(
3
), pp.
19
30
.
8.
Pawlus
,
P.
,
Reizer
,
R.
,
Wieczorowski
,
M.
, and
Krolczyk
,
G.
,
2020
, “
Material Ratio Curve as Information on the State of Surface Topography—A Review
,”
Precis. Eng.
,
65
(
9
), pp.
240
258
.
9.
Goeldel
,
B.
,
El Mansori
,
M.
, and
Dumur
,
D.
,
2013
, “
Simulation of Roughness and Surface Texture Evolution at Macroscopic Scale During Cylinder Honing Process
,”
Procedia CIRP
,
8
, pp.
27
32
.
10.
Kersting
,
P.
,
Joliet
,
R.
, and
Kansteiner
,
M.
,
2015
, “
Modeling and Simulative Analysis of the Micro-Finishing Process
,”
CIRP Ann.
,
64
(
1
), pp.
321
324
.
11.
Joliet
,
R.
,
Kansteiner
,
M.
, and
Kersting
,
P.
,
2015
, “
A Process Model for Force-Controlled Honing Simulations
,”
Procedia CIRP
,
28
(
3
), pp.
46
51
.
12.
Zhang
,
X.
,
Zhou
,
Z.
,
Yao
,
Z.
, and
Xi
,
L.
,
2020
, “
Analytically Predicating the Multi-Dimensional Accuracy of the Honed Engine Cylinder Bore
,”
ASME J. Tribol.
,
142
(
9
), p.
091201
.
13.
Pandiyan
,
V.
,
Shevchik
,
S.
,
Wasmer
,
K.
,
Castagne
,
S.
, and
Tjahjowidodo
,
T.
,
2020
, “
Modelling and Monitoring of Abrasive Finishing Processes Using Artificial Intelligence Techniques: A Review
,”
J. Manuf. Process.
,
57
, pp.
114
135
.
14.
Buj-Corral
,
I.
,
Sivatte-Adroer
,
M.
, and
Llanas-Parra
,
X.
,
2020
, “
Adaptive Indirect Neural Network Model for Roughness in Honing Processes
,”
Tribol. Int.
,
141
, p.
105891
.
15.
Sivatte-Adroer
,
M.
,
Llanas-Parra
,
X.
,
Buj-Corral
,
I.
, and
Vivancos-Calvet
,
J.
,
2016
, “
Indirect Model for Roughness in Rough Honing Processes Based on Artificial Neural Networks
,”
Precis. Eng.
,
43
(
1
), pp.
505
513
.
16.
Archer
,
K. J.
, and
Kimes
,
R. V.
,
2008
, “
Empirical Characterization of Random Forest Variable Importance Measures
,”
Comput. Stat. Data Anal.
,
52
(
4
), pp.
2249
2260
.
17.
Didona
,
D.
,
Quaglia
,
F.
,
Romano
,
P.
, and
Torre
,
E.
,
2015
, “
Enhancing Performance Prediction Robustness by Combining Analytical Modeling and Machine Learning
,”
Proceedings of the 6th ACM/SPEC International Conference on Performance Engineering—ICPE
, Vol.
15
,
ACM Press
,
New York, NY,
pp.
145
156
.
18.
Zhou
,
Z.
,
Zhang
,
X.
,
Lv
,
K.
,
Wu
,
J.
,
Yao
,
Z.
, and
Xi
,
L.
,
2020
, “
Honed Surface Multi-Scale Prediction Based on Multi-Stage Honing Process of Engine Cylinder Bore
,”
ASME J. Tribol.
,
142
(
1
), p.
011802
.
19.
Caruana
,
R.
, and
Niculescu-Mizil
,
A.
,
2006
, “
An Empirical Comparison of Supervised Learning Algorithms
,”
Proceedings of the 23rd International Conference on Machine Learning – ICML'06
,
Pittsburgh, PA
,
June 25–29
, Association for Computing Machinery, pp.
161
168
.
20.
Breiman
,
L.
,
2001
, “
Random Forests
,”
Mach. Learn.
,
45
(
1
), pp.
5
32
.
21.
Verikas
,
A.
,
Gelzinis
,
A.
, and
Bacauskiene
,
M.
,
2011
, “
Mining Data with Random Forests: A Survey and Results of New Tests
,”
Pattern Recognit.
,
44
(
2
), pp.
330
349
.
22.
Hastie
,
T.
,
Tibshirani
,
R.
, and
Friedman
,
J.
,
2009
,
The Elements of Statistical Learning: Data Mining, Inference, and Prediction
,
Springer Science & Business Media
,
New York
.
23.
Benardos
,
P. G.
, and
Vosniakos
,
G. C.
,
2003
, “
Predicting Surface Roughness in Machining: A Review
,”
Int. J. Mach. Tools Manuf.
,
43
(
8
), pp.
833
844
.
24.
FEPA
,
1997
, “
FEPA, 61/97 - FEPA Standard for Superabrasives Grain Sizes
.”
25.
Kanthababu
,
M.
,
Shunmugam
,
M. S.
, and
Singaperumal
,
M.
,
2009
, “
Identification of Significant Parameters and Appropriate Levels in Honing of Cylinder Liners
,”
Int. J. Mach. Mach. Mater.
,
5
(
1
), pp.
80
96
.
26.
Sivatte-Adroer
,
M.
,
Buj-Corral
,
I.
, and
Llanas-Parra
,
X.
,
2017
, “
Neural Network Modelling of Abbott-Firestone Roughness Parameters in Honing Processes
,”
Int. J. Surf. Sci. Eng.
,
11
(
6
), pp.
512
530
.
27.
Feurer
,
M.
, and
Hutter
,
F.
,
2019
, “Hyperparameter Optimization,”
Automated Machine Learning
,
Springer
,
Cham
, pp.
3
33
.
28.
Han
,
J.
,
Pei
,
J.
, and
Kamber
,
M.
,
2011
,
Data Mining: Concepts and Techniques
,
Elsevier
,
New York
.
29.
El Mansori
,
M.
,
Goeldel
,
B.
, and
Sabri
,
L.
,
2013
, “
Performance Impact of Honing Dynamics on Surface Finish of Precoated Cylinder Bores
,”
Surf. Coatings Technol.
,
215
(
1
), pp.
334
339
.
30.
Pawlus
,
P.
,
Cieslak
,
T.
, and
Mathia
,
T.
,
2009
, “
The Study of Cylinder Liner Plateau Honing Process
,”
J. Mater. Process. Technol.
,
209
(
20
), pp.
6078
6086
.
31.
Mezghani
,
S.
,
Demirci
,
I.
,
Yousfi
,
M.
, and
El Mansori
,
M.
,
2013
, “
Mutual Influence of Crosshatch Angle and Superficial Roughness of Honed Surfaces on Friction in Ring-Pack Tribo-System
,”
Tribol. Int.
,
66
(
10
), pp.
54
59
.
32.
Saravanakumar
,
P.
,
Manesh
,
K. K.
,
Singaperumal
,
M.
, and
Ramamoorthy
,
B.
,
2009
, “
Modelling of Fluid Continuum Considering 3D Surface Parameters in Hydraulic Assemblies
,”
Precis. Eng.
,
33
(
1
), pp.
99
106
.
You do not currently have access to this content.