Davim J. Paulo (editor). Machining. Fundamentals and Recent Advances
Подождите немного. Документ загружается.
354 S. Deb and U.S. Dixit
The search for the optima in GA is started by taking a number of random
strings forming the population. Choosing an appropriate population size is crucial.
The population of the strings is successively evolved by three operators: reproduc-
tion, crossover and mutation.
In reproduction, the good strings in the population are probabilistically as-
signed to a large number of copies. The fitness of the string decides how good the
string is. In minimization problem, the fitness function can be taken as
11=+
F
() /( f())xx
, (12.32)
For infeasible solution, a very low value of fitness may be assigned. There are
a number of ways to do reproduction. One popular and easy-to-implement method is
the tournament selection. In this, each string plays duel tournaments with two other
randomly chosen strings. In a tournament, the fitnesses of the two strings is compared
and the winning string is retained. It is clear that the best string will always remain and
the worst string will be eliminated from the population. The fate of the other strings is
dependent on chance. Finally, it is expected that, as a result of this operation, the
number of good strings will be more than the bad ones in the population.
The second operation is crossover. In this, two new strings are created by ex-
changing the bits between two strings. For example, consider two strings chosen at
random from a population, called parent strings. A single-point crossover opera-
tion is performed by randomly choosing a crossing site along the string and by
exchanging all the bits on the right-hand side of the crossing site as shown;
010001 111 010001 011
100110 011 100110 111
⇒
||
||
The new strings formed are called the children strings. The crossover operation
is performed with certain a crossover probability, usually lying between 0.75 to
0.95.
In the last operation, mutation, one or more bit of a string may be changed ran-
domly. However, the probability of mutation is kept quite low, between around
0.01 and 0.05. The mutation operation serves the crucial role of preventing the
algorithm from becoming stuck in the local optimum.
After the application of three GA operators in succession, a new generation is
formed and an iteration is said to be complete. The iterations are carried out until
the average fitness in successive generations more or less becomes constant. The
entire methodology is illustrated by a flowchart in Figure 12.14. The application
of GA to machining process optimization has been carried out by a number of
researchers [34–36].
There are other newer population-based techniques that are proving to match the
capabilities of GAs and on occasions outperform GAs. Two such techniques are
particle swarm optimization (PSO) that was developed by Eberhert and Kennedy
[37] and ant colony optimization (ACO) that was first proposed by Dorigo
et al.
[38]. PSO is a population-based algorithm that simulates the social behaviour of
a flock of birds for the search of approximate solutions to optimization problems.
The ACO algorithm is a population-based algorithm that simulates the social
behaviour of a colony of ants for the search of approximate solutions to optimization
Intelligent Machining: Computational Methods and Optimization 355
Figure 12.14. A flow chart illustrating the methodology of genetic algorithm
problems. ACO algorithm has been used for the determination of optimal machin-
ing parameters such as cutting speed, feed, depth of cut and number of cuts in
order to minimize the production cost subject to various machining constraints
such as tool life, surface finish, cutting forces and power, and temperatures [39].
12.7 Future Challenges
Earlier in this chapter, we compared the intelligent system of a machine tool with
a skilled human operator. The performance of a skilled operator is dependent to
356 S. Deb and U.S. Dixit
a great extent on the sensory organs and the brain. Therefore, to develop an intelli-
gent system that is able to function like a skilled operator, it is necessary to develop
good sensors and efficient computing tools. A lot of research needs to be done to
develop effective, compact and low-cost sensors. At the same time, computational
methods and optimization algorithms need to be further improved. The compua-
tional methods that model based on the available data need to be made more robust.
They should be able to eliminate noise from the data and make the best out of the
available information. There should be simultaneous efforts to understand the phys-
ics of the process and use that knowledge to complement the data modelling task.
The proper formulation of optimization problems for different processes and choos-
ing of an efficient algorithm is another area that needs to be explored further. Lastly,
the intelligent system must exploit the developments in Internet technologies, which
requires research in the Internet-based machining area.
References
[1] Szecsi T (1999) Cutting force modelling using artificial neural networks. J Mater
Process Technol 92:344–349.
[2] Hao, W, Zhu, X, Li, X and Turyagyenda, G (2006), Prediction of cutting force for
self-propelled rotary tool using artificial neural networks, Journal of Materials Proc-
essing Technology, Vol. 180, pp. 23-29.
[3] Azouzi R, Guillot M (1997) On-line prediction of surface finish and dimensional
deviation in turning using neural network based sensor fusion. Int J Mach Tools
Manuf 37:1201–1217.
[4] Risbood KA, Dixit US, Sahasrabudhe AD (2003) Prediction of surface roughness and
dimensional deviation by measuring cutting forces and vibrations in turning process.
J Mater Process Technol 132:203–214.
[5] Kohli A, Dixit US (2004) A neural-network-based methodology for the prediction of
surface roughness in a turning process. Int J Adv Manuf Technol 25: 118–129.
[6] Özel T, Karpat Y (2005) Predictive modelling of surface roughness and tool wear in hard
turning using regression and neural networks, Int J Mach Tools Manuf 45:467–479.
[7] Ezugwu EO, Arthur SJ, Hines EL (1995) Tool-wear prediction using artificial neural
networks. J Mater Process Technol 49: 255–264.
[8] Tosun N, Ozler L (2002) A study of tool life in hot machining using artificial neural
networks and regression analysis method. J Mater Process Technol 124:99–104.
[9] Ojha DK, Dixit US (2005) An economic and reliable tool life estimation procedure
for turning. Int J Adv Manuf Technol 26: 726–732.
[10] Sonar DK, Dixit US, Ojha DK (2006) Application of radial basis function neural
network for predicting the surface roughness in turning process. Int J Adv Manuf
Technol 27:661–666.
[11] Chen JC, Black JT (1997), A fuzzy-nets in-process (FNIP) systems for tool-breakage
monitoring in end-milling operations. Int J Mach Tools Manuf 37: 783–800.
[12] Abburi NR, US Dixit (2006) A knowledge-based system for the prediction of surface
roughness in turning process. Robot Comput-Integr Manuf 22: 363–372.
[13] Jang JSR, Sun CT, Mizutani E (2002) Neuro-Fuzzy and Soft Computing – A compu-
tational Approach to Learning and Machine Intelligence. Prentice-Hall of India, New
Delhi.
Intelligent Machining: Computational Methods and Optimization 357
[14] Kosko B (1992) Neural Networks and Fuzzy Systems: a Dynamical Systems Ap-
proach to Machine Intelligence. Prentice-Hall, NJ.
[15] Tsoukalas LH, Uhrig RE (1996) Fuzzy and Neural Approaches in Engineering.
Wiley, New York, NY.
[16] Reddy JN (1993) An Introduction to the Finite Element Method, second edition.
McGraw-Hill, New York, NY.
[17] Cook RD, Malkus DS, Plesha ME (1989) Concepts and Applications of Finite Ele-
ment Analysis, 3rd edn. Wiley, New York, NY.
[18] Bathe KJ (1996) Finite Element Procedures. Prentice-Hall of India, New Delhi.
[19] Grzesik W (2006), Determination of temperature distribution in the cutting zone
using hybrid analytical-FEM technique. Int J Mach Tools Manuf 46: 651–658.
[20] Fang G, Zeng P (2005) Three-dimensional thermo-elastic-plastic coupled FEM simu-
lations for metal oblique cutting processes. J Mater Process Technol 168: 42–48.
[21] Abukhshim NA, Mativenga PT, Sheikh MA (2006) Heat generation and temperature
prediction in metal cutting: A review and implications for high speed machining. Int
J Mach Tools Manuf 46:782–800.
[22] Tay AOO, Lee KH (1992) Calculation of temperature distribution in machining using
a hybrid finite-element-boundary-element method. J Mater Process Technol 29:47–62.
[23] Ozel T (2006) The influence of friction models on finite element simulations of
machining. Int J Mach Tools Manuf 46:518–530.
[24] Joshi VS, Dixit PM, Jain VK (1994) Viscoplastic analysis of metal cutting by finite
element method. Int J Mach Tools Manuf 34:553–571.
[25] Filice L, Micari F, Settineri L, Umbrello D (2007) Wear modelling in mild steel
orthogonal cutting when using uncoated carbide tools. Wear 262: 545–554.
[26] Xie L-J, Schmidt J, Schmidt C, Biesinger F (2005) 2D FEM estimate of tool wear in
turning operation. Wear 258: 1479–1490.
[27] Ahmad MM, Draper WA, Derricott RT (1989) An application of the finite element
method to the prediction of cutting tool performance. Int J Mach Tools Manuf
29:197–206.
[28] Cakir MC, Sik YI (2005) Finite element analysis of cutting tools prior to fracture in
hard turning operations. Mater Des 26:105–112.
[29] Monaghan J, Brazil D (1997) Modelling the sub-surface damage associated with the
machining of particle reinforced MMCs. J Comput Mater Sci 9:99–107.
[30] Wen Q, Guo YB, Todd BA (2006) An adaptive FEA method to predict surface qual-
ity in hard machining. J Mater Process Technol 173:21–28.
[31] Rao SS (1996) Engineering Optimization – Theory and Practice. Wiley and New Age
International (P), New Delhi.
[32] Deb K (2005) Optimization for Engineering Design – Algorithms and Examples.
Prentice-Hall of India, New Delhi.
[33] Deb K (2002) Multi-Objective Optimization Using Evolutionary Algorithms. Wiley,
Singapore.
[34] Wang X, Da ZJ, Balaji AK, Jawahir IS (2002) Performance-based optimal selection
of cutting conditions and cutting tools in multi-pass turning operations using genetic
algorithms. Int J Prod Res 40:2053–2065.
[35] Sarvanan R, Asokan P, Vijyakumar K (2003) Machining parameter optimization for
turning cylindrical stock into a continuous finished profile using genetic algorithm
(GA) and simulated annealing (SA). Int J Adv Manuf Technol 21:1–9.
[36] Abburi NR, Dixit US (2007), Multi-objective optimization of multipass turning
processes. Int J Adv Manuf Technol 32:902–910.
358 S. Deb and U.S. Dixit
[37] Kennedy J, Eberhart R (1995) Particle swarm optimization, Proceedings of the IEEE
international conference on neural networks (Perth, Australia), pp. 1942–1948. Pis-
cataway, NJ.
[38] Dorigo M, Maniezzo V, Colorni A (1996) Ant system: optimization by a colony of
cooperating agents. IEEE Trans Syst Man Cybern 26:29–41.
[39] Vijayakumar K, Prabhaharan G, Asokan P, Saravanan R (2003) Optimization of
multi-pass turning operations using ant colony system. Int J Mach Tools Manuf
43:1633–1639.
Index
Abrasive flow machining (AFM)
317
Abrasive water jet cutting (AWJC)
304
Abrasive wheels
CBN 258
conventional 250
Advanced
metal cutting mechanics 1
methodology 4
non-traditional machining 299
numerical modelling 21
Aerosol
composition 208
supply 202
Carbides 39
Ceramics 43
Chip
formation 105, 129, 281
management 219
Coating 40
Computational methods and
optimization 329
Computer-assisted manufacturing
(CAM) 231
Cooling lubricant 258
Cubic boron nitride (CBN) 44
Cutting
forces 105, 145
forces prediction 239
temperature 108
tools 159
Damage
evaluation methods 183
structural 183
suppression methods 188
Delamination 184
Dies and moulds
five-axis 243
high-speed milling 120
three-axis 242
three-axis deep 245
Dressing
diamond 256
high efficiency 265
Drilling
conditions 189
conventional process 173
unconventional processes 178
Ecological machining 195
Electro-chemical machining 313
Electro-discharge machining (EDM)
307
360 Index
Fine finishing processes 317
Finished surface characteristics 325
Finite element analysis 13
Finite element modelling 1
Friction angles 142, 144
Fuzzy set theory 339
Genetic algorithms 353
Grinding 249
high efficiency 250, 258,
264–266
process parameters 257
wheels 249, 258, 265, 266
Hard
broaching 122
machining (HM) 97, 100, 105,
113, 123
reaming 121
skive hobbing 122
turning 86, 119
Hardness 115, 141
Hole manufacturing 91
Intelligent machining 329
Laser beam machining (LBM) 312
Machine tools 101
Machining
conventional 294
effects of the microscale 272
electro-chemical advanced 313
hard materials 97
hybrid processes 104
nanometric 294
optimization 348
thermo-electric advanced
processes 307
Magnetic abrasive finishing (MAF)
320
Magnetic float polishing (MFP) 323
Manufacturing process 227
Mesh design 16
Metal cutting mechanics 1
Metal matrix composites (MMCs)
127, 130
Method
golden section search 350
sequential quadratic
programming (SQP) 352
Micromachining 271, 282, 324
Milling, five-axis 229
Minor cutting edge 7
Model
Langford and Cohen 278
Usui 280
validation 22
Walker and Shaw 279
Modelling
chip segmentation 15
chip separation 15
contact conditions 19
conventional drilling 179
delamination 185
forces 147
hard cutting process 110
neural network 332
neuro-fuzzy 344
residual stresses 74
tool wear 161
Nanomachining 271, 282, 284
Near-dry machining (NDM) 195
classification 202
system components 217
Numerical
formulations 14
integration 19
Optimization
hard machining processes 123
techniques 350
Polycrystalline diamond (PCD) 45
Polymeric matrix composites
(PMCs) 167
Index 361
Residual mechanical properties
183, 186, 187
Residual stresses 114, 139
Sculptured machining 225
Shear, angle prediction 275
Special tools 190
Super-finishing 89, 117
Surface integrity 59, 113, 129, 135
Surface roughness 113, 135
Taylor’s tool life
expanded formula 55
formula 53
Thermal effects
with microstructural changes 71
without microstructural changes
71
Thrust force 175
Tool
angles 35
life 52
life evaluation 55
materials 37
wear 29, 48, 159
wear evolution 50
wear mechanisms 52
wear types 48
Tool path
five-axis 241
three-axis 240
Tools
geometry 29
material 37
Torque 177
Ultrasonic machining (USM) 301
White layer 115
Workpieces
precision 233
roughness 239
surface integrity 59