Академический Документы
Профессиональный Документы
Культура Документы
H. K. D. H BHADESHIA
University of Cambridge, Department of Materials Science and Metallurgy, PembrokeStreet, Cambridge CB23aZ, UK.
E-mail: hkdb@cus.cam.ac.uk www,msm.cam,ac,uk/phase-trans
(Received on April 2. 1999, accepted in final form on June 12. 1999)
There are difficult problems in materials science where the generai concepts might be understood but
which are not as yet amenableto scientific treatment. We are at the sametime told that good engineering
has the responsibility to reach objectives in a cost and time-effective way. Any model which deals with
only a smali part of the required technology is therefore unlikely to be treated with respect. Neural network
analysis is a form of regression or classification modelling which can help resolve these difficulties whilst
striving for longer term solutions. This paper begins with an introduction to neural networks and contains
a review of someapp]ications of the technique in the context of materia]s science.
KEYWORDS:
neural networks; materials science; introduction; applications.
1. Introduction to materials.
3. Linear Regression
~
Most are familiar with regression analysis
scientists (a) (b)
where data are best-fitted to a specified relationship which
is usually linear. The result is
an equation in which each
Fig. 1. (a)
A neulal network representation of linear re-
as linear regression or neural network analysis are only used whenphysical models are not available or whenthe latter are tedious to apply.
f{xj
}
Fig. 2. (a) Three hyperbolic tangent functions; the
different
"strength" of each depends on the weights. (b) A
~ OUtput node
>, ;b
o 2 4 6 8 o 8
x x
o
:b UJ
8 Complexity of model
Fig. 4. Variations in the test and training errors as a function of model complexity, for noisy data in a case wherey
should vary with x3. The filled points were used to create the models (i.e, they represent training data), and
the circles constitute the test data. (a) A
Iinear function which is too simple. (b) cubic polynomial with A
optimum representation of both the training and test data. (c) fifth order polynomial which generalises
A
poorly. (d) Schematic illustration of the variation in the test and training errors as a function of the model
complexity.
ED is expected to Increase if important input variables ated coefficients (the weights). Both the equation
have been excluded from the analysis. WhereasEDgives and the weights can be studied to reveal rela-
an overall perceived level of noise in the output pa- tionships and interactions.
rameter, it is, on its own, an unsatisfying description of
Wenowproceed to discuss specific applications of neural
the uncertainties of prediction. Figure illustrates the 5 networks in the context of materials. There are some
problem; the practice of using the best-fit function (i.e. general principles which emerge; these are emphasisedin
the most probable values of the weights) does not
adequately describe the uncertainties in regions of the
narrow paragraphs.
input space where data are sparse (B), or where the data 7. Welding
are noisy (A).
MacKayhas developed a particularly useful treatment We]ding has seen major applications of the neural
of neural networks in a Bayesian framework,5,6) which network method. Examplesinclude: weld seamtracking
allows the calculation of error bars representing the where the oLutput from sensors is interpreted by a trained
uncertainty in the fitting parameters. The method rec- network to control a welding robot8); the interpretation
ognises that there are many functions which can be of sensor information measured during welding to de-
fitted or extrapolated into uncertain regions of the input termine weld quality9'10); the detection of defects in
space, wlthout unduly compromising the
fit in adjacent welds using ultrasonic, radiation or other signalsll ~ 19)'
reglons which are rich in accurate data. Instead of the estimation of weld profile (including penetration)
calculating a unique set of weights, a probability dis- from varlations in welding parameters or other sensed
tribution of sets of weights is used to define the fitting parameters. 20 - 27)
uncertainty. The error bars therefore become large The use of neural networks is therefore well established
whendata are sparse or locally noisy, as illustrated in in the control and monitoring of welds. Weshall focus
Fig. 5. here on specific applications of greatest interest in
This methodology has proved to be extremely useful materials science. There are other papers in the present
in materials science where properties need to be estimated issue of ISIJ Intel'national, which are not discussed
here.
as a function of a vast array of inputs. It is then most
unlikely that the inputs are uniformly distributed in the
Charpy Toughnessof Steel Weld Metal
input space.
The concept of toughness as a measureof the energy
absorbed durlng fracture is weli-developed.28,29) It is
often measuredusing notched-bar impact tests of which
6. Miscellany
the most
commonis the Charpy test. A square section
Neural networks are often associated with the working notched bar is fractured under specified conditions and
of the humanbrain or with artificial intelligence. This the energy absorbed during fracture is taken as a measure
0.8
~I 0.6 eo
'o
233 K
caE
0.4
~
/::
0.5
O' t~
!~
~5
0.2 o
~l
0.0
1:!
0.0 a)
~D
J::
,~ ~ c:f
o ~~
-0.5
~
~
o
;~
~ \.
-1.0
Fig. 6. Bar chart showing a measure of the model-perceived O 500 1000
significance of each of the input variables in influencing
toughness.30].
/
Oxygen p.p,m.
Fig. 7. Variation in the normalised toughness as a function
of the oxygen concentration. Oxygen is varied here
of toughness. The Charpy test is empirical in that the without changing any of the other inputs. The max-
data cannot be used directly in engineering design. It imumoxygen concentration in the training data was
821 p,p.m.
does not provide the most searching mechanical con-
ditions. The sample has a notch, but this is less than
the atomically sharp brittle crack. Although the test that acicular ferrite greatly infiuences toughness, Ni-
involves impact loading, there is
a requirement to start trogen has a large effect, as is well estab]ished experi-
a brittle crack from rest at the tip of the notch, suggest- mentally.
ing that the test is optimistic in its comparison against a
propagating brittle crack.29) Most materials can be as- A trained neural network is assoclated with reveal-
sumedto contain sub-critical cracks so that the initia- ing parameters other than just the transfer function
tion of a crack seemsseldom to be an issuc. and weights. For example, the extent to which each
The Charpy test is nevertheless
a vital quality con- input explains variations in the output parameter
trol
measure which is specified widely in international can easily be examined.
standards, and in the ranking of samples in research
and development exercises. It is the most common first It is that carbon has such a small effect
surprising
assessment of toughness and in this has (Fig. but what the results really demonstrate is that
6),
sense a proven
record of reliability. The test is usually carried out at a the influence of carbon comes in via the strength and
variety of temperatures in order to characterlse the microstructure. Other trends have been discussed in Ref.
30).
ductilebrittle transition intrinsic to body-centred cubic
metals with their large Peierls barriers to dislocation OxygenInfluences welds in both beneficial and harmful
motion. ways, e.g. by helping the nucleation of acicular ferrite
The toughness of ferritic steel welds has been studied or contributing to fracture by nucleating oxides. The
using neural networks.30) The Charpy toughness was predicted effect of oxygen concentration is illustrated in
Fig. 7 a]ong with the
expressed as a function of the welding process (manual I standard ~
deviation predicted
metal arc or submergedarc), the chemical composition error bars. It is clear that extrapolation into regions where
data are sparse or noisy is identified with large error bars.
(C, Mn, Si. Al, P, S, O&
N), the test temperature and
The training data used for the toughness model had a
the microstructure (primary, secondary, allotriomorphic
ferrite, and acicular ferrite). The
Widmanstatten ferrite, maximum oxygenconcentration of 82 1parts per million.
inclusion of microstructure
greatly limited the quantity
of data available for analysis because few such results Neural network models which indicate appropri-
ately large error bars in regions of the input space
are reported in the literature. Nevertheless, the aim of
the analysis was to see if the network recognised known where the fitting is uncertain
are less dangerous in
trends in toughness as a function of the microstructure. applications than those which simply identify a
global level of noise in the output.
Thewelding process wasnumerically distinguished in the
O I
analysis by using and for the manual and submerged
arc methods. Figure 8showshowthe toughness varies as a function
Figure 6
Illustrates the significance ((T~) of each of the of the manganese concentration and the test temperature,
input variables, as perceived by the neural network, in It is obvious that the effect of temperature is smaller at
influencing the toughness of the weld. As expected, the large concentrations of manganese, i,e, there is an
welding-process has its ownlarge effect; it is well known interaction between the manganeseand temperature.
that submerged arc welds are in general of a lower Thls interaction has been recognlsed naturally by the
quality than manua] metal arc welds. The yield strength model and is expected from a metallurgical point of
has a major effect; it is known that an increase in the view,30)
yield strength frequently leads to a deterioration in the
toughness. It is also widely believed, as seen in Fig. 6,
Neural networks deduce the relationship between The toughness model described above30) js revealing
variables, including any interactions. In complex but nevertheless, Impractical for routine use because the
cases involving many variables, the interactions inputs include the microstructure, which can be difficult
are revealed both qualitatively and quantitatively to predict or measure. This can be resolved by eliminating
by exarnining the predictions, as illustrated in Fig. 8 the microstructural inputs and including the welding
.
~
::h
presented in Table 2, which contains information about 0.6
the range of each variable. It is emphasised however,
O,4 ~
c*
that unlike equation I the informatlon in Table 2cannot OL
,
0.2
be used to define the range of appiicability of the neural
network model. This Is because the inputs are in general
O.
1O,4 O
12 iO
expected to interact. Weshall see later that it is the O 0,08
O_06 0.3 O2
Bayesian framework which allows the calculation of error Carbon wt e'~ ,r
slgnlficant variable Influencing the tensile properties, generallty or to give only qualitative indications of the
both temperature dependence of strengthening
via the trends.41'42) Experiments on the initiation
and prop-
mechanismsand due to variations in the y' fraction wlth agation of cracks In turbine-disc superalloys have faiied
temperature. Since precipitation hardening is a dominant to clarify howfatigue theory could be used to makequan-
strengthening mechanism, it was encouraglng that the titative predictions.
network recognised Ti, Al and Nb to be key factors A neural network
methodhas therefore been used after
controlling the strength. The physical significance of the identifying some variables that could
51 be expected to
neural network was apparent in all the interrogations influence the fatigue crack growth rate in nickel base
performed. superalloys.43) In fact, it is not difficult to compile an
Oneexample illustrating this last point is presented in even larger list of variables which could Influence fatigue
Fig. 10. The softening of the matrix is offset by the
y properties, but an over ambitlous choice of inputs is
remarkable reversible increase in the strength of the y' likely to reduce the number of data available in the
with Increasing temperature. literature.
Fatigue is
one of the most difficult mechanical prop- Thevariables studied included the stress intenslty range
erties An extensive literature review has been
to predict.
AK, Iog{AK} chemical composition, temperature, grain
carried out to assess methods for predicting the fatigue size, heat treatment, frequency, Ioad waveform, atmo-
crack growth rates.41) This Included an examination sphere. R-ratio, the dlstinction between short and long
of physical models, which where either found to lack crack growth, sample thickness and yleld strength. The
analysls wasconducted on some1894 data collected from
lOOO the published literature. The reason for including both
c$ :h AK and log{AK} as inputs is because the latter has
A*
~: 800 ~\\ +1
l' ~ =~\ metallurgical significance since a plot of the logarithm
\ ~ of the crack growth rate versus log{AK} is a simple and
~
~~ 600 \
-- /
/ ~~
\ well-established relationship. However, there mayexist
~~
\ /
~' unknownand separate effects of AK, in which case that
~
C,~
400 ~~
\i
should be included as an additional input. It is
en-
15f couraging that the trained network in fact assigned
~g 200 ~ the greatest significance to log{AK}.
;~ ' Experimental r8sults ~1
~
O O O
Ifa certaln functional relationship Is expected be-
2 O 4 O 6 O 8O 10 12
tween the raw output and a particular input, than
Temperature f 'C that inpLrt can be included twice, in its functional
Fig. lO. Predicted temperature dependence of the yield form and in its raw form. The inclusion of the latter
strength of a y/y' superalloy (after Tancret), prevents bias.
_J
~~ -3
~-4
,,
~o -4
-J
h
e)
~)
c,
\~-5 \~-5
~
hd/ ll-13
um ~
~; ~;
~4;
r::,
-e 40-50 ,hm '~~
\
1~
s]
-e 11-13 uIn
j
/+:
~oo t:'c-7 40-50 ,1
m
-7 ~'
.r'lh
-8 -B
4 e B Io iao 40 4 6 B iO i
~0 40
AK (MPa m~)
~ AK (MPa m~
MPam~)
Fig. Il. Astroloy: (a) effect of grain size alone; (b) effect of heat treatment alone.43)
The model, unlike any experimental approach, could shape and the solidification method.
be used to study the effect of each variable in isolation. Sathyanarayanan et al.46) have developed a neural
This gave interesting results. For example, it was verified network model for the "creep feed grinding" of nickel-
that an increase in the grain size should lead to a decrease 'base superalloys and titanium alloys, using the feed
in the fatigue crack growth rate, when the grain size is rate, depth of cut and wheel bond type as Inputs, and
varied without affecting any other input. This cannot be the surface finish, force and power as outputs.
done in experiments because the change in grain size is
Lattice Parameters of Superalloys
achieved by altering the heat treatment, which in turn
influences other features of the microstructure (Fig. 11). The lattice constants of the
y and y' phases of nickel
superalloys have been modelled using a neural network
It
was also possible to confirm that log{AK} is more within a Bayesian framework.47) The analysis was based
strongly llnked to the fatigue crack growth rate than to
AK, as expected from the Paris law. There are many on newX-ray measurementsand peak separation tech-
niques, for a numberof alloys and as a function of tem-
other metallurgical trends revealed.43)
perature. These data were supplemented using the pub-
lished literature.
The neural network model can in principle be used
Thelattice parameters of the two phases were expressed
to examine the effect of an individual input on the
as a non-1inear functlon of eighteen variables including
output parameter, whereas this be
may incredibly the chemical composition and temperature. It was pos-
difficult to do experimentally. sible to estimate the uncertainties and the method has
proved to be extremely useful in understanding both
In another approach44) a different neural computing
the effect of solutes on the lattice mismatch, and on
approach was used to focus on stage 11 of the Paris
regime, where the growth rate should depend mainly on how this mismatch changes with temperature.
the stress intensity range. Young's modulus and yield
strength. The model was used successfully in estimating 10. Transformations
newtest data. The effect of the ultimate tensile strength Martensite-start Temperature
and phase stability was a]so investigated; although this
Martensite forms without diffusion and has a well-
proved promlsing, it is probable that the results will be
defined start-temperature (Ms), which for the majority
more convincing whena greater range of data become
of engineering steels is only sensitive to the chemical
available.
composltion of the austenite. There are numerous re-
Fatigue Threshold gression equations in the published literature, which
In a recent study of the fatigue thresholds in nickel-base have been used for manydccades in the estimation of
superalloys, Schooling et al. have attempted to compare Ms, mostly as a linear function of the chemical com-
a "neurofuzzy" modelling approach with the classical position. Vermeulen et a/.48) demonstrated that a neu-
neural network.7) The application of fuzzy rules to the ral network model can do this muchmore effectively,
network involves the biassing of the inputs according to and at the same time demonstrated clear interactions
humanexperience. between the elernents. For example, the magnitude of
It
was suggested that the fuzzy method has an ad- the effect of a given carbon content on Ms is much
vantage with restricted datasets because the complexity larger at low manganeselevels than at high
manganese
of the relationships can be restricted by the operator. concentrations. This is in contrast to all published
This conclusion is surprising because the complexity of equations where the sensitivity to carbon is independent
a classical neural network, whenassessed for generalisa- of the presence of other alloying elements.
tion, naturally tends to be minimised for small datasets.
Schooling et al. found it necessary to makesignificant Continuous Cooling Transformation Diagrams
adjustments to the fuzzy rules in order reduce the mean The transformation of austenite as the temperature
decreases during continuous cooling has been modelled
square error to a value comparable to the classical
network. It is evident that there is considerable operator with the neural network method using the chemical
bias introduced in designing fuzzy networks. This composition, the austenitisation temperature and cooling
may rate as inputs.49] The results were concluded to be
not be satisfactory for complexproblems wherethe actual
relatlonships are not understood to begin with. satisfactory but with large errors particularly for the
bainite reaction. Theselarge errors were attributed partly
The comparison of the two methods by Schooling et
al. does not to noise in the experimental data, to the neglect of
seemjustified because the predictions of the austenite grain size as an input, and to the assumption
neurofuzzy methodwere not accompaniedby error bars
that all transformations occur at all cooling rates,
(other than the meansquare error).
whereas this Is not the case in practice.
Creep of Superalloys The network is empirical and hence permits a calcula-
The creep rupture life of nicke] base superalloys has tion of each transformation under all circumstances, even
been modelled as a function of 42 variables including whenthis involves extrapolation into forbidden domains.
Cr, Co, C, Si. Mn, P, S, Mo, Cu, Ti, A1, B, N, Nb, Ta, This difficulty might be avoided by modelling the total
Zr, Fe, W, V, Hf, Re, Mg, La and Th02'45) Other fraction of transformation and the transformation-start
variables include four heat treatment steps (characterised temperatures separately, and then using a logical ruie to
by temperature, duration and cooling rate), the sample determine whether the transformatlon is real or not.
fh
CJ
e*_.
U
,~:
700
oo 02 04 06 08 Io oo a2 04 05 oS Ic
c (Wt. %) c (Wt. %)
940
.~
u v
e*_,
cr)
~ u
.~
7so 820
O1 1 1100 1000
10 O1 1 1 10 100 Iaao
Heating Rate ('C/s) Heating Rate ('C/s)
Fig. 13. (a, b)The predicted variation in the Acl and Ac3 temperatures of plain carbon steels as a function of
the carbon concentration at a heating rate of l'Cs~1. (c,d) The predicted variation in the Acl and Ac3
temperatures of an Fe-0.2 wto/o alloy as a function of the heating rate. In all of these diagrams, the lines
represent the l(T
~error bars about the calculated points. All the results presented here are based on
models with four and two hidden units for the Acl and Ac3 temperatures respectively.
model during extrapolation. As a consequence, the neural There is application which falls in the
one particular
network is likely to violate physical princip]es whenused category of "alloy design"; Asada et a/.78) trained a
without restriction. The continuous cooling transforma- neural network on a database of (Y1_*Ca*)Ba2Cu30_.
tion curve model discussed above49'50) Is an example and Y(Ba2_*Ca*)Cu30=,where -' is generally less than
where the neural network produces information in 7, the ideal number of
oxygen atoms. The output pa-
forbidden domains and produces jagged curves, which a rameter was the superconducting transition tempera-
physical model using the samedata would not because ture as a function of x and z. They were thus able to
the form of the curves would be based on phase predict the transition temperature of YBa2Cu30= doped
transformation theory [e,g. Ref. 69)]. with calclum. It was demonstrated that the highest
temperature is expected for x=0.3 and z=6.5 in
13. Ceramics (Y1_*Ca*)Ba2Cu30=whereas a different behaviour oc-
Ceramic Matrix Composites curs for Y(Ba2_*Ca*)Cu30..
Ceramic matrix composites rely on a weak interface
between the matrlx and fibre. This introduces slip and l 5. Composites
debonding durlng deformation, thus avoidlng the catas- There are manyapplications where vibration informa-
trophic propagation of failure. The mathernatlcal treat- tlon can be used to assess the damagein composite
ment of the deformation has a large numberof variables structures e.g.79 ~ 81) Acoustic emission signals have been
with manyfitting parameters. For an Al203 matrix SiC used to train a neural network to determine the burst
whisker composite a constitutive law has been derived pressure of fiberglass epoxy pr~ssure vessels.82) There has
using an artificial neural network, using inputs generated even been an application trr the detection of cracks in
by finite element analysis.70) eggs.83)
Onedifferentapplication is in the optimisation of the
Hybrid models can be created by training neural curing process for polymer-matrix composites made
networks on data generated by physical models. using thermosetting resins.84) An interesting applica-
tion is the modelling of damageevolution during forging
of AlSiC particle relnforced brake dlscs.85) The authors
Machining and Processing
There are manyexamples where neural networks have were able to predict damagein a brake component
previously unseen by the neural network model.
been used to estimate machine-tool wear. For example,
Ezuguwuet al.71) have modelled the tool 1lfe of a Hwanget cd.86) compareda prediction of the failure
mixed-oxide ceramlc cutting tool as a function of the strength of carbon fibre reinforced polymer composite,
feed rate, cutting speed and depth of cut. Tribology madeusing a neural network model, against the Tsai-Wu
issues in machining, Including the use of neural networks, theory and an alternative hybrid model. Of the three
have been reviewed by Jahanmir.72) models, the neural network gave the smallest root-mean
Neural networks are also used routinely in the control square error. Nevertheless, the earlier commentsabout
of cast ceramic products madeusing the slip casting the validityof the neural network in extrapolation etc.
technique, using variables such as the ambient conditions, remain as a cautionary note in comparisons of neural
and physical models.
raw materlal information and production line settings.73)
In another application, scanning electron microscope
images of ceramic powders were digitised and processed 16. Publication
to obtain the particle boundary profile; this informa-
Theapplication of neural networks in materials science
tlon was then classified using a neural approach, with is
a rapidly growing field. There are numerous papers
exceptionally good results even on unseen data.74) being published but the vast majority are of little use
other than to the authors. This is becausethe publications
almost never include detailed algorithms, weights and
14. Thin Films and Superconductors
databases of the kind necessary to reproduce the work.
A Iotof the materials science type issues about thin Work which cannot be reproduced or checked goes
films naturallyinvolve deposition and characterisation. against the principles of scientlfic publication.
The deposition process can be very compllcated to con- The mlnimuminformation required to reproduce a
trol and is ideally suited for neural network applica- trained network is the structure of the network, the nature
tions. of the transfer functions, the weights corresponding to
Neural networks have been used to interpret Raman the optimised network and the range of each input and
spectroscopy data to deduce the superconducting output variable. Such detalled numerical information is
transition temperature of YBCO thin fiims during the unlikely to be accepted for publication in journals. There
process75); to characterise reflection hlgh-
deposition is
nowa world wide website where this information can
energy electron dlffractlon patterns from semiconductor be logged for common access:
thin films in order to monitor the deposition process76).
wT'vvv.msm.ca,11.ac.uk/map/mcrpmain.html
to rapidly estimate the optical constants of thin films
using the computationa] results of a physical model of It is also good practice to deposit the datasets used in
thin films77). and there are numerous other simi]ar the development of neural networks in this materials
examples. algorithms library.87)
13)
U!trasonics, Ferroe!ectrics andFrecf uenc;,' C0,It,'o!. 45 1
T. W. Liao and K. Tang: Appliec[A,'!~ficia! Inte!!igence,
998). 614.
11 (1997),
( France, (1998), 6-1 to 6-6,
51) L. Gavard, H. K. D. H Bhadeshia, D. J. C. MacKayand S,
l 97 . Suzuki: Mate,', Sci. Technol., 12 (1996), 453.
l 4) A. Masnata and M. Sunseri: NDT &EInt., 29 (1996), 87. 52) S. B. Singh, H. K. D. H. Bhadeshia, D, J. C. MacKay.H. Carey
15) D. Farson and J. Kern: Lase,'s in Enginee"i,1g, 4 (1995), 13. and I. Martin: I,'on,naking Steelmalcing, 25 (1998), 355.
16) L. M. Brown and R. Denale: Nav. Eng. J., 107 (1995), 179. 53) P. Korczak, H. Dyja and E. Labuda: J. Mater. Process. Techno!.,
17) A. McNaband l. Dunlop: Insight, 37 (1995), Il. 80-1 (1998), 481.
I8) E. V. Hill. P. L, Israel and G. L. Knotts: Mater. Eval., 51 (1993), 54) W. G. Vermeulen, A. Bodin and S, van der Zwaag: Stee/ Res.,
l 040. 68 (1997), 20.
19) C. G. Winsdor, F. Anselme. L. Capineri and J. P. Mason: Br. 55) D. Loney, I. Roberts and J. Watson: Ironmaking Steelmaking, 24
J. Non-Desn'. Test., 35 (1993), 15.
(1997), 34.
20) J. D. Brown, M. G. Rodd and N. T. Williams: Ironmaking 56) W. G. Vermeulen. P. J, van der Wolk. A. P. de Weijer and S.
Steelmaki,1g, 25 (1998), 199.
van der Zwaag: J. Mate,'. Eng. Pe,formance, 5 (1996), 57.
21) S. C. Juang, Y, S. Tarng and H. R. Lii: J. Mate". P,'ocess. Tech,10!., 57) C. Dumortier, P. Lehert. P. Krupa and A. Charlier: Mater. Sci.
75 (1998), 54. Forum, 284 (1998), 393.
2,~) P. Li. M. T. C. Fang and J. Lucas: J. Mate". P,'ocess. Tc'cll'70!.,
58) P, Myllykoski: J. Mate,'. Process. Tecll,10!., 79 (1998), 9.
71 (1997). 288. 59) P. Myllykoski. J. Larkiola and J. Nylander: J. Mate,'. P,'ocess,
,~3) Y. M. Zhang, L. L1 and R. Kovacevic: J. Manuf: Sci. Eng.- Techno!., 60 (1996), 399.
Tra,',sactions of'
ASME,119 (1997), 63 1 . 60) Z. Y. Liu, W. D. Wang and W. Gao: J. Mater. P,'ocess. Tech,10l.,
24) H. S. Moonand S. J. Na: J. ManLtf, Sys!., 15 (1996), 392. 57 (1996), 332.
25) R. Kovacevic, Y. M. Zhangand L. Li: Weld. J., 75 (1 996). S3 17. 61) A. Y. Badmos,H. K. D. H. Bhadeshla and D. J. C. MacKay:
26) D Farson. K. Hillsley, J. Sames and R. Young: J. Laser Mate,'. Sci. Tc'chnol., 14 (1998), 793.
Applicafions. 8(1996), 33. 62) A. Y. Badmosand H. K. D. H. Bhadeshia: Mater. Sci. Tecllno!.,
27) Y. M. Zhang. R. Kovacevic and L. Li: 1,1!. J. Mach. Too!s Manuf., 14 (1998), 1221.
36 (1996), 799. 63) V, Narayan. R. Abad-Lera, B. Lopez, H. K. D. H. Bhadeshia
28) J. F. Knott: Fundamentals of Fracture Mechanics. Butter-
and D. J. C. MacKay: ISIJ In!., 39 (1999). 999.
64) C. W. Ulmer. D. A. Smith, B. G. Sumpter and D. I. Noid: 77) Y. S. Ma. X. Liu, P. F. Guand J. F. Tang: App!ied Optics, 35
Comput. Theoretica/ Polym. Sci., 8 (1998), 31 1. (1996), 5035.
65) B.G. SumpterandD.W.Noid:J. Therm.Anal.,46(1996), 833. 78) Y, Asada, E. Nakada, S. Matsumotoand H. Uesaka: Jout'nal of
66) B, G. Sumpter and D. W. Noid: Mac,'omolecula,' Theory and Superconductivity, 10 (1997), 23.
Simulalions, 3(1994), 363. 79) M. Q. Fengand F, Y. Bahng: J. Struct. Eng.ASCE,125 (1999),
67) S. J. Osguthorpe, J. A. Padgett and G. J Price: J.
Joyce. D. J. 265.
80) X. Xu. J. Evans and H. Vanderveldt: Modelling and Control of
Chem.Soc.-Faraday Trans., 91 (1995), 2491 .
68) T. R. Cundari and E. W, Moody: J. Cl7em. Inf. Comput, Sci., 37 Joining Processes, ed. by T. Zacharia. American Welding Society,
(1997), 871 Florida. USA, (1993), 203.
.
69) H. K. D. H. Bhadeshia: MetalSci., 16 (1982), 159. 81) C. Doyle and G. Fernando: Smarl Mate,'ials a,Id St,'uctu,'es, 7
70) H. S. Rao, J. M. DeshpandeandA. Mukherjee: Sci. Eng. Compos. (1998). 543.
Mater., 6 (1997), 225. 82) M. E. Fisher and E. V. Hill: Mater. Eval., 56 (1998), 1395.
71) E. O. Ezugwu, S, J. Arthur and E. L Hines: J. Mater. Process. 83) V. C Patel,R. W. McClendonand J. W. Goodrum: A,'t~ficicd
Technol., 49 (1995), 225, In!e!!igence App!icalions, 10 (1996), 19.
72) S. Jahanmir: Mac:hining Science and Technology, 2 (1998), 137, 84) N. Rai and R, Pitchumani: J. Mater. P,'ocess. Manuf'. Sci., 6
73) S. E. Martinez, A.E.Smith and B. Bidanda: J. Inte!ligentManuf., (1997), 39.
76) A. Bensaoula, H. A. Malki and A. M.Kwari: IEEE Transactions Bhadeshia, The Institute of Materials, London, (1998), 235.
on Semiconducto,' Manufacturing, Il (1998), 421 .