We are IntechOpen,
the world’s leading publisher of
Open Access books
Built by scientists, for scientists
5,400
Open access books available
132,000
International authors and editors
160M Downloads
Our authors are among the
154
Countries delivered to
TOP 1%
most cited scientists
12.2%
Contributors from top 500 universities
Selection of our books indexed in the Book Citation Index
in Web of Science™ Core Collection (BKCI)
Interested in publishing with us?
Contact
[email protected] Numbers displayed above are based on latest data collected.
For more information visit www.intechopen.com
Chapter 19
Robust Design, Sensitivity Analysis,
and Tolerance Setting
Jaroslav Menčík
Additional information is available at the end of the chapter
http://dx.doi.org/10.5772/62373
Abstract
This chapter describes various methods for reduction of uncertainties in the determina‐
tion of characteristic values of random quantities (quantiles of normal and Weibull distri‐
bution, tolerance limits, linearly correlated data, interference method, Monte Carlo
method, bootstrap method).
Keywords: Random quantity, uncertainty, normal distribution, Weibull distribution, tol‐
erance limits, correlation, interference method, Monte Carlo method, bootstrap method
The reliability and safety of engineering objects are mostly formed during the design. Every
design process has three stages:
1. Proposal of conception,
2. Determination of parameters,
3. Setting the tolerances.
Here, stages 2 and 3 will be explained in more detail, as they are very important for reliability.
1. Determination of optimum parameters — Robust design
After the concept of the construction (an engine, a bridge, a transmitter, etc.) has been pro‐
posed, it is necessary to determine all important parameters. However, input quantities often
vary or can attain values different from those assumed in design. Good design ensures that
the important output quantities will always lie within the allowable limits. This can be
© 2016 The Author(s). Licensee InTech. This chapter is distributed under the terms of the Creative Commons
Attribution License (http://creativecommons.org/licenses/by/3.0), which permits unrestricted use, distribution,
and reproduction in any medium, provided the original work is properly cited.
144 Concise Reliability for Engineers
achieved by a suitable choice of nominal values of input quantities and by setting their
tolerances.
The nominal values of input quantities form together the design point. Its position should
ensure the low sensitivity of the output parameters to the deviations of input quantities from
nominal values. This is called robust design [1]. Figure 1 illustrates its principle on an example
with one input variable x: the design point 1 is with high sensitivity, whereas point 2 is with
low sensitivity. One can see that the changes of the output quantity y around point 2 are much
smaller than around point 1, in both cases for the same changes of x. This also means that
acceptable scatter of y can sometimes be achieved with lower demands on the accuracy of input
parameters. The reliability is influenced not only by the scatter of input quantities, but also by
the position of design point. The ideal position, with the lowest sensitivity to the parameter
variations, corresponds to an extreme of the response function y = f(x1, x2, ..., xn). Various
optimization methods exist for finding this position, analytical or with computer modeling.
Universal is the ”simplex method“, where the input variables approach the optimum step-by-
step according to a simple algorithm [2, 3]. The graphical representation of the response is very
informative. Also, the procedures of design of experiments (DOE) are suitable; see books by
G. Taguchi and other authors [4 - 7]. The determination of optimum parameters should go
hand in hand with the sensitivity analysis.
Figure 1. Principle of robust design. Note the influence of the position of the design point on the sensitivity of the out‐
put (∆y) to variations of input variable x.
2. Sensitivity analysis
After the design point has been found, the sensitivity analysis could be made to show the
influence of the variations of input variables on the variability of the output [8]. The results
Robust Design, Sensitivity Analysis, and Tolerance Setting 145
http://dx.doi.org/10.5772/62373
may be used for setting the tolerances of input quantities to keep the output in the allowable
range. The sensitivity analysis can be done using analytical expressions or simulation methods.
The analytical expression for the output variable y,
y = f ( x1 , x2 , ..., xn ) , (1)
is known exactly only in simple cases (e.g. resonant frequency of an oscillator or deflection of
a beam). Often, the response function must be found by numerical solution (e.g. using the
finite element method). Then, an approximate expression is obtained by regression fitting the
response computed for several combinations of input variables (Fig. 3 in Chapter 15).
The sensitivity analysis is usually done in two steps. First, the influence of individual variables
is investigated. Several groups of computations are carried out, and in each group, only one
variable (xi) is changed, whereas the others keep their nominal values x1,0, x2,0, ..., xn,0, corre‐
sponding to the design point. Then, the y values for the individual groups are fitted by a
suitable regression function (e.g. a polynomial),
yi = a0 + ai 1xi + ai 2 xi 2 + ai 3 xi 3 + ...., (2)
or
yi = y0 + ai ( xi - xi ,0 ) + bi ( xi - xi ,0 )2 + ...., (3)
the latter expression characterizes the changes of y as a function of deviations of the i-th input
variable from the design point. These regression functions correspond to the cuts through the
response surface (Fig. 3 in Chapter 15). The sensitivity analysis will depend on whether the
deviations are small or large.
Small changes of the input and output quantities
In this case, linear approximation of the response function may be used, which yields simple
expressions. The sensitivity of the response to the variations of individual variables is
obtained from partial derivatives at the pertinent point,
ci = ¶ y ¶ xi » Dy / Dxi . (4)
For linear approximation, the sensitivity coefficients ci correspond to the constants ai,1 in (2)
and ai in (3). Further information is obtained from relative sensitivities,
¶ y xi , 0 Dy D xi
cr i = » , (5)
¶ xi y 0 y0 xi , 0
where y0 and xi,0 are the values corresponding to the design point. Coefficient cri expresses the
change of y (in %, for example) caused by 1% deviation of xi from the nominal value xi,0. For
linear approximation, cr,i = ai(xi,0 /y0).
146 Concise Reliability for Engineers
Generally, two kinds of sensitivity analysis can be made: (1) deterministic, which assumes that
the deviations of individual quantities from nominal values have constant magnitude, and (2)
stochastic, which assumes the random scatter of individual input quantities around their
nominal values.
Both approaches will be illustrated on an example [9]. A cantilever flat spring of rectangular
cross-section (Fig. 2) should be used in a precise measuring device. It is necessary to get an
idea how the deviations of its individual dimensions and material properties from the nominal
values will influence its compliance. The spring compliance C is given by the formula:
C = y / F = 4 L3 / ( Ewt ) ;
3
(6)
y is deflection, F is load, L is length, E is elastic modulus, w is spring width, and t is spring
thickness.
F
y
L
Figure 2. Spring for a measuring device (a schematic).
Deterministic analysis for small deviations
The incrementsFigure 46. Spring
of y are calculated via thefor
firstaderivatives.
measuring devicesurface
The response (a schematic).
is replaced
by a tangent plane at the investigated point. For y = f(x1, x2,..., xn), the infinitesimal increment
of y can be expressed generally as
dy = (¶y / ¶x1 )dx1 + (¶y / ¶x2 )dx2 + ... + (¶y / ¶xn )dxn , (7)
where ∂y/∂x1 expresses partial derivatives. For practical reasons, the differentials are replaced
by small finite increments ∆,
Dy = (¶y / ¶x1 )Dx1 + (¶y / ¶x2 )Dx2 + ... + (¶y / ¶xn )Dxn . (8)
In our example with the spring, the partial derivative of Equation (6) with respect to the first
variable (x1 = L) is
Robust Design, Sensitivity Analysis, and Tolerance Setting 147
http://dx.doi.org/10.5772/62373
(
¶C / ¶L = 3 L2 ´ 4 / Ewt 3 ) ( )
= é 4 L3 / Ewt 3 ù ´ 3 / L =
ë û ( 3 / L) ´ C, (9)
and the increment of compliance due to a small increment of the beam length ∆L is thus
DC = 3C ( DL / L ) . (10)
The formulas for other variables are obtained in a similar way. The resultant expression,
involving the changes of all variables, is
DC = C( 3DL / L – DE / E – Dw / w – 3Dt / t ) , (11)
and the relative sensitivity of the stiffness is
DC / C = 3DL / L – DE / E – Dw / w – 3Dt / t. (12)
This formula shows the influence of individual quantities. If the spring will be longer by 1%
than the nominal value, the compliance will be higher by 3%; if the elastic modulus E will be
higher by 1%, the compliance will be lower by 1%, etc. The constants at individual terms
correspond to their exponents in Equation (6), and the signs depend on whether the quantity
was in the numerator or denominator.
This preliminary analysis reveals which input quantities have very small influence on the
variability of the output quantity y and may thus be considered as constants in the following
analysis of simultaneous random variance of the input quantities. However, one must always
keep in mind that the variance of the output depends on both the sensitivity ci and the variance
of the pertinent input quantity xi.
Deterministic analysis for large deviations
The above approach is acceptable if the response function is linear or if the errors due to
approximation by linear function are small. If the response function is nonlinear and the
investigated ranges of input quantities are not small, the errors will not be negligible (Fig. 3).
In such case, it is better to study the influence of deviations of input quantities by modeling
the response without simplifications. For example, the influence of j-th variable can be studied
from Equation (1), in which only xj varies, whereas the others keep their values corresponding
to the design point.
Influence of random variability – small scatter
The influence of random variability of input quantities can be investigated using the formula
for the scatter of a function of several random variables. For small scatter,
148 Concise Reliability for Engineers
↓
y(x) ∆(x)
↑
y0
x0 x
Figure 3. Error caused by linear approximation of response function y = f(x).
2 2
æ¶yö æ¶yö æ ¶ y öæ ¶ y ö
sy 2
= çç 2
÷÷ sx 1 + çç
2
÷÷ sx 2 + ... + 2 çç ÷ç
÷ç ÷÷ cov( x1 , x2 ) + ..., (13)
è ¶ x1 ø è ¶ x2 ø è ¶ x1 øè ¶ x2 ø
where sxj2 is the scatter of the j-th variable (quadrate of standard deviation). The far right-hand
term is nonzero if the variables are correlated; often, it can be omitted. For linear approximation
of y,
y = a0 + a1x1 + a2 x2 + ... + an xn , (14)
the scatter is
sy 2 = a12 sx 12 + a2 2 sx 2 2 + ... + an 2 sx n 2 + ... (15)
The individual components, syj2 = aj2sxj2, give the scatter of y caused by random variations of j-
th variable. Similarly to deterministic analysis, the contribution of a certain variable xj to the
total scatter is larger for large scatter of this variable (sxj2) and for large sensitivity (aj) of the
output y to its changes.
The expression obtained by dividing Equation (10) or (12) by the total scatter sy2 gives the
relative proportions of individual factors in the total scatter,
2
sx 1 2 2
sx 2 2 2
sx n 2
1 = a1 + a2 + ... + an + ... (16)
sy 2 sy 2 sy 2
Robust Design, Sensitivity Analysis, and Tolerance Setting 149
http://dx.doi.org/10.5772/62373
The square root of scatter (10) is the standard deviation sy. If the input quantities have normal
distribution, the confidence interval for the output quantity y can be calculated as
ylower,upper = y0 ± ua sy ; (17)
the + or – sign corresponds to the upper (or lower) confidence limit and uα is the α-critical value
of standard normal distribution. The probability that y will lie out of these limits is 2α.
If Formula (12) is applied on the above example with a spring, one obtains the following
expression for the standard deviation of the compliance caused, for example, by random
variability of the length L:
sCL = 3C( sL / L); (18)
cf. Equation (11). Similar expressions can be written for other variables. The random variability
of all input quantities causes the following variability of the spring compliance:
sC = [( 3C / L ) sL 2 + ( C / E ) sE 2 + ( C / w ) sw 2 + ( 3C / t )
2 2 2 2
st 2 ]1/ 2 . (19)
The ratio of the standard deviation of a quantity and its mean is the variation coefficient,
v = s / m, (20)
so that the combination of Equations (16) and (17) gives the variation coefficient of the
compliance,
vC = sC / C = [9 vL 2 + vE 2 + vw 2 + 9 vt 2 ]1/ 2 . (21)
Stochastic analysis for large scatter
The above approach, based on the linearization of the response function, is suitable for small
values of variance coefficients of input quantities, say vj ≤ 10%. If their scatter is large, it is better
to study the influence of variability or deviations of input quantities by the Monte Carlo
simulation method. A preliminary assessment consists of making m simulation experiments
with random variable only xj, for j = 1, 2,... n, and then calculating partial scatter syj2 of the
obtained values y. Using the characteristics sxi, xi,0, and y0, one can determine the variation
coefficients vj or the sensitivity coefficients aj (= sy/sxj).
The approximate value of the total scatter is obtained by summing up the partial scatters,
150 Concise Reliability for Engineers
sy 2 = sy 12 + sy 2 2 + ... + syn 2 + ... (22)
More accurate value is obtained if all input variables, x1, x2, ..., xn are considered as random in
the Monte Carlo simulations, and the scatter is calculated from all values yj. Dividing Equa‐
tion (19) by the total scatter sy2 gives the relative influence of individual factors, like in Equa‐
tion (13).
3. Determination of tolerances of input quantities
If the variability or deviation of the output quantity y from the nominal value is larger than
allowed, it must be reduced. The procedure depends on whether the variability is random or
deterministic.
Deterministic deviations
If the deviation of y is caused by the deviation of one or more input quantities, Equation (12)
or (12), showing the contribution of individual factors to the total deviation of y, can be used
to decide which factor should be aimed at. Let us assume that the deviation of y in Equation
(12) is caused only by the deviation of xj. The allowable magnitude of ∆xj, ensuring that the
deviation of y does not exceed ∆y, is
Dx j £ Dy / ( ¶y / ¶x ) .
j (23)
For example, the allowable length tolerance of the above spring, ensuring the compliance
tolerance ∆C, is
DL = DC ( L / 3C ) , or DL / L = ( 1 / 3 ) ( DC / C ) . (24)
The tolerances of other quantities can be determined in similar way. One must respect that the
deviations of some input quantities influence the output in one direction, whereas the
deviations of other quantities can have the opposite influence. Generally, the deviations of y
depend on the deviations of input quantities and also on the sensitivity of y to the changes of
xj. The reduction of the tolerance of y can thus be accomplished by tightening the tolerances
of individual input quantities or by changing the position of the design point towards lower
sensitivity. The decision will also depend on the costs related to the individual adjustments.
Random variability of input quantities
The following analysis assumes that the range of probable occurrence of y (i.e. the half-width
∆yα of the α-confidence interval for y) is directly proportional to the standard deviation sy,
equal to the square root of the scatter. In production, the allowable limits of a quantity x are
Robust Design, Sensitivity Analysis, and Tolerance Setting 151
http://dx.doi.org/10.5772/62373
also often determined as xnom ± ksx, where k is a constant (e.g. a suitable quantile of standard
normal distribution). With this assumption, the tolerance of y can be reduced from ∆yα to ∆yα'
by reducing the standard deviation of y from the original value sy to sy'. This may be accom‐
plished by the reduction of the variance or influence of input factors.
Often, the influence of one factor prevails (e.g. xk). In such case, most of the scatter of y can be
reduced by reducing its component due to this factor. As it follows from Equation (12), the
scatter of y can be reduced by reducing the standard deviation sx,k or the sensitivity of y to the
changes of xk (coefficient ak). The reduction of variance of yk can be attained by more accurate
manufacturing or by better control and sorting out the components that are out of the tolerance
limits. The reduction of sensitivity of y to the changes of xk can be accomplished by changing
the parameters of the design point (Fig. 1). An example is a prestressed flange connection in
steam turbines: the use of long bolts increases the compliance of the joint and reduces the
sensitivity of the prestress to the variations of pressure in the pipe and thermal dilatations of
the flanges. Sometimes, both ways, the reduction of sx,k and ak is combined.
If several input variables vary, one must decide, which of them should be reduced. As the
standard deviation equals the square root of the scatter, it is obvious that the reduction of
scatter of a quantity, contributing to the total scatter by only 5% to 10%, will have negligible
effect. Also, the costs of the pertinent improving operation must be considered, as they usually
increase with tightening the tolerances.
After having obtained the corrected standard deviation sxi', the lower (L) and upper (U)
allowable limit for the input quantity xj can be determined as
xi , L , U = xi , 0 ± k L , U s x i , (25)
xj,0 is the nominal (design) value and k is a constant (e.g. 5% quantile of standard normal
distribution). kL corresponds to the lower limit, whereas kU corresponds to the upper limit.
The above optimization can be performed even if the scatter sy2 from the preliminary design
is smaller than the allowable value. The optimization assigns such tolerances that the total
costs are minimal. Sometimes, the tolerances may even be made wider, with lower costs.
Often, the scatter of some input quantities cannot be changed continuously. In such cases, the
response must be evaluated for each possible value of every discontinuous quantity.
The determination of suitable tolerances will be illustrated on the following example, adapted
from [9].
Example 1
A cantilever microbeam from Figure 2, with length L = 10 mm, width w = 1.0 mm and thickness
t = 50 μm, made of a material with elastic modulus E = 200 GPa, has compliance C = 4L3/(Ewt3)
= 0.16 mm/mN. Each input quantity has coefficient of variation vl = vw = vt = vE = v = 0.01 = 1%.
The variation coefficient of the compliance, Equation (17), is vC = (9vL2 + vE2 + vw2 + 9vt 2)1/2 =
152 Concise Reliability for Engineers
0.0447, and the standard deviation sC = CvC = 0.00716 mm/mN. Such variation of compliance
is unacceptably high and must be reduced to sC' = 0.004 mm/mN.
Solution. The corresponding reduced variation coefficient is vC' = sC'/C = 0.004/0.16 = 0.025. It
is possible to reduce the scatter of L, w, and t; the material (E) remains unchanged. The easiest
way is to reduce the scatter of L. However, even if this scatter were zero, the variation coefficient
of compliance would be vC' = 0.033, which is much more than demanded. Therefore, the
variance of all three quantities (L, w, and t) must be reduced by more accurate manufacturing.
If the new variation coefficients of L, w, and t would have the same value, vL' = vw' = vt' = v', this
value v' can be calculated from the modified Equation (18):
vC ' = [9 v '2 + vE 2 + v '2 + 9 v '2 )]1/ 2 . (26)
With the variation coefficient of elastic modulus unchanged, vE = 0.01, the new coefficients of
variation of L, w, and t must be reduced to v' ≤ 0.005256, which is approximately v' = 0.005. The
corresponding allowable standard deviations, obtained by multiplying the variation coeffi‐
cient v' by the nominal values of L, w, and t, are sl ' ≤ 0.05 mm, sw' ≤ 0.005 mm, and st' ≤ 0.25 μm.
In the limit case, vC' = 0.024 and sC' = 0.0038 m/N. However, the tolerances of individual
dimensions could be adjusted with respect to the manufacturing possibilities, the principal
condition being sC' ≤ 0.004 m/N.
4. Uncertainties in ensuring safety and lifetime using proof testing
If the high reliability of a certain object must be ensured, a proof-test is often used: the
component is exposed to some overload, specified so that only sufficiently strong components
survive it; the weaker ones are destroyed. In the same way, sufficient lifetime can be ensured
for components made of brittle materials suffering by static fatigue. The minimum time to
failure of a component that has passed a proof-test is [10 - 12]
2 s pt N - 2
tmin = , (27)
( N - 2) AY 2 K IC N - 2s 0 N
where KIC is the fracture toughness of the material, N and A are the parameters of subcritical
crack growth, Y is the geometrical factor of typical crack, responsible for fatigue failure, σ0 is
the characteristic operational stress (assumed constant), and σpt is the proof-test stress. A
rearrangement of Equation (24) gives the formula for the proof stress needed to guarantee the
minimum lifetime:
1 ( N - 2)
N ( N - 2) éN - 2 ù
s pt = s 0 K IC ê AY 2tmin ú . (28)
ë 2 û
However, KIC, N, and A were determined by measurement and are known only approximately
and Y was estimated. Therefore, it is recommended to perform sensitivity analysis and correct
Robust Design, Sensitivity Analysis, and Tolerance Setting 153
http://dx.doi.org/10.5772/62373
the proof stress appropriately. The pertinent theory, based on probabilistic analysis, is
explained in [11, 12] or in [10]. For easier application, strength-probability-time diagrams were
developed [13 – 15], in which the necessary proof stress can be found for the demanded time
to failure and confidence level.
Author details
Jaroslav Menčík
Department of Mechanics, Materials and Machine Parts, Jan Perner Transport Faculty,
University of Pardubice, Czech Republic
References
[1] Dieter G E. Engineering Design. 2nd ed. New York: McGraw-Hill; 1991. 721 p.
[2] Spendley W, Hext G R, Himsworth F R. Technometrics. 1962; 4: No. 4, 441 – 461.
[3] Menčík J. Efficient tools for reliability-based optimisation. In: 2nd ASRANET Interna‐
tional Colloquium, Barcelona, 5-7 July 2004. Universities of Glasgow and Strathclyde,
2004.
[4] Taguchi G. Introduction to Quality Engineering: Designing Quality into Products
and Processes. Tokyo: Asian Productivity Organization; 1986. 191 p.
[5] Ross P J. Taguchi Techniques for Quality Engineering. New York: McGraw-Hill;
1996. 329 p.
[6] Taguchi G, Chowdhury S, Wu Y. Taguchi´s Quality Engineering Handbook. Hobo‐
ken, New Jersey: John Wiley & Sons; 2005. 1696 p.
[7] Fowlkes W Y, Creveling C M. Engineering methods for robust product design. (Us‐
ing Taguchi methods in technology and product development.) New York: Addison-
Wesley; 1995. 432 p.
[8] Novák D, Teplý B, Shiraishi N. Sensitivity Analysis of Structures: A Review. In: Int.
Conf. CIVIL COMP“93, August 1993. Edinburgh, Scotland: 1993. p. 201-207
[9] Menčík J. Reliability-based parameter optimisation and tolerancing in structural de‐
sign. In: 8th Int. Conf. ICOSSAR 2001. Newport Beach, USA. Structural Safety and
Reliability (R B Corotis, G I Schuëller, M Shinozuka, editors. Lisse: A.A. Balkema
Publishers; p. 188
154 Concise Reliability for Engineers
[10] Menčík J. Strength and fracture of glass and ceramics. Amsterdam: Elsevier; 1992.
357 p.
[11] Jacobs D F, Ritter J E jr. Uncertainty in minimum lifetime predictions. J. Am. Ceram.
Soc. 1976; 59: No. 11/12, 481 – 487
[12] Wiederhorn S M, Fuller E R jr, Mandel J, Evans A G. An error analysis of failure pre‐
diction techniques derived from fracture mechanics. J. Am. Ceram. Soc. 1976; 59: No.
9/10, 403 – 411
[13] Davidge R W. Mechanical behaviour of ceramics. Cambridge: Cambridge University
Press; 1979. 174 p.
[14] Davidge R W, McLaren J R, Tappin G. Strength probability time (SPT) relationships
in ceramics. J. Mater. Sci., 1973; 8: No. 12, 1699 – 1705.
[15] Evans A G, Langdon T G. Structural ceramics. Prog. Mater. Sci. 1976; 21: No. 3 – 4,
171 – 441.
