CL 425 Tutorial 3
1. Suppose an engineering variable Y is an exponential function of a random variable X as
follows: Y = e X and X ~ N(2, 0.4). Derive the PDF of Y and show that it follows a
2
1 ln y −
1 −
lognormal distribution. [Ans: fY ( y ) = e 2
, where, = 2.0; = 0.4 ]
2 y
2. The absolute velocity (X) of particles in a gas follows a Maxwell distribution, with the
4 x2 x2
PDF: f X ( x ) = exp − 2 , x 0
a3 a
1
where 𝑎 is a constant. Determine the PDF 𝑓𝑌 (𝑦) for the particle kinetic energy Y = mX 2
2
4 2y 2y
3 exp( − ) y 0
where m is the mass of a particle. Ans : fY ( y) = a m3 ma 2
0
y 0
3. The sources of electrical power for a region are nuclear, fossil, and hydroelectric. The
respective generating capacities of these sources can be described as independent Gaussian
random variables as follows (in megawatt power):
Nuclear: N(100,15)
Fossil: N(200,40)
Hydro: N(400,100)
(a) Determine the total power supply for the region; i.e., define the probability
distribution of the power supply with the corresponding mean and standard
deviation. Ans: T = total power supply N ( 700,58.5) MW
(b) The power demand of the region during normal weather is 400 megawatt, whereas
during extreme weather the demand would be 600 megawatt. In any given year,
normal weather is twice as likely to occur as extreme weather. With the generating
capacity of (a), what is the probability that power shortage for the region (i.e.,
demand exceeding supply) will occur during the year? Ans: 0.667
(c) If power shortage should occur during a given year, what is the probability that it
will occur during normal weather? Ans: 0.5
(d) Suppose that the three power sources are assigned to supply the following respective
percentages of the total power demand:
Nuclear = 15% of demand; Fossil = 30% of demand; and Hydro = 55% of
demand
During normal weather, what is the probability that at least one of the three
sources will be unable to supply their respective allocations? Assume statistical
independence. Ans: 0.027
4. X and Y are traveling from city A to city D. X decides to take the upper route (through B),
whereas Y takes the lower route (through C) as shown in the following figure:
1/5
The travel times (in hours) between the cities indicated are normally distributed as
follows:
T1 ~ N(6, 2)
T2 ~ N(4, l)
T3 ~ N(5, 3)
T4 ~ N(4, 1)
Although the travel times can generally be assumed to be statistically independent, T3
and T4 are dependent with a correlation coefficient of 0.8.
(a) What is the probability that Y will not arrive in city D within 10 hours?
Ans: 0.397
(b) What is the probability that X will arrive in city D earlier than John by at least 1
hour? Ans: 0.327
(c) Which route (upper or lower) should be taken if one wishes to minimize the
expected travel time from A to D? Justify. Ans: Lower route
Ans: Since the lower route (A-C-D) has a smaller expected travel time of TJ = 9
hours as compared to the upper (with expected travel time = TB = 10 hours), one
should take the lower route to minimize expected travel time from A to D.
5. A structure is resting on a soil stratum (see accompanying figure) in which the
compressibility of each of the three layers of soil is well established. The settlement (in cm)
of the building may be evaluated from: S = 0.3 A + 0.2 B + 0.1 C; where A, B, and C are,
respectively, the thickness (in m) of the three layers of soil. Suppose A, B, and C are
modelled as independent normal random variables as follows:
A ~ N(5, 1)
B ~ N(8, 2)
C ~ N(7, 1)
(a) Determine the probability that the settlement will exceed 4 cm. Ans: 0.347
(b) If the total thickness of the three layers is known exactly as 20 m, and furthermore,
thickness A and B are correlated with a correlation coefficient equal to 0.5,
determine the probability that the settlement will exceed 4 cm. Ans: 0.282
2/5
6. The flows in two tributaries 1 and 2 combine to form stream 3 as shown in the figure below.
Suppose the concentration of pollutants in tributary 1 is X, which is normally distributed as
N(20, 4) parts per unit volume (puv), whereas that in tributary 2 is Y which is N(15, 3) puv.
The flow rate in tributary 1 is 600 cubic feet per sec (cfs) and that in 2 is 400 cfs. Hence,
the concentration of pollutants in the stream is
600 X + 400Y
Z= = 0.6 X + 0.4Y
600 + 400
Pollution occurs if pollutant concentration exceeds 20 puv.
(a) What is the probability that at least one of the two tributaries will be polluted?
Ans: 0.524
(b) Assume X and Y are statistically independent. Determine the probability of a
polluted stream. Ans: 0.2282
(c) Suppose the same industrial plant dumps the pollutants into the two tributaries:
hence X and Y are correlated, say with 𝜌 = 0.8. What is the probability of a polluted
stream? Ans: 0.28
7. During the next month, the amount of water available for a city is lognormally distributed
with a mean of 1 million and a c.o.v. of 40%, whereas the total demand is expected to
follow a lognormal distribution with a mean of 1.5 million gallons with a c.o.v. of 10%.
What is the probability of a water shortage in this city over the next month? Ans: 0.883
8. A large parabolic antenna is designed against wind load. During a wind storm, the
1
maximum wind-induced pressure on the antenna, P, is given by: P = CRV 2 ; C = drag
2
3
coefficient, R = air mass density (slugs / ft ), V = maximum wind speed (ft/s), P = pressure
(lb/ft2). P, R and V are statistically independent log-normal variates with the respective
means and cov’s ( ) :
C = 1.8 C = 0.20
R = 2.310−3 R = 0.10
V = 120 V = 0.45
a) What is the pdf of the maximum wind pressure and its mean and variance?
Ans: Lognormal; P = 3.186, P = 0.887
b) What is the probability that the maximum wind pressure will exceed 30lb/ft2?
Ans: 0.596
c) The actual wind resistance capacity of the antenna is also a lognormal random
variable with a mean of 90lb/ft2 and a cov of 0.15. failure of the antenna will
occur whenever the maximum applied wind pressure exceeds its wind resistance
3/5
capacity. During a wind storm what is the probability of failure of the antenna?
Ans: 0.029
d) If the occurrence of wind storms in (c) constitute a Poisson process with a mean
occurrence rate of once every 5 years, what is the probability of antenna failure
in 25 years? Ans: 0.135
e) Suppose 5 antennas were installed in a given region. Wat is the probability that
at least two of the five antennas will not fail in 25 years? Assume that the failures
between the antennas are statistically independent. Ans: 0.138
9. Five cylindrical tanks are used to store oil; each of the tanks is shown below. The weight,
W of each tank and its contents is 200 kips. When subjected to an earthquake, the horizontal
W
inertial force may be calculated as F = a , Where: g = acceleration of gravity = 32.2
g
2
ft/sec ; a = maximum horizontal acceleration of the earthquake ground motion
During an earthquake, the frictional force at the base of a tank keeps it from sliding.
The coefficient of friction between the tank and the base support is a lognormal variate
with a median value of 0.40 and a c.o.v. of 0.20. Also, during an earthquake assume
that the maximum ground acceleration is a lognormal variate with a mean of 0.30g and
a c.o.v. of 0.25%.
(a) What is the probability that during an earthquake a tank will slide from its base
support? Ans: 0.184
(b) Of the five tanks, what is the probability that none of them will slide during an
earthquake, assuming that the conditions between the tanks are statistically
independent? Ans: 0.00021
10. The time T in minutes for each car to clear the toll station on a highway is exponentially
distributed with a mean value of 5 sec. What is the probability that a line of 50 cars waiting
to pay toll at this tunnel can be completely served in less than 3.5 min? Use Central Limit
Theorem (CLT) for solution. Ans: 0.129 The Central Limit Theorem (CLT) states that
sample means of sufficiently large samples (n 30) from any population will be normally
distributed, regardless of the original population's distribution. The formula for
the sampling distribution mean ( x ) and standard deviation ( x ) or the Z-value is:
x −
X N , or Z = .
n n
4/5
11. Manning’s formula which is frequently used for determining the flow capacity (Q) of a
circular storm sewer, is given by: Q = 0.463n−1D2.67 S 0.5 , where Q is the flow rate (ft3/s), n
= roughness coefficient, D is the sewer diameter (ft), and S is the pipe slope (ft/ft).
Due to manufacturing imprecision and construction error, the values of n, D and S are
subject to uncertainty; the statistical properties of the three parameters are given by:
Parameter Mean COV
n 0.015 0.1
D (ft) 3.0 0.02
S (ft/ft) 0.005 0.05
Suppose the parameters are statistically independent.
(a) Using the first order approximation estimate the mean and variance of the sewer flow
( )
capacity Ans: 41.0 ft 3 / s; 22.67 ft 3 / s
2
(b) Compute the percentage of contribution of each random variable to the total uncertainty
of the sewer flow capacity and identify the relative importance of each variable.
Ans: 74.2%,21.2%,4.6%
(c) Assuming that the sewer flow capacity follows the lognormal distribution with the
mean and variance obtained in part (a), determine the reliability that the sewer capacity
can accommodate an inflow of 30ft3/s Ans: 0.996
12. The natural frequency of a single degree of freedom spring mass mechanical system is:
K
= , K = spring stiffness and M is the system mass.
M
(a) If the mean value and standard deviation of K are respectively 400 and 200 and M =
100, determine the first order approximate values of the mean and standard deviation
of the natural frequency of the system. Ans: 2.0; 0.5
(b) Now, if M is also a random variable with standard deviation of 20, determine the
corresponding mean and standard deviation of the natural frequency. Ans: 2.0; 0.54
(c) Determine the approximate second order mean of the natural frequency. Ans: 1.968
5/5