REPLACEMENT PROBLEM

By

Yogendra Mani Tripathi – Asst. Professor

Faculty of Management and Technology, Harish Chandra PG College

LECTURE CONTENT
 Introduction to Replacement Problem
 Types or Classification of Replacement Problem
 Simple Numerical based on types of Replacement problem
Replacement Problem – Introduction

 In Industries, all equipments are put to continuous use which

reduces the efficiency of the equipment. The study of replacement is
concerned with situations that arise when some items such as
machines, electric-light bulbs, etc., need replacement due to their
deteriorating efficiency, failure or breakdown.

 The deteriorating efficiency or complete breakdown may be either

gradual or all of a sudden. In all such situations, there is a need to
formulate a most economic replacement policy for replacing faulty
units or to take some remedial special action to restore the efficiency
of deteriorating units.

 A replacement is also needed for the equipment if the cost incurred

in operating and maintaining the equipment exceeds the benefit
derived out of it.

 The objective of the Replacement problem is therefore to determine

the optimal time at which the equipment is to be replaced with new
one.
Types of Replacement Problem
Replacement problems, in general, are of three types.
1. Replacement of items that deteriorate with time.
2. Replacement of items that break down completely, and
3. Replacement of items that becomes out of date due to new
developments.

Replacement Model

Replacement of items
Replacement of items that
that detoriated with
falls suddenly
time

Ignoring Time Considering Individual Group

value of time value of Replacement Replacement
money money Policy Policy

REPLACEMENT OF ITEMS THAT DETERIORATE WITH TIME

Generally, the maintenance cost of certain items, e.g., machine, always
increases gradually with time and a stage comes when the maintenance
cost becomes so large that it is better and economical to replace the item
with a new one. There may be a number of alternative choices and in each
choice, we make a comparison between various alternatives by
considering and safety risks, etc.
REPLACEMENT OF ITEMS THAT FAIL COMPLETELY
We always come across practical situations in real life where the failure
of certain item occurs all of a sudden, instead of gradual deterioration
(e.g., the failure of an electric light-bulb). The failure of the item may
result in complete breakdown of the system.
If the time of failure can be predicted, preventive replacement will often
be the appropriate course of action. However, in many cases it may not be
possible to predict failure time accurately. In such cases we shall assume
that the probability distribution of failure time may be obtained, based on
the past experience. Here it is assumed that the failure occurs only at the
end of a certain period, say till time (t). The problem is to determine an
optimal value of ‘t’ so as to minimize the total cost involved in the
system.
We shall consider the following two types of replacement policies:
1. Individual replacement policy: Under this policy, an item is replaced
immediately after its failure.
2. Group replacement policy: Under this policy, we take decision as to
when all the items must be replaced, irrespective of the fact that
items have failed or have not failed, with a provision that if any item
fails before the optimal time, it may be individually replaced.

Numerical based upon Replacement Problem of items that

deteriorates with time
Case – 1 : Replacement Policy when Value of Money does not change
with time
The objective here is to determine the optimum replacement age of an
equipment/ item whose running/maintenance cost increases with time and
the value of money remains static during that period.
Solution: An optimum replacement policy suggest that replace the
equipment at the end of n years, if the average total cost in the (n+1)th
year is more than the average total cost in the nth year and the nth
year’s maintenance cost is less than the previous year’s average total
cost.

Let C = Capital Cost of Equipment, S= scrap value of equipment

n = number of years that equipment would be in use
f (t) =maintenance cost function and, A(n) = Average total annual cost.

Question 1: A firm is considering replacement of a machine, whose cost price is Rs.

12,200 and the scrap value is Rs. 200. The running (maintenance and operating) cost
are found from experience are as follows:

Year 1 2 3 4 5 6 7 8
Running 200 500 800 1200 1800 2500 3200 4000
Cost

When should the machine be replaced?

Solution:

In the problem given above we are provided with running cost f(t), Scrap Value S=200 and the
cost of the machine C = Rs. 12,200.

In order to find out the optimal time n when the machine would be replaced, we will calculate the
average total cost per year during the life of the machine as shown in the table below:

Years Running Cumulative Depreciation Total Cost Average Total Cost

Cost f(n) running cost ∑ f(n) Cost = C-S TC = (3) + (4) A(n)= (5)/(1)
(1) (2) (3) (4) (5) (6)
1 200 200 12000 12,200 12,200
2 500 700 12000 12,700 6,350
3 800 1500 12000 13,500 4,500
4 1200 2700 12000 14,700 3,675
5 1800 4500 12000 16,500 3,300
6 2500 7000 12000 19,000 3,167
7 3200 10200 12000 22,200 3,171
8 4000 14200 12000 26,200 3,275
From the above table we can see that the average total cost A(n) is minimum at the end of 6th
year and then from 7th year onwards it starts increasing, hence we would take a decision to
replace the machine at the end of the 6th year where the value of A(n) is minimum.
Question 2: The data collected in running a machine, the cost of which is
Rs. 60,000 are given below
Year 1 2 3 4 5
Resale Value 42000 30000 20400 14400 9650
Cost of Spares 4000 4270 4880 5700 6800
Cost of Labour 14000 16000 18000 21000 25000

Determine the optimum period for the replacement of the machine.

Solution: To determine the running cost we add the cost of spares and cost of labour.

Years Running Cumulative Resale Depreciation Total Cost Average Total

Cost f(n) running cost ∑ Value Cost = C-S TC = (5) + Cost A(n)=
(1) (2) f(n) (4) (5) (3) (6)/(1)
(3) (6) (7)
1 18000 18000 42000 18,000 36,000 36,000
2 20270 38270 30000 30,000 68,270 34,135
3 22880 61150 20400 39,600 1,00,750 33,583
4 26700 87850 14400 45,600 1,33,450 33,362
5 31800 1,19,650 9650 50,350 1,70,000 34,000

From the above table we can see that the average total cost A(n) is minimum at the end of 4th
year and then from 5th year onwards it starts increasing, hence we would take a decision to
replace the machine at the end of the 4th year where the value of A(n) is minimum i.e Rs. 33,362/-
.
Numerical based upon Replacement Problem of items that fails
suddenly.
It is usually very difficult to predict the time when particular equipment
will fail suddenly. This problem can be overcome by determining the
probability distribution of failures. Also, it is presumed that the failure
occurs only at the end of the period say t.
Thus the objective is to find the value of t which minimizes the total cost
involved for the replacement.
In such situation, there are two types of replacement policies are being
followed:
(a) Individual Replacement Policy : Under this policy, an item is replaced
immediately upon its failure.
(b) Group Replacement Policy: Under this policy, it is decided to replace
all the items after a certain time period irrespective of the facts that items
have failed or have not failed with an option that if any item before the
optimal time, it may be individually replaced.

Question 3: The following failures have been observed for a certain type
of transistors in a digital computer:
End of 1 2 3 4 5 6 7 8
Week
Probability .05 .13 .25 .43 .68 .88 .96 1.00
of failure
to date

Total number of transistors at the beginning of assembly is 1000 units.

The cost of replacing the individual failed transistors is Rs. 1.25/-. The
decision is made to replace all these transistors simultaneously at fixed
intervals and to replace the individual transistors as they fails in service. If
the cost of group replacement is 30 paisa per transistors, what is the best
interval between group replacement?
Solution:
Let Pi be the probability that a transistors which was new when placed in position for use, fails
during the ith week of its life. Thus we have,

P1 = 0.05 P2 = 0.13 – 0.05 = 0.08

P3 = 0.25 – 0.13 = 0.12 P4 = 0.43 – 0.25 = 0.18
P5 = 0.68 – 0.43 = 0.25 P6 = 0.88 – 0.68 = 0.20
P7 = 0.96 – 0.88 = 0.08 P8 = 1.00 – 0.96 = 0.04

Let Ni denotes the number of replacement made at the end of ith week. Then we have,

N0 = Number of transistors at the beginning = 1000

N1 = N0P1 = 1000 * 0.05 = 50

N2= N0P2 + N1P0 = 1000*0.08 + 50*0.05 = 82

N3= N0P3 + N1P2 + N2P1 = 1000*0.12 + 50*0.08 + 82*0.05 = 128

N4= N0P4 + N1P3 + N2P2 + N3P1 = 199

N5= N0P5 + N1P4 + N2P3 + N3P2 + N4P1 = 289

N6 = N0P6 + N1P5 + N2P4 + N3P3 + N4P2 + N5P1 = 272

N7 = N0P7 + N1P6 + N2P5 + N3P4 + N4P3 + N5P2 + N6P1 = 194

N8 = N0P8 + N1P7 + N2P6 + N3P5 + N4P4 + N5P3 + N6P2 + N7P1 = 195

Now, as we know that group replacement of all the 1000 transistors at one go cost 30 paisa per
transistors and the replacement of individual transistors on failure cost Rs.1.25, the average cost
for different group replacement policies are given as under:

End of Individual Total Cost Average Cost

Week Replacement (Individual + Group Replacement)
1 50 50*1.25 + 1000 x 0.30 = 363 363
2 50+82=132 132*1.25 + 1000*0.30 = 465 232.50
3 132+128=260 260*1.25 + 1000 * 0.30 = 625 208.30
4 260+199= 459 459 * 1.25 + 1000 * 0.30 = 874 218.50
5 459+289= 748
6 748+272= 1020
7 1020+194= 1214
8 1214+195 = 1409

Since the average cost is lowest at week 3 hence the optimum interval between group replacement
is 3 weeks.