Scribd
Upload
3 views

Lab Module9_WSME_P Chart

The document outlines a lab exercise focused on creating a P-Chart to analyze the fraction of defective plastic balls in a quality control context. It includes evaluation criteria, a theoretical background on attributes and defects, a detailed procedure for conducting the experiment, and observations for recording results. The conclusion emphasizes the importance of control limits in determining the statistical quality control of the process.

Uploaded by

Rai Waqas
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
3 views

Lab Module9_WSME_P Chart

The document outlines a lab exercise focused on creating a P-Chart to analyze the fraction of defective plastic balls in a quality control context. It includes evaluation criteria, a theoretical background on attributes and defects, a detailed procedure for conducting the experiment, and observations for recording results. The conclusion emphasizes the importance of control limits in determining the statistical quality control of the process.

Uploaded by

Rai Waqas
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 4

Lab Title: P- Chart for fraction defectives

Course Title: Work Study and Methods Engineering (IE-315 L)


Practical No: _______
Student Name: _____________________________________________
Registration no: _____________________________________________

Evaluation Criteria
Taxonomy Max Marks
Knowledge Components Domain Contribution
Level Marks Obtained

1. To Analyze and Compare nature of


work, methods engineering & work Cognitive Analyze (C4) 20 % 02
measurement techniques.

2. Analyze the different problems of


work study and refine the existing
system (Method, Layout, Material Precision (P3) 10 % 01
Handling, Workers Efficiency and
Reduce Delay.
Psychomotor
3. Demonstration of Charts using
standard symbol and to find out the
Manipulating
Dexterity, Basic time, Bottleneck, 50% 05
(P2)
Allowances and Standard time of
different activities.

Students will be able to Express and


Behave effectively in each Affective Valuing (A3) 20 % 02
Situation/Task/Scenario.

Total Marks 10

Signed by Course teacher/ Lab Instructor


Experiment No. 9
P- Chart for fraction defectives
Aim: To draw P-Chart for fraction defective and to check the control of the process for a given
set of plastic balls.
Apparatus Required:
1) Sample of marble/plastic balls – 500 nos
2) Tray – 1 no
Theory: The quality characteristics, which are not amendable to measurement, are called
attributes. Such characteristics can be identified by their presence or absence from the product.
For example we may say that the surface of the plastic product is cracked or not cracked.
Whether castings produced are having surface defects or not, whether the bottles that have been
manufactured contain holes or not. Thus attributes may be judged either by the proportion or
units that are defective or by the number of defects/unit.
In general the failure to meet the requirement imposed on an item with respect to a single
characteristic is called as a defect. An item the quality of which does not meet the specified
requirements is known as a defective item.
The most widely used attributes control chart is the P- chart. The attributes control charts for
fraction defective (or percent defective) is called the P-chart. Fraction defective may be defined
as the number of defective articles found in any inspection or series of inspection to the number
of articles actually inspected whereas percent defective is 100 times the fraction defective. If ‘P’
represents fraction defective, then the expression for ‘P’ may be written as
No of defectives in a sub group or sample
P = -----------------------------------------------------------
No of inspected in the sub group
Percent defective = 100 P

Generally in a production process a sample of items consisting of different sub groups is taken
and defective items for each sub group are traced by using suitable inspection methods. Then the
fraction defective or percent defective per each sub group will be calculated and these values are
plotted on P –chart.
The central line of the P – chart is expressed as
−
P = average of all fraction defectives

OR
Total number of defectives
P = ------------------------------------------
Total number of pieces inspected
The fraction defectives tend to approach binomial distribution and the control limits (UCL &
LCL) are set at 3σ of the fractional defectives from mean ¯P. Thus the upper and lower control
limits are given by

UCLp = ¯P + 3σ P LCLp = ¯P - 3σ P
Where σP = Standard deviation of the distribution of the fraction defectives. Whenever
calculations give a negative value of LCL of P –chart, that limit is recorded as zero.
PROCEDURE:
1) Take the random samples of size 50 each (n) and make 10 groups.
2) Observe the number of green balls in each sample (di).
3) Find the fraction defective in each sample (di / n). _
4) Calculate the center line or mean fraction defective (P = ΣPi /10).
5) Compute the control limits (UCL & LCL)

6) Draw the P- chart by plotting fraction defectives against each sample.


7) Comment the nature of control of the process.

OBSERVATIONS: sample size = n=50


Sr. Number of defective Fraction defective of
Sample Number (i)
No. Balls (di) sample (Pi = di /n)
1
2
3
4
5
6
7
8
9
10
CONCLUSION: If all the observations are within the upper and lower limits of P- chart, the
process is under statistical quality control. If any value lies outside the control limit, recalculate
¯P ,UCLp, LCLp excluding the data for all those outside lying points. Repeat the process until
all values lie within UCLp & LCLp.

Review Questions
Q#1: Provide an example from a manufacturing setting where a P chart could be effectively
employed for quality control. Discuss the specific variable being monitored and its implications.

Q#2: If a point on the P chart falls outside the control limits, what does this indicate about the
process? How would you distinguish between common cause and special cause variation in this
scenario?

Q#3: How does changing the sample size influence the width and position of the control limits?

You might also like