This document is posted to help you gain knowledge. Please leave a comment to let me know what you think about it! Share it to your friends and learn new things together.
Transcript
Slide 1
PROCESS CAPABILITY AND STATISTICAL PROCESS CONTROL
OPERATION/PRODUCTION MANAGEMENT Group III
Slide 2
REPORTERS: Ester D. Gamad: 1.The Basics of Statistical Process
Control 2.Control Charts 3.Control Charts for Attributes Cecilia T.
Panghulan 1.Control Charts for Variables 2.Control Chart Patterns
3.SPC with Excel and OM Tools 4.Process Capability
Slide 3
The Basics of Statistical Process Control Statistical Process
Control (SPC) is a statistical procedure using control charts to
see if any part of the production process is not functioning
properly and could cause poor quality. used to inspect &
measure the production process to see if it is varying from what is
supposed to be doing & if there is unusual or undesirable
variability, process is corrected so that the defects will not
occur.
Slide 4
To Achieved Process Control Take Samples from the process and
plot the sample points on a chart to see if the process with in the
statistical limits. Sample can be single item or group of items. If
sample is outside limits, process maybe out of control, cause is
sought so that the problem can be corrected. If sample is within
the control limits process continuous without interference but with
continued monitoring. In order that the SPC to be effective, it
requires continuous comprehensive training of employees of SPC
methods.
Slide 5
All Processes Contain Certain Amount of Variability Two Reasons
of Variability 1. Natural Occurrence : Inherent random variability
of the process which depends on the following: a) Equipment &
machinery b) Engineering c) Operator d) System used for
measurements minor factors, impact of the process is negligible
Ex.: older machines generally exhibit a higher degree of natural
variability than new machines because of worn parts & new
machines may incorporate design improvements that lessen the
variability in the output 2
Slide 6
2. Unique or Special causes that are identifiable and can be
corrected and if left unattended will cause poor quality: equipment
that is out of adjustment changes in parts or materials broken
machinery or equipment operator fatigue or poor work methods errors
due to lack of training
Slide 7
Several Quality Control Tools in identifying causes of the
Problem: 1. brainstorming - technique in which group of people
share thoughts & ideas on the problem in a relaxed atmosphere
that encourages unrestrained collective thinking & the goal of
which is to generate free flow of ideas on identifying problems,
and finding causes, solutions and ways to implement the
solutions.
Slide 8
2.Check Sheets a format that enable the users to record &
organize data in a way that facilitate collection & analysis.
It deals with types of defects; location of defects and the time of
day each occurred. 3. Histograms useful in getting a sense of
distribution of observed values. These can be observed if the
distribution is symmetrical, what the range of values is and if
there are any unusual values.
Slide 9
4. Pareto Charts diagram that arranges categories from highest
to the lowest frequency of occurrence. 5. Fishbone diagram used to
organize a search for the cause of a problem. If problem can not be
corrected by employee, management should initiate problem solving
activity with in a group which may include other employees,
engineers & quality experts.
Slide 10
How Can the Quality of Product or Service be Evaluated? The
Quality of Product or Service can be evaluated by using the
following: 1.Attribute of a products or service 2.Variable measure
of product or service Attribute - a product characteristic such as
color, surface texture, cleanliness, or perhaps smell or taste.
Known as Qualitative Classification Method
Slide 11
Attributes can be evaluated with discrete response such as: 1.
good or bad 2. acceptable or not 3. yes or no Example of attribute
test to determine the product is defective or not: Operator might
test a light bulb by simply turning it on and seeing if it
lights.
Slide 12
Variable measure a product characteristics that is measured on
a continuous scale such as length, weight, temperature or time.
Example : the amount of liquid detergent in a plastic container can
be measured to see if it conforms to the company product
specification. Known as Qualitative Classification Method.
Slide 13
Variable Classification is more informative because of its
measurements that provides more information about the product.
Example: the weight of a product is more informative than simply
saying the product is good or bad. Control Charts historically have
been used to monitor the quality of manufacturing processes &
quality in services.
Slide 14
Control Charts for service processes tend to use quality
characteristics and measurements such a time & customer
satisfaction which is determined by surveys, questionnaires or
inspections. Following are example of services monitored with
control charts. 1. Hospitals: Timeliness & quickness of care;
staff responses to requests; accuracy of Lab Tests; cleanliness;
courtesy; accuracy of paperwork; speed of admittance &
checkouts.
Slide 15
2. Grocery Stores : waiting time to checkout; frequency of
out-of-stock items; quality of food items; cleanliness; customer
complaints; checkout register errors. 3.Airlines: Flight delays;
lost luggage & luggage handling; waiting time at ticket
counters & check-in; agent and flight attendant courtesy;
accurate flight information; passenger cabin cleanliness &
maintenance. 4.Fast food restaurants: waiting time for service;
customer complaints; cleanliness; food quality; order accuracy;
employee courtesy.
Slide 16
Control Charts - Graphs that visually show if a sample is with
in the statistical control limits. -used at critical points in the
process where historically the process has shown to go out of
control and at points where if the process goes out of control it
is particularly harmful & costly. Control Charts exist for
Attributes & Variables
Slide 17
Commonly used control charts: 1. Attributes 2. Variables a)
p-Charts a. mean (x) b) c- Charts b. range (R) Control charts
differ in how they measure process control but have certain similar
characteristics. They have a line through the center of a graph
indicating the process average and lines above & below
representing the upper & lower limits of the process.
Slide 18
Upper Control limit Process Average Lower control limit 1 2 3 4
5 6 7 8 9 10 Sample Number PROCESS CONTROL CHART Out of control z
represent number of standard deviations from the process average
according to normal distribution equal to 3.00 which corresponds to
a normal probability of 99.74%
Slide 19
Control Charts for Attributes: - discrete values reflecting a
simple decision good or bad. 1.p-Chart is used to monitor the
proportion of defective items generated in the process. -
appropriate when a data consist of two categories of items.
Observation that can be classified into: good or bad; pass or fail;
operate or dont operate - the data consist of multiple samples
each.
Slide 20
A sample of n items is taken periodically on service process
and the proportion of defective items in the sample is determined
to see if the proportion falls within the control limits on the
chart. Formulas : Upper Limit - UCL = p + z p Lower Limit LCL = p z
p z - the number of standard deviations from the process average. p
the sample proportion defective; estimate z p - standard deviation
of the sample proportion z p = p(1-p) n n sample size
Slide 21
Example: 20 samples containing 100 pairs of denim jeans (n=100
) 99.74% or z=3.00. The company has taken 20 samples 1 per day for
20 days. Proportion defective for population is not known.
SampleNo. of DefectiveProportion Defective 16.06 20.00 34.04 410.10
56.06 64.04 712.12 810.10 98.08
Prepare a p-chart. P= total defective = 200 = 0.10 total sample
observations 20(100) Upper control Limit UCL =p + z p(1-p) n = 0.10
+ 3 0.10 (1-0.10) = 0.190 100 Lower Control Limit LCL = p-z p(1-p)
n = 0.10- 3 0.10 (1-0.10) = 0.010 100
Slide 24
UCL =0.190
Slide 25
Day 2 = 0.0 below the lower control limit of 0. 010 means very
few defects may suggest something was wrong with the inspection
during the week; should be checked out management want to know what
caused the quality of the process to improve; perhaps better denim
material from the supplier that week or different operator was
working. Day 19 = 0.20 above upper limit of 0. 190 process not in
control & cause should be investigated. Causes could be
defective or maladjusted machinery; problem with operator;
defective materials or other correctable problems.
Slide 26
There is an upward trend in the number of defectives throughout
the 20-day test period. The process was consistently moving toward
an out-of-control situation wherein the pattern in the observations
suggests a nonrandom cause which would make the operator alerted to
make corrections.
Slide 27
Example of occurrences & unit of measure: 1.Scratches,
chips, dents or errors per item. 2.Cracks or faults per unit of
distance. 3.Breaks or tears per unit of area. 4.Bacteria or
pollutants per unit of volume. 5.Calls, complaints, failures,
equipment breakdown or crime per unit of time 2. c-chart used to
control the number occurrence of defects per unit when it is not
possible to compute a proportion defective.
Slide 28
Formula for Control Limits: Upper Control Limit UCL = c + z c
Lower Control Limit LCL = c + z c c = total number of defects
number of samples Example: Ritz house Hotel -240 rooms;
Housekeeping Dept. responsible for maintaining the quality of the
rooms cleanliness & appearance; 20 rooms per 1 housekeeper;
housekeeping supervisor inspected every room each day; management
had detailed inspection at random for quality-control purposes;
inspection sample 12 rooms which is one room selected at random
from each of the twelve 20 room blocks service by a
housekeeper.
Slide 29
99% defects or 3.00 of the defects caused by natural,random
variations in the house keeping and room maintenance service &
1% caused by non-random variability by nonrandom variability.
Sample Number of Defects 112 28 316 414 510 611 79
Slide 30
Sample Number of Defects 814 913 1015 1112 10 1314 17 15 190 c
= 190 = 12.67 15
Slide 31
Upper Control Limit UCL = c + z c = 12.67 + 3 12.67 = 23.35
Lower Control Limit LCL = c -z c = 12.67 -3 12.67 = 1.99
Slide 32
All the sample observations are within the control limits,
suggesting that the room quality is in control. This chart would be
considered reliable to monitor the room quality in the future.