Understanding Shewhart Variation in SPC
Uploaded by
ScribdTranslationsUnderstanding Shewhart Variation in SPC
Uploaded by
ScribdTranslationsCHIMBORAZO POLYTECHNIC HIGHER SCHOOL
FACULTY OF ANIMAL SCIENCES
SCHOOL OF ENGINEERING IN LIVESTOCK INDUSTRIES
TEMA:PREGUNTAS DE ANÁLISIS
1. Mention the two types of Shewhart variation. What else are they called?
llama?
Types of Shewhart variation: common and special causes are also called
natural and assignable variation.
2. Define 'under statistical control'.
A process is said to be operating under statistical control when the only source
of variation is natural or common causes.
3. Briefly explain what the graph does and the
̅ graphicalR.
The bar graph X indicates whether there have been changes in the central tendency of a
process; the R-chart indicates whether there has been a gain or a loss in the
uniformity.
4. What could cause a process to be out of control?
A process can be out of control due to assignable variation, which can be
traced to specific causes. Examples include factors such as:
Tool wear
A change in raw materials
A change in the work environment (temperature or humidity, for example)
The tired or poorly trained work.
5. Enliste los cinco pasos a seguir en el desarrollo y uso de gráficas
̅ and graphicsR.
The 5 steps are:
1. Collect 20 to 25 samples, often of n = 4 or 5 each; calculate the mean and the
range of each sample.
2. Calculate the general means (x and R), establish appropriate control limits, by
generally at a level of 99.73%, and the calculation of the upper and lower control limits
preliminaries. If the process is not stable, use the desired medium, μ, instead of x
for the calculation of limits.
3. Graph the sample means and the ranges of their respective control charts.
and determine if they fall outside the acceptable limits.
4. Investigate points or patterns that indicate the process is out of control. Try
to assign causes of the variation, against the causes, and then resume the process.
5. Collect additional samples and, if necessary, revalidate the control limits
using the new data.
6. List some possible causes of assignable variation.
The list of text includes machine wear, misaligned equipment, workers
fatigued or untrained, the new batches of raw materials, etc. Others could be
bad measuring device, the lighting of the workplace, other conditions
ergonomic.
7. Explain why it is easier for a person to find samples 'outside of the
"limits" if using the 2 sigma control charts than with the 3 control charts
sigma. What are some possible consequences of this fact?
Two sigmas cover only 95.5% of the total natural variation; even in the absence of
Assignable cause, points will fall outside the control limits 4.5% of the time.
8. When is the desired mean, μ, used instead of to establish the center line
from a control chart ? ̿
The desired average is used when the average of an observed process is
unknown or out of control or when there is an established or known μ,
provided by the manufacturer or designer of the equipment or process.
9. Will a production process be marked as 'out of control' because it is
Too good? Explain your answer.
It means that the process has changed. If we are doing something 'too well',
so the process has changed from the norm. We want to know what we are
doing "very well", so we cannot do the same in the future and for others
products.
10. In a control chart, what would be the effect on the control limits if the
Does the sample size vary from one sample to another?
Control charts are designed for specific sample sizes because
The sample standard deviation or the interval depends on the sample size.
The control charts presented here should not be used if the size of the
Sample varies.
11. Defina Cpk y explique lo que significa un Cpk de 1.0. ¿Qué es la Cp?
It is the process capability index, it is a way to express the capacity of the
process. The proportion of natural variation (3 σ) is measured against the center of the process
and the nearest specification limit.
Check the process capability ratio and determine if the process meets the requirements.
design specifications.
12. What does a 5 point run above or below the central line imply in a
control chart?
A '5 run' implies that assignable variation is present.
What are the acceptable quality level (AQL) and the percentage of defects?
tolerated in the lot (LTPD)? How are they used?
The NCA is the quality level of a batch considered as good.
The LTPD is the quality level of a lot that we consider bad. These are combined with
the risk levels to determine an acceptance sampling plan.
14. What is a test run and when is it used?
It is a functional test used to help abnormalities occurring in a
graphic control process. It is used if the points are not individually outside of
control, but they form a pattern above or below the nominal line (center).
15. Analyze the administrative aspects related to the use of graphs.
control.
The administrative aspects related to the use of control charts
son
The selection of places in a process that need SPC
The decision on which type of control charts fit best
The establishment of rules for workers to follow if certain points or
patterns emerge
16. What is an OC curve?
AOC curve is a graph that shows the probability of accepting a large quantity.
given a certain quality (percentage of defects)
17. What is the purpose of acceptance sampling?
The purpose of acceptance sampling is to determine a course of action (accept or
reject) regarding the disposal of a lot without inspecting each item of a
batch.
Acceptance sampling does not estimate the quality of a lot.
18. What are the two risks present when using sampling?
acceptance?
The two risks when using acceptance sampling are of type
Type I error: the rejection of a good lot
Type II error: accepting a bad batch.
19. Is a capable process a perfect process? That is to say, can a capable process...
generate only outputs that meet the specifications? Explain your
answer.
When a process has a capability index of one or more; it produces
small percentages of unacceptable items.
The formula is built around an assumption of exactly one, those
parts that are more than three sigma from the center are unacceptable; which are 0.00135 of