Scribd
Upload
3 views

Statistical Process Control 2

Uploaded by

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

Statistical Process Control 2

Uploaded by

Tahoor Asim
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 13

Statistical Process Control

12
Introduction to Statistical Process Control
The Value SPC Can Add to Quality, Operations, Supply Chain Management,

Other Control Charts


and Continuous Improvement Programs
Variation and What it Means to be in Control and Capable
Introduction to Control Charts
Hands-on - Control Charts in Minitab -17
Basic Control Charts for Variables
Hands-on - Basic Control Charts for Variables in Minitab -17
Advanced Control Charts for Variables
Hands-on - Advanced Control Charts for Variables in Minitab -17
Control Charts for Attributes
Hands-on - Control Charts for Attributes in Minitab -17
Other control charts
Process Capability
Hands-on - Process Capability in Minitab -17
SPC in Service Sector/ Industries
Case Studies in SPC
Latest trends in SPC including AI
Discussion Topics

• 3 way Chart
• Charts to adjust for data distribution
• Special Control Chart
• Laney P’ and U’ Chart

2
Introduction

• Most control charts are based on certain assumptions such as:


• Process is stable (only contains common cause variations)
• Variable data is normally distributed - thus satisfies normality and central limit
theorem
• Situations where such conditions are not likely to be met include:
• Low production levels
• Sudden change in production scheduling thus outputs created may involve
different machines, workers, suppliers etc.
• Variation within the piece requires to be measured
• Therefore, special control charts may need to be designed
3
3 Way Control Chart

• Three-way control chart assesses both between-subgroup and within-subgroup


variations, thus provides a method of assessing the stability of process location. It
includes an Individuals chart (I), a moving range chart (MR) and a R/S chart
• Variation in a process comes from both common causes and special causes:
‣ Variability within a subgroup should encompass common cause
‣ Variability between subgroups should encompass special cause
• Standard Deviation and thus UCL/ LCL are calculated using variability within
subgroups

4
3 Way Control Chart

• In many situations thus, specially


where batches may not reflect ideal
subgroups, LCL/ UCL may become too
narrow or too wide
• It is therefore logical to use a chart/
set of charts that show both within
subgroup and between subgroups
variation. Minitab calls the 3-way chart
as I-MR-R/S or Between/ Within Charts

5
Charts to adjust for data distributions

• Shehwart’s charts assume data normality - and encourage data normalisation it not
so already. Control charts limits are also calculated under the assumptions of
Central Limit Theorem
• However, in many cases, available data may not be large enough to satisfy
conditions of normality or Central Limit Theorem
• In such cases, procedures may need to be devised to assess the true distribution of
data and construct the chart (CL and UCL/ LCL) accordingly
• Example: Data following the new Weibull-Pareto distribution (Boyapati, S. R., Nasiru, S., &
Lakshmi, K. N. V. R. (2015). Variable control charts based on percentiles of the new weibull-pareto distribution. Pakistan Journal of
Statistics and Operation Research, 631-643.) Available on canvas group

6
Special Control Charts

1. Interrupted Average and Range Chart


2. Multiple Variation Chart
3. Print Tolerance Control Chart
4. PreControl Chart
Anagun, A. S. (1999). Special Control
5. Two-R Control Chart Charts. Industrial Engineering Applications and
Practices: Users Encyclopedia; Eskisehir Osmangazi
University: Eskisehir, Turkey.
6. Deviation Charts
Available on canvas group
A. Deviation from Nominal Chart
B. Deviation from Target Chart
7. Short Run Chart

7
Special Control Charts

1. Interrupted Average and Range Chart


‣ Similar to the average and range chart, may be used for discrete or low volume
production. It is also used when there are unexpected delays in process due to
lack of materials and sudden changes in production scheduling
2. Multiple Variation Chart
‣ May be used when specification limits or the population mean and standard
deviation are known. Consequently, there is no need to collect data to establish
control limits
3. Print Tolerance Control Chart
‣ Similar to Multiple Variation Chart - good for low and high volumes

8
Special Control Charts

4. PreControl Chart
‣ Aka stoplight or target control chart is a basic chart using green yellow and red
areas without burdening the operators in constructing and interpreting the chart.
Usually deployed at the start of SPC adoption and eventually replaced by more
sensitive charts
5. Two-R Control Chart
‣ Used to analyse within piece variation. Has 3 charts including I or x̅ chart, a R
chart for piece to piece variation and a R chart for within piece variation

9
Special Control Charts

6. Deviation Charts (Delta Charts - See Session 8)


7. Short Run Chart
‣ Used where calculated SD may be too large and thus plotted points tightly hug
the CL, masking point to point variation. This chart eliminates the effect of having
the range or the standard deviation in the calculation of the control limits by
plotting point (independent of the range or standard deviation) using a series of
inequalities

10
Special Control Charts
Sample size: 1- One, 2- More than one,
Quality characteris;c: 1- Measurable, 2-
Countable,
Number of characteris;cs: 1- One, 2- More than
one,
Type of varia;on observed: 1- Time-to-;me, 2-
Piece-to-piece, 3- Varia;on within the piece,
Control limits: 1- Calculated using raw data, 2-
Drawn directly using specifica;on limits, 3- Drawn
directly using coefficients for sample size of n,
Manufacturing volume/type: 1- Low/Discrete, 2-
High/Con;nuous,
Type of inspec;on: 1- Non-destruc;ve, 2-
Destruc;ve,
Inspec;on strategy: 1- In-process, 2- Pre-process,
Type of data used: 1- Raw, 2- Devia;on from
nominal, 3- Devia;on from target, 4- Min/Max
values, 5- Pre-processed,
Interpreta;on: 1- Similar to Xbar-R, 2- Rule-based,
3- Similar to individuals and moving range, 4-
Similar to Xbar-R but separately for each
characteris;c.

11
Laney P’ and U’ Charts

Used to adjust for Over-dispersion or Under-dispersion in data


•Over-dispersion
‣ Exists when there is more variation in your data than you would expect based
on a binomial distribution (for defectives) or a Poisson distribution (for defects)
‣ In very large data sets, control charts have the power to detect very small
variations - which may not be of interest , may appear to be significant
•Under-dispersion
‣ Occurs when there is less variation in your data than you would expect …
‣ In under-dispersion, the control limits on a traditional P chart or U chart may be
too wide. If the control limits are too wide, you can overlook special cause
variation and mistake it for common cause variation
12
Questions?

You might also like