UNIT-5 STATISTICAL QUALITY CONTROL (10Hrs)

Introduction to SQC, Uses of SQC, Process and Product Control, Control Charts: Upper Control
Limit, Lower Control Limit, Central Line. Construction and Statistical basis of 3-σ Control charts
( X-bar & R-chart, X-bar & s-chart np-chart, p-chart, c-chart and u-chart)[Theory Only],

Introduction to SQC (Statistical Quality Control)

Statistical Quality Control (SQC) refers to the use of statistical methods and techniques to
monitor, control, and improve the quality of processes and products. It is a powerful tool used
in manufacturing and service industries to ensure that processes are operating efficiently and
producing products that meet specified quality standards.

 Quality Control: The process of maintaining and improving product quality through
inspections, testing, and measuring.
 Statistical Methods: The application of statistics to assess variability, detect
deviations, and ensure that processes remain within control limits.

SQC helps in identifying problems before they affect the product, leading to fewer defects,
higher consistency, and lower costs.

Uses of SQC

SQC is applied in various fields and for different purposes. Some of the key uses include:

1. Quality Assurance: To ensure products meet specified quality standards by

identifying variations in the manufacturing process.
2. Process Monitoring and Control: By using control charts, SQC helps monitor the
stability of processes, detecting out-of-control conditions.
3. Defect Reduction: Helps identify and reduce variations and defects in products,
leading to improved product quality.
4. Cost Reduction: By preventing defects and rework, SQC can significantly reduce the
cost of production.
5. Continuous Improvement: Provides a data-driven approach for process
improvement and achieving higher product quality over time.
6. Compliance: Helps companies comply with industry standards, regulations, and
customer requirements.

Process and Product Control

1. Process Control: The ability to monitor and regulate a manufacturing or service

process to ensure it operates within acceptable limits.
o Objective: The goal of process control is to ensure that the process remains
stable, predictable, and produces consistent quality products.
2. Product Control: The act of checking the quality of the product against specified
standards to ensure it meets the desired characteristics.
o Objective: To ensure that the final product is free of defects and conforms to
the quality specifications.
Control Charts

Control charts, also known as Shewhart charts, are graphical tools used in quality control to
monitor and track a process over time, helping identify variations and potential issues,
ultimately leading to process improvement.

Control charts are used to monitor the variation in a process over time. They help in
determining whether a process is in control (stable) or out of control (unstable). A control
chart consists of three main components:

1. Upper Control Limit (UCL): The upper limit of acceptable variation. If a data point
exceeds the UCL, the process is considered out of control.
2. Lower Control Limit (LCL): The lower limit of acceptable variation. If a data point
falls below the LCL, the process is considered out of control.
3. Central Line (CL): Represents the average or mean of the process data. It is the
expected value if the process is in control.

Control charts are constructed to help identify patterns in the data and signal whether
corrective actions are needed.

Construction and Statistical Basis of 3-σ Control Charts

The term "3-σ" refers to the control limits set at three standard deviations (σ) above and
below the process average (central line). This approach helps detect abnormal variations in
the process. If data points fall outside of these limits, it is a signal that the process may be out
of control.

The general steps for constructing a control chart include:

1. Collect data: Sample data from the process at regular intervals.

2. Calculate the average: Compute the mean and standard deviation of the sample data.
3. Determine control limits: Set the control limits using the formula:
o For the upper control limit (UCL): UCL=CL+3σ
o For the lower control limit (LCL): LCL=CL−3σ
4. Plot the control chart: Plot the sample data points, central line, and control limits on
the chart.
 5. Analyse the chart: Look for any points outside the control limits or unusual patterns
indicating an issue with the process.

Types of Control Charts

There are several types of control charts, each suited for different types of data and processes.
The most common types include:

1. X-bar and R-chart (for variable data):

An X-bar and R (range) chart is a pair of control charts used with processes that have a
subgroup size of two or more. The standard chart for variables data, X-bar and R charts help
determine if a process is stable and predictable.

o X-bar chart: Monitors the mean of a sample or subgroup. It helps detect shifts
in the average value of a process.
o R-chart: Monitors the range (the difference between the highest and lowest
values) of a sample. It detects variability in the process.
o Construction: Typically used together to monitor both the average (central
tendency) and the spread (variability) of the data.

2. X-bar and s-chart (for variable data):

The Xbar chart (the upper chart in this figure) plots the average of individual values in a
subgroup (i.e., the subgroup mean). The s chart (the lower chart in the figure) plots the
sample standard deviation of the individual values in the subgroup.

o X-bar chart: As above, monitors the average of the sample data.

o s-chart: Monitors the standard deviation of a sample instead of the range. It is
used when sample sizes are large, as the range becomes less reliable.
3. np-chart (for attribute data):

An np chart, or attributes control chart, is used to monitor the number of nonconforming

units in subgroups of the same size, helping to determine if a process is stable and
predictable.

o Definition: This chart monitors the number of defective items in a sample,

specifically when the sample size is constant.
o Construction: Used for data that can be classified as either defective or non-
defective (binary data).

4. p-chart (for attribute data):

A p-chart is also known as an attribute-based control chart. This chart monitors the
proportion of nonconforming items in a process, using categorical data. Its use in quality
control helps ensure that systems remain statistically controlled.

o Definition: The p-chart monitors the proportion of defective items in a

sample. Unlike the np-chart, the sample size can vary.
o Construction: Used when dealing with proportions or percentages of
defective items in a sample.
 5. c-chart (for attribute data):
o Definition: The c-chart is used for monitoring the count of defects in a sample
when the sample size is constant.
o Construction: Suitable for situations where the number of defects per unit is
being tracked (e.g., number of flaws in a product).
6. u-chart (for attribute data):
o Definition: The u-chart monitors the number of defects per unit, similar to the
c-chart, but the sample size can vary.
o Construction: It is useful when the unit size changes, but you want to monitor
the number of defects per unit.

Theory Behind Control Charts

1. Central Limit Theorem (CLT):

o The CLT states that, for a large enough sample size, the distribution of the
sample means will be approximately normal, regardless of the original
population distribution. This makes control charts statistically valid for use in
process control, assuming the data are randomly distributed.
2. 3-σ Rule (Empirical Rule):
o The 3-σ control limits are based on the empirical rule, which states that for a
normal distribution:
 About 68% of the data lies within 1 standard deviation of the mean.
 About 95% of the data lies within 2 standard deviations.
 About 99.7% of the data lies within 3 standard deviations.
o By setting control limits at 3 standard deviations, we ensure that 99.7% of the
data points will fall within these limits if the process is stable. Any data points
outside these limits are considered "out of control."

Conclusion

 Statistical Quality Control (SQC) is a vital tool for ensuring that processes and
products meet the desired quality standards through monitoring and control.
 Control charts are at the heart of SQC, providing a graphical method to monitor
process stability and detect variations that may require corrective action.
 Types of control charts (X-bar & R, X-bar & s, np, p, c, and u charts) are selected
based on the nature of the data (variable or attribute) and the specific needs of the
process being controlled.
 3-σ control limits ensure that process variations are kept within acceptable bounds,
and deviations outside these limits signal the need for intervention.
Problems

Steps to Construct X-bar and R-Chart

Step 1: Collect Sample Data

Suppose you are taking 5 subgroups of data from a manufacturing process. Each subgroup
consists of 4 samples.

Subgroup (i) Sample 1 Sample 2 Sample 3 Sample 4 X-bar (mean) R (range)

1 12 15 14 13 13.5 3
2 14 13 16 14 14.25 3
3 11 14 12 13 12.5 3
4 13 15 14 12 13.5 3
5 14 15 13 12 13.5 3

Step 2: Calculate the Mean (X-bar) and Range (R) for Each Subgroup

 X-bar (mean) is calculated by adding the values of the samples in a subgroup and
dividing by the number of samples.

For Subgroup 1: Xbar=12+15+14+134=544=13.

Repeat this for all subgroups.

 Range (R) is the difference between the maximum and minimum values in each
subgroup.

For Subgroup 1: R=15−12=3

Repeat this for all subgroups.

Step 3: Calculate Overall Averages

Step 4: Calculate Control Limits for X-bar and R Charts

X-bar Chart:
Q1. A machine bores holes with a mean of 0.48 cm and a S.D of 0.002 cms. Find the 3σ upper and
lower control limits for mean of samples of size 5, given A = 1.342.

Solu: Given that

μ ‘ = 0.48, σ ‘ = 0.002 and n = 5

The 3σ control limits for Xbar – chart (when standards are known) are

UCLxbar = μ ‘ + A σ ‘ = 0.48 + 1.342(0.002) = 0.48268

LCLxbar = μ ‘ - A σ ‘ = 0.48 - 1.342(0.002) = 0.4773

Therefore,

CLxbar = μ ‘ = 0.48
Q2. Measurements of metal strips from samples each of size 5 gave results of Xbar = 90.3 and Rbar
= 6.2. Find the values of control limits for drawing Xbar charts given A2 = 0.577.

Solu: Given that

Xbar = 90.3 and Rbar = 6.2, A2 = 0.577 and n =5

The 3σ control limits for Xbar – chart (when standards are unknown) are

UCLxbar = Xbar + A2 Rbar = 90.3 + 0.577(6.2) = 93.877

LCLxbar = Xbar - A2 Rbar = 90.3 - 0.577(6.2) = 86.72

Therfore,

C.LXbar = 90.3