Quality 7 QC Tools | 7 QC Tools in Quality

Seven Quality Control Tools or 7 QC TOOLS are simple but powerful techniques used in quality management and problem-solving. These tools help in identifying, analyzing, and controlling quality-related issues in manufacturing, engineering, and service industries.

1. The Cause-and-Effect Diagram 

The Cause-and-Effect Diagram is also called the Fishbone Diagram or Ishikawa Diagram.
A tool used to identify and organize possible causes of a specific problem (effect).The diagram looks like a fish skeleton, which is why it’s called a fishbone diagram. Developed by Kaoru Ishikawa, a Japanese quality expert.

The Cause-and-Effect Diagram Purpose:

To find the root causes of a problem rather than just addressing symptoms. encourages brainstorming and systematic thinking with the team.

Main Categories of Causes (commonly used in manufacturing):

Man (People) – Human errors, lack of training, skill issues.
Machine (Equipment) – Faulty machines, improper maintenance.
Method (Process) – Wrong procedure, lack of standardization.
Material (Raw Material) – Poor quality inputs, defects in material.

Measurement – Inaccurate tools, inspection errors.

Environment – Temperature, humidity, workspace conditions.

2. Check Sheet:

A structured, prepared form used to collect and analyze data systematically.
It helps in recording the frequency of defects, events, or problems as they occur.
Very simple but powerful tool for data collection and pattern analysis.
A Check Sheet = A simple tool for collecting and analyzing data, which helps in detecting patterns and making improvements.

Purpose of a Check Sheet:

To collect real-time data at the location where the data is generated.
To make decisions based on facts rather than assumptions.
To identify patterns or trends (e.g., which defect occurs most often, when, or where).

3. Control Chart:

A graphical tool used to study how a process changes over time.
It plots data points (measurements) in time order and compares them with control limits.
Helps to identify whether a process is stable (in control) or has abnormal variations (out of control).

Elements of a Control Chart:

Central Line (CL) – The average (mean) of the data.
Upper Control Limit (UCL) – The highest acceptable value (usually mean + 3σ).
Lower Control Limit (LCL) – The lowest acceptable value (usually mean – 3σ).
Data Points – The actual process measurements plotted over time.

Purpose of a Control Chart:

To monitor process performance.
To detect whether variation is due to common causes (natural, unavoidable) or special causes (problems that must be fixed).
To prevent defects by taking corrective action before process goes out of control.

Types of Control Charts:

For Variable Data (measured values):
X̄ – R Chart → For small sample sizes.
X̄ – S Chart → For larger sample sizes.
Individuals (I-MR) Chart → For single measurements.

For Attribute Data (counts, defects):
p-Chart → Proportion of defective items.
np-Chart → Number of defectives.
c-Chart → Count of defects per unit.
u-Chart → Defects per unit (when sample size varies).

4. Histogram:

A bar graph that shows how often (frequency) data values occur.
It represents the distribution of data in different ranges (intervals or “bins”).
In Quality Control, it helps us understand variation in a process.
A Histogram helps visualize how data is spread, making it easier to judge process stability and quality performance.

Purpose of Histogram in Quality:

To see the pattern of variation in a process.
To check whether the process is centered around the target value or not.
To detect whether the data follows a normal distribution (bell curve).
To identify common cause variation vs. special cause variation.

5. Pareto Chart:

A special type of bar graph combined with a line graph.
Bars show the frequency (or impact) of problems/defects.
The line shows the cumulative percentage.
Based on the Pareto Principle (80/20 Rule) → 80% of problems are caused by 20% of causes.
A Pareto Chart = a priority-setting tool in quality control → Focus on the few major problems that will give the biggest improvement.

Purpose of Pareto Chart:

To identify the most important problems to focus on.
To prioritize actions for quality improvement.
To separate the “vital few” causes from the “trivial many”.
When you have many problems/defects and want to know which ones are most significant. 
For defect analysis, cost analysis, complaint analysis, etc.

Interpretation
Tallest bars (left side) = Major issues.
Short bars (right side) = Minor issues.

The line graph helps visualize how quickly cumulative % reaches 80%.

6. Scatter Diagram:

A graph showing the relationship between two variables (X and Y).

Each point on the graph represents a pair of values.

Also called Scatter Plot or Correlation Diagram.

A Scatter Diagram = A visual tool to study the relationship between two variables and decide if they are related.

Purpose of Scatter Diagram:

To check if two factors are related.

To find if changes in one variable affect the other (correlation).

To help in root cause analysis (whether a cause is actually linked to the problem).

Types of Correlation in Scatter Diagram:

Positive Correlation  – When X increases, Y also increases.

(e.g., More training hours → Better product quality)

Negative Correlation  – When X increases, Y decreases.

(e.g., More machine speed → Less product accuracy)

No Correlation  – No visible relationship.

(e.g., Indian reality shows vs. Actual Real 😀)

7. Flow Chart or Stratification:

1. Flow Chart in Quality:

A visual diagram that shows the steps of a process in sequence.
Uses standard symbols (rectangle = process step, diamond = decision, oval = start/end).
Helps in understanding, analyzing, and improving a process.

Flow Chart = Picture of how a process works.

Purpose of Flow Chart:

To map a process clearly.
To identify unnecessary steps, bottlenecks, or points where errors may occur.
To communicate process flow to employees for standardization.

2. Stratification in Quality:

A method of classifying data into different groups (layers/strata) to identify patterns.
Instead of looking at combined data (which may hide causes), stratification separates data by factors like: Machine, Operator, Shift (day/night), Material supplier & Region.

Purpose of Stratification:

To separate “mixed” data and find hidden causes of variation.
Helps in discovering whether a problem is specific to one condition or is general.

Thanks.