Understanding Control Charts in Quality Control
Control charts are a fundamental tool in statistical process control (SPC) and operations management. They are graphical tools used to study how a process changes over time. By plotting data points over time, control charts help distinguish between common cause variation (inherent in the process) and special cause variation (assignable to specific events or factors).
The Purpose of Control Charts
The primary goal of a control chart is to monitor a process and determine if it is in a state of statistical control. A process is in statistical control when it exhibits only common cause variation. This allows for process improvement by identifying and eliminating special causes of variation. They are crucial for maintaining quality, reducing defects, and optimizing efficiency in manufacturing and service industries.
Common cause variation and special cause variation.
Key Components of a Control Chart
A typical control chart consists of several key elements:
- Center Line (CL): Represents the average value of the process data.
- Upper Control Limit (UCL): The upper boundary for common cause variation.
- Lower Control Limit (LCL): The lower boundary for common cause variation.
- Data Points: Individual measurements or subgroup averages plotted over time.
When data points fall outside the control limits or exhibit non-random patterns within the limits, it signals that the process may be out of statistical control.
Control limits are not specifications; they are derived from the process data itself.
Control limits (UCL and LCL) are calculated based on the historical performance of the process, typically using standard deviations. They define the expected range of variation when only common causes are present. Specification limits, on the other hand, are set by customers or regulatory bodies and define acceptable product or service characteristics.
It is a common misconception that control limits are the same as specification limits. Control limits are a statistical measure of process capability and stability, calculated from the process's own data. They tell us what the process is doing. Specification limits, however, are external requirements that define what the process should be doing. A process can be in statistical control (within its control limits) but still produce output that is outside of specification limits, indicating a need for process improvement to reduce variation or shift the process average.
Types of Control Charts
The choice of control chart depends on the type of data being monitored. Data can be either continuous (variable data) or discrete (attribute data).
- For Variable Data (Continuous):
- X-bar and R charts (for subgroups)
- X-bar and S charts (for subgroups)
- Individuals and Moving Range (I-MR) charts (for individual measurements)
- For Attribute Data (Discrete):
- p-charts (for proportion of nonconforming items)
- np-charts (for number of nonconforming items)
- c-charts (for number of nonconformities)
- u-charts (for number of nonconformities per unit)
| Chart Type | Data Type | Purpose |
|---|---|---|
| X-bar & R Chart | Variable (Subgroups) | Monitors process average and variation |
| I-MR Chart | Variable (Individual) | Monitors individual measurements and variation between consecutive points |
| p-Chart | Attribute (Proportion) | Monitors the proportion of defective items in samples |
| c-Chart | Attribute (Count) | Monitors the number of defects per unit or area |
Interpreting Control Charts: Identifying Special Causes
Beyond points falling outside the control limits, several patterns within the chart can indicate special causes of variation:
- Runs: Seven or more consecutive points above or below the center line.
- Trends: Six or more consecutive points steadily increasing or decreasing.
- Cycles: Repeating patterns that are not random.
- Hugging the Center Line: Too many points clustered around the center line, suggesting reduced variation.
- Hugging the Control Limits: Points consistently near the UCL or LCL, indicating potential instability.
A typical control chart displays data points plotted sequentially over time. The horizontal axis represents time or sample number, and the vertical axis represents the measured characteristic (e.g., weight, length, defect count). A horizontal line indicates the process average (Center Line). Two additional horizontal lines, equidistant from the center line, represent the Upper Control Limit (UCL) and Lower Control Limit (LCL). These limits are typically set at +/- 3 standard deviations from the center line. Data points falling outside these limits, or exhibiting non-random patterns within them, signal potential issues with the process.
Text-based content
Library pages focus on text content
Remember: A process is only considered stable and predictable (in statistical control) when all variation is due to common causes.
Implementing Control Charts
Implementing control charts involves several steps:
- Define the Process: Clearly identify the process to be monitored.
- Select the Appropriate Chart: Choose the control chart type based on the data.
- Collect Data: Gather data systematically over time.
- Calculate Control Limits: Determine the center line, UCL, and LCL.
- Plot Data: Graph the data points on the control chart.
- Interpret the Chart: Analyze the chart for out-of-control signals.
- Take Action: Investigate and address any identified special causes of variation.
- Monitor Continuously: Regularly update and review the control chart.
To identify signals of special cause variation that indicate the process is out of statistical control.
Learning Resources
The American Society for Quality (ASQ) provides a comprehensive overview of SPC, including the role and types of control charts.
This article offers a practical introduction to control charts, explaining their purpose, components, and interpretation with clear examples.
MindTools explains how to use control charts to monitor processes, identify variations, and make informed decisions for improvement.
A guide to the different types of control charts, detailing when to use each based on the nature of the data.
Provides a broad understanding of SPC, its history, principles, and its relationship with control charts.
A clear and concise video explanation of what control charts are, how they work, and how to interpret them.
This tutorial focuses on control charts within the Six Sigma methodology, explaining their application in process improvement.
A PDF document from NIST covering various basic statistical tools for quality, including a section on control charts.
Minitab, a statistical software provider, offers detailed documentation and explanations of control charts and their use in quality management.
An article from the Western Association of Laboratory Science (WALS) discussing process behavior charts, a term often used interchangeably with control charts, emphasizing their role in understanding process stability.