Statistical Process Control or SPCs is a very useful methodology to help improve and control product quality. To know more about its history, I would recommend reading Father of SPC .
Before implementing SPC or any new quality system, the manufacturing process should be evaluated to determine the main areas of waste. Some examples of manufacturing process waste are rework, scrap and excessive inspection time. It is beneficial to first apply the SPC tools to these areas of waste. For additional reading on where to apply SPC, you should refer Why SPC .
Control charts is a tool used to determine whether a manufacturing or business process is in a state of statistical control or not.
- If data points fall outside of control limits, it means that there is some reason(s) that causes the data to fall outside the control limits. Something within process should be changed to fix the issue before further defects occur.
- When data points fall within control limits, everything seems operating as expected. But you may find trends in the chronological data
SPCs are process control charts which take advantage of statistical interpretation of data. Control charts are classified into Variable charts or Attribute Charts.
- Variable Control Charts: Charts would fall in this category when the data to be plotted results from measurement on a variable or continuous scale.
- Attribute Control Charts: Attributes are discrete, counted data. Unlike variables charts, only one chart is plotted for attributes These type of charts are used when each data element is classified in one of the two categories, such as Good or Bad, Pass or Fail, Red or Blue etc.
Variable Charts
1. XBAR & Range
It helps in controlling the level of variability of a Process. This control chart is also very useful in monitoring the effects of Process improvement theories.
- X-Bar chart shows how the mean or average changes over time for a subgroup.
- R chart shows how the range of subgroups changes over time.
2. XBAR & Sigma
X-Bar charts and S charts show if the system is stable and predictable. These charts use a subgroup standard deviation.
3. Median Charts
Chart shows the spread of the Process output and gives a picture of the Process variation. Shows users that individual data points can fall outside the control limits, while the central location is within the limits.
4. Individual Measurement
Shows individual readings instead of subgroup averages .Used for short production runs, small amounts of data.
5. EWMA Chars (Exponentially Weighted Moving Average)
For variable data that is both continuous and quantitative in measurement such as a measured dimension or time. A weighting factor is chosen by the user to determine how older data points affect the mean value compared to more recent ones. Because a EWMA chart uses information from all samples, it detects much smaller Process shifts than a normal control chart would.
Attribute Charts
1. P Chart
Displays the fraction of non-conforming (defective) samples, which is the ratio of non-conforming parts/samples to the total quantity of parts inspected.
2. NP Chart
Monitors the number of non-conformances (np). Multiplies the sample size (n) by proportion (p) to show the actual count of nonconforming items
3. C Chart
Displays how the number of defects, or nonconformities, for a Process or system changes over time. Helps determine if a process is stable and in-control or unstable and out of control.
4. U Chart
Displays the number of non-conformities per unit.
5. Run Chart
Displays plots of Process Characteristics against time or in chronological sequence. Helps find trends or patterns in a process. It can be a valuable tool at beginning of a project as it reveals information about a process before collecting enough data to create reliable control limits.
Watch out this space to know more about the rules that can be configured on SPC charts to highlight values and generate automated alerts.
Additional Reading:
