Information & Training. | SPC and Statistical Methods for Process Improvement.
The Process Control Chart
What performance characteristic to measure?Clearly this is a critical decision. Creating and monitoring control charts requires a significant effort and usually requires input from a number of staff. The key is to ensure you focus on those quality attributes which are CRITICAL to process performance.
How to make the measurement?It must be possible to consistently, repeatedly and accurately make measurements. The potential for error or variation within the measurement process needs to be avoided. If test, measurement or inspection equipment is to be utilized, such equipment should be regularly calibrated and maintained. In addition gage repeatable and reproducibility studies may need to be performed. Where observations will be made by a number of individuals, they need to clearly understand the required pass / fail criteria. The objective needs to be that variation within the measurement process does not result in decisions regarding variability within the process being monitored.
What type of Process Control Chart are you going to use, Variable or Attribute?The decision to use a variable or attribute control chart will be relatively easy to make and will be determined by the type of measurements to be recorded. Similarly, sample size numbers and variation of sample numbers will in turn determine the specific optimum control chart type.
What are the sample sizes or sample groupings sizes?The sample size will be determined by the ease of sampling, the ease of measurement, the relationship between the sample sizes versus the total population, the type of chart selected. The key determinant of the sample size needs to be the ability of the sampling to detect shifts within the process.
There are two types of sample size to be determined. The first sample size will relate to when the control chart is being initially created and the sample sizes for follow-on sampling. The initial sample will be of the order of 25 times the ongoing sample sizes. Therefore if the ongoing samples will be of the order of 5 samples, then the initial sample in creating the chart should be 125 samples.
The ongoing sample size can be determined with a high level of accuracy from the standard MIL-STD-414, which provides guidance on the number of samples to be checked per lot or batch size.
Lot Size 60 – 300, percent to be sampled 10%
Lot Size 301 – 1000, percent to be sampled 5%
Lot Size 1001 – 5000, percent to be sampled 2%
Lot Size 5001+ , percent to be sampled 1%
As the control chart is developed and confidence in the data grows, sample rates will be reviewed.
Calculate the Process Control Chart, Center line and Control Limits.With the type of control chart and sample sized determined the center line and control limits can now be determined. The center line will be related to the process mean (X bar chart), standard deviation mean (S chart), etc.. The upper and lower control limits will be set at +/- 3 standard deviations from the mean. Setting at the +/- 3 standard deviations will result in 99.7% of all readings landing within the control limits. Any reading taken outside the control limits will act as a warning that the process may be deviating out of control. Similarly any data trends within the control limits will become very visual and will clearly show any changes or shifts within the process.
Interpreting the results.With the process established and data monitoring ongoing, the control chart can now be investigated to help develop an understanding of the process operation. The charts will also show the effect of any changes to the process or its inputs.
Information & Training.
SPC & Statistical Methods for Process Improvement.
- Process Capability. Variability Reduction. Statistical Process Control.
- Pre-Control. R&R Studies.
- Process capability indices Cp, Cpk, Cpm, Capability ratio.
- Performance indices Pp and Ppk.
- Variable Control Charts.
- Attribute Charts.
- Pareto Charts.
- Individual – X Charts.
- Histograms / Process Capability Analysis.
- Scatter Diagrams.
- Etc. … Etc. …
- Information & Training presentation >>>