A tool for on-line process control, the control chart is widely used for the detection of assignable causes of variation. It is a graphical display of a sample quality measure versus sample number (or time).
The centre line represents the average value of the quality characteristic corresponding to the in-control state. Two other parallel horizontal lines, the upper control limit (UCL) and the lower controls limit (LCL), are also shown on the chart. A typical control chart looks as follows:
Choice of Quality Characteristic:
To begin with, a decision has to be made on the quality characteristic for which a control programme would be derived. The characteristics affecting the performance of the product should normally be taken first. To take an example, these could be features of the materials, components or parts used, for the tensile strength of some steel item, thickness of some insulation, internal diameters of steel tubes, etc.
Image Source: brilyncontact.com
Choice of Control Station:
In any manufacturing process, control charts are used at strategic points to conduct proper checks. To decide the ideal place for such controls, it is best to determine the areas of maximum potential for return in the form of direct profits reduction in scrap, increase in production, etc. It is also worthwhile to study the production process to determine the nature and location of the causes that tend to give rise to deviations in the characteristic chosen.
Choice of Rational Sub-groups:
When creating sub-groups it is best to ensure against sub-groups consisting of items manufactured in different shifts, components obtained from different sources, from different production times, from different machines, moulds, operators, etc.
Frequency and Size of Samples:
A number of practical considerations dictate the size and frequency of samples. Small samples taken at more frequent intervals will detect a large shift more quickly. Samples of size 4 or 5 should generally be used.
Choice of the Type of Control Charts to be used:
ADVERTISEMENTS:
When measuring quality characteristics a pair of control charts,— X to control the average level of the process and the other range (R) to control dispersion—would be used. Many quality characteristics are not measured on a numerical scale. In such cases, each unit of product should be judged as either conforming or nonconforming on the basis of whether or not it possesses certain attributes. We could count the number of nonconformities (defects) appearing on a unit of product. In such situations, control charts are used to count the number of defects or of defectives.
As long as the points plot within the control limits, the process is assumed to be in control and no action is necessary. When a point plots outside of the control limits, it is interpreted as evidence that the process is out of control, and an investigative and corrective action is required to find and eliminate the assignable cause or other causes responsible for this behaviour.