Page 71 - DMGT206_PRODUCTION_AND_OPERATIONS_MANAGEMENT

Production and Operations Management

Notes SPC uses control charts to determine if a process is within controlled parameters.
1. If it is determined that a process is ‘out of control’,
2. SPC provides the opportunity to investigate and determine the cause of this condition.
3. When the root cause of the problem is determined, a strategy can be identified to correct it.
4. Adjustments can be made to the process so that the process is unable to produce defective
parts.
5. The investigation and subsequent correction strategy is frequently a team process and one
or more of the TQM process improvement tools are used to identify the root cause.

4.2.1 Control Charts

When the quality of a product depends on some measurable physical quantity, e.g., weight,
height, length, diameter, etc., control charts are used to ensure that these quantities are within
limits permitted by the process. Control charts are time-sequenced charts showing plotted
values of a statistic including a centerline average and one or more control limits.

Central Limit Theorem of Statistics

1. Data on the critical characteristic in a large lot of an item that is produced by an operation
will often display a pattern similar to a normal distribution. The theoretical basis of
control charts is the Central Limit Theorem of statistics.
2. Control charts use this theorem to predict the performance of a process.
3. The theorem specifies that if we compute averages of many random samples, the
characteristics will be distributed approximately normally irrespective of the distribution
of the specific characteristic, if the subgroups are ordered in time.
This means that we can use a control chart based upon the properties of the normal distribution
to determine if the operation was ‘in control’ during its performance.
The control chart will, therefore, also indicate the likelihood if the process were going out of
control. It also imputes that the lot of characteristics about the mean will be similar to the
measured ranges of the samples. The standard deviation of the ranges can be calculated by
formula derived from the normal distribution.
There can be two types of control charts representing the two types of sampling:
1. Control charts for variables, and
2. Control charts for attributes.
1. Control charts for variable: In the case of variables, control of the process average or
mean quality level is usually determined with the control chart for means (µ), or the X bar
chart. The control of the variability of the process is determined by using the control chart
for range, or the R chart. The X bar chart is developed from the average of each subgroup
data, i.e., the data in each R chart is taken as a single reading, and from a number of these
data points, the X bar chart is constructed.
2. Control charts for attributes: Similarly, control charts for sampling by attributes are
called ‘p’ charts. ‘P’ charts measure the variability in a process. c-chart is another device for
controlling attributes. It is used where the total number of defects (of all kinds) in the
product must be kept under control. The c-chart is useful where the opportunity for defects
is large while the actual occurrence is small.
Control Charts, rather than merely identifying defectives after they are produced, as in
acceptance sampling, help to prevent the production of defectives.

66 LOVELY PROFESSIONAL UNIVERSITY