Using control charts to improve your manufacturing process

When attempting to implement improvements to a working process such as manufacturing, it is helpful to have a way to measure the effectiveness of the process improvement. You can do so using control charts. There are several different control chart programs available, but you can also use a spreadsheet program, such as Microsoft Excel to create these charts.

In order to evaluate the effectiveness of your process, you must gather some information to evaluate. Let's say, for example, that you intend to decrease the number of accidents in a particular part of your process. To start with, you would need to have the data available of the number of accidents for this process function. In order to have this data available, capturing this data must become part of the process. The data can then be plugged into your control chart spreadsheet to be analyzed by a function or macro. After analyzing the data with a control chart, you will then be able to determine whether or not the process change was effective or not, or if the process is staying close to a specified target.

In order for the control chart to be meaningful, it should be based on a particular methodology for statistical control, such as the Six Sigma methodology, or at least the analyst should have a basic understanding of statistical analysis such as standard deviation. If you are not familiar with statistics or Six Sigma, then you should get training first. You should also get training in the tool, such as the spreadsheet application, if you are unfamiliar with it.

There are many different types of control charts. Depending on the type of analysis being done, a different type of control chart can be used. Some of the types of charts include:
- The histogram: A chart where the values are show by the area under curve of the graph. This is useful when trying to find out what happened over a period of time.
- The XmR graph: A graph where upper and lower limits are determined from the data being analyzed. These limits could be determined using a certain number of standard deviations from the data average. If one of the incidents falls outside of the established limits, then an exception occurs.
- The c chart:A line graph that helps you track the number of something per event. For example, the number of sales per month. This simple graph can show trends and stability, or lack of stability.
- The XbarR chart: This is a two scale graph also with upper and lower limits. It is typically used to measure the amount of time it takes to complete something.
- The p chart: This is used similar to the above mentioned graphs, but is useful when the data used to create the graph is not from the same sample size. For example, the data used may come from the number of accidents per employee, but the number of employees changes over time. The u chart is another similar variable sample chart.
- The Cusum chart: This is a graph which is useful in locating trends.

There are many more types of control charts and graphs. Using a well designed database, data access tools such as ODBC, and a spreadsheet program, and control charts, you will be able to discover ways to improve the quality of your product in ways that you never thought possible.