When Statistical Process Control is applied properly, tremendous benefits in profitability and process understanding are achieved.
In addition, SPC data has other, less commonly recognized uses that can empower manufacturing. Other benefits from SPC data include efficient problem resolution, performance prediction, machine and tooling reliability, comparisons of processes/groups, and feedback to engineering/R&D.
Efficient Problem Resolution or Performance Prediction
Often, manufacturers discover some amount of unacceptable product through various testing. For example, automotive suppliers may find that their components make excessive noise or fail to meet certain performance requirements such as torque or efficiency or leak rate. In these situations, finding root causes may be challenging, and although properly designed experiments can quickly resolve such issues, looking at the SPC data first can be valuable.
In some manufacturing facilities, dimensional and material measurements are taken (in addition to final testing and performance data). Sometimes, changes in the dimensional or material measurements correlate to final performance features. A statistical method called “regression” can be used to quickly identify relationships between dimensional and design data and final performance data. The information in this data may resolve the issue, but even if it doesn’t, the data can be used to assist in the design of a more effective experiment.
Machine and Tooling Reliability
Waiting for a machine component or tool to break often causes excessive downtime and cost. In some instances, maintaining or replacing machine components is quicker and less expensive than dealing with broken equipment.
SPC data can be used to identify trends associated with the wear of tools or equipment components, and this data can be used to determine when equipment should be repaired or replaced. By using SPC data to predict when a component or tool is approaching its end-of-life, and by performing the needed repair or replacement prior to its failure, the expense of fixing a more complex break in the equipment can be avoided.
Comparisons of Processes/Cavities/Lines/Nests/Spindles/Measurement Devices/Shifts
Modern day production systems often produce multiple parts at the same time. For example, injection and compression molding operations output numerous components from multiple cavities. Often, parts are processes on different spindles or in different nests.
Other manufacturing processes output one product number on several production lines. In these instances, natural questions arise:
- Do the cavities run consistently with regard to dimensional or material properties?
- Does one cavity have more variation than another?
- Does the in-line tester measure consistently with the tester in the QA/QC Lab?
- Do different production lines run consistently with each other?
- Does one spindle have more variation than another—or produce larger values?
- Does shift one produce and/or measure consistently with shifts two or three?
Numerous statistical methods have been developed to answer these types of questions. The methods depend on the nature of the data (continuous, ordinal, nominal) and the question being asked (questions regarding averages or variation). The SPC data can be used for statistical hypothesis testing to quickly detect sources of variation that could negatively impact profitability or customer satisfaction. The data may also point to processes or areas where operations are superior, and identify inferior lines, dies, tools, measurement systems, etc. where operations can be upgraded.
Feedback to Engineering and/or R&D
When engineering and R&D design and develop new products or technologies, they often do not have much (or any) experience with the materials or chemicals they are using. During design and development, only a limited number of parts or product may be developed. Furthermore, the parts or products are usually developed on different equipment and in different scales (batch sizes or quantities) than manufacturing will handle.
Sometimes, initial designs or production systems do not perform exactly as anticipated when manufactured. If engineering or R&D does not receive feedback from manufacturing, they will not know whether their specifications and/or material choices are optimal. Furthermore, they may not know how production equipment interacts with some of their design choices, and whether other choices may be more robust against conditions in a production setting.
If SPC data is collected, the data can be reviewed by those responsible for design and development, and issues or suboptimal choices can be dealt with earlier—rather than too late.
Final Note
This article only suggests a few additional benefits of SPC data, but there are many others. Hopefully, readers will think about taking full advantage of SPC data to prevent problems, quickly resolve issues, and fully understand operations so that their companies satisfy customers while realizing maximum profitability.
Allise Wachs, PhD
Integral Concepts, Inc.
Integral Concepts provides consulting services and training in the application of quantitative methods to understand, predict, and optimize product designs, manufacturing operations, and product reliability. www.integral-concepts.com