Statistical Process Control (SPC) is a set of statistical and related methods for monitoring processes with an aim to improve productivity and reduce costs, time, and waste incurred by these processes. In fact, SPC is a philosophy surrounding the monitoring, analysis, and adjustment of process variables to produce continuous improvements in the process.
There are a lot of terms that mean SPC, or that are a part of SPC. I plan to address some of these topics in more detail in future posts.
- Process Control
- Process Capability
- Quality Assurance
- Quality Control
- Total Quality Management
- Reliability Engineering
- Six Sigma
- Lean Manufacturing
- Continuous Improvement
Statistical tools commonly used in SPC include the following (with links to pages on the Peltier Tech web site):
- Run Charts (Control Charts)
- Box and Whisker Charts
- Probability Plots
- Pareto Charts
- Scatter Plots
- Regression Analysis
- Analysis of Variance
I will discuss several of these charting techniques in future posts.
Here are a few online resources you can visit to learn more about SPC.
- National Institute of Standards and Technology
NIST/SEMATECH e-Handbook of Statistical Methods
Process Control Techniques
- Business Process Improvement
SPC Articles and Newsletter
SPC for Excel Software
Statistical Process Control on Wikipedia
Stay tuned for my follow-up posts on SPC. I will build a running index on this page as I add topics.
Awaiting the series in frothing anticipation… sounds like it could be very useful.
Jon, I would be interested in hearing your thoughts not only on the technical areas of quality (charting, controls, etc.), but quality theory as well. Sometime back I spent several years working in quality for a large manufacturing company. My job was to monitor machine downtimes, general maintenance, parts replacement, and the costs associated with those activities. It was interesting to see how the emphasis on quality changed as the bottom line changed. You would think that as profits fell the emphasis on quality and efficiency would increase. However, my experience tended to move more toward the opposite. As profits fell the company wanted to reduce costs. The results of improvements in efficiency and maintenance were often very hard to quantify and many could not see the value. As a result, quality was often an easy area to target because it was thought of as pure overhead.
Jon Peltier says
Good question, and I don’t think the answer is not in quality theory, but rather in quality “psychology”. I think the problem is that many middle and upper managers haven’t really bought into the “Quality” philosophy. They have all the posters on the wall, all the visual workplace bulletin boards. They say the right words. And they don’t walk the talk.
Partly I think it’s that they don’t understand the theories and methodologies. Partly they’re afraid of new things. Partly, they don’t think they have time for a longer range quality implementation: they need a quick fix, and they jerk their knees. They see a blip in a control chart and panic, they holler and stamp their feet, and lo and behold, next month it improves; they give out awards, and OH NO, next month it’s bad again. They don’t see that the process is unchanged and all three points are “in control”. Or worse, the process has been changed, in fact, subverted, and they end up paying next month because someone gamed the numbers this month.
When I was doing the TQ/Six Sigma training, at first the line workers were hard to sell on the ideas. But they realized that when they recorded and tracked and analyzed their processes, they could understand what was going on, and they could see obvious ways to improve the process. Once they got a few big gains plotted on the bulletin boards, they were sold.
The managers at first seemed to buy in, but it was apparent that they put on the whole TQ face because it was decreed from above that they would buy in. But they couldn’t believe the line workers were smart enough, and this new thing was just the new flavor-of-the-month. And if the managers don’t really buy in, the line guys lose interest, and next time it’s harder to gt them on board. And really, if you can get the line guys on board, long enough to make it a habit, you will have a good foundation.
I’ve seen these quality initiatives in several divisions of a large manufacturing company as an employee, in another division of a smaller manufacturing company again as an employee, and in several other companies as vendor, customer, or collaborator. The implementation ranged from very good, in organizations where all levels bought in, to horrendous, in organizations where the managers told the workers they will do it this way and they will like it. No surprise, really.
Jon Peltier says
Damir – Good point. Not only do they not make the connection, many are not motivated to learn enough to make the connection.
One of the first lessons I learned after I got my doctorate and entered the corporate world, was that the guy running a machine may never had finished high school, but he knew more about that machine than everyone in the plant.
I was visiting a manufacturing facility to process some exotic new alloy we’d developed, and the plant manager was telling us how our material would be handled, and how it would behave during the process. Then I went onto the floor (the plant manager never went on the floor, it turns out), and everything was completely different. The workers were not lazy bums: they hustled with the material in one direction, but going back empty handed, they took their time, but that’s what the manager saw from his window. The guy running the press didn’t just gun it, he felt how the material responded and he tweaked the controls accordingly. It was like he was guiding a fighter in for a difficult landing. He just had an instinctive feel. Upon retrospect with my fancy diploma and all, I could later determine what were the physical mechanisms underlying the behavior. But the operator could make the adjustments on the fly.
One of the first topics in my quality classes was that the person who knows the most about a job is the person doing it. This was very hard for many managers, and even for many engineers, to comprehend. I had the benefit of seeing it in practice on my first trip outside the lab into a real-world manufacturing facility. Most managers are “too busy” to walk around the shop to see how things worked, and even a lot of engineers don’t bother. At least Dilbert’s manager practiced “management by walking around”, but he did it walking in the park at lunchtime.
I’ve always made a point of going out on the floor to talk with the workers. You ask about the job they just finished, why something deviated. Then you talk about the Sox game last night. You develop a rapport with them, and then when something comes up that you should know about, one of the “special causes” of SPC, they’re not afraid you’ll go ballistic when they tell you about it. In my last manufacturing job, I knew the guys on the floor, and the guys knew me. Maybe not too well, but well enough to shoot the breeze. My boss and his boss didn’t know any of the guys, and when they went out on the floor, the workers said, “Who’s that?” The bosses had been there twenty years, yet had never interacted with the people making the product that their livelihood depended upon.
I think the main problem is simply in understanding what SPC actually is.
In my experience, a “seasoned” process engineer or machinist has no problem with understanding sigma-related charts. Most of these people have even developed a gut feeling for this. In most cases, people in management and paper-pushing engineering positions simply can not connect these numbers/charts to actual process–yet they are the ones making presentations and decisions.
C Marsden says
Some interesting articles and comments.
Aaron Varuolo says
Interesting article. Well written. Thank you for the post.
Aaron Varuolo says
Germaine Koziarski says
Very interesting article! Thanks Jon for sharing this helpful information! Having read your article, I will now do further research to see if SPC can help my business.
Thanks again! :-)