Is SPC (Statistical Process Control) useful?

Effocus, thanks for the frank comments. Several discussions are occurring on the Cove about usefullness of SPC, and at least I seem to have rattled some cages about encouraging folks to use SPC. I have several papers here and at the EFCOG website about use of SPC, and case studies. One is available at http :// www. efcog .org/wg/ca/events/spring09mtg/docs/2-Steve_Prevette_Leading_Indicators.pdf - OBSOLETE BROKEN 404 LINK(s) UNLINKED

Thanks but I need some time for reading your presentation. It seams that you use the I-MR chart and can you give some example for Xbar-R chart?

Must admit I don't use the Xbar-R since the early days of doing this 20 years ago. The management I deal with manages by month, and the concept of a differing time interval worth of data going into the chart (based upon rational subgrouping) blew their minds.

I will say I find discussions of the worth of SPC interesting. The fact that folks ask the question means they must have some seed of doubt in their minds about their current methods. And then I run into the folks that say "I'll do SPC when appropriate" which in 20 years experience always translates to "never".

I think SPC is kind of like flossing your teeth. It really doesn't take that long to do or that much of an effort, but we all tend to make excuses as to why we don't do it when the dental hygienist is chiseling away at the plaque on our teeth.

You can also read Free - Bob Doering's Blog Post Series , which shows how SPC can accurately determine when to make adjustments when machining and avoid overcontrol - saving time and effort for the operator. It can also provide a leading indicator to tool change prior to breakage, and much more. But...it must be performed correctly, or it will be a waste of time and effort.

Effocus said:

I do not think SPC is the easiest tool! For you may be but just image for the production floor, where they have to face with many other thing during his working day. And I think, the tool is quite difficult in the applying conditions for each chart (that in many real case are not "practicable")

As you can see in the practice, why the tool is "usefull" but very little application, and the value-added process is even less? In posting this, I do not intend to say the control chart is not correct, but I think the current way now of applying the control chart is too expensive meanwhile the value its brought is too little. So, as SPC experts - we might think of some more efficient tool, that are statistical based but applicable to daily production fields.

May be I'm not experience enough, but could you please to share with me some real example, when the production can use the control charts for the quality / productivity improvement and got actual benefit in long run (said at least 1 - 2 years)

Click to expand...

I wouldn't expect shop floor personnel to be able to set up SPC. That should be done by someone trained to do it. But once set up, it is easy to use. Add up 5 numbers, move the decimal point. Subtract the high from the low. Plot the two calculations. I have been very successful training shop floor people to do this.

Also keep in mind that there are many measurement products that do the work for you, so there is nothing to do but take the measurements. Some machine tools do everything so there's nothing to do but make adjustments.

The big benefit is that the tool tells when to make adjustments. I have found that machine operators tend to make adjustments too often. SPC provides some discipline.

I'm sorry you find SPC difficult to use, but if you work at it, you might change your mind.

In 1972 - NBC did a White Paper on the ever increasing quality level of Japans Auto Industry, they sent a plane full of reporters and industry experts to Japan to find the answer.

One of the things they found is the massive use of SPC methods to gain understanding of their process variation.

What we apparently saw was the massive use of SPC.

General Motors started using massive SPC shortly after that, however the results were less than hoped for due to the lack of understanding - some areas failed - which the blame was put on SPC - some areas were successful in varying degrees.

In one application SPC was used to prove that something had changed in the material that was being used to manufacture a small worm gear in power steering gears.

The shop floor only knew that Broachs, Drills, and most other machining tools were wearing out much sooner and it became nearly impossible hold all of the tolerances to an acceptable level.

Managements response was "nothing had changed"

We found 2 gons (about 15,000 pieces) of unmachined blanks that were dated prior to when the we believed things went bad - we applied SPC to these parts as we put them into the system and the system became in-control, stable,capable, and tool life returned to normal - after processing these parts we continued to monitor and found that when more recent material was reintroduced into the system stability, control, and capability was lost.

When management was approached with this evidence (control charts all around the conference room) the real cause was revealed - Lead had been removed from the blend without our knowledge - and was being mandated by the government soon anyway.

So, while we were unable to get this fixed in terms of getting the blend of material corrected - we were able work on Feeds & Speeds, tool design and a number of other things to get the processes back in a relatively stable condition.

My opinion of SPC has not changed in over 45 years - with the proper understanding and application it's hard to beat.

Tom

I have anecdotal evidence to support the value of SPC. For many years spring coilers used controllers that would adjust springs (while coiling) when they got too long or too short. You could tell the controller what length to adjust but that was it. Once this length was input, you couldn’t vary it. These sorters often resulted in huge amounts of scrap. It would adjust with just one spring running on the max. Now coilers use optical measuring and SPC. The over adjusting is almost completely eliminated. The scrap rate has dropped drastically and the resulting springs are much closer to the mean requirement.

I have found the use of SPC to depend heavily on the process, the product characteristic and the cost vs. benefit of using SPC.

On the positive side, I implemented SPC on an extruded automotive weatherstrip cut to length process. Prior to SPC, we had a classic case of process tampering. The line operator would set up, an inspector would check a part each hour and the operator would adjust the process in response to the inspector's results. SPC stopped the process tampering and the resulting variation went form incapable to capable. And the process did not require any adjustments throughout the run.

On the negative side, our automotive customer (OEM) forced us to implement SPC on a process that was under automated process control (can you spell redundancy?). This resulted in continual runs above and below the mean, but a very well maintained, stable and capable process in no need of SPC.

In another, short run machining business, I chose not to implement SPC. We were very capable of setting up to nominal, had extremely tight variation relative to specifications and the runs were too short to detect any appreciable tool wear. Yes, short run SPC was a possibility, but the benefit vs. cost simply was not worth the effort.

In my final analysis, SPC is a good tool, but should be used judiciously.

SPC only is a statistical tool
so i think it not all of industry are applicable; such as stamping and injection and electronic is suitable for SPC

Reading all these there is a common over-riding theme..."if applied properly"

And my experience is that SPC is rarely applied properly...it becomes an exercise unto itself...in which case it is an utter waste of time and resources.