What you are asking is this: is there a way to solve my problem before I know what the problem is – and the answer is “no”. The whole point of DMAIC is that of problem identification, investigation, and resolution.

No, that’s called cheating. We are assuming your upper spec limit is there for a reason. If it isn’t arbitrary then, given your description of events, you are just trying to pretend that some kind of special cause which is driving your process to the upper spec limit (and presumably at some future date will drive your process past that limit) doesn’t matter. The only solution your approach provides is a way to ignore problems with your process for the time being – this is not process improvement.

@feodor85 First if it is acceptable to move the spec then it should not have been there in the first place. You don’t move the spec just because the process is drifting closer to it.

Let me try an example. I had a process where I was plating gold. The most profitable place to operate is right on the lower spec limit with a mean equal to the spec limit and a std deviation of 0. That won’t happen so I need to set a target as close to the spec as possible. I can do that by using my process mean and std deviation but I am assuming I can shift the mean without affecting the std deviation – you need to verify that.

The mean movement id frequently done with knobs. I try to move my mean closer to the target I calculated and then do a follow on study to verify I am still ok. As I continue to improve my process and decrease the std deviation I can shift my mean closer to my optimal target.

You shift based on data.