Previous in Forum: Welding Gas Pipe   Next in Forum: Quality: Fillet Leg Length Size for Tree Joint
Close
Close
Close
6 comments
Rate Comments: Nested
Anonymous Poster #1

What Statistical Approach for Maximizing Output?

05/26/2012 5:39 PM

Thanks in advance for looking at this thread. I'm currently looking at a bottleneck in production, whereby I've been asked to maximise the output of an oven. The output material must pass a strict specification. The easiest way to do this would be increase speed / add more material to the boats being processed. There are other things to consider eg adding more material will probably mean a rise in temp etc... Because of the price of gas I'd like to keep this constant. How would you do this ....change one variable at a time, and record....see if the material is a pass/fail? When the details of these trials have been received what statistical tools should I use to get the best combination of parameters to produce a maximum output? Could I use a doe in mini tab for this...haven't done stats for a long time so just downloaded a free trial of mini tab!

Reply
Interested in this topic? By joining CR4 you can "subscribe" to
this discussion and receive notification when new comments are added.

"Almost" Good Answers:

Check out these comments that don't yet have enough votes to be "official" good answers and, if you agree with them, vote them!
Guru

Join Date: Oct 2008
Posts: 42355
Good Answers: 1693
#1

Re: What statistical approach for maximising output?

05/26/2012 6:21 PM

Just show the results of your meticulous testing to someone who is familiar with the raw materials, methods used to process the materials and the end requirements of the product and let him decide how to modify the process.

You can still take credit for the improvement, if any.

Reply
Anonymous Poster #1
#2
In reply to #1

Re: What statistical approach for maximising output?

05/26/2012 7:10 PM

Was working with the oven manufacturers who have experience of all sorts of product. Their suggestions / settings were way off....

Would like to get back into stats...Do something that will be more concrete so people will stop repeating the tinkering thats currently going on.

I'm sure some of this work will be 'old ground' but if noone has ever recorded it I'll just have to revisit it...

Want to know how many experiments I should do... Quite a lot of variables I could potentially explore.

speed, temp, bed height, heat permeability of boat ( where material sits ) etc

Reply
Guru

Join Date: Oct 2008
Posts: 42355
Good Answers: 1693
#4
In reply to #2

Re: What statistical approach for maximising output?

05/26/2012 9:48 PM

List all the variables you can change and rank them.

Then go from there.

Reply
Guru

Join Date: Aug 2009
Location: Glen Mills, PA.
Posts: 2385
Good Answers: 114
#3

Re: What statistical approach for maximising output?

05/26/2012 8:08 PM

I don't think statistics work for this, it is more like selective breeding. Improvement A may negate improvement B but you won't know until you try them together. Try each improvement individually and then try to pair them and maybe, then triple them.

__________________
In a time of universal deceit, telling the truth is a revolutionary act. George Orwell
Reply
Associate

Join Date: Feb 2009
Posts: 26
#5

Re: What statistical approach for maximising output?

05/26/2012 10:30 PM

Don't know what your "load" is, but if you can pre-heat it with wasted heat from your oven or the discharge (cooling) side you will find an extreme gain there. Any gain would be better than room temperature, which I always refer to as "ice".. and it is "free" heat.. Once upon a time I had a client load his product onto carts and let the Sun do his pre-heat out side....Cycle time on the oven is another big deal.. If it cycles very often, for long periods, poor insulation or too much heat loss from wherever is an issue. If you are high tech and maintain something like +/- 2 degrees, there should be very short bursts of heat..... High tech is the way to go if you are not there already.. Get your oven as perfect as you can, then go from there.....

Reply Score 1 for Good Answer
Active Contributor

Join Date: Jun 2012
Location: Phoenix, AZ
Posts: 19
Good Answers: 1
#6

Re: What Statistical Approach for Maximizing Output?

06/06/2012 10:57 AM

To maximise the output there are several things to consider. Is the oven running at the same temperature all of the time and at the same speed or is there a variation of temps and speed necessary. How does the oven process parts? on a conveyor, a rack, etc? How many hours a day is the oven running? If you divide the number of parts parocessed by the total time it takes to get through the oven to find out what the actual time per part. balance your production line so that every operation takes that amount of time. This will result in a production line that is in constant motion. For every part put in at the beginning of the line, one should be completed. It may require combining operations or breaking them down but it will increase efficiency. It may not seem like much but every minute spent waiting for parts to come out of the oven is wasted.

__________________
""We are what we repeatedly do. Therefore, excellence is not an act, it's a habit", Aristotle.
Reply
Reply to Forum Thread 6 comments

"Almost" Good Answers:

Check out these comments that don't yet have enough votes to be "official" good answers and, if you agree with them, vote them!
Copy to Clipboard

Users who posted comments:

Anonymous Poster (1); Dammit (1); lyn (2); passingtongreen (1); qcmanager (1)

Previous in Forum: Welding Gas Pipe   Next in Forum: Quality: Fillet Leg Length Size for Tree Joint

Advertisement