uncertainty budget excel

[CalLabSolutions]

We have DC Fluke 732b-10V, divider Fluke 752a, and null indicator Keithley 2182. With this units i calibrate 5720 (100 mV, 1V, 10V,100V, and 1kV range), and than i can use specification 24hr+this U95 calibration certificate in uncertainty budget?

Irv1n sounds like you guys have it all put together right.  In your uncertainty budget you may have to add the resolution and repeatability of the UUT / Measurement.  But that should be small contributor if you have a good set of test leads. When I was working on the procedure we had to dig around for some good cables.  And in the end the customer decided to order the 8508A-Leads.

Mike

[Hawaii596]

MetVet I agree about the unbroken chain.  I was just simplifying.

Regarding the 4 to 1 and 10 to 1, those were simpler times.  I miss them.  But even the 4 to 1 and 10 to 1 were simplified means to deal with those uncertainties that were present even back then.  The concept of uncertainty has been around a very long time and was used way back into the MIL-STD-45662 days.  We just didn't use them at Cal Lab levels.  I believe in terms of quality, the application of uncertainty has been an improvement needed as technologies push the envelope.  The demand for accuracy is ever increasing.  4 to 1 and 10 to 1 were a little more "qualitative" whereas the MU method (if I may be so loose with my language) is turning it more "quantitative."  Like it or not, I believe the day is coming when uncertainties will need to be calculated for every calibration.  Hopefully later than sooner, as there are many calibrations where those calculations don't make much sense.  Not to mention that easy application of methods to calculate and report uncertainties in accordance with ILAC P14 are not universally available (many of us spend a lot of hours on uncertainties).

[microwave-kevin]

Okey, may be anyone give excel template calculating with uncertainty toolbox?

There was book by ASQ (Dilip Shaw and some others) a a few years back that came with a CD with spreadsheet examples for several chapters, could not find on Amazon, check with NCLSI, ASQ and ask for Dilips book..... everyone knows Diiip!

[scottbp]

We have DC Fluke 732b-10V, divider Fluke 752a, and null indicator Keithley 2182. With this units i calibrate 5720 (100 mV, 1V, 10V,100V, and 1kV range), and than i can use specification 24hr+this U95 calibration certificate in uncertainty budget?

Irv1n sounds like you guys have it all put together right.  In your uncertainty budget you may have to add the resolution and repeatability of the UUT / Measurement.  But that should be small contributor if you have a good set of test leads. When I was working on the procedure we had to dig around for some good cables.  And in the end the customer decided to order the 8508A-Leads.

Mike

I worked out a way to calibrate our 5720A by using the 8508A in ratio mode. The process goes basically like this:

1. Connect the standard cell output to the rear terminals of the 8508A and the 5720A to the front terminals of the 8508A. 
2. Set the 8508A on the 20V range, then set the output of the 5720A to 10 volts, and operate.
3. Set the 8508A for ratio measurement by pushing the Input button, then the Scan button, then F÷R.
4. Next, dial the 5720A to the predicted value of the standard cell from the control chart (e.g. 9.999893 V), then press the "NEW REF" button.
5. Then dial the knob until the 8508A reads as close to 1.0000000 as possible.
6. The actual output of the 5720A can then be calculated from the error displayed on the screen (e.g. if the error is -0.7 ppm, then the actual output of the 5720A at 10 V  is 9.999993 V).

You theoretically could then turn off the ratio mode of the 8508A, return the 5720A to nominal 10V and read the output displayed on the 8508A, then calculate the difference from the actual 5720A output found in step 6 above. That way you have calibrated your 5720A and 8508A at the same time.

For 100 and 1000 volt ranges, the uncertainty is too large across the ranges of the 8508A to use it by itself for a 10:1 and 100:1 ratio; so instead you would use a (properly balanced) 752A divider to divide down the 5720A output to stay within same 20 V range as the standard cell, so you can still take a 1:1 ratio measurement.

For 1 V and 100 mV ranges, instead of dividing the 5720A output with the 752A, you would divide down the standard cell output, and connect the 5720A directly to the 8508A. The 8508A would still be doing a 1:1 ratio measurement, except this time on the 2 V and 200 mV ranges.

BTW- just to keep on topic- another great uncertainty budget excel template can be found at the NIST website at http://www.nist.gov/pml/wmd/labmetrology/upload/Uncertainty_Budget_Table_Template_16Jan2013.xlsx

[Hawaii596]

I'll have to try it.  I do have a 752A.

[CalLabSolutions]

Scott,
I pretty much did the same thing only with a 3458A.. We all know the adjustment of the 3458A is done with a 10V cell and two resistors.   So I used the HP 3458A because of its design.  Its internal circuits take that 10V and transfer it to all the ranges.  That leaves the question, what dividers are better, but for me I like the 3458A because I can compare the 10% of one range to 100% of the other. 
Mike

[Irv1n]

We have DC Fluke 732b-10V, divider Fluke 752a, and null indicator Keithley 2182. With this units i calibrate 5720 (100 mV, 1V, 10V,100V, and 1kV range), and than i can use specification 24hr+this U95 calibration certificate in uncertainty budget?

Irv1n sounds like you guys have it all put together right.  In your uncertainty budget you may have to add the resolution and repeatability of the UUT / Measurement.  But that should be small contributor if you have a good set of test leads. When I was working on the procedure we had to dig around for some good cables.  And in the end the customer decided to order the 8508A-Leads.

Mike

I worked out a way to calibrate our 5720A by using the 8508A in ratio mode. The process goes basically like this:

1. Connect the standard cell output to the rear terminals of the 8508A and the 5720A to the front terminals of the 8508A. 
2. Set the 8508A on the 20V range, then set the output of the 5720A to 10 volts, and operate.
3. Set the 8508A for ratio measurement by pushing the Input button, then the Scan button, then F÷R.
4. Next, dial the 5720A to the predicted value of the standard cell from the control chart (e.g. 9.999893 V), then press the "NEW REF" button.
5. Then dial the knob until the 8508A reads as close to 1.0000000 as possible.
6. The actual output of the 5720A can then be calculated from the error displayed on the screen (e.g. if the error is -0.7 ppm, then the actual output of the 5720A at 10 V  is 9.999993 V).

You theoretically could then turn off the ratio mode of the 8508A, return the 5720A to nominal 10V and read the output displayed on the 8508A, then calculate the difference from the actual 5720A output found in step 6 above. That way you have calibrated your 5720A and 8508A at the same time.

For 100 and 1000 volt ranges, the uncertainty is too large across the ranges of the 8508A to use it by itself for a 10:1 and 100:1 ratio; so instead you would use a (properly balanced) 752A divider to divide down the 5720A output to stay within same 20 V range as the standard cell, so you can still take a 1:1 ratio measurement.

For 1 V and 100 mV ranges, instead of dividing the 5720A output with the 752A, you would divide down the standard cell output, and connect the 5720A directly to the 8508A. The 8508A would still be doing a 1:1 ratio measurement, except this time on the 2 V and 200 mV ranges.

BTW- just to keep on topic- another great uncertainty budget excel template can be found at the NIST website at http://www.nist.gov/pml/wmd/labmetrology/upload/Uncertainty_Budget_Table_Template_16Jan2013.xlsx

and what uncertainty model (mathematical model) of this measurements?

[CalLabSolutions]

UGH.. I spent as much time on the Unc calculations as I did writing the software.

[Hawaii596]

It is pretty straightforward to do calculations for ScottBP's method.  But not simple.  You have to go through each step, enumerate all the contributors, and run the various RSS calculations, etc. 

Just lots of work in Excel.

[scottbp]

I worked up a quick and dirty budget as follows:
10 V standard cell: 0.7 µV/V
8508A ratio uncert. on 20V range: 0.12 ppm rdg+0.1 ppm rng
This works out to be 1.43 µV/V, which is ±14.3 µV at 10V. The 1 year, 95% spec of the 5720 at 10V is 37.5 µV, so it's about a 2.61 t.u.r. The largest uncertainty contributor is the standard cell; if we could hold it down to about half, we could bring the uncertainty down to 7.66 µV and the t.u.r. up to 4.89.

The divider adds 0.2 ppm on the 10:1 ratio, and 0.5 ppm on the 100:1 ratio.
The 8508A is 0.4 ppm rdg + 0.3 ppm rng on the 200 mV range, and 0.12 ppm rdg+0.1 ppm rng on the 2 V range.

Like you say... Straightforward, but not simple; a lot of Excel calculations.

[Bryan]

With the standard cell on the back of the 8508, 5720 on the front doing F/R ratio you could just set the 5720 to the nominal value and then multiply the 8508 measured ratio times the standard cells value to determine the 5720 actual.  At least that's what I'm working on, hoping to shelve the 752 and come up with a setup that lessens operator influence/interpolation

[CalLabSolutions]

You are not making absolute measurements with the meter, so you don't have to use the absolute spec.  Because we made the measurements, one after the other at 10V, we only used the meter's floor value.  Then we RSS-ed in the 5720's linearity spec. Because our ultimate goal was to generate exactly 10.000000000V. 
This also allowed us to test our methodology.  We can then cal a 3458A to the 10V cell and see just how close we came to our 10V.
Mike

[Irv1n]

What resolution uncertainty i can use for analog devices, how calculate?

[CalLabSolutions]

Tom Morgon did a great article on this..
http://www.callabmag.com/?p=4201

[Irv1n]

8508A ratio uncert. on 20V range: 0.12 ppm rdg+0.1 ppm rng
This works out to be 1.43 µV/V, which is ±14.3 µV at 10V.

how u receive 14.3 µV at 10V? what rdg was in measurements?