cancel
Showing results for 
Show  only  | Search instead for 
Did you mean: 
Browse apps to extend the software in the new JMP Marketplace
Choose Language Hide Translation Bar

How do I create a correlation or fit model to identify power consumption increase?

Hi, I am an absolute beginner in JMP and I am interested to know an accurate representation of what is the extra power that my motor will consume if the filter dP is at 1500 psi vs 2000 psi.

 

I did a multivariate analysis and using my process knowledge I am able to narrow down the parameters that will affect the power consumption. I did a preliminary test using fit model and able to create an equation with a pretty solid Rsquared however I am not sure if this is the right track. Should I then use the prediction profiler and set my dP at 1500 vs 2000 psi and look at the resulting power comparing those two? 

1 REPLY 1
dale_lehman
Level VII

Re: How do I create a correlation or fit model to identify power consumption increase?

I notice that you colored the points by year but did not include year in your model - I would add year as an effect.  But I believe your conjecture about how to proceed is appropriate - you can use the profiler to see the estimated power along with confidence intervals from your model.  I would only add that I think there might be a bit more accurate model lurking if you explore the behavior over time.  Month seems to entail both power and dP varying (with month as a nominal variable) and produces a slightly better model.  I don't understand your motor and the process at all, so that expertise probably would help understand how/why things might change throughout the year.  But I didn't see any interaction between the year and the effects of dP on power.