1
$\begingroup$

I have the following FFT result charts. Searching for a way to forecast the future AMPLITUDE steps from the Time Domain Plot if possible, or the next maximum/minimum deviation based on some previous AMPLITUDE in time.

Is that possible when we have a Frequency Domain Plot which looks like that:

enter image description here

enter image description here

$\endgroup$
1
  • $\begingroup$ You can certainly do an inverse transform, but it will probably (certainly) be wrong. You might get a reasonable estimate using ARMA methods, en.wikipedia.org/wiki/…, but the frequency spectrum doesn't look right to me. So if we punt and assume it's "noise" then you can use various noise techniques. The first thing is to plot and analyze the first differences since you want step size. That may or may not help but will allow you to work with what you want. In any case, provide a link to the real data and other instances. $\endgroup$ – rrogers Dec 29 '20 at 21:54

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.