quote:


Document Type and Number:
United States Patent 6173074
Link to this page:
http://www.freepatentsonline.com/6173074.html
Abstract:
An acoustic signature recognition and identification system receives signals from a sensor placed on a designated piece of equipment. The acoustic data is digitized and processed, via a Fast Fourier Transform routine, to create a spectrogram image of frequency versus time. The spectrogram image is then normalized to permit acoustic pattern recognition regardless of the surrounding environment or magnitude of the acoustic signal. A feature extractor then detects, tracks and characterizes the lines which form the spectrogram. Specifically, the lines are detected via a KY process that is applied to each pixel in the line. A blob coloring process then groups spatially connected pixels into a single signal object. The harmonic content of the lines is then determined and compared with stored templates of known acoustic signatures to ascertain the type of machinery. An alert is then generated in response to the recognized and identified machinery. 

quote:

ORIGINAL: Ponyboy7

Nope, it's real. As someone who works in a related field, I know this works.

quote:

ORIGINAL: Real0ne

quote:

ORIGINAL: Ponyboy7

Nope, it's real. As someone who works in a related field, I know this works.

Can it work with jet engines ya think?

quote:

ORIGINAL: Termyn8or

Absolutely possible, and popeye is about right, FFT has been applied to acoustics for quite some time.

Back when they made really good high fidelity speakers they used it as a more accurate way to measure frequency response. This was in the mid to late 70s. They abandoned it for the pink noise method because it gave better readings on the junky speakers they started building, you know, the 15" five way speaker system that only weighs 12 lbs.

This is really only a different form of spectography. It would blow your mind what they can do with that. They can literally detect one pot plant in a three acre cornfield. They don't have to focus, just look for the signature.

Actually I don't see all that much in the way of applications for acoustic modeling of the sort, except for the military. Unless there is a band of thieves stealing jet engines. Yeah, I could see it now, they roust a rich guy after he lands "So just where did you get the engine for that Learjet ?".

T

quote:

ORIGINAL: thornhappy

Don't try it with a camcorder recording.

thornhappy

quote:

ORIGINAL: Real0ne

quote:

ORIGINAL: thornhappy

Don't try it with a camcorder recording.

thornhappy

why not?

quote:

ORIGINAL: thornhappy

quote:

ORIGINAL: Real0ne

quote:

ORIGINAL: thornhappy

Don't try it with a camcorder recording.

thornhappy

why not?

you'd want a nice, decent, calibrated microphone with a wide frequency response and the audio undistorted.

thornhappy

quote:

ORIGINAL: Termyn8or

For FFT, forget a dynamic mike, you need a really good one. There is not a dynamic mike made that does not have resonances. While uneven frequenct response, even phase distortion can be dealt with electronically, a mechanical resonance cannot.

When there is a serious error in the input that cannot be corrected, the output will be incorrect. I didn't say may, I said will.

Yes, expect to pay considerably more than five bux for it.

T

quote:

ORIGINAL: Real0ne

quote:

ORIGINAL: Termyn8or

For FFT, forget a dynamic mike, you need a really good one. There is not a dynamic mike made that does not have resonances. While uneven frequenct response, even phase distortion can be dealt with electronically, a mechanical resonance cannot.

When there is a serious error in the input that cannot be corrected, the output will be incorrect. I didn't say may, I said will.

Yes, expect to pay considerably more than five bux for it.

T

although I hear you I would have to disagree with this one simply because its unlikely to get a resonance in the usable area with a 1/8" diam mic diaphram.

I am very interesteed in hearing how accurate a mic has to be however to be useable in determining 2 different engines regarding the thron post

quote:

ORIGINAL: thornhappy

quote:

ORIGINAL: Real0ne

quote:

ORIGINAL: Termyn8or

For FFT, forget a dynamic mike, you need a really good one. There is not a dynamic mike made that does not have resonances. While uneven frequenct response, even phase distortion can be dealt with electronically, a mechanical resonance cannot.

When there is a serious error in the input that cannot be corrected, the output will be incorrect. I didn't say may, I said will.

Yes, expect to pay considerably more than five bux for it.

T

although I hear you I would have to disagree with this one simply because its unlikely to get a resonance in the usable area with a 1/8" diam mic diaphram.

I am very interesteed in hearing how accurate a mic has to be however to be useable in determining 2 different engines regarding the thron post

let me guess....you're going to try an FFT on the 9/11 jet noise to see if it's a commercial airliner vs a fighter aircraft.

thornhappy

quote:

ORIGINAL: Rule

quote:

ORIGINAL: thornhappy
let me guess....you're going to try an FFT on the 9/11 jet noise to see if it's a commercial airliner vs a fighter aircraft.

That would fail. The planes flight 11 and 175 in the films are computer generated images. It has been demonstrated that those movies have been tampered with. Presumably the sounds of those airplanes - if those are also in those films - have also been dubbed in correctly.
 
Now a cockpit voice recording, though... Conceivably it might be shown from the echoes, if any, that the cockpit voice recordings of the non-existent flights 11 and 77 were not recorded in a cockpit, or in the cockpit of a different type of plane...