System and method for statistically separating and characterizing noise which is added to a signal of a machine or a system
First Claim
1. A method for an electronic noise estimation unit to determine the probability density function type of a noise component in a signal, the method comprising:
- using the electronic noise estimation unit, numerically differentiating the signal within a window at least m number of times to obtain an m-order differentiated signal;
providing a histogram having a distribution that approximates the m-order differentiated signal;
selecting a probability density function type that approximates the distribution of the histogram from a library of probability density function types available to the noise estimation unit, wherein the probability density function type that approximates the distribution of the histogram is the probability density function type of the noise component; and
outputting the probability density function type of the noise component on an output line of the electronic noise estimation unit.
3 Assignments
0 Petitions
Accused Products
Abstract
Method for finding the probability density function type and the variance properties of the noise component N of a raw signal S of a machine or a system, said raw signal S being combined of a pure signal component P and said noise component N, the method comprising: (a) defining a window within said raw signal; (b) recording the raw signal S; (c) numerically differentiating the raw signal S within the range of said window at least a number of times m to obtain an m order differentiated signal; (d) finding a histogram that best fits the m order differentiated signal; (e) finding a probability density function type that fits the distribution of the histogram; (f) determining the variance of the histogram, said histogram variance being essentially the m order variance σ2(m) of the noise component N; and (g) knowing the histogram distribution type, and the m order variance σ2(m) of the histogram, transforming the m order variance σ2(m) to the zero order variance σ2(0), σ2(0) being the variance of the pdf of the noise component N, and wherein the histogram type as found in step (e) being the probability density function type of the noise component N.
16 Citations
18 Claims
-
1. A method for an electronic noise estimation unit to determine the probability density function type of a noise component in a signal, the method comprising:
-
using the electronic noise estimation unit, numerically differentiating the signal within a window at least m number of times to obtain an m-order differentiated signal; providing a histogram having a distribution that approximates the m-order differentiated signal; selecting a probability density function type that approximates the distribution of the histogram from a library of probability density function types available to the noise estimation unit, wherein the probability density function type that approximates the distribution of the histogram is the probability density function type of the noise component; and outputting the probability density function type of the noise component on an output line of the electronic noise estimation unit. - View Dependent Claims (2)
-
-
3. A method for an electronic noise estimation unit to characterize noise in a signal, the method comprising:
-
using the electronic noise estimation unit, numerically differentiating the signal within a window at least m number of times to obtain an m-order differentiated signal; providing a histogram having a distribution that approximates the m-order differentiated signal; providing a probability density function type that approximates the distribution of the histogram, wherein said providing a probability density function type includes selecting a probability density function type from a library of probability density function types available to the noise estimation unit; determining a variance of the histogram; determining a zero-order variance using the variance of the histogram and the probability density function type; and outputting at least one of the probability density function type or the zero-order variance on an output line of the electronic noise estimation unit. - View Dependent Claims (4, 5, 6, 7, 8, 9)
-
-
10. An apparatus for estimating noise in a signal, the apparatus comprising:
-
a differentiation module configured to receive the signal and numerically differentiate the signal within a range of a window at least m number of times to obtain an m-order differentiated signal; a first module configured to determine a histogram that approximates the m-order differentiated signal; a second module configured to determine a probability density function type that approximates the distribution of the histogram; a third module configured to determine a variance of the histogram; a fourth module configured to determine a zero-order variance using the variance of the histogram and the probability density function type; and an interface module configured to output at least one of the zero-order variance or the probability density function type. - View Dependent Claims (11, 12, 13, 14)
-
-
15. A system for estimating a pure signal component of a raw signal that includes the pure signal component and a noise signal component, the system comprising:
an electronic noise estimation unit including; a differentiation module configured to receive a raw signal and numerically differentiate the raw signal within a range of a window at least m number of times to obtain an m-order differentiated signal; a first module configured to determine a histogram that approximates the m-order differentiated signal; a second module configured to determine a probability density function type that approximates the distribution of the histogram; a third module configured to determine a variance of the histogram; and a fourth module configured to determine a zero-order variance using the variance of the histogram and the probability density function type; and a filter coupled to the noise estimation unit, wherein the filter is configured to receive the zero-order variance and the raw signal and to output the estimated pure signal component of the raw signal. - View Dependent Claims (16, 17, 18)
Specification