CN101729157A - Method for separating vibration signal blind sources under strong noise environment - Google Patents
Method for separating vibration signal blind sources under strong noise environment Download PDFInfo
- Publication number
- CN101729157A CN101729157A CN200910232300A CN200910232300A CN101729157A CN 101729157 A CN101729157 A CN 101729157A CN 200910232300 A CN200910232300 A CN 200910232300A CN 200910232300 A CN200910232300 A CN 200910232300A CN 101729157 A CN101729157 A CN 101729157A
- Authority
- CN
- China
- Prior art keywords
- matrix
- signal
- separation
- order
- noise reduction
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 38
- 238000000926 separation method Methods 0.000 claims abstract description 33
- 230000002087 whitening effect Effects 0.000 claims abstract description 7
- 239000011159 matrix material Substances 0.000 claims description 87
- 230000009467 reduction Effects 0.000 claims description 22
- 238000001914 filtration Methods 0.000 claims description 8
- 238000000354 decomposition reaction Methods 0.000 claims description 6
- 239000000654 additive Substances 0.000 claims description 5
- 230000000996 additive effect Effects 0.000 claims description 5
- 230000008569 process Effects 0.000 claims description 5
- 238000011946 reduction process Methods 0.000 claims description 5
- 238000002203 pretreatment Methods 0.000 claims description 3
- 230000000694 effects Effects 0.000 abstract description 4
- 230000008901 benefit Effects 0.000 abstract description 3
- 230000001955 cumulated effect Effects 0.000 abstract 3
- 238000005457 optimization Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 238000005311 autocorrelation function Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 230000002950 deficient Effects 0.000 description 1
- 238000002955 isolation Methods 0.000 description 1
- 239000010977 jade Substances 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 238000001228 spectrum Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Images
Landscapes
- Filters That Use Time-Delay Elements (AREA)
Abstract
The invention discloses an algorithm for separating vibration signal blind sources under a strong noise environment. The method comprises the following steps: 1, de-noising a group of given mixed signals containing noise through a time delay autocorrelation method to acquire de-noised mixed signals; 2, performing mean value removal and steady whitening pretreatment on the mixed signals acquired in the first step to further reduce the influence of the noise signals on the separation result; and 3, calculating second-order and fourth-order cumulated amount of the initial separate signals, using the sum of diagonal elements of second-order and fourth-order cumulated amount matrixes as a cost function, and maximizing the cost function to similarly diagonalize the joints of the cumulated amount matrixes so as to realize the separation of the signals of the independent sources and acquire orthogonal separation matrixes. The method combines the conventional de-noising method and the blind separation algorithm to realize the separation of the mixed signals under the strong noise environment, and has the advantages of good separation effect, high convergence rate and de-noising effect free from the limitation of the set threshold value compared with the conventional algorithm.
Description
Technical field
The present invention relates to the isolation technics of aliasing vibration signal, the aliasing vibration signal under especially a kind of strong noise environment separates technology.
Background technology
Aliasing vibration signal blind under the strong noise environment separates, because of its more near actual conditions, be the signal of interest processing method of identification signal of vibrating and small-signal, become related scientific research mechanism, and various countries scholar's research focus.
Existing method is mostly based on such fact: ignoring under the situation of noise, utilizing optimal method the optimization of independence criterion to be realized the separation of Instantaneous Mixtures.Vibration signal is as a kind of signal with time structure, the diagonal element quadratic sum that can adopt second order cumulant matrix usually is as cost function, this cost function of optimization is realized the separation of mixed signal, and its complexity is low, computational speed is fast, but noise signal is not had robustness.Having utilized the Higher Order Cumulants of noise signal based on the JADE algorithm of fourth order cumulant matrix is zero characteristic, realize the separation of mixed signal by each fourth order cumulant matrix of associating approximate diagonalization, because it has utilized Higher Order Cumulants, its complexity is big, computational speed is slow, responsive to the open country value, and only the white Gaussian coloured noise is had robustness.
At the aliasing signal that contains noise, consider to utilize the wavelet de-noising method that signals and associated noises is carried out noise reduction earlier, reducing the influence of noise signal, and then the aliasing signal behind the noise reduction is separated separating effect.Yet in the wavelet de-noising method, choosing of threshold values is most important, selects the improper algorithm that will cause to lose efficacy.
Summary of the invention
The present invention seeks at the defective that prior art exists provide a kind of proposition under strong noise environment, have good separating property, faster separating rate, the strong aliasing vibration signal of noise robustness is separated algorithm.
The present invention adopts following technical scheme for achieving the above object:
The method for separating vibration signal blind sources of a kind of strong noise environment of the present invention is characterized in that, this method may further comprise the steps:
(1), one group of given mixed signal that contains noise is carried out noise reduction process through autocorrelation method, then the mixed signal after the autocorrelation method noise reduction process is realized the secondary noise reduction through the time delay method, obtain the mixed signal x (t) behind the noise reduction, wherein t is a time series;
(2), the mixed signal x (t) behind the described noise reduction of step (1) is gone additive white Gaussian among the mixed signal x (t) behind average and the described noise reduction of steady whitening pretreatment filtering;
Described sane whitening pretreatment method is as follows:
(A) the mixed signal x (t) behind the calculating noise reduction is at time delay τ
jUnder covariance matrix C
x(τ
j), and with covariance matrix C
x(τ
j) be adjusted into:
In the following formula, τ
jRepresent j time delay, j=1,2 ..., J, J are the time delay number and are natural number that T represents transpose of a matrix, with M
x(τ
j) be configured to a combinatorial matrix M, and carry out singular value decomposition, that is:
M=[M
x(τ
1),…,M
x(τ
J)]
M=U∑V
T
In the following formula, U is the orthogonal matrix identical with the Metzler matrix dimension; ∑ is the diagonal matrix of being made up of the singular value of M; V is an orthogonal matrix;
(B) picked at random parameter matrix α=[α
1..., α
j..., α
J], α wherein
jJ the vector of expression parameter matrix α is for time delay τ
j, calculate:
f
j=U
TM
x(τ
j)U
Carrying out linear combination has:
When matrix F satisfies orthotropicity, then forward step (D) to, otherwise forward step (C) to;
(C) adjust parameter matrix α according to the pairing characteristic vector u of the minimal eigenvalue of matrix F, that is:
Go to step (B) then, satisfy orthotropicity up to matrix F;
(D) the parameter matrix α that utilizes step (C) to obtain calculates objective matrix C, and it is made characteristic value decomposition, that is:
C=RDR
T
In the formula, D is the diagonal matrix of being made up of the characteristic value of objective matrix C, the R eigenvectors matrix that each characteristic value characteristic of correspondence vector is formed of serving as reasons;
(E) try to achieve albefaction matrix Q=D
-1/2R
T, whitened signal is z (t)=Qx (t).
(3), calculate the second order and the fourth order cumulant of initially-separate signal, with the diagonal element quadratic sum of second order and fourth order cumulant matrix as cost function;
Described initially-separate signal is as follows:
Initial quadrature separation matrix is W, then initially-separate signal y (t)=Wz (t);
(4), by cost function in the maximization steps (3), realize the associating approximate diagonalization of each second order and fourth order cumulant matrix, the quadrature separation matrix P that obtains making the mixed signal of the described filtering additive white Gaussian of step (2) to separate, thus separation matrix H and separation signal s (t) obtained; H=PQ wherein, s (t)=Hx (t).
The blind source separation method of described a kind of strong noise environment is characterized in that described quadrature separation matrix P adopts the Givens rotary process to try to achieve.
The invention has the beneficial effects as follows that the present invention is the algorithm that the aliasing vibration signal blind separates under a kind of strong noise environment, comprise noise reduction, sane preliminary treatment, structure cost function, optimize cost function and find the solution 4 steps of separation matrix.Before separating, fully the filtering noise signal to reduce the influence of noise signal to separating resulting, is finally realized the separation of aliasing signal under the strong noise environment.
In (1) step, the present invention has adopted time delay auto-correlation noise-reduction method, when this method of use is carried out noise reduction to the aliasing signals and associated noises, can realize the secondary noise reduction and not need to be provided with threshold values, and auto-correlation processing can keep the periodicity useful information in the vibration signal, remove noise aperiodic at random, the feasibility of its noise reduction has obtained affirming of people in the industry.Therefore, with the effective noise signal in the filtering aliasing signals and associated noises of this method.
In (2) step, the present invention is directed to the aliasing signal behind the noise reduction in (1) step, propose to utilize the additive white Gaussian in the sane preprocess method filtering aliasing signal, further reduce the influence of noise to separating resulting.
In (3) step, taken all factors into consideration advantage based on second order cumulant and fourth order cumulant algorithm, with the quadratic sum of the diagonal element of second order cumulant and fourth order cumulant matrix as cost function, make algorithm the convergence speed fast and insensitive, and avoided second order cumulant algorithm and can not separate deficiency with same spectrum architecture signals to the open country value than the fourth order cumulant algorithm.
In (4) step, the present invention utilizes optimal method that cost function is carried out optimization, realizes the associating approximate diagonalization of second order cumulant and fourth order cumulant, therefore realizes the separation of aliasing signal.
Therefore, the existing algorithm of the present invention has: under the strong noise environment good separating effect and stable, be not subjected to threshold values that the advantage of restriction is set, and have the characteristic of fast convergence rate for the separation of a plurality of aliasing signals.
Description of drawings
Fig. 1 is a method flow diagram of the present invention.
Embodiment
Be elaborated below in conjunction with the technical scheme of accompanying drawing to invention:
In conjunction with the accompanying drawings enforcement of the present invention is made and being further specified.Fig. 1 is a method flow diagram of the present invention, and as shown in Figure 1, this algorithm comprises following four steps.
Step 1: for one group of given mixed signal that contains noise, at first mixed signal is made auto-correlation processing, remove then after the auto-correlation processing signal time delay be zero and the time delay maximum near part, to realize the secondary noise reduction, obtain the mixed signal behind the noise reduction.Be specially:
With the auto-correlation noise-reduction method noisy aliasing signal is carried out noise reduction, the auto-correlation function of signal x (t) is defined as:
Wherein, L is the cycle of signal x (t), and τ is a delay parameter.
Noisy aliasing signal is carried out auto-correlation processing to reduce the random Gaussian signal in the aliasing signal, for further reducing the influence of noise signal, data after the auto-correlation processing are carried out time delay processing, promptly remove time delay and be near zero and time delay is near the maximum data.The data length of removing depends on the circumstances.
The also spendable noise-reduction method of this 1 step comprises: methods such as wavelet de-noising method, medium filtering, but the auto-correlation noise-reduction method need not to set threshold values in noise reduction process, can not destroy the original structure of signal.
Step 2: the mixed signal x behind the noise reduction (t) (wherein t is a time series) is gone average and steady whitening pretreatment.
The sane whitening pretreatment method that this step adopted is:
(A) mixed signal behind the calculating noise reduction is at different delay τ
jUnder covariance matrix C
x(τ
j), have better symmetrical structure in order to make covariance matrix, it is adjusted into
In the formula, j=1,2 ..., J (J is the time delay number and is natural number), T represents transpose of a matrix, with M
x(τ
j) be configured to a big combinatorial matrix M, and carry out singular value decomposition, promptly
M=[M
x(τ
1),…,M
x(τ
J)] (3)
M=U∑V
T (4)
In the formula, U is the orthogonal matrix identical with the Metzler matrix dimension; ∑ is the diagonal matrix of being made up of the singular value of M; V is an orthogonal matrix.
(B) picked at random parameter matrix α=[α
1..., α
J], for each time delay τ
j, calculate
f
j=U
TM
x(τ
j)U (5)
Carrying out linear combination has
Whether judgment matrix F satisfies orthotropicity, if matrix F is a positive definite, forwards (D) so to, otherwise forwards (C) to.
(C) adjust parameter alpha according to the pairing characteristic vector u of the minimal eigenvalue of matrix F, promptly
Go to (B) then, satisfy orthotropicity up to matrix F.
(D) the parameter matrix α that utilizes (C) to obtain calculates objective matrix C, and it is done characteristic value decomposition, promptly
C=RDR
T (9)
In the formula, D is the diagonal matrix of being made up of the characteristic value of Matrix C, the R eigenvectors matrix that each characteristic value characteristic of correspondence vector is formed of serving as reasons.
(E) try to achieve albefaction matrix Q=D
-1/2R
T, whitened signal is z (t)=Qx (t).
Step 3: calculate the second order and the fourth order cumulant of initially-separate signal, and with the quadratic sum of the diagonal element of second order and fourth order cumulant matrix as cost function.Implementation procedure is as follows:
If y (t) is the initially-separate signal, W is the initial quadrature separation matrix identical with the aliasing signal dimension, then y (t)=Wz (t).The second order and the fourth order cumulant of initially-separate signal are defined as respectively:
For realizing the associating approximate diagonalization of each cumulant matrix, with the quadratic sum of the diagonal element of cumulant matrix as cost function, promptly
Wherein, N is the number of source signal.According to principle of stacking, with two cost functions of formula (11) superpose algorithm cost function of the present invention:
ψ
24=ψ
2+ψ
4 (12)
Step 4: by maximizing this cost function, realize the associating approximate diagonalization of each cumulant matrix, obtain separation matrix and separation signal.
In realizing the aliasing signal separating process, generally comprise two steps: i.e. signal albefaction reaches carries out the quadrature rotation transformation to the signal after the albefaction.Specifically be described below:
(1) to the albefaction of aliasing signal,, reduces the computation complexity of subsequent step to remove correlation between signals.The albefaction process of this step is realized by step 2.Here do not give unnecessary details.
(2) orthogonal transform of whitened signal.Usually, the cost function of maximization formula (12) is and looks for a quadrature separation matrix P.Here adopt the Givens rotary process to ask for a quadrature separation matrix.
The separation matrix that obtains is the product of albefaction matrix and quadrature separation matrix, i.e. H=PQ.Separation signal is s (t)=Hx (t).
Claims (2)
1. the method for separating vibration signal blind sources under the strong noise environment, it is characterized in that, this method may further comprise the steps: (1), one group of given mixed signal that contains noise is carried out noise reduction process through autocorrelation method, then the mixed signal after the autocorrelation method noise reduction process is realized the secondary noise reduction through the time delay method, obtain the mixed signal x (t) behind the noise reduction, wherein t is a time series;
(2), the mixed signal x (t) behind the described noise reduction of step (1) is gone additive white Gaussian among the mixed signal x (t) behind average and the described noise reduction of steady whitening pretreatment filtering;
Described sane whitening pretreatment method is as follows:
(A) the mixed signal x (t) behind the calculating noise reduction is at time delay τ
jUnder covariance matrix C
x(τ
j), and with covariance matrix C
x(τ
j) be adjusted into:
In the following formula, τ
jRepresent j time delay, j=1,2 ..., J, J are the time delay number and are natural number that T represents transpose of a matrix, with M
x(τ
j) be configured to a combinatorial matrix M, and carry out singular value decomposition, that is:
M=[M
x(τ
1),…,M
x(τ
J)]
M=U∑V
T
In the following formula, U is the orthogonal matrix identical with the Metzler matrix dimension; ∑ is the diagonal matrix of being made up of the singular value of M; V is an orthogonal matrix;
(B) picked at random parameter matrix α=[α
1..., α
j..., α
J], α wherein
jJ the vector of expression parameter matrix α is for time delay τ
j, calculate:
f
j=U
TM
x(τ
j)U
Carrying out linear combination has:
When matrix F satisfies orthotropicity, then forward step (D) to, otherwise forward step (C) to;
(C) adjust parameter matrix α according to the pairing characteristic vector u of the minimal eigenvalue of matrix F, that is:
Go to step (B) then, satisfy orthotropicity up to matrix F;
(D) the parameter matrix α that utilizes step (C) to obtain calculates objective matrix C, and it is made characteristic value decomposition, that is:
C=RDR
T
In the formula, D is the diagonal matrix of being made up of the characteristic value of objective matrix C, the R eigenvectors matrix that each characteristic value characteristic of correspondence vector is formed of serving as reasons;
(E) try to achieve albefaction matrix Q=D
-1/2R
T, whitened signal is z (t)=Qx (t).
(3), calculate the second order and the fourth order cumulant of initially-separate signal, with the diagonal element quadratic sum of second order and fourth order cumulant matrix as cost function;
Described initially-separate signal is as follows:
Initial quadrature separation matrix is W, then initially-separate signal y (t)=Wz (t);
(4), by cost function in the maximization steps (3), realize the associating approximate diagonalization of each second order and fourth order cumulant matrix, the quadrature separation matrix P that obtains making the mixed signal of the described filtering additive white Gaussian of step (2) to separate, thus separation matrix H and separation signal s (t) obtained; H=PQ wherein, s (t)=Hx (t).
2. the blind source separation method of a kind of strong noise environment according to claim 1 is characterized in that described quadrature separation matrix P adopts the Givens rotary process to try to achieve.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN200910232300.1A CN101729157B (en) | 2009-12-11 | 2009-12-11 | Method for separating vibration signal blind sources under a kind of strong noise environment |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN200910232300.1A CN101729157B (en) | 2009-12-11 | 2009-12-11 | Method for separating vibration signal blind sources under a kind of strong noise environment |
Publications (2)
Publication Number | Publication Date |
---|---|
CN101729157A true CN101729157A (en) | 2010-06-09 |
CN101729157B CN101729157B (en) | 2016-02-17 |
Family
ID=42449467
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN200910232300.1A Active CN101729157B (en) | 2009-12-11 | 2009-12-11 | Method for separating vibration signal blind sources under a kind of strong noise environment |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN101729157B (en) |
Cited By (16)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101951619A (en) * | 2010-09-03 | 2011-01-19 | 电子科技大学 | Compressive sensing-based broadband signal separation method in cognitive network |
CN102288285A (en) * | 2011-05-24 | 2011-12-21 | 南京航空航天大学 | Blind source separation method for single-channel vibration signals |
CN102445650A (en) * | 2011-09-22 | 2012-05-09 | 重庆大学 | Blind signal separation algorithm-based circuit fault diagnosis method |
CN104180846A (en) * | 2014-04-22 | 2014-12-03 | 中国商用飞机有限责任公司北京民用飞机技术研究中心 | Signal analysis method and device applied to passenger plane structure health monitoring |
CN104359685A (en) * | 2014-11-24 | 2015-02-18 | 沈阳化工大学 | Diesel engine fault identification method |
CN104913355A (en) * | 2015-06-29 | 2015-09-16 | 珠海格力电器股份有限公司 | Range hood noise treatment system, method, and device |
CN105609112A (en) * | 2016-01-15 | 2016-05-25 | 苏州宾果智能科技有限公司 | Sound source positioning method and apparatus and time delay estimation method and apparatus |
CN105717543A (en) * | 2016-01-25 | 2016-06-29 | 浪潮(北京)电子信息产业有限公司 | Noise suppression method and system |
CN106126479A (en) * | 2016-07-07 | 2016-11-16 | 重庆邮电大学 | The order Oscillating population blind source separation method optimized based on hereditary variation |
CN109684898A (en) * | 2017-10-18 | 2019-04-26 | 中国航发商用航空发动机有限责任公司 | Aero-engine and its vibration signal blind separating method and device |
CN109856252A (en) * | 2019-02-01 | 2019-06-07 | 南京信息工程大学 | A kind of multi-mode Lamb wave separation method based on dispersion compensation and blind separation |
CN110792613A (en) * | 2019-09-18 | 2020-02-14 | 山东建筑大学 | Method for extracting weak signal modulation characteristics of centrifugal pump |
CN111190049A (en) * | 2020-01-14 | 2020-05-22 | 洛阳师范学院 | Method for detecting nano-volt level weak sinusoidal signal by chaotic system of principal component analysis |
CN112082792A (en) * | 2020-08-31 | 2020-12-15 | 洛阳师范学院 | Rotary machine fault diagnosis method based on MF-JADE |
CN112326017A (en) * | 2020-09-28 | 2021-02-05 | 南京航空航天大学 | Weak signal detection method based on improved semi-classical signal analysis |
CN113432876A (en) * | 2021-06-24 | 2021-09-24 | 西安电子科技大学 | Conjugate gradient method-based aeroengine main shaft bearing fault signal blind extraction method |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105788295B (en) * | 2014-12-26 | 2018-12-28 | 中国移动通信集团公司 | A kind of detection method and device of the magnitude of traffic flow |
Family Cites Families (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6711528B2 (en) * | 2002-04-22 | 2004-03-23 | Harris Corporation | Blind source separation utilizing a spatial fourth order cumulant matrix pencil |
EP1956718A1 (en) * | 2007-02-09 | 2008-08-13 | Research In Motion Limited | Apparatus, and associated method, for filtering a receive signal by adaptive operation of an input noise whitening filter |
CN101546993B (en) * | 2009-04-23 | 2012-06-27 | 华为技术有限公司 | Method and device for whitening filtration with self-adapting iterations |
-
2009
- 2009-12-11 CN CN200910232300.1A patent/CN101729157B/en active Active
Cited By (25)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101951619A (en) * | 2010-09-03 | 2011-01-19 | 电子科技大学 | Compressive sensing-based broadband signal separation method in cognitive network |
CN101951619B (en) * | 2010-09-03 | 2013-01-02 | 电子科技大学 | Compressive sensing-based broadband signal separation method in cognitive network |
CN102288285A (en) * | 2011-05-24 | 2011-12-21 | 南京航空航天大学 | Blind source separation method for single-channel vibration signals |
CN102288285B (en) * | 2011-05-24 | 2012-11-28 | 南京航空航天大学 | Blind source separation method for single-channel vibration signals |
CN102445650A (en) * | 2011-09-22 | 2012-05-09 | 重庆大学 | Blind signal separation algorithm-based circuit fault diagnosis method |
CN102445650B (en) * | 2011-09-22 | 2014-09-24 | 重庆大学 | Blind signal separation algorithm-based circuit fault diagnosis method |
CN104180846A (en) * | 2014-04-22 | 2014-12-03 | 中国商用飞机有限责任公司北京民用飞机技术研究中心 | Signal analysis method and device applied to passenger plane structure health monitoring |
CN104359685A (en) * | 2014-11-24 | 2015-02-18 | 沈阳化工大学 | Diesel engine fault identification method |
CN104913355A (en) * | 2015-06-29 | 2015-09-16 | 珠海格力电器股份有限公司 | Range hood noise treatment system, method, and device |
CN105609112A (en) * | 2016-01-15 | 2016-05-25 | 苏州宾果智能科技有限公司 | Sound source positioning method and apparatus and time delay estimation method and apparatus |
CN105717543B (en) * | 2016-01-25 | 2018-07-13 | 浪潮(北京)电子信息产业有限公司 | A kind of noise drawing method and system |
CN105717543A (en) * | 2016-01-25 | 2016-06-29 | 浪潮(北京)电子信息产业有限公司 | Noise suppression method and system |
CN106126479A (en) * | 2016-07-07 | 2016-11-16 | 重庆邮电大学 | The order Oscillating population blind source separation method optimized based on hereditary variation |
CN106126479B (en) * | 2016-07-07 | 2019-04-12 | 重庆邮电大学 | Order Oscillating population blind source separation method based on hereditary variation optimization |
CN109684898A (en) * | 2017-10-18 | 2019-04-26 | 中国航发商用航空发动机有限责任公司 | Aero-engine and its vibration signal blind separating method and device |
CN109856252B (en) * | 2019-02-01 | 2021-03-16 | 南京信息工程大学 | Multimode lamb wave separation method based on frequency dispersion compensation and blind separation |
CN109856252A (en) * | 2019-02-01 | 2019-06-07 | 南京信息工程大学 | A kind of multi-mode Lamb wave separation method based on dispersion compensation and blind separation |
CN110792613A (en) * | 2019-09-18 | 2020-02-14 | 山东建筑大学 | Method for extracting weak signal modulation characteristics of centrifugal pump |
CN111190049A (en) * | 2020-01-14 | 2020-05-22 | 洛阳师范学院 | Method for detecting nano-volt level weak sinusoidal signal by chaotic system of principal component analysis |
CN111190049B (en) * | 2020-01-14 | 2022-04-05 | 洛阳师范学院 | Method for detecting nano-volt level weak sinusoidal signal by chaotic system of principal component analysis |
CN112082792A (en) * | 2020-08-31 | 2020-12-15 | 洛阳师范学院 | Rotary machine fault diagnosis method based on MF-JADE |
CN112326017A (en) * | 2020-09-28 | 2021-02-05 | 南京航空航天大学 | Weak signal detection method based on improved semi-classical signal analysis |
CN112326017B (en) * | 2020-09-28 | 2022-01-04 | 南京航空航天大学 | Weak signal detection method based on improved semi-classical signal analysis |
CN113432876A (en) * | 2021-06-24 | 2021-09-24 | 西安电子科技大学 | Conjugate gradient method-based aeroengine main shaft bearing fault signal blind extraction method |
CN113432876B (en) * | 2021-06-24 | 2022-04-19 | 西安电子科技大学 | Conjugate gradient method-based aeroengine main shaft bearing fault signal blind extraction method |
Also Published As
Publication number | Publication date |
---|---|
CN101729157B (en) | 2016-02-17 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN101729157A (en) | Method for separating vibration signal blind sources under strong noise environment | |
CN105607125A (en) | Seismic data noise suppression method based on block matching algorithm and singular value decompression | |
CN103093434B (en) | Non-local wiener filtering image denoising method based on singular value decomposition | |
CN107392952B (en) | no-reference mixed distortion image quality evaluation method | |
CN105741844B (en) | A kind of digital audio watermarking algorithm based on DWT-SVD-ICA | |
CN112735460B (en) | Beam forming method and system based on time-frequency masking value estimation | |
CN110490816B (en) | Underwater heterogeneous information data noise reduction method | |
Nesta et al. | Convolutive underdetermined source separation through weighted interleaved ICA and spatio-temporal source correlation | |
CN111723701A (en) | Underwater target identification method | |
CN102945670A (en) | Multi-environment characteristic compensation method for voice recognition system | |
CN107292852A (en) | A kind of Image denoising algorithm theoretical based on low-rank | |
WO2013089536A1 (en) | Target sound source removal method and speech recognition method and apparatus according to same | |
CN109884591A (en) | A kind of multi-rotor unmanned aerial vehicle acoustical signal Enhancement Method based on microphone array | |
Hao et al. | A Unified Framework for Low-Latency Speaker Extraction in Cocktail Party Environments. | |
CN104240717B (en) | Voice enhancement method based on combination of sparse code and ideal binary system mask | |
CN104978716A (en) | SAR image noise reduction method based on linear minimum mean square error estimation | |
CN105429720B (en) | The Time Delay Estimation Based reconstructed based on EMD | |
CN104408027A (en) | Underdetermined blind identification method based on general covariance and tensor decomposition | |
CN114897002A (en) | LPINet-based low interception probability radar signal intra-pulse modulation identification method | |
CN112652326B (en) | Ambient sound identification method based on pseudo-color time-frequency image and convolution network | |
CN113204051A (en) | Low-rank tensor seismic data denoising method based on variational modal decomposition | |
CN103208113A (en) | Image segmentation method based on non-subsmapled contourlet and multi-phase chan-vese (CV) models | |
CN115426055B (en) | Noise-containing underwater acoustic signal blind source separation method based on decoupling convolutional neural network | |
CN102509268B (en) | Immune-clonal-selection-based nonsubsampled contourlet domain image denoising method | |
KR101568282B1 (en) | Mask estimation method and apparatus in cluster based missing feature reconstruction |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
C14 | Grant of patent or utility model | ||
GR01 | Patent grant |