阅读说明：本技术 光纤入侵混合信号分离方法及装置 (Optical fiber invasion mixed signal separation method and device ) 是由 田青 于 2021-07-29 设计创作，主要内容包括：本发明公开了一种光纤入侵混合信号分离方法及装置,可用于光纤监测预警技术领域,其中方法包括：获得光纤入侵混合信号；根据所述光纤入侵混合信号,确定超对称张量和对应的初始特征向量；根据所述初始特征向量,确定正交补投影矩阵；根据所述正交补投影矩阵,对所述超对称张量进行修正；利用修正后的超对称张量和预先建立的最优化模型,进行光纤入侵混合信号分离。本发明可以进行光纤入侵混合信号分离,提高多种入侵行为同时发生时的识别性能。(The invention discloses a method and a device for separating fiber invasion mixed signals, which can be used in the technical field of fiber monitoring and early warning, wherein the method comprises the following steps: acquiring an optical fiber invasion mixed signal; determining a hypersymmetry tensor and a corresponding initial eigenvector according to the optical fiber invasion mixed signal; determining an orthogonal complement projection matrix according to the initial characteristic vector; correcting the hypersymmetric tensor according to the orthogonal complement projection matrix; and separating the fiber invasion mixed signals by using the corrected hypersymmetry tensor and a pre-established optimization model. The invention can separate the mixed signals of the optical fiber invasion and improve the identification performance when various invasion behaviors occur simultaneously.)

1. A method for separating a fiber-optic intrusion mixed signal, comprising:

acquiring an optical fiber invasion mixed signal;

determining a hypersymmetry tensor and a corresponding initial eigenvector according to the optical fiber invasion mixed signal;

determining an orthogonal complement projection matrix according to the initial characteristic vector;

correcting the hypersymmetric tensor according to the orthogonal complement projection matrix;

and separating the fiber invasion mixed signals by using the corrected hypersymmetry tensor and a pre-established optimization model.

2. The method for separating the fiber intrusion mixed signal according to claim 1, wherein determining the hyper-symmetry tensor and the corresponding initial eigenvector according to the fiber intrusion mixed signal comprises:

performing outer product operation on the optical fiber invasion mixed signal to obtain a hypersymmetry tensor;

and extracting features of the hypersymmetry tensor to obtain corresponding initial feature vectors.

3. The method of claim 1, wherein determining an orthogonal complement projection matrix from the initial eigenvector comprises:

performing a kronecker product operation on the initial characteristic vector to obtain a new characteristic vector;

and determining an orthogonal complement projection matrix according to the new eigenvector.

4. The method of separating an optical fiber intrusion mixed signal according to claim 1, wherein the correcting the hyper-symmetric tensor according to the orthogonal complement projection matrix comprises:

obtaining a corresponding one-dimensional vector according to the hypersymmetry tensor;

and correcting the hypersymmetry tensor according to the orthogonal complement projection matrix and the one-dimensional vector.

5. An optical fiber intrusion mixing signal separation apparatus, comprising:

the mixed signal obtaining module is used for obtaining an optical fiber invasion mixed signal;

the characteristic vector determining module is used for determining the hypersymmetry tensor and the corresponding initial characteristic vector according to the optical fiber invasion mixed signal;

the projection matrix determining module is used for determining an orthogonal complement projection matrix according to the initial characteristic vector;

the hypersymmetry tensor correction module is used for correcting the hypersymmetry tensor according to the orthogonal complement projection matrix;

and the mixed signal separation module is used for separating the optical fiber invasion mixed signals by using the corrected hypersymmetry tensor and a pre-established optimization model.

6. The fiber optic intrusion mixed signal separation device of claim 5, wherein the eigenvector determination module is further configured to:

performing outer product operation on the optical fiber invasion mixed signal to obtain a hypersymmetry tensor;

and extracting features of the hypersymmetry tensor to obtain corresponding initial feature vectors.

7. The fiber optic intrusion mixing signal separation device of claim 5, wherein the projection matrix determination module is further configured to:

performing a kronecker product operation on the initial characteristic vector to obtain a new characteristic vector;

and determining an orthogonal complement projection matrix according to the new eigenvector.

8. The fiber optic intrusion mixing signal separation apparatus of claim 5, wherein the hyper-symmetry tensor correction module is further for:

obtaining a corresponding one-dimensional vector according to the hypersymmetry tensor;

and correcting the hypersymmetry tensor according to the orthogonal complement projection matrix and the one-dimensional vector.

9. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the method of any one of claims 1 to 4 when executing the computer program.

10. A computer-readable storage medium, characterized in that the computer-readable storage medium stores a computer program for executing the method of any one of claims 1 to 4.

Technical Field

The invention relates to the technical field of optical fiber monitoring and early warning, in particular to a method and a device for separating an optical fiber invasion mixed signal.

Background

An Optical Fiber Pre-warning System (OFPS) lays an Optical cable in parallel with an object to be monitored, collects backscattered light caused by external vibration, and finally converts the backscattered light into an intrusion signal. The intrusion signal is generally a mixture of various types of signature signals, and its frequency spectrum is also a mixture of frequency spectrums. The signature signal refers to a pure signal formed by a single intrusion action. The existing optical fiber early warning system can detect and identify various characteristic signals, however, when various intrusion behaviors occur simultaneously, the OFPS lacks the separation capability of mixed signals, and the identification performance is seriously reduced.

Therefore, there is a need for a fiber-optic intrusion hybrid signal separation scheme that overcomes the above-mentioned problems.

Disclosure of Invention

The embodiment of the invention provides an optical fiber invasion mixed signal separation method, which is used for separating optical fiber invasion mixed signals and improving the identification performance when multiple invasion behaviors occur simultaneously, and comprises the following steps:

acquiring an optical fiber invasion mixed signal;

determining a hypersymmetry tensor and a corresponding initial eigenvector according to the optical fiber invasion mixed signal;

determining an orthogonal complement projection matrix according to the initial characteristic vector;

correcting the hypersymmetric tensor according to the orthogonal complement projection matrix;

and separating the fiber invasion mixed signals by using the corrected hypersymmetry tensor and a pre-established optimization model.

The embodiment of the invention provides an optical fiber invasion mixed signal separation device, which is used for separating optical fiber invasion mixed signals and improving the identification performance when multiple invasion behaviors occur simultaneously, and comprises the following components:

the mixed signal obtaining module is used for obtaining an optical fiber invasion mixed signal;

the characteristic vector determining module is used for determining the hypersymmetry tensor and the corresponding initial characteristic vector according to the optical fiber invasion mixed signal;

the projection matrix determining module is used for determining an orthogonal complement projection matrix according to the initial characteristic vector;

the hypersymmetry tensor correction module is used for correcting the hypersymmetry tensor according to the orthogonal complement projection matrix;

and the mixed signal separation module is used for separating the optical fiber invasion mixed signals by using the corrected hypersymmetry tensor and a pre-established optimization model.

The embodiment of the invention also provides computer equipment which comprises a memory, a processor and a computer program which is stored on the memory and can run on the processor, wherein the processor realizes the optical fiber intrusion mixed signal separation method when executing the computer program.

An embodiment of the present invention further provides a computer-readable storage medium, where a computer program for executing the method for separating an optical fiber intrusion mixed signal is stored in the computer-readable storage medium.

The embodiment of the invention obtains the optical fiber invasion mixed signal; determining a hypersymmetry tensor and a corresponding initial eigenvector according to the optical fiber invasion mixed signal; determining an orthogonal complement projection matrix according to the initial characteristic vector; correcting the hypersymmetric tensor according to the orthogonal complement projection matrix; and separating the fiber invasion mixed signals by using the corrected hypersymmetry tensor and a pre-established optimization model. The embodiment of the invention considers the non-orthogonality of the hypersymmetry tensor of the optical fiber invasion mixed signal, corrects the hypersymmetry tensor by using the orthogonal complement projection matrix of the initial eigenvector, and separates the optical fiber invasion mixed signal by using the corrected hypersymmetry tensor and the pre-established optimization model to be closer to the actual eigenvector, thereby effectively improving the identification performance when multiple invasion behaviors occur simultaneously.

Drawings

In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts. In the drawings:

FIG. 1 is a schematic diagram of a method for separating a fiber-optic intrusion mixed signal according to an embodiment of the present invention;

FIGS. 2-4 are schematic diagrams of a method for separating a fiber-optic intrusion mixed signal according to an embodiment of the present invention;

FIG. 5 is a diagram of a fiber-optic intrusion hybrid signal separation apparatus according to an embodiment of the present invention;

fig. 6 is a schematic structural diagram of a computer device according to an embodiment of the present invention.

Detailed Description

In order to make the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the embodiments of the present invention are further described in detail below with reference to the accompanying drawings. The exemplary embodiments and descriptions of the present invention are provided to explain the present invention, but not to limit the present invention.

In order to perform fiber-optic hybrid intrusion signal separation and simplify the operation, an embodiment of the present invention provides a fiber-optic hybrid intrusion signal separation method, as shown in fig. 1, where the method may include:

step 101, obtaining an optical fiber invasion mixed signal;

102, determining a hypersymmetry tensor and a corresponding initial eigenvector according to the optical fiber invasion mixed signal;

103, determining an orthogonal complement projection matrix according to the initial characteristic vector;

step 104, correcting the hypersymmetry tensor according to the orthogonal complementary projection matrix;

and 105, separating the optical fiber invasion mixed signals by using the corrected hypersymmetry tensor and a pre-established optimization model.

As can be seen from fig. 1, the embodiment of the present invention obtains the fiber-optic intrusion mixed signal; determining a hypersymmetry tensor and a corresponding initial eigenvector according to the optical fiber invasion mixed signal; determining an orthogonal complement projection matrix according to the initial characteristic vector; correcting the hypersymmetric tensor according to the orthogonal complement projection matrix; and separating the fiber invasion mixed signals by using the corrected hypersymmetry tensor and a pre-established optimization model. The embodiment of the invention considers the non-orthogonality of the hypersymmetry tensor of the optical fiber invasion mixed signal, corrects the hypersymmetry tensor by using the orthogonal complement projection matrix of the initial eigenvector, and separates the optical fiber invasion mixed signal by using the corrected hypersymmetry tensor and the pre-established optimization model to be closer to the actual eigenvector, thereby effectively improving the identification performance when multiple invasion behaviors occur simultaneously.

In an embodiment, a fiber intrusion mixing signal is obtained.

In an embodiment, a hypersymmetry tensor and a corresponding initial eigenvector are determined according to the fiber intrusion mixing signal.

In this embodiment, determining a hypersymmetry tensor and a corresponding initial eigenvector according to the fiber intrusion mixing signal includes:

performing outer product operation on the optical fiber invasion mixed signal to obtain a hypersymmetry tensor;

and extracting features of the hypersymmetry tensor to obtain corresponding initial feature vectors.

In this embodiment, the outer product operation is performed on the fiber-optic intrusion mixed signal according to the following formula:

wherein r is_iIs the fiber invasion mixed signal, N is the sample number of the fiber invasion mixed signal,to calculate the outer product of the two signals.

In this embodiment, the feature extraction is performed on the hypersymmetric tensor according to the following formula:

wherein | u | purple₂Is the 2 norm of the initial feature vector u.

In the specific implementation, the mixed signal of the fiber invasion is assumed to be r_iFirstly, a hypersymmetry tensor S is obtained through the outer product operation of the optical fiber invading mixed signal, and then the initial eigenvector u can be obtained through feature extraction of the hypersymmetry tensor.

In an embodiment, an orthogonal complement projection matrix is determined according to the initial eigenvector.

In this embodiment, determining an orthogonal projection matrix according to the initial feature vector includes:

performing a kronecker product operation on the initial characteristic vector to obtain a new characteristic vector;

and determining an orthogonal complement projection matrix according to the new eigenvector.

In this embodiment, the kronecker product operation is performed on the initial feature vector according to the following formula:

where u is the initial feature vector.

In this embodiment, the orthogonal projection matrix is determined according to the following formula:

wherein the content of the first and second substances,is the 3 x kronecker product of the matrix I.

In an embodiment, the hypersymmetric tensor is corrected according to the orthogonal projection complement matrix.

In this embodiment, the correcting the hypersymmetric tensor according to the orthogonal projection matrix includes:

obtaining a corresponding one-dimensional vector according to the hypersymmetry tensor;

and correcting the hypersymmetry tensor according to the orthogonal complement projection matrix and the one-dimensional vector.

In this embodiment, obtaining a corresponding one-dimensional vector according to the hypersymmetry tensor includes: obtaining a corresponding two-dimensional plane according to the hypersymmetry tensor; and obtaining a corresponding one-dimensional vector according to the two-dimensional plane.

In this embodiment, the corresponding two-dimensional plane is obtained according to the following formula:

s_i＝vec(S_i)

wherein the content of the first and second substances,l is the dimension of the sample, L²The dimension of the sample is 2.

In this embodiment, the corresponding one-dimensional vector is obtained according to the following formula:

wherein the content of the first and second substances,L³representing a sample with dimension 3.

In this embodiment, the hypersymmetric tensor is corrected as follows:

wherein, S' is the corrected hypersymmetric tensor, and unwec represents the vector change tensor.

In the embodiment, the fiber invasion mixed signal separation is carried out by utilizing the corrected hypersymmetry tensor and a pre-established optimization model.

In this embodiment, the optimization model is pre-established as follows:

maxS′×₁u×₂u×₃u+λ||u||₂

wherein λ is a regularization parameter

In specific implementation, according to the optimized model, the corrected hypersymmetry tensor is used to obtain the final eigenvector, namely the separated characteristic signal.

A specific embodiment is given below to illustrate a specific application of the fiber-optic intrusion hybrid signal separation in the embodiment of the present invention. In this embodiment, as shown in fig. 2, an initial feature vector is obtained first, then the optical fiber intrusion mixed signal is used to calculate an outer product to obtain a hypersymmetry tensor, the hypersymmetry tensor is further modified, and finally a final feature vector, that is, a separated feature signal, is obtained according to an optimization model. Comparing the separation effect of the optical fiber signals when the lambda values are different. The essence of the OFPS split signal is to find the graphics endpoint where the sample data is located. Fig. 3 is a two-dimensional distribution diagram of optical fiber signals, and three signals of an electric drill, an electric pick and a pick plane are selected in the embodiment of the invention. The scattered points in the middle of fig. 3 represent samples of the fiber intrusion mixed signal, the mixed signal is randomly distributed in a triangle formed by three characteristic signals, and the star-shaped points represent extracted characteristic signals. It can be seen that the signal separation effect is best when λ is 0.001. Three characteristic signals extracted at different lambda values are shown in fig. 4, and the triangular line represents a characteristic spectrum, namely a spectrum of a characteristic signal calibrated by a laboratory. The line graph formed by circles, squares, vertical lines and stars represents λ of 0.001, 0.01, 0.05 and 0.1 in this order. As can be easily seen from fig. 4, the extracted pure spectrum is closer to the characteristic spectrum in the case where λ is 0.001.

In the embodiment of the invention, the angle of the characteristic vector obtained by the method for separating the fiber-invasive mixed signals deviating from the actual characteristic vector is small, and the new characteristic vector is calculated by correcting the characteristic vector in consideration of the non-orthogonality of the hypersymmetry tensor, so that the characteristic vector is closer to the actual characteristic vector. The separated optical fiber characteristic signals are obtained by a method of solving the characteristic vector, and the physical essence of the optical fiber signals is better met, so that the identification performance of multiple intrusion behaviors when the intrusion behaviors occur simultaneously is effectively improved.

Based on the same inventive concept, the embodiment of the present invention further provides an optical fiber intrusion mixed signal separation apparatus, as described in the following embodiments. Since the principles of these solutions are similar to the method for separating the optical fiber ingress mixed signal, the implementation of the apparatus for separating the optical fiber ingress mixed signal can be referred to the implementation of the method, and the repeated parts are not described again.

Fig. 5 is a structural diagram of an optical fiber ingress mixed signal splitting apparatus according to an embodiment of the present invention, and as shown in fig. 5, the optical fiber ingress mixed signal splitting apparatus includes:

a mixed signal obtaining module 501, configured to obtain a fiber-optic intrusion mixed signal;

an eigenvector determining module 502, configured to determine a hypersymmetry tensor and a corresponding initial eigenvector according to the fiber intrusion mixed signal;

a projection matrix determining module 503, configured to determine an orthogonal complement projection matrix according to the initial eigenvector;

a hypersymmetry tensor correction module 504, configured to correct the hypersymmetry tensor according to the orthogonal complement projection matrix;

and a mixed signal separation module 505, configured to separate the fiber-optic invasive mixed signal by using the modified hypersymmetry tensor and a pre-established optimization model.

In one embodiment, the feature vector determination module 502 is further configured to:

performing outer product operation on the optical fiber invasion mixed signal to obtain a hypersymmetry tensor;

and extracting features of the hypersymmetry tensor to obtain corresponding initial feature vectors.

In one embodiment, the projection matrix determination module 503 is further configured to:

performing a kronecker product operation on the initial characteristic vector to obtain a new characteristic vector;

and determining an orthogonal complement projection matrix according to the new eigenvector.

In one embodiment, the hypersymmetric tensor modification module 504 is further to:

obtaining a corresponding one-dimensional vector according to the hypersymmetry tensor;

and correcting the hypersymmetry tensor according to the orthogonal complement projection matrix and the one-dimensional vector.

In summary, in the embodiments of the present invention, the optical fiber intrusion mixed signal is obtained; determining a hypersymmetry tensor and a corresponding initial eigenvector according to the optical fiber invasion mixed signal; determining an orthogonal complement projection matrix according to the initial characteristic vector; correcting the hypersymmetric tensor according to the orthogonal complement projection matrix; and separating the fiber invasion mixed signals by using the corrected hypersymmetry tensor and a pre-established optimization model. The embodiment of the invention considers the non-orthogonality of the hypersymmetry tensor of the optical fiber invasion mixed signal, corrects the hypersymmetry tensor by using the orthogonal complement projection matrix of the initial eigenvector, and separates the optical fiber invasion mixed signal by using the corrected hypersymmetry tensor and the pre-established optimization model to be closer to the actual eigenvector, thereby effectively improving the identification performance when multiple invasion behaviors occur simultaneously.

Based on the aforementioned inventive concept, as shown in fig. 6, the present invention further provides a computer device 600, which includes a memory 610, a processor 620, and a computer program 630 stored in the memory 610 and executable on the processor 620, wherein the processor 620 implements the aforementioned fiber-optic intrusion mixed-signal separation method when executing the computer program 630.

Based on the foregoing inventive concept, the present invention proposes a computer-readable storage medium storing a computer program which, when executed by a processor, implements the foregoing optical fiber intrusion mixed signal separation method.

As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.

The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

The above-mentioned embodiments are intended to illustrate the objects, technical solutions and advantages of the present invention in further detail, and it should be understood that the above-mentioned embodiments are only exemplary embodiments of the present invention, and are not intended to limit the scope of the present invention, and any modifications, equivalent substitutions, improvements and the like made within the spirit and principle of the present invention should be included in the scope of the present invention.