CN115830738B - Area identification method based on wireless channel fingerprint characteristics of converter station inspection robot - Google Patents

Abstract

The application relates to a region identification method, a device, computer equipment, a storage medium and a computer program product based on wireless channel fingerprint characteristics of a converter station inspection robot. The method comprises the steps of obtaining a patrol robot transmitting signal received by a signal receiving end of a converter station, extracting a plurality of fingerprint feature information corresponding to a wireless channel of the patrol robot according to the patrol robot transmitting signal, generating fingerprint feature vectors corresponding to the current region of the patrol robot according to the fingerprint feature information, obtaining the fingerprint feature vectors corresponding to all the patrol regions in the converter station, comparing the corresponding fingerprint feature vectors of all the patrol regions with the fingerprint feature vectors corresponding to the current region to obtain region similar information corresponding to all the patrol regions, and determining the region position information of the current region in the converter station according to the region similar information. By adopting the method, the current inspection area of the inspection robot can be accurately identified.

Description

Area identification method based on wireless channel fingerprint characteristics of converter station inspection robot

Technical Field

The application relates to the technical field of computers, in particular to a region identification method, a device, computer equipment, a storage medium and a computer program product based on wireless channel fingerprint characteristics of a converter station inspection robot.

Background

The inspection task of the converter station is a key for ensuring the normal operation of the power grid, and various inspection methods of the converter station are layered with the development of computer technology.

At present, when the converter station is inspected, the inspection robot is often adopted to inspect the converter station, so that the traditional manual inspection mode is replaced. However, due to complex signal interference in the converter station, when the four inspection robots inspect the converter station, the current position of the inspection robot cannot be accurately monitored, and inspection management of the inspection robot is inconvenient.

Therefore, the conventional technology has the problem that the inspection area of the inspection robot is not accurately recognized.

Disclosure of Invention

In view of the foregoing, it is desirable to provide a method, an apparatus, a computer device, a computer readable storage medium, and a computer program product for identifying a region based on a wireless channel fingerprint feature of a converter station inspection robot, which can more accurately identify a current position of the inspection robot.

The area identification method based on the wireless channel fingerprint characteristics of the converter station inspection robot is characterized by comprising the following steps:

The method comprises the steps of acquiring a patrol robot transmitting signal received by a signal receiving end of a converter station, wherein the patrol robot transmitting signal is a wireless signal transmitted by a patrol robot in the converter station;

extracting a plurality of pieces of fingerprint characteristic information corresponding to the wireless channel of the inspection robot according to the signal transmitted by the inspection robot, wherein each piece of fingerprint characteristic information is used for representing corresponding signal fading characteristics in the wireless channel of the inspection robot;

Generating fingerprint feature vectors corresponding to the current region of the inspection robot according to the plurality of fingerprint feature information;

And acquiring fingerprint feature vectors corresponding to all the inspection areas in the converter station, respectively comparing the fingerprint feature vectors corresponding to all the inspection areas with the fingerprint feature vectors corresponding to the current area to obtain area similar information corresponding to all the inspection areas, wherein the area similar information is used for determining the area position information of the current area in the converter station.

In one embodiment, extracting a plurality of fingerprint feature information corresponding to a wireless channel of the inspection robot according to an emission signal of the inspection robot includes:

Inputting the inspection robot transmission signals into a wireless channel characteristic extraction model to obtain signal characteristic data corresponding to each channel sample point in a wireless channel of the inspection robot;

and generating a signal characteristic data sequence according to the signal characteristic data corresponding to each channel sample point, and extracting fingerprint characteristics of the signal characteristic data sequence to obtain a plurality of fingerprint characteristic information corresponding to the wireless channel of the inspection robot.

In one embodiment, inputting a signal sent by the inspection robot to a wireless channel feature extraction model to obtain signal feature data corresponding to each channel sample point in a wireless channel of the inspection robot, the method includes:

Inputting the inspection robot transmission signal into an ideal signal characteristic extraction submodel to obtain ideal signal characteristic data corresponding to each channel sample point in a wireless channel of the inspection robot;

and inputting the ideal signal characteristic data into the actual signal characteristic extraction submodel to obtain the signal characteristic data actually corresponding to each channel sample point in the wireless channel of the inspection robot.

In one embodiment, generating a signal characteristic data sequence according to signal characteristic data corresponding to each channel sample point, and performing fingerprint feature extraction on the signal characteristic data sequence to obtain a plurality of fingerprint feature information corresponding to a wireless channel of the inspection robot, where the method includes:

Generating a signal characteristic data sequence corresponding to a wireless channel of the inspection robot according to the signal characteristic data corresponding to each channel sample point;

Noise reduction processing is carried out on the signal characteristic data sequence to obtain a noise-reduced signal characteristic data sequence;

And carrying out fingerprint feature extraction on the noise-reduced signal feature data sequence to obtain a plurality of fingerprint feature information corresponding to the wireless channel of the inspection robot.

In one embodiment, the noise reduction processing is performed on the signal characteristic data sequence to obtain a noise-reduced signal characteristic data sequence, including:

generating a signal characteristic matrix corresponding to a wireless channel of the inspection robot according to the signal characteristic data sequence;

Pre-denoising the signal characteristic matrix to obtain a pre-denoised signal characteristic matrix;

extracting elements in the pre-noise-reduced signal feature matrix to generate a noise-reduced signal feature data sequence;

and inputting the pre-noise-reduced signal characteristic data sequence into a wavelet noise reduction model to obtain a noise-reduced signal characteristic data sequence.

In one embodiment, obtaining a fingerprint feature vector corresponding to each inspection area in a converter station, and comparing the fingerprint feature vector corresponding to each inspection area with the fingerprint feature vector corresponding to the current area to obtain area similar information corresponding to each inspection area, including:

Acquiring fingerprint feature vectors corresponding to all the inspection areas in the converter station, and respectively comparing the fingerprint feature vectors corresponding to all the inspection areas with the fingerprint feature vectors corresponding to the current area to obtain fingerprint feature similar vectors corresponding to all the inspection areas;

Generating a fingerprint feature weight vector according to the weight information corresponding to each fingerprint feature information, and determining the region similarity information corresponding to each inspection region according to the fingerprint feature similarity vector and the fingerprint feature weight vector corresponding to each inspection region, wherein the region similarity information corresponding to each inspection region characterizes the region similarity of each inspection region and the current region.

An area identification device based on wireless channel fingerprint feature of converter station inspection robot, its characterized in that, the device includes:

The system comprises an acquisition module, a transmission module, a control module and a control module, wherein the acquisition module is used for acquiring a patrol robot transmitting signal received by a signal receiving end of a converter station;

The system comprises an extraction module, a detection module and a detection module, wherein the extraction module is used for extracting a plurality of fingerprint characteristic information corresponding to a wireless channel of the inspection robot according to a signal transmitted by the inspection robot;

the generating module is used for generating fingerprint feature vectors corresponding to the current area of the inspection robot according to the plurality of fingerprint feature information;

the determining module is used for obtaining fingerprint feature vectors corresponding to all the inspection areas in the converter station, comparing the fingerprint feature vectors corresponding to all the inspection areas with the fingerprint feature vectors corresponding to the current area to obtain area similar information corresponding to all the inspection areas, and determining the area position information of the current area in the converter station.

A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor implements the steps of the method described above when executing the computer program.

A computer readable storage medium having stored thereon a computer program, characterized in that the computer program when executed by a processor realizes the steps of the above-mentioned method.

A computer program product comprising a computer program, characterized in that the computer program, when being executed by a processor, implements the steps of the method described above.

The region identification method, the device, the computer equipment, the storage medium and the computer program product based on the wireless channel fingerprint characteristics of the inspection robot of the converter station are characterized in that the inspection robot transmits a human signal to the inspection robot through the signal receiving end of the converter station, the inspection robot transmits a wireless signal transmitted by the inspection robot in the converter station, a plurality of fingerprint characteristic information corresponding to the wireless channel of the inspection robot is extracted according to the inspection robot transmitting signal, each fingerprint characteristic information is used for representing corresponding signal fading characteristics in the wireless channel of the inspection robot, fingerprint characteristic vectors corresponding to the current region of the inspection robot are generated according to the fingerprint characteristic information, fingerprint characteristic vectors corresponding to the inspection regions of the converter station are obtained, the fingerprint characteristic vectors corresponding to the inspection regions are compared with the fingerprint characteristic vectors corresponding to the current region respectively, region similar information corresponding to the inspection regions is obtained, the region similar information is used for determining region position information of the current region in the converter station, accordingly, the inspection robot can be accurately managed according to the current channel characteristics of the inspection robot, the current channel of the inspection robot can be more safely maintained in the converter station, and the environment can be more safely maintained.

Drawings

FIG. 1 is a diagram of an application environment of a wireless channel fingerprint feature area identification method in one embodiment;

FIG. 2 is a flowchart of a method for identifying a fingerprint feature area of a wireless channel according to an embodiment;

FIG. 3 is a schematic diagram illustrating a transmission process of a signal transmitted by the inspection robot in one embodiment;

FIG. 4 is an analysis flow chart of a wireless channel fingerprint feature analysis method in one embodiment;

FIG. 5 is a flowchart of a wavelet denoising method based on SVD singular value decomposition in one embodiment;

FIG. 6 is a flow chart of a wavelet denoising method based on a fixed threshold in one embodiment;

FIG. 7 is a flowchart of a method for identifying a fingerprint feature area of a wireless channel according to another embodiment;

FIG. 8 is a block diagram illustrating a wireless channel fingerprint feature area identification apparatus according to one embodiment;

fig. 9 is an internal structural diagram of a computer device in one embodiment.

Detailed Description

The present application will be described in further detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present application more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the application.

The area identification method based on the wireless channel fingerprint characteristics of the converter station inspection robot provided by the embodiment of the application can be applied to an application environment shown in fig. 1. Wherein the inspection robot 102 communicates with the server 104 via a network. The method comprises the steps of obtaining a patrol robot sending signal received through a signal receiving end of a converter station by a server 104, wherein the patrol robot sending signal is a wireless signal sent by a patrol robot in the converter station, the server 104 extracts a plurality of fingerprint feature information corresponding to a wireless channel of the patrol robot according to the patrol robot sending signal, each fingerprint feature information is used for representing corresponding signal fading features in the wireless channel of the patrol robot, the server 104 generates fingerprint feature vectors corresponding to the current region of the patrol robot according to the fingerprint feature information, the server 104 obtains the fingerprint feature vectors corresponding to each patrol region in the converter station, compares the corresponding fingerprint feature vectors of each patrol region with the fingerprint feature vectors corresponding to the current region to obtain region similar information corresponding to each patrol region, and the region similar information is used for determining the region position information of the current region in the converter station. The server 104 may be implemented as a stand-alone server or a server cluster including a plurality of servers.

In one embodiment, as shown in fig. 2, a method for identifying a region based on a wireless channel fingerprint feature of a converter station inspection robot is provided, and the method is applied to the server 104 in fig. 1 for illustration, and includes the following steps:

Step S202, a patrol robot transmitting signal received by a signal receiving end of the converter station is obtained, and the patrol robot transmitting signal is a wireless signal transmitted by the patrol robot in the converter station.

In a specific implementation, the server transmits a signal to the inspection robot through a signal receiving end of the converter station.

The transmission process of the inspection robot transmitting signal is shown in fig. 3, firstly, the central control platform of the inspection robot transmits a radio wave signal, the radio wave signal is subjected to filtering processing through the radio frequency filter, then the radio wave signal after the filtering processing is transmitted to a communication wireless channel, wherein the radio wave signal is influenced by strong electromagnetic noise signals caused by multipath transmission difference, external environment noise interference and multipath time delay in the communication wireless channel, finally, the radio wave signal influenced by the strong electromagnetic noise signals is received by the wireless switch, the wireless switch performs data processing on the radio wave signal to obtain a signal processing result, and the signal processing result is sent to the client.

Step S204, extracting a plurality of pieces of fingerprint characteristic information corresponding to the wireless channel of the inspection robot according to the signal transmitted by the inspection robot, wherein each piece of fingerprint characteristic information is used for representing corresponding signal fading characteristics in the wireless channel of the inspection robot.

The signal fading characteristic can be a parameter characteristic obtained by processing signal data based on Doppler spread, time delay spread, path loss, time domain peak analysis, frequency domain peak analysis and other methods.

In the specific implementation, the server processes data of the inspection robot emission signal according to the inspection robot emission signal to obtain each fingerprint characteristic information corresponding to the wireless channel of the inspection robot, such as parameter characteristics obtained by data processing of the signal based on Doppler spread, time delay spread, path loss, time domain peak analysis, frequency domain peak analysis and other methods.

Step S206, generating fingerprint feature vectors corresponding to the current area of the inspection robot according to the plurality of fingerprint feature information.

In the specific implementation, the server generates fingerprint feature vectors corresponding to the wireless channels of the current area of the inspection robot according to the fingerprint feature information.

Step S208, obtaining fingerprint feature vectors corresponding to all the inspection areas in the converter station, comparing the fingerprint feature vectors corresponding to all the inspection areas with the fingerprint feature vectors corresponding to the current area to obtain area similar information corresponding to all the inspection areas, wherein the area similar information is used for determining the area position information of the current area in the converter station.

The region similarity information may be feature similarity information characterizing correspondence between each inspection region and a wireless channel fading feature of a current region.

In the specific implementation, the server acquires fingerprint feature vectors corresponding to all the inspection areas in the converter station, the server compares the fingerprint feature vectors corresponding to all the inspection areas with the fingerprint feature vectors corresponding to the areas where the inspection robots are currently located to obtain wireless channel similar information of all the inspection areas and the areas where the inspection robots are currently located, the wireless channel similar information is used as the area similar information corresponding to all the inspection areas, the server compares the similarity corresponding to the area similar information, and the inspection area with the largest area similarity is used as the area where the inspection robots are currently located to finish positioning identification of the inspection robots.

For ease of understanding by those skilled in the art, fig. 4 exemplarily provides an analysis flowchart of a wireless channel fingerprint feature analysis method based on a converter station quadruped robot. Firstly, a model is built based on a wireless channel, dynamic changes of the quadruped robot are considered, a wireless channel time-varying model is built, a wireless channel time-varying model is used for converting a quadruped robot transmit signal into signal characteristic data to obtain a signal characteristic data matrix, then, pre-noise reduction processing is carried out on the signal characteristic data matrix based on SVD singular value decomposition (a machine learning data dimension reduction algorithm) principle, further, secondary noise reduction processing is carried out on the pre-noise reduction processed signal characteristic data through a wavelet noise reduction method with a fixed threshold value, finally, data processing is carried out on basic parameters of the signal characteristic data to calculate wireless channel fingerprint characteristic data, and inspection areas of the quadruped robot are identified according to the wireless channel fingerprint characteristic data.

The region identification method, the device, the computer equipment, the storage medium and the computer program product based on the wireless channel fingerprint characteristics of the inspection robot of the converter station are characterized in that the inspection robot transmits a human signal to the inspection robot through the signal receiving end of the converter station, the inspection robot transmits a wireless signal transmitted by the inspection robot in the converter station, a plurality of fingerprint characteristic information corresponding to the wireless channel of the inspection robot is extracted according to the inspection robot transmitting signal, each fingerprint characteristic information is used for representing corresponding signal fading characteristics in the wireless channel of the inspection robot, fingerprint characteristic vectors corresponding to the current region of the inspection robot are generated according to the fingerprint characteristic information, fingerprint characteristic vectors corresponding to the inspection regions of the converter station are obtained, the fingerprint characteristic vectors corresponding to the inspection regions are compared with the fingerprint characteristic vectors corresponding to the current region respectively, region similar information corresponding to the inspection regions is obtained, the region similar information is used for determining region position information of the current region in the converter station, accordingly, the inspection robot can be accurately managed according to the current channel characteristics of the inspection robot, the current channel of the inspection robot can be more safely maintained in the converter station, and the environment can be more safely maintained.

In another embodiment, the method comprises the steps of extracting a plurality of fingerprint feature information corresponding to a wireless channel of the inspection robot according to an emission signal of the inspection robot, wherein the method comprises the steps of inputting the emission signal of the inspection robot into a wireless channel feature extraction model to obtain signal feature data corresponding to each channel sample point in the wireless channel of the inspection robot, generating a signal feature data sequence according to the signal feature data corresponding to each channel sample point, and extracting the fingerprint feature of the signal feature data sequence to obtain a plurality of fingerprint feature information corresponding to the wireless channel of the inspection robot.

The wireless channel feature extraction model may be a model for determining signal feature data in a wireless channel.

Wherein the signal characteristic data may be signal values in a wireless channel.

In a specific implementation, a server inputs a routing inspection robot transmit signal to a wireless channel feature extraction model to obtain signal values corresponding to all channel sample points in a wireless channel of the routing inspection robot, the server generates a signal feature data sequence according to the signal values corresponding to all channel sample points in the wireless channel of the routing inspection robot, and the server performs fingerprint feature extraction on the signal feature data sequence to obtain a plurality of fingerprint feature information corresponding to the wireless channel of the routing inspection robot, such as Doppler spread parameter information, time delay spread parameter information, path loss parameter information, time domain peak analysis parameter information and frequency domain peak analysis parameter information.

According to the technical scheme, the inspection robot transmits the transmission signals to the wireless channel characteristic model, signal characteristic data corresponding to each channel sample point in the wireless channel are obtained, a signal characteristic data sequence is generated, fingerprint characteristic extraction is carried out on the signal characteristic data sequence according to channel fading characteristics, and complex and changeable wireless signals are converted into visual data, so that positioning identification of the inspection robot is facilitated.

In another embodiment, the method for obtaining the signal characteristic data corresponding to each channel sample point in the wireless channel of the inspection robot comprises the steps of inputting the inspection robot human transmission signal into an ideal signal characteristic extraction submodel to obtain the ideal signal characteristic data corresponding to each channel sample point in the wireless channel of the inspection robot, and inputting the ideal signal characteristic data into an actual signal characteristic extraction submodel to obtain the signal characteristic data actually corresponding to each channel sample point in the wireless channel of the inspection robot.

The ideal signal feature extraction sub-model may be a model for obtaining ideal signal values in a wireless channel, among other things.

Wherein the actual signal feature extraction sub-model may be a model for converting ideal signal values in the wireless channel into actual signal values.

In the specific implementation, the server inputs the inspection robot transmit signal to the ideal signal feature extraction sub-model to obtain ideal signal feature data corresponding to each channel sample point in the wireless channel of the inspection robot, and the server inputs the ideal signal feature data to the actual signal feature extraction sub-model to obtain signal feature data actually corresponding to each channel sample point in the wireless channel of the inspection robot.

For ease of understanding by those skilled in the art, the following exemplary provides a method of modeling a wireless channel to determine signal characteristics data of the wireless channel. According to the flat fading channel model theory, due to the fact that multipath transmission difference exists in the transmitted signals, different time delays and different channel coefficients exist in different transmission paths of the transmitted signals, wherein the time delays lead to transmission delay of the signals in the transmission process, and the channel coefficients lead to signal attenuation in the transmission process. Because the transmission performance of the signals is the superposition of the signals on all transmission paths, the method firstly establishes an ideal wireless channel characteristic model, then establishes a basic wireless channel characteristic model, further establishes a test transmitting signal required to be selected by the wireless channel characteristic model, and finally introduces a time parameter t to establish a wireless channel time-varying model. The method comprises the following specific steps:

Step 1, building an ideal channel model:

Since the channel samples are distributed at a certain time interval in the channel, the sampling time interval delta kappa is set, the sampling time interval delta kappa is the time T _N corresponding to the total length of the signal divided by the total number N of samples, the channel samples are sampled from 0 time, so the channel samples N are the codes of signal values acquired at the (N-1) delta kappa time, in the formula, L is the total number of signal transmission paths at the current time, N is the total number of sample identifiers, namely the signal length, gamma _l is the channel coefficient of the first signal transmission path at the current time, reflects the fading condition of the signal transmitted in the first path, and therefore the value range is (0, 1), tau _l is the time delay of the first path at the current time, tau _l is the integral multiple of the samples, namely the signal is delayed by tau _l samples at the time, the unit of tau _l is the integral multiple of the samples, and X (N) is the measurement result of the sample N in the ideal channel, namely the transmission channel under the influence of noise-free signal, is the ideal transmission condition, and can represent the ideal transmission characteristics of the ideal wireless transmission channel.

Step 2, introducing external noise influence into the ideal channel model, and establishing a basic wireless channel characteristic model:

Wherein Y (n) is a measurement result of a signal value of a signal at a sample point n under the influence of external noise, is a real signal measurement result, and represents the real transmission characteristic of a wireless channel; The filter length, ζ (μ) is a filter coefficient when the radio frequency filter length corresponds to μ, and is equivalent to an influence of all radio frequency filters in a wireless channel, and since the adopted filters are known, filter parameters are known quantities, and φ (n) is an influence of an electromagnetic noise signal introduced by a sample point n at the moment.

And 3, constructing a test transmitting signal of the basic wireless channel characteristic model in the step 2. Assume that the test transmit signal is a unit step pulse signal:

And 4, establishing a wireless channel time-varying model. Introducing a time parameter t on the basis of a basic wireless channel characteristic model, dividing a two-dimensional inspection plane progressive area of the inspection robot according to the actual situation, describing an inspection area where the inspection robot is located in real time by coordinates (i, j) to reflect the dynamic change of the position of the inspection robot, synthesizing the data, and establishing a wireless channel time-varying model considering the dynamic change of the quadruped robot based on the established basic wireless channel characteristic model:

wherein T is the test time corresponding to the sample identification point, Channel coefficients of the signal in the first signal transmission path at the time instant t for the region coordinates (i, j); For the time delay of the signal at the first path at the time instant t, the value of the noise signal at the sample point n is phi _i,j (n, t) at the time instant t, the value of the wanted channel signal is processed at the sample point n at X _i,j (n, t) at the time instant t, the value of the true measurement of the signal at the sample point n is Y _i,j (n, t) at the time instant t.

According to the technical scheme, through inputting the inspection robot transmit signals into the ideal signal feature extraction submodel, and considering the influence of signal noise, ideal signal feature data are input into the actual signal feature extraction submodel, so that signal feature data actually corresponding to each channel sample point in a wireless channel of the inspection robot are obtained, when fingerprint feature extraction is carried out on a signal feature data sequence, more accurate fingerprint feature information can be obtained, and positioning identification of the inspection robot is facilitated to be realized more accurately.

In another embodiment, a signal characteristic data sequence is generated according to signal characteristic data corresponding to each channel sample point, fingerprint characteristic extraction is carried out on the signal characteristic data sequence to obtain a plurality of fingerprint characteristic information corresponding to a wireless channel of the inspection robot, the method comprises the steps of generating the signal characteristic data sequence corresponding to the wireless channel of the inspection robot according to the signal characteristic data corresponding to each channel sample point, carrying out noise reduction processing on the signal characteristic data sequence to obtain a noise-reduced signal characteristic data sequence, and carrying out fingerprint characteristic extraction on the noise-reduced signal characteristic data sequence to obtain a plurality of fingerprint characteristic information corresponding to the wireless channel of the inspection robot.

In a specific implementation, a server generates a signal characteristic data sequence corresponding to a wireless channel of a patrol robot according to signal characteristic data corresponding to each channel sample point of the wireless channel of the patrol robot, the server performs noise reduction processing on the signal characteristic data sequence to obtain a noise-reduced signal characteristic data sequence, and the server performs fingerprint feature extraction on the noise-reduced signal characteristic data sequence to obtain a plurality of fingerprint feature information corresponding to the wireless channel of the patrol robot, such as Doppler spread parameter information, time delay spread parameter information, path loss parameter information, time domain peak analysis parameter information and frequency domain peak analysis parameter information.

In order to facilitate understanding of those skilled in the art, the following exemplary method for extracting fingerprint features of a wireless channel of a converter station inspection robot is provided, which is based on fading features of the wireless channel, firstly, preprocessing basic parameters of signal data, and then calculating fingerprint feature parameters according to the basic parameters of the signal data.

In the process of preprocessing the basic parameters of the signal data, firstly, the noise-reduced signal characteristic data Y ' _i,j (n, t) is processed, and as Y ' _i,j (n, t) is a complex signal, the instantaneous amplitude and the instantaneous power of Y ' _i,j (n, t) are calculated according to the following formula:

The instantaneous amplitude Ap _i,j (n, t) of Y ' _i,j (n, t) is calculated, where real (Y ' _i,j (n, t)) is the real part of the complex signal Y ' _i,j (n, t) and imag (Y ' _i,j (n, t)) is the imaginary part of the complex signal Y ' _i,j (n, t). According to the following formula:

P_i,j(n,t)＝[Ap_i,j(n,t)]²

The instantaneous power P _i,j (n, t) of Y' _i,j (n, t) is calculated. According to the following formula

Ap_i,j(n,t)→Fourier transform→Af_i,j(n,t)

The instantaneous amplitude Ap _i,j (n, t) of Y' _i,j (n, t) is fourier transformed to obtain frequency domain analyzed data Af _i,j (n, t).

In the process of calculating the fingerprint characteristic parameters according to the signal data basic parameters, doppler expansion calculation, delay expansion calculation, path loss calculation and signal peak analysis are required.

Wherein, in the doppler spread calculation, a maximum frequency shift f _m needs to be determined, where f _m is according to the formula:

And (5) calculating to obtain the product. Where v is the transmission speed of the signal in the channel, the speed is the signal transmission distance divided by the signal transmission time (the maximum value of the instantaneous amplitude of the signal transmitted to the received signal is approximately the signal transmission time), c is the propagation speed of the electromagnetic wave under ideal conditions, and f _c is the transmission frequency of the signal, which can be known from the information of the transmitted signal.

The Doppler spread is calculated based on a typical Doppler power spectrum formula:

Calculation is performed using the doppler power value at f=f _c in the doppler power spectrum As a characteristic parameter of doppler spread.

When the time delay expansion is calculated, the calculation is performed based on a calculation method of global average additional time delay and global rms time delay expansion, and a specific calculation formula is as follows:

Wherein, For the instantaneous power of the step signal input to the filter at the signal identification point n, at is the measurement interval of adjacent samples in the signal sequence,For the corresponding delay at the peak r _t′_op n, t,For the global additional delay time to be added,Is a global rms delay spread.Is the expected value of the global additional delay square,Is a characteristic parameter of delay spread.

Wherein, when the path loss is calculated, the method is based on the formula

And calculating the path loss of the communication signal of the regional inspection robot. Wherein, P _r is the power of the transmitted signal,For the calculated path loss of the signal at time t. The path loss set of the communication signals of the regional inspection robot is obtained by calculating the path loss at different times:

the data fitting is carried out on the set by utilizing a linear least square method, so that the slope of a fitting straight line can be obtained I.e. the characteristic parameter of the path loss.

Wherein, when signal peak analysis is performed, for noise reduction signal data Y' _i,j, signal amplitude peak value number sets of different amplitude intervals are extracted from the angles of time domain analysis and frequency domain analysisWherein num1 is the number of peak intervals in time domain analysis, num2 is the number of peak intervals in frequency domain analysis, and peak numbers of Ap _i,j(n,t)、Af_i,j (n, t) data need to be counted according to different amplitude intervals.

In this way, fingerprint characteristic information of the wireless channel of the inspection robot in the converter station is determined, wherein the fingerprint characteristic information comprises Doppler spread parameter information, time delay spread parameter information, path loss parameter information, time domain peak analysis parameter information and frequency domain peak analysis parameter information.

According to the technical scheme, the signal characteristic data sequence is generated through the signal characteristic data corresponding to each channel sample point in the wireless channel, noise reduction processing is carried out on the signal characteristic data sequence, fingerprint characteristic extraction is carried out on the signal characteristic data sequence after noise reduction, complex signal data are converted into characteristic data with practical meanings, characteristic analysis of the wireless channel is achieved, and characteristic identification of the wireless channel of the inspection robot is facilitated.

In another embodiment, the noise reduction processing is performed on the signal characteristic data sequence to obtain a noise-reduced signal characteristic data sequence, and the noise-reduced signal characteristic data sequence comprises the steps of generating a signal characteristic matrix corresponding to a wireless channel of the inspection robot according to the signal characteristic data sequence, performing pre-noise reduction processing on the signal characteristic matrix to obtain a pre-noise-reduced signal characteristic matrix, extracting elements in the pre-noise-reduced signal characteristic matrix to generate a noise-reduced signal characteristic data sequence, and inputting the pre-noise-reduced signal characteristic data sequence into a wavelet noise reduction model to obtain the noise-reduced signal characteristic data sequence.

The wavelet noise reduction model may be a model for performing noise reduction processing on signal feature data.

In the specific implementation, a server generates a signal feature matrix corresponding to a wireless channel of the inspection robot according to a signal feature data sequence, the signal feature matrix is a signal matrix containing signal noise information, the server performs pre-noise reduction processing on the signal feature matrix to obtain a pre-noise-reduced signal feature matrix, the server extracts elements in the pre-noise-reduced signal feature matrix to generate a noise-reduced signal feature data sequence, and the server performs wavelet noise reduction processing on the noise-reduced signal feature data sequence to obtain a noise-reduced signal feature data sequence.

In order to facilitate understanding of those skilled in the art, fig. 5 exemplarily provides a flowchart of a wavelet denoising method based on SVD singular value decomposition, which constructs a noisy matrix according to original signal data, performs SVD decomposition on the noisy matrix, performs pre-denoising after the SVD decomposition is completed, and performs secondary denoising on the pre-denoising data according to a wavelet denoising method based on a fixed threshold value, thereby outputting denoising signal data. The method comprises the following specific steps:

And 1, constructing a matrix with noise according to the signal length. The noisy signal sequence measured by a signal receiving end at a certain moment in a certain area is marked as Y, N which is 0.5 times of epsilon and is a positive integer is taken according to the data in the Y, the noisy signal sequence is constructed as epsilon× (N-epsilon+1) matrix, and the constructed noisy matrix is obtained by the following steps:

and 2, carrying out SVD decomposition on the constructed noisy matrix R. According to the SVD singular value decomposition principle, a singular value decomposition expression and a related formula of the noisy matrix R can be obtained and expressed as follows:

Wherein, sigma is an N× (N- ε+1) diagonal matrix composed of nonnegative diagonal elements arranged in descending order, U, V is an N×N, (N- ε+1) × (N- ε+1) orthogonal matrix, respectively. The matrix U, V, Σ can be obtained by singular value decomposition calculation.

And 3, pre-noise reduction treatment after SVD decomposition. Selecting a proper main singular value S _va, carrying out zero-giving treatment on the matrix sigma to obtain a matrix sigma', obtaining a preprocessing matrix R' according to a formula R '=U.sigma'.V ^T, and extracting corresponding elements in the preprocessing matrix R ', thus obtaining a pre-noise reduction signal sequence Y'.

And 4, performing secondary noise reduction processing based on a wavelet noise reduction method with a fixed threshold value. A wavelet noise reduction method based on a fixed threshold is adopted for the pre-noise reduction signal sequence Y', and a specific flow of the wavelet noise reduction method based on the fixed threshold is shown in fig. 6. The wavelet noise reduction method comprises performing wavelet decomposition on original signal by selecting proper wavelet type and decomposition layer number to obtain each layer coefficient, further, setting threshold value to perform threshold value processing on each layer coefficient, wherein the threshold value setting method is selected according to the following stepsThe method comprises the steps of setting, wherein the purpose of setting a threshold value is to reject strong noise signals in signals, a certain noise reduction effect can only be carried out on weak but continuously existing Gaussian signals in the environment through SVD singular values, the effect on the strong noise signals in the environment is not obvious, secondary noise reduction processing is needed through wavelet noise reduction, denoising is carried out on each layer coefficient according to a denoising method based on a fixed threshold value, and finally wavelet reconstruction is carried out on each layer coefficient after processing (namely quantized coefficients), so that a denoised signal Y' _i,j (n, t) is obtained.

According to the technical scheme, the signal characteristic data corresponding to the wireless channel of the inspection robot is subjected to noise reduction for a plurality of times, so that a noise-reduced signal characteristic data sequence is obtained, the influence of strong electromagnetic interference on the wireless signal in the wireless channel of the inspection robot caused by Gaussian noise signals originally existing in the environment and the strong electromagnetic interference on the environment of the converter station is reduced, the acquired fingerprint characteristic information is more accurate, and the positioning identification of the inspection robot is facilitated.

In another embodiment, the method comprises the steps of obtaining fingerprint feature vectors corresponding to all the inspection areas in the converter station, comparing the fingerprint feature vectors corresponding to all the inspection areas with the fingerprint feature vectors corresponding to the current area to obtain area similarity information corresponding to all the inspection areas, obtaining the fingerprint feature vectors corresponding to all the inspection areas in the converter station, comparing the fingerprint feature vectors corresponding to all the inspection areas with the fingerprint feature vectors corresponding to the current area to obtain the fingerprint feature similarity vectors corresponding to all the inspection areas, generating fingerprint feature weight vectors according to the weight information corresponding to all the fingerprint feature information, and determining the area similarity information corresponding to all the inspection areas according to the fingerprint feature similarity vectors and the fingerprint feature weight vectors corresponding to all the inspection areas, wherein the area similarity information corresponding to all the inspection areas represents the area similarity of all the inspection areas and the current area.

The elements in the fingerprint feature similarity vector may be the similarity between the fingerprint feature data of the wireless channel corresponding to the characterization inspection area.

The elements in the fingerprint feature weight vector may be importance degrees corresponding to the respective fingerprint features characterizing the wireless channel.

In the specific implementation, a server acquires fingerprint feature vectors corresponding to wireless channels of all patrol areas in a converter station, compares the fingerprint feature vectors corresponding to the wireless channels of all patrol areas with the fingerprint feature vectors corresponding to the areas where the patrol robots are currently located to obtain fingerprint feature similar vectors of the wireless channels of all patrol areas and the wireless channels of the areas where the patrol robots are currently located, generates fingerprint feature weight vectors according to weight information corresponding to all the fingerprint feature information, distributes the fingerprint feature weight vectors according to the fingerprint feature similar vectors and the fingerprint feature weight vectors corresponding to all the patrol areas to obtain the area similarity of all the patrol areas and the areas where the patrol robots are currently located, and determines the patrol area with the highest area similarity as the specific position of the patrol robots in the converter station according to the area similarity of all the patrol areas and the areas where the patrol robots are currently located.

In order to facilitate understanding of those skilled in the art, the following exemplary provides a channel region identification model based on weight distribution, and in the case that the positioning of the inspection robot is unknown, the inspection robot is combined with the fingerprint feature of the existing region channel to perform inspection region identification by extracting the real-time signal of the inspection robot, and the similarity of the doppler spread feature parameter, the time delay spread feature parameter, the path loss feature parameter, the time domain peak analysis feature parameter and the frequency domain peak analysis feature parameter is according to the following formula:

Calculating, wherein (i, j) respectively refers to the coordinates of the inspection area to be identified and the coordinates of the inspection area with known channel characteristics, and inputting the wireless channel characteristics of the area to be identified into the 5 formulas to obtain five similarity indexes, which are recorded as similarity vectors

Further, according to the above method, the similarity vector between the required identification region and all the known channel characteristic regions is calculated, and then a weight distribution vector Ω= [ ω ₁,ω₂,ω₃,ω₄,ω₅ ] is set according to the following formula

And calculating the comprehensive similarity. Wherein q _vg is the channel characteristic similarity between the inspection area to be identified in the v-th and the inspection area with the known channel characteristics in the g-th feature, and map is the coordinate set of the inspection area with the known channel characteristics. According to the calculation, a comprehensive similarity analysis network Q can be established, and Q _(i,j) epsilon Q, wherein the coordinate corresponding to the maximum comprehensive similarity in the network is the coordinate of the inspection area.

According to the technical scheme of the embodiment, the fingerprint feature similarity vectors corresponding to the inspection areas are calculated according to the fingerprint feature vectors of the inspection areas and the areas where the inspection robots are currently located, and then the fingerprint feature similarity information corresponding to the inspection areas is determined according to the weight information corresponding to the fingerprint features in the fingerprint feature vectors, namely, the area similarity information corresponding to the inspection areas comprehensively considers the importance of the fingerprint feature information, so that more accurate area similarity information can be obtained, and the positioning identification of the inspection robots is facilitated.

In another embodiment, as shown in fig. 7, a method for identifying a region based on a wireless channel fingerprint feature of a converter station inspection robot is provided, and the method is applied to the server 104 in fig. 1 for illustration, and includes the following steps:

Step S702, acquiring a patrol robot transmitting signal received by a signal receiving end of a converter station, wherein the patrol robot transmitting signal is a wireless signal transmitted by a patrol robot in the converter station;

step S704, transmitting a signal sent by the inspection robot to a wireless channel feature extraction model to obtain signal feature data corresponding to each channel sample point in a wireless channel of the inspection robot;

Step S706, generating a signal characteristic data sequence according to the signal characteristic data corresponding to each channel sample point, and extracting fingerprint characteristics of the signal characteristic data sequence to obtain a plurality of pieces of fingerprint characteristic information corresponding to the wireless channel of the inspection robot;

Step S708, generating a fingerprint feature vector corresponding to the current area of the inspection robot according to the plurality of fingerprint feature information;

Step S710, obtaining fingerprint feature vectors corresponding to all the inspection areas in the converter station, comparing the fingerprint feature vectors corresponding to all the inspection areas with the fingerprint feature vectors corresponding to the current area to obtain area similar information corresponding to all the inspection areas, wherein the area similar information is used for determining the area position information of the current area in the converter station.

It should be noted that, the specific limitation of the above steps may refer to the specific limitation of the area identification method based on the wireless channel fingerprint feature of the converter station inspection robot, which is not described herein.

It should be understood that, although the steps in the flowcharts related to the embodiments described above are sequentially shown as indicated by arrows, these steps are not necessarily sequentially performed in the order indicated by the arrows. The steps are not strictly limited to the order of execution unless explicitly recited herein, and the steps may be executed in other orders. Moreover, at least some of the steps in the flowcharts described in the above embodiments may include a plurality of steps or a plurality of stages, which are not necessarily performed at the same time, but may be performed at different times, and the order of the steps or stages is not necessarily performed sequentially, but may be performed alternately or alternately with at least some of the other steps or stages.

Based on the same inventive concept, the embodiment of the application also provides a region identification device based on the wireless channel fingerprint characteristics of the converter station inspection robot, which is used for realizing the region identification method based on the wireless channel fingerprint characteristics of the converter station inspection robot. The implementation scheme of the device for solving the problem is similar to the implementation scheme recorded in the method, so the specific limitation in the embodiment of the device for identifying the region based on the wireless channel fingerprint characteristic of the converter station inspection robot provided below can be referred to the limitation of the method for identifying the region based on the wireless channel fingerprint characteristic of the converter station inspection robot hereinabove, and the description is omitted here.

In one embodiment, as shown in fig. 8, there is provided an area identifying device based on a wireless channel fingerprint feature of a converter station inspection robot, including:

An acquisition module 802, configured to acquire a transmission signal of the inspection robot received through a signal receiving end of the converter station, where the transmission signal of the inspection robot is a wireless signal transmitted by the inspection robot in the converter station;

The extraction module 804 is configured to extract, according to a signal transmitted by the inspection robot, a plurality of fingerprint feature information corresponding to a wireless channel of the inspection robot, where each fingerprint feature information is used to characterize a corresponding signal fading feature in the wireless channel of the inspection robot;

The generating module 806 is configured to generate, according to the plurality of fingerprint feature information, a fingerprint feature vector corresponding to an area where the inspection robot is currently located;

The determining module 808 is configured to obtain a fingerprint feature vector corresponding to each inspection area in the converter station, compare the fingerprint feature vector corresponding to each inspection area with the fingerprint feature vector corresponding to the current area, and obtain area similar information corresponding to each inspection area, where the area similar information is used to determine the area position information of the current area in the converter station.

In one embodiment, according to the signal transmitted by the inspection robot, a plurality of fingerprint feature information corresponding to the wireless channel of the inspection robot is extracted, and the extraction module 804 is specifically configured to input the signal transmitted by the inspection robot to the wireless channel feature extraction model to obtain signal feature data corresponding to each channel sample point in the wireless channel of the inspection robot, generate a signal feature data sequence according to the signal feature data corresponding to each channel sample point, and perform fingerprint feature extraction on the signal feature data sequence to obtain a plurality of fingerprint feature information corresponding to the wireless channel of the inspection robot.

In one embodiment, a patrol robot transmits a transmit signal to a wireless channel feature extraction model to obtain signal feature data corresponding to each channel sample point in a wireless channel of the patrol robot, and an extraction module 804 is specifically configured to input the transmit signal of the patrol robot to an ideal signal feature extraction sub-model to obtain ideal signal feature data corresponding to each channel sample point in the wireless channel of the patrol robot, and input the ideal signal feature data to an actual signal feature extraction sub-model to obtain signal feature data actually corresponding to each channel sample point in the wireless channel of the patrol robot.

In one embodiment, a signal feature data sequence is generated according to signal feature data corresponding to each channel sample point, fingerprint feature extraction is performed on the signal feature data sequence to obtain a plurality of fingerprint feature information corresponding to a wireless channel of the inspection robot, and an extraction module 804 is specifically configured to generate a signal feature data sequence corresponding to the wireless channel of the inspection robot according to the signal feature data corresponding to each channel sample point, perform noise reduction processing on the signal feature data sequence to obtain a noise-reduced signal feature data sequence, and perform fingerprint feature extraction on the noise-reduced signal feature data sequence to obtain a plurality of fingerprint feature information corresponding to the wireless channel of the inspection robot.

In one embodiment, the method includes performing noise reduction processing on a signal feature data sequence to obtain a noise-reduced signal feature data sequence, an extraction module 804, specifically configured to generate a signal feature matrix corresponding to a wireless channel of the inspection robot according to the signal feature data sequence, performing pre-noise reduction processing on the signal feature matrix to obtain a pre-noise-reduced signal feature matrix, extracting elements in the pre-noise-reduced signal feature matrix to generate a noise-reduced signal feature data sequence, and inputting the pre-noise-reduced signal feature data sequence into a wavelet noise reduction model to obtain a noise-reduced signal feature data sequence.

In one embodiment, fingerprint feature vectors corresponding to all the inspection areas in the converter station are obtained, the fingerprint feature vectors corresponding to all the inspection areas are compared with the fingerprint feature vectors corresponding to the current area to obtain area similarity information corresponding to all the inspection areas, the determining module is specifically configured to obtain the fingerprint feature vectors corresponding to all the inspection areas in the converter station, compare the fingerprint feature vectors corresponding to all the inspection areas with the fingerprint feature vectors corresponding to the current area to obtain the fingerprint feature similarity vectors corresponding to all the inspection areas, generate fingerprint feature weight vectors according to the weight information corresponding to all the fingerprint feature information, and determine the area similarity information corresponding to all the inspection areas according to the fingerprint feature similarity vectors and the fingerprint feature weight vectors corresponding to all the inspection areas, wherein the area similarity information corresponding to all the inspection areas characterizes the area similarity of all the inspection areas and the current area.

All or part of the modules in the area identification device based on the wireless channel fingerprint characteristics of the converter station inspection robot can be realized by software, hardware and a combination of the software and the hardware. The above modules may be embedded in hardware or may be independent of a processor in the computer device, or may be stored in software in a memory in the computer device, so that the processor may call and execute operations corresponding to the above modules.

In one embodiment, a computer device is provided, which may be a server, and the internal structure of which may be as shown in fig. 9. The computer device includes a processor, a memory, and a network interface connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The database of the computer equipment is used for storing area identification data based on the wireless channel fingerprint characteristics of the converter station inspection robot. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program when executed by the processor is used for realizing an area identification method based on the wireless channel fingerprint characteristics of the converter station inspection robot.

It will be appreciated by persons skilled in the art that the architecture shown in fig. 9 is merely a block diagram of some of the architecture relevant to the present inventive arrangements and is not limiting as to the computer device to which the present inventive arrangements are applicable, and that a particular computer device may include more or fewer components than shown, or may combine some of the components, or have a different arrangement of components.

In one embodiment, a computer device is provided, including a memory and a processor, where the memory stores a computer program, and where the computer program when executed by the processor causes the processor to perform the steps of a method for identifying a region based on a wireless channel fingerprint feature of a converter station inspection robot. The step of a method for identifying a region based on the wireless channel fingerprint feature of the converter station inspection robot may be the step of a method for identifying a region based on the wireless channel fingerprint feature of the converter station inspection robot in the above embodiments.

In one embodiment, a computer readable storage medium is provided, in which a computer program is stored, where the computer program when executed by a processor causes the processor to perform the steps of a method for identifying a region based on a wireless channel fingerprint feature of a converter station inspection robot. The step of a method for identifying a region based on the wireless channel fingerprint feature of the converter station inspection robot may be the step of a method for identifying a region based on the wireless channel fingerprint feature of the converter station inspection robot in the above embodiments.

In one embodiment, a computer program product is provided, including a computer program, which when executed by a processor causes the processor to perform the steps of a method for identifying a region based on a wireless channel fingerprint feature of a converter station inspection robot as described above. The step of a method for identifying a region based on the wireless channel fingerprint feature of the converter station inspection robot may be the step of a method for identifying a region based on the wireless channel fingerprint feature of the converter station inspection robot in the above embodiments.

The user information (including but not limited to user equipment information, user personal information, etc.) and the data (including but not limited to data for analysis, stored data, presented data, etc.) related to the present application are information and data authorized by the user or sufficiently authorized by each party.

Those skilled in the art will appreciate that implementing all or part of the above described methods may be accomplished by way of a computer program stored on a non-transitory computer readable storage medium, which when executed, may comprise the steps of the embodiments of the methods described above. Any reference to memory, database, or other medium used in embodiments provided herein may include at least one of non-volatile and volatile memory. The nonvolatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical Memory, high density embedded nonvolatile Memory, resistive random access Memory (ReRAM), magneto-resistive random access Memory (Magnetoresistive Random Access Memory, MRAM), ferroelectric Memory (Ferroelectric Random Access Memory, FRAM), phase change Memory (PHASE CHANGE Memory, PCM), graphene Memory, and the like. Volatile memory can include random access memory (Random Access Memory, RAM) or external cache memory, and the like. By way of illustration, and not limitation, RAM can be in various forms such as static random access memory (Static Random Access Memory, SRAM) or dynamic random access memory (Dynamic Random Access Memory, DRAM), etc. The databases referred to in the embodiments provided herein may include at least one of a relational database and a non-relational database. The non-relational database may include, but is not limited to, a blockchain-based distributed database, and the like. The processor referred to in the embodiments provided in the present application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic unit, a data processing logic unit based on quantum computing, or the like, but is not limited thereto.

The technical features of the above embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.

The foregoing examples illustrate only a few embodiments of the application and are described in detail herein without thereby limiting the scope of the application. It should be noted that it will be apparent to those skilled in the art that several variations and modifications can be made without departing from the spirit of the application, which are all within the scope of the application. Accordingly, the scope of the application should be assessed as that of the appended claims.

Claims (9)

1. The area identification method based on the wireless channel fingerprint characteristics of the converter station inspection robot is characterized by comprising the following steps:

the method comprises the steps of obtaining a patrol robot transmitting signal received by a signal receiving end of a converter station, wherein the patrol robot transmitting signal is a wireless signal transmitted by a patrol robot in the converter station;

Extracting a plurality of pieces of fingerprint characteristic information corresponding to the wireless channel of the inspection robot according to the inspection robot transmitting signals, wherein each piece of fingerprint characteristic information is used for representing corresponding signal fading characteristics in the wireless channel of the inspection robot;

Generating a fingerprint feature vector corresponding to the current area of the inspection robot according to the fingerprint feature information;

The method comprises the steps of obtaining fingerprint feature vectors corresponding to all inspection areas in a converter station, comparing the fingerprint feature vectors corresponding to all inspection areas with the fingerprint feature vectors corresponding to the current area to obtain area similarity information corresponding to all inspection areas, comparing the fingerprint feature vectors corresponding to all inspection areas with the fingerprint feature vectors corresponding to the current area to obtain fingerprint feature similarity vectors corresponding to all inspection areas, generating fingerprint feature weight vectors according to weight information corresponding to all the fingerprint feature information, and determining area similarity information corresponding to all the inspection areas according to the fingerprint feature similarity vectors corresponding to all the inspection areas and the fingerprint feature weight vectors, wherein the area similarity information corresponding to all the inspection areas represents the area similarity of all the inspection areas and the current area, and the area similarity information is used for determining the area position information of the current area in the converter station.

2. The method according to claim 1, wherein the extracting a plurality of fingerprint feature information corresponding to a wireless channel of the inspection robot according to the inspection robot transmit a signal, includes:

inputting the inspection robot transmission signals into a wireless channel feature extraction model to obtain signal feature data corresponding to each channel sample point in a wireless channel of the inspection robot;

Generating a signal characteristic data sequence according to the signal characteristic data corresponding to each channel sample point, and extracting fingerprint characteristics of the signal characteristic data sequence to obtain a plurality of fingerprint characteristic information corresponding to the wireless channel of the inspection robot.

3. The method according to claim 2, wherein the wireless channel feature extraction model includes an ideal signal feature extraction sub-model and an actual signal feature extraction sub-model, the inputting the inspection robot transmit a signal to a first wireless channel feature model, and obtaining signal feature data corresponding to each channel sample in a wireless channel of the inspection robot, includes:

inputting the inspection robot transmission signal to the ideal signal characteristic extraction submodel to obtain ideal signal characteristic data corresponding to each channel sample point in a wireless channel of the inspection robot;

And inputting the ideal signal characteristic data into the actual signal characteristic extraction submodel to obtain signal characteristic data actually corresponding to each channel sample point in the wireless channel of the inspection robot.

4. The method according to claim 2, wherein the generating a signal characteristic data sequence according to the signal characteristic data corresponding to each channel sample point, and performing fingerprint feature extraction on the signal characteristic data sequence, to obtain a plurality of fingerprint feature information corresponding to the wireless channel of the inspection robot, includes:

generating a signal characteristic data sequence corresponding to a wireless channel of the inspection robot according to the signal characteristic data corresponding to each channel sample point;

carrying out noise reduction treatment on the signal characteristic data sequence to obtain a noise-reduced signal characteristic data sequence;

And carrying out fingerprint feature extraction on the noise-reduced signal feature data sequence to obtain a plurality of fingerprint feature information corresponding to the wireless channel of the inspection robot.

5. The method of claim 4, wherein the denoising the signal feature data sequence to obtain a denoised signal feature data sequence comprises:

Generating a signal characteristic matrix corresponding to a wireless channel of the inspection robot according to the signal characteristic data sequence;

Pre-denoising the signal characteristic matrix to obtain a pre-denoised signal characteristic matrix;

Extracting elements in the pre-noise-reduced signal feature matrix to generate a noise-reduced signal feature data sequence;

and inputting the pre-noise-reduced signal characteristic data sequence into a wavelet noise reduction model to obtain a noise-reduced signal characteristic data sequence.

6. An area identification device based on wireless channel fingerprint characteristics of a converter station inspection robot, which is characterized by comprising:

The system comprises an acquisition module, a detection module and a control module, wherein the acquisition module is used for acquiring a detection signal transmitted by a detection robot received by a signal receiving end of a converter station, wherein the detection signal transmitted by the detection robot is a wireless signal transmitted by the detection robot in the converter station;

The system comprises an extraction module, a detection module and a detection module, wherein the extraction module is used for extracting a plurality of fingerprint characteristic information corresponding to a wireless channel of the inspection robot according to the inspection robot emission signal, wherein each fingerprint characteristic information is used for representing corresponding signal fading characteristics in the wireless channel of the inspection robot;

the generating module is used for generating fingerprint feature vectors corresponding to the current area of the inspection robot according to the fingerprint feature information;

The determining module is used for obtaining fingerprint feature vectors corresponding to all the inspection areas in the converter station, comparing the fingerprint feature vectors corresponding to all the inspection areas with the fingerprint feature vectors corresponding to the current area to obtain area similarity information corresponding to all the inspection areas, wherein the determining module is used for comparing the fingerprint feature vectors corresponding to all the inspection areas with the fingerprint feature vectors corresponding to the current area to obtain fingerprint feature similarity vectors corresponding to all the inspection areas, generating fingerprint feature weight vectors according to weight information corresponding to all the fingerprint feature information, determining area similarity information corresponding to all the inspection areas according to the fingerprint feature similarity vectors corresponding to all the inspection areas and the fingerprint feature weight vectors, and determining area similarity information corresponding to all the inspection areas, wherein the area similarity information corresponding to all the inspection areas is used for determining area position information of all the inspection areas and the current area.

7. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor implements the steps of the method of any one of claims 1 to 5 when the computer program is executed.

8. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any of claims 1 to 5.

9. A computer program product comprising a computer program, characterized in that the computer program, when being executed by a processor, implements the steps of the method according to any one of claims 1 to 5.