CN111585671A - Electric power LTE wireless private network electromagnetic interference monitoring and identifying method - Google Patents
Electric power LTE wireless private network electromagnetic interference monitoring and identifying method Download PDFInfo
- Publication number
- CN111585671A CN111585671A CN202010297105.3A CN202010297105A CN111585671A CN 111585671 A CN111585671 A CN 111585671A CN 202010297105 A CN202010297105 A CN 202010297105A CN 111585671 A CN111585671 A CN 111585671A
- Authority
- CN
- China
- Prior art keywords
- frequency
- interference
- monitoring
- signal
- spectrum
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000012544 monitoring process Methods 0.000 title claims abstract description 49
- 238000000034 method Methods 0.000 title claims abstract description 35
- 238000001228 spectrum Methods 0.000 claims abstract description 53
- 238000012360 testing method Methods 0.000 claims abstract description 38
- 230000006870 function Effects 0.000 claims abstract description 27
- 238000012545 processing Methods 0.000 claims abstract description 14
- 238000006243 chemical reaction Methods 0.000 claims abstract description 12
- 238000013145 classification model Methods 0.000 claims abstract description 12
- 238000013461 design Methods 0.000 claims abstract description 12
- 230000008569 process Effects 0.000 claims abstract description 12
- 238000007781 pre-processing Methods 0.000 claims abstract description 7
- 238000005070 sampling Methods 0.000 claims abstract description 4
- 239000000523 sample Substances 0.000 claims description 18
- 238000010586 diagram Methods 0.000 claims description 15
- 230000000694 effects Effects 0.000 claims description 12
- 238000000605 extraction Methods 0.000 claims description 12
- 230000003750 conditioning effect Effects 0.000 claims description 9
- 238000012549 training Methods 0.000 claims description 8
- 238000013527 convolutional neural network Methods 0.000 claims description 7
- 230000004913 activation Effects 0.000 claims description 6
- 230000008878 coupling Effects 0.000 claims description 6
- 238000010168 coupling process Methods 0.000 claims description 6
- 238000005859 coupling reaction Methods 0.000 claims description 6
- 230000009466 transformation Effects 0.000 claims description 6
- 238000011156 evaluation Methods 0.000 claims description 5
- 230000005540 biological transmission Effects 0.000 claims description 4
- 238000013135 deep learning Methods 0.000 claims description 4
- 238000005516 engineering process Methods 0.000 claims description 4
- 238000010183 spectrum analysis Methods 0.000 claims description 4
- 238000010606 normalization Methods 0.000 claims description 3
- 230000000737 periodic effect Effects 0.000 claims description 3
- 238000011176 pooling Methods 0.000 claims description 3
- 238000000513 principal component analysis Methods 0.000 claims description 3
- 230000005855 radiation Effects 0.000 claims description 3
- 230000009467 reduction Effects 0.000 claims description 3
- 230000000087 stabilizing effect Effects 0.000 claims description 3
- 238000013507 mapping Methods 0.000 claims description 2
- 238000011002 quantification Methods 0.000 claims description 2
- 238000010801 machine learning Methods 0.000 abstract description 3
- 238000013139 quantization Methods 0.000 abstract description 2
- 238000004458 analytical method Methods 0.000 description 4
- 238000001514 detection method Methods 0.000 description 3
- 238000004891 communication Methods 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 230000003321 amplification Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003199 nucleic acid amplification method Methods 0.000 description 1
- 238000013468 resource allocation Methods 0.000 description 1
- 238000000528 statistical test Methods 0.000 description 1
- 238000010408 sweeping Methods 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04B—TRANSMISSION
- H04B17/00—Monitoring; Testing
- H04B17/30—Monitoring; Testing of propagation channels
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/001—Measuring interference from external sources to, or emission from, the device under test, e.g. EMC, EMI, EMP or ESD testing
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04B—TRANSMISSION
- H04B17/00—Monitoring; Testing
- H04B17/30—Monitoring; Testing of propagation channels
- H04B17/382—Monitoring; Testing of propagation channels for resource allocation, admission control or handover
Abstract
A method for monitoring and identifying electromagnetic interference of an electric LTE wireless private network comprises the following two processes: spectrum monitoring and interference identification, spectrum monitoring has adopted the design of scanning heterodyne spectrum monitoring at the high frequency channel, through multistage frequency conversion processing, on becoming lower intermediate frequency with the incoming signal, then has adopted the design of Fourier spectrum monitoring at the intermediate frequency channel, carries out the AD sampling quantization to the signal of frequency conversion to the intermediate frequency, becomes digital signal, recycles digital intermediate frequency technique, Fourier transform and accomplishes spectrum monitoring. The interference source identification process comprises the steps of preprocessing collected data, extracting features and selecting the features, learning the relation between collected signal features and an interference source by using a machine learning algorithm to obtain a classification model based on interference source identification, extracting the features of a test signal, and identifying a result by using the obtained classification model. The invention can closely combine the electromagnetic spectrum with the functions of spectrum monitoring and interference identification aiming at the needs of the power system, and is suitable for a 1.8GLTE wireless private network.
Description
Technical Field
The invention belongs to the field of radio frequency spectrum detection and interference analysis, and particularly relates to an electromagnetic interference monitoring and identifying method for an electric power LTE wireless private network.
Background
At present, power wireless private network construction work based on an LTE technology is carried out in a power system in multiple cities, communication bearing requirements of power services are effectively supported, flexible and ubiquitous access of terminal-side services is realized, intelligent development of services is promoted, some problems existing in wireless communication are gradually exposed while power application achieves certain results, interference problems particularly affect the performance of a network and even directly cause interruption of the power services, and therefore real-time monitoring of radio frequency spectrums in the power system and interference analysis, judgment and investigation of a power wireless private network are urgently needed.
Frequency resources are important factors influencing network performance, construction cost and the like of an electric power wireless private network, a 230MHz discrete frequency band and a 1.8GHz continuous frequency band are mainly adopted, conditions of multi-service frequency resource allocation, same-frequency different-system shared resources and the like exist in private network systems based on different frequency bands, how to efficiently use frequency and quickly locate interference is the next key work of improving service quality of the electric power wireless private network, frequency spectrum monitoring is to measure basic parameters and frequency spectrum characteristic parameters of radio transmission by adopting technical means and certain equipment, and the frequency spectrum characteristic analysis of digital signals can be realized; carrying out statistical test analysis on frequency band utilization rate and frequency band occupancy; testing and counting the use condition of the assigned frequency so as to carry out reasonable and effective frequency assignment; and checking and processing illegal radio stations and interference source direction finding and positioning.
The wireless power application scenes are many, the coverage range is wide, an intelligent electromagnetic environment comprehensive evaluation mechanism is lacked, decision-making bases cannot be provided for frequency resource management, the current frequency allocation means is extensive, allocation is mainly carried out by means of manual experience and rough service requirement estimation, scientificity, automation and refinement need to be improved, small-range frequency sweeping can only be carried out through a handheld instrument in electromagnetic environment evaluation, flexibility is insufficient, and instantaneity is low.
The frequency bands of the existing private network are frequency bands shared by multiple industries, the stability of the wireless private network is interfered due to the reasons of signal leakage, signal overlapping and the like of adjacent frequency bands, the service access quality is influenced, meanwhile, more hidden dangers are brought to the reliable operation of the electric wireless private network due to the occurrence of various illegal radio stations, the interference type and the interference tracing source must be accurately judged by searching a feasible method, and then relevant measures are taken, so that the large-area service disconnection is avoided, and the electric service bearing quality is influenced.
Disclosure of Invention
The technical problem to be solved by the invention is as follows: the method overcomes the defects of the prior art, and provides the electromagnetic interference monitoring and identifying method for the power LTE wireless private network, which can obviously improve the identification precision.
The technical scheme adopted by the invention for solving the technical problem is as follows:
a method for monitoring and identifying electromagnetic interference of an electric LTE wireless private network comprises the following two processes: the method comprises the following steps of spectrum monitoring and interference identification:
step 1, converting a non-voltage signal input from the outside into a voltage signal by using a sensor, and sending the voltage signal to a signal conditioning device for processing;
step 2, the signal conditioning equipment amplifies, attenuates and filters the input voltage signal, and finally sends the processed signal to a spectrum analyzer;
step 3, the spectrum analyzer carries out A/D conversion on the input signal processed in the step 2 to finish the acquisition of test data;
step 4, analyzing, calculating and processing the data collected in the step 3 to realize interference source identification, wherein the interference source identification process is as follows:
step 4-1, data preprocessing: denoising original test data by utilizing wavelet transformation, performing data normalization operation on the original test data, performing envelope and continuation processing on an emission characteristic curve, and mapping a high-dimensional vector to a low-dimensional space through dimension reduction operation;
step 4-2, feature extraction: extracting the characteristics of the acquired signals, including peak characteristics, envelope characteristics and harmonic characteristics, and performing frequency domain characteristic extraction on the periodic signals and the ringing signals by adopting Fourier transform; performing frequency domain feature extraction on the discrete signals by adopting fast Fourier transform; extracting the frequency spectrum characteristics of the pulse signals by adopting short-time Fourier transform; extracting frequency domain characteristics of the non-stationary signals by adopting wavelet transformation;
4-3, selecting characteristics; the feature selection comprises two contents, wherein the first is to select a statistical feature evaluation algorithm of a training sample to evaluate the features and calculate the contribution value of each feature to the classification effect; secondly, selecting partial attributes by using a principal component analysis algorithm, selecting different characteristics as identification objects aiming at different electromagnetic compatibility test objects, selecting subsets with strong distinguishing capability from a current vector attribute set, and removing redundant characteristics or invalid characteristics of interference classification effects to form a compact characteristic set;
step 4-4, learning and training; learning the relation between the acquired signal characteristics and the interference source by using a deep learning algorithm based on a convolutional neural network to obtain a classification model based on interference source identification;
the mathematical form of the convolution is as follows:
y＝f(∑x*wij+b)
wherein x is the convolutional layer input characteristic diagram; y is the convolutional layer output characteristic diagram; w is aijIs a two-dimensional convolution kernel; b is a bias term; f (-) is an activation function, such as a sigmoid function or tanh function or ReLU function;
the convolutional neural network uses a plurality of filters, a plurality of convolutional layers and a plurality of pooling layers, and finally, a full connection layer and a softmax layer are connected, and finally, probability distribution of corresponding input on each type of output is output;
the output of the whole network is
o＝f(n-1)(f(n-2)(...f(1)(x)))
Wherein x is the convolutional layer input characteristic diagram; f (-) is an activation function, such as a sigmoid function or tanh function or ReLU function;
forming a series of parameters corresponding to the mode classification method according to the corresponding relation between the sample set with known class attributes and the vector values thereof;
4-5, classifying and identifying; and (4) extracting characteristics of the test signals, classifying the interference sources of the test data set with unknown class attributes by adopting the classification model obtained in the step (4-4), if the class attributes in the test data set are known, the process can be used for verifying the classification effect of the classifier, and if the classification effect is ideal, the classification model can be applied to actual flow classification.
Further, in step 1, the sensor comprises a current probe, a voltage probe, a near-field probe and a receiving antenna; when conducting transmission test is carried out, the frequency spectrograph is connected with the power supply impedance stabilizing network or the current probe; when a radiation emission test is carried out, the frequency spectrograph is connected with the receiving antenna; in the test of the coupling degree between the antennas, the vehicle-mounted antenna is connected to the receiver, and the coupling degree of the antenna is analyzed accordingly.
Further, in step 2, the signal conditioning device comprises a signal amplifier, a linear impedance attenuator, a band-stop filter and a high-pass filter.
Further, in step 3, the monitoring process of the spectrum analyzer on the data spectrum in step 2 is as follows: adopting a scanning heterodyne spectrum monitoring design in a high-frequency section, and changing an input signal to a lower intermediate frequency through multi-stage frequency conversion processing; and a Fourier spectrum monitoring design is adopted in the middle frequency band, A/D sampling quantification is carried out on signals from frequency conversion to intermediate frequency, the signals are converted into digital signals, and then the frequency spectrum analysis is completed by utilizing a digital intermediate frequency technology and Fourier transform.
The invention has the following positive beneficial effects:
1. the frequency spectrum monitoring of the invention adopts the scanning heterodyne type frequency spectrum monitoring design and the Fourier frequency spectrum monitoring design respectively in the high frequency band and the medium frequency, can exert the advantages of wide measuring frequency range of the scanning heterodyne type frequency spectrum design and strong frequency resolution of the Fourier frequency spectrum monitoring design, and greatly improves the performance of the frequency spectrum monitoring.
2. The interference identification problem is converted into a machine learning classification problem, after data preprocessing, feature extraction and feature selection are carried out on the acquired data, the deep learning algorithm based on the convolutional neural network is utilized to learn the relation between the acquired signal features and the interference source, a classification model based on the interference source identification is obtained, and the identification precision can be obviously improved.
3. The invention can closely combine the electromagnetic spectrum with the functions of spectrum monitoring and interference identification aiming at the needs of the power system, and is suitable for a 1.8GLTE wireless private network.
Drawings
FIG. 1 is a general block diagram of spectrum monitoring and interference identification in the present invention;
FIG. 2 is a schematic diagram of heterodyne spectrum monitoring of frequency sweep in accordance with the present invention;
FIG. 3 is a schematic diagram of Fourier-based spectrum monitoring according to the present invention;
FIG. 4 is a flow chart of interference source identification in the present invention;
FIG. 5 is a data flow diagram based on a multi-user, multi-tasking scheme in accordance with an embodiment of the present invention.
Detailed Description
The technical scheme of the invention is further explained in detail by combining the accompanying drawings 1, 2, 3, 4, 5 and the specific embodiment:
a method for monitoring and identifying electromagnetic interference of an electric LTE wireless private network comprises the following two processes: the method comprises the following steps of spectrum monitoring and interference identification:
step 1, converting a non-voltage signal input from the outside into a voltage signal by using a sensor, and sending the voltage signal to a signal conditioning device for processing;
step 2, the signal conditioning equipment amplifies, attenuates and filters the input voltage signal, and finally sends the processed signal to a spectrum analyzer;
step 3, the spectrum analyzer carries out A/D conversion on the input signal processed in the step 2 to finish the acquisition of test data;
and 4, analyzing, calculating and processing the data acquired in the step 3 to realize interference source identification, wherein the interference source identification process comprises data preprocessing, feature extraction, feature selection, learning and training and classification identification.
Further, in step 1, the sensor comprises a current probe, a voltage probe, a near-field probe and a receiving antenna; when conducting transmission test is carried out, the frequency spectrograph is connected with the power supply impedance stabilizing network or the current probe; when a radiation emission test is carried out, the frequency spectrograph is connected with the receiving antenna; in the test of the coupling degree between the antennas, the vehicle-mounted antenna is connected to the receiver, and the coupling degree of the antenna is analyzed accordingly.
Further, in step 2, the signal conditioning device comprises a signal amplifier, a linear impedance attenuator, a band-stop filter and a high-pass filter.
As shown in fig. 1, the present invention includes two basic functions: spectrum monitoring and interference source identification, a spectrum analyzer is used for spectrum monitoring, a machine learning algorithm is used for interference identification,
in the invention, the electromagnetic interference monitoring adopts a scanning heterodyne design in a high frequency band, an input signal is changed to a lower intermediate frequency through multi-stage frequency conversion processing, a Fourier spectrometer design is adopted in a middle frequency band, A/D sampling quantization is carried out on the signal which is converted to the intermediate frequency, the signal is changed into a digital signal, and then the digital intermediate frequency technology and FFT conversion are utilized to complete spectrum analysis.
As shown in fig. 2, the swept heterodyne spectrum monitoring uses auto-tuning to change the frequency of the local oscillator to continuously perform frequency mixing to obtain a fixed intermediate frequency, which is converted by the same frequency conversion principle as that of the super heterodyne radio, except that a swept oscillator is used as the local oscillator.
The frequency sweep heterodyne frequency spectrograph mainly comprises an input channel, a frequency mixing circuit, an intermediate frequency processing circuit, a detection circuit, a video filter and the like, wherein a local oscillator signal is controlled by a scanning generator, after a signal is input, the local oscillator signal and a local oscillator signal are subjected to difference frequency in the frequency mixer, only when the frequency of the difference frequency signal is within the bandwidth of an intermediate frequency filter, an intermediate frequency amplifier outputs a signal in direct proportion to the amplitude of the input signal, and then the signal is output on a display after detection and amplification, so that the frequency can be continuously selected by continuously adjusting the frequency of the local oscillator signal through the scanning generator, and the purpose of spectrum measurement is achieved.
The fourier spectrum monitoring is based on fast fourier transform to realize spectrum analysis, and a schematic block diagram of the fourier spectrum monitoring is shown in fig. 3, wherein an input signal is filtered by a low-pass filter to remove high-frequency components outside a measurement frequency band, then the signal is sampled and quantized by an ADC, so that the input signal is converted into a digital signal, and then the obtained digital signal is subjected to FFT, so that spectrum information of the input signal, including frequency, phase, modulation and other information, can be obtained.
As shown in fig. 4, the interference identification scheme of the present invention is to establish a template database of the key device, then use the test result of the interfered device as the data to be identified, compare the data with the data in the template database through the interference source identification algorithm, and finally identify the interference source.
The interference identification process comprises the following steps: data preprocessing, feature extraction, feature selection, learning and training, and classification and identification.
Data preprocessing: the test result of the invention contains various noise signals, which need to be denoised, the original test data is denoised by wavelet transformation, the original test data is subjected to data normalization operation, the emission characteristic curve is enveloped and extended, and the high-dimensional vector is mapped to the low-dimensional space by dimension reduction operation;
feature extraction: the field electromagnetic compatibility test result has a data record which is a numerical object and is a characteristic per se; extracting the characteristics of the acquired signals, including peak characteristics, envelope characteristics and harmonic characteristics, and performing frequency domain characteristic extraction on the periodic signals and the ringing signals by adopting Fourier transform; performing frequency domain feature extraction on the discrete signals by adopting fast Fourier transform; extracting the frequency spectrum characteristics of the pulse signals by adopting short-time Fourier transform; extracting frequency domain characteristics of the non-stationary signals by adopting wavelet transformation;
selecting characteristics: the feature selection comprises two contents, wherein the first is to select a statistical feature evaluation algorithm of a training sample to evaluate the features and calculate the contribution value of each feature to the classification effect; secondly, partial attributes are selected by utilizing a principal component analysis algorithm, different characteristics can be selected as identification objects aiming at different electromagnetic compatibility test objects, for example, peak characteristic and harmonic characteristic of object characteristic selection of radio stations are more suitable, and envelope characteristic of object characteristic selection of power sources is more suitable; selecting a subset with strong distinguishing capability from the current vector attribute set, and removing redundant features or invalid features interfering with classification effect to form a compact feature set;
learning and training: learning the relation between the acquired signal characteristics and the interference source by using a deep learning algorithm based on a convolutional neural network to obtain a classification model based on interference source identification;
the mathematical form of the convolution is as follows:
y＝f(∑x*wij+b)
wherein x is the convolutional layer input characteristic diagram; y is the convolutional layer output characteristic diagram; w is aijIs a two-dimensional convolution kernel; b is a bias term; f (-) is an activation function, such as a sigmoid function or tanh function or ReLU function;
the convolutional neural network uses a plurality of filters, a plurality of convolutional layers and a plurality of pooling layers, and finally, a full connection layer and a softmax layer are connected, and finally, probability distribution of corresponding input on each type of output is output;
the output of the whole network is
o＝f(n-1)(f(n-2)(...f(1)(x)))
Wherein x is the convolutional layer input characteristic diagram; f (-) is an activation function, such as a sigmoid function or tanh function or ReLU function;
forming a series of parameters corresponding to the mode classification method according to the corresponding relation between the sample set with known class attributes and the vector values thereof;
classification and identification: and (4) extracting characteristics of the test signals, classifying the interference sources of the test data set with unknown class attributes by adopting the classification model obtained in the step (4-4), if the class attributes in the test data set are known, the process can be used for verifying the classification effect of the classifier, and if the classification effect is ideal, the classification model can be applied to actual flow classification.
In an actual application scene, a frequency spectrum monitoring and interference source positioning system adopts an available B/S framework, each group can be divided into a plurality of small monitoring stations, a mobile monitoring vehicle is communicated with a server through a network, the groups form a multi-task mode, each group can execute different tasks, a monitoring control system software platform supports a plurality of user operations, a later expansion user can be connected to the monitoring control system through a handheld terminal to issue a test item instruction, a certain group can be designated to carry out interference positioning tests or frequency spectrum monitoring tests, and the like, the user can also directly carry out instruction issuing through a browser login account number in an internal network, and fig. 5 describes a data flow diagram of the invention based on multi-user and multi-task mode actual application.
The above description is only a preferred embodiment of the present invention, and the scope of the present invention is not limited to the above embodiment, but equivalent modifications or changes made by those skilled in the art according to the present disclosure should be included in the scope of the present invention as set forth in the appended claims.
Claims (4)
1. A method for monitoring and identifying electromagnetic interference of an electric LTE wireless private network comprises the following two processes: the method comprises the following steps of spectrum monitoring and interference identification:
step 1, converting a non-voltage signal input from the outside into a voltage signal by using a sensor, and sending the voltage signal to a signal conditioning device for processing;
step 2, the signal conditioning equipment amplifies, attenuates and filters the input voltage signal, and finally sends the processed signal to a spectrum analyzer;
step 3, the spectrum analyzer carries out A/D conversion on the input signal processed in the step 2 to finish the acquisition of test data;
step 4, analyzing, calculating and processing the data collected in the step 3 to realize interference source identification, wherein the interference source identification process is as follows:
step 4-1, data preprocessing: denoising original test data by utilizing wavelet transformation, performing data normalization operation on the original test data, performing envelope and continuation processing on an emission characteristic curve, and mapping a high-dimensional vector to a low-dimensional space through dimension reduction operation;
step 4-2, feature extraction: extracting the characteristics of the acquired signals, including peak characteristics, envelope characteristics and harmonic characteristics, and performing frequency domain characteristic extraction on the periodic signals and the ringing signals by adopting Fourier transform; performing frequency domain feature extraction on the discrete signals by adopting fast Fourier transform; extracting the frequency spectrum characteristics of the pulse signals by adopting short-time Fourier transform; extracting frequency domain characteristics of the non-stationary signals by adopting wavelet transformation;
4-3, selecting characteristics; the feature selection comprises two contents, wherein the first is to select a statistical feature evaluation algorithm of a training sample to evaluate the features and calculate the contribution value of each feature to the classification effect; secondly, selecting partial attributes by using a principal component analysis algorithm, selecting different characteristics as identification objects aiming at different electromagnetic compatibility test objects, selecting subsets with strong distinguishing capability from a current vector attribute set, and removing redundant characteristics or invalid characteristics of interference classification effects to form a compact characteristic set;
step 4-4, learning and training; learning the relation between the acquired signal characteristics and the interference source by using a deep learning algorithm based on a convolutional neural network to obtain a classification model based on interference source identification;
the mathematical form of the convolution is as follows:
y＝f(∑x*wij+b)
wherein x is the convolutional layer input characteristic diagram; y is the convolutional layer output characteristic diagram; w is aijIs a two-dimensional convolution kernel; b is a bias term; f (-) is an activation function, such as a sigmoid function or tanh function or ReLU function;
the convolutional neural network uses a plurality of filters, a plurality of convolutional layers and a plurality of pooling layers, and finally, a full connection layer and a softmax layer are connected, and finally, probability distribution of corresponding input on each type of output is output;
the output of the whole network is
o＝f(n-1)(f(n-2)(...f(1)(x)))
Wherein x is the convolutional layer input characteristic diagram; f (-) is an activation function, such as a sigmoid function or tanh function or ReLU function;
forming a series of parameters corresponding to the mode classification method according to the corresponding relation between the sample set with known class attributes and the vector values thereof;
4-5, classifying and identifying; and (4) extracting characteristics of the test signals, classifying the interference sources of the test data set with unknown class attributes by adopting the classification model obtained in the step (4-4), if the class attributes in the test data set are known, the process can be used for verifying the classification effect of the classifier, and if the classification effect is ideal, the classification model can be applied to actual flow classification.
2. The method for monitoring and identifying the electromagnetic interference of the electric LTE wireless private network according to claim 1, wherein the method comprises the following steps: in step 1, the sensor comprises a current probe, a voltage probe, a near-field probe and a receiving antenna; when conducting transmission test is carried out, the frequency spectrograph is connected with the power supply impedance stabilizing network or the current probe; when a radiation emission test is carried out, the frequency spectrograph is connected with the receiving antenna; in the test of the coupling degree between the antennas, the vehicle-mounted antenna is connected to the receiver, and the coupling degree of the antenna is analyzed accordingly.
3. The method for monitoring and identifying the electromagnetic interference of the electric LTE wireless private network according to claim 1, wherein the method comprises the following steps: in step 2, the signal conditioning device comprises a signal amplifier, a linear impedance attenuator, a band-stop filter and a high-pass filter.
4. The method for monitoring and identifying the electromagnetic interference of the electric LTE wireless private network according to claim 1, wherein the method comprises the following steps: in step 3, the monitoring process of the spectrum analyzer on the data spectrum in step 2 is as follows: adopting a scanning heterodyne spectrum monitoring design in a high-frequency section, and changing an input signal to a lower intermediate frequency through multi-stage frequency conversion processing; and a Fourier spectrum monitoring design is adopted in the middle frequency band, A/D sampling quantification is carried out on signals from frequency conversion to intermediate frequency, the signals are converted into digital signals, and then the frequency spectrum analysis is completed by utilizing a digital intermediate frequency technology and Fourier transform.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010297105.3A CN111585671B (en) | 2020-04-15 | 2020-04-15 | Electric power LTE wireless private network electromagnetic interference monitoring and identifying method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010297105.3A CN111585671B (en) | 2020-04-15 | 2020-04-15 | Electric power LTE wireless private network electromagnetic interference monitoring and identifying method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111585671A true CN111585671A (en) | 2020-08-25 |
| CN111585671B CN111585671B (en) | 2022-06-10 |
Family
ID=72111536
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010297105.3A Expired - Fee Related CN111585671B (en) | 2020-04-15 | 2020-04-15 | Electric power LTE wireless private network electromagnetic interference monitoring and identifying method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111585671B (en) |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112165365A (en) * | 2020-09-29 | 2021-01-01 | 封开低频时码授时台 | Wireless spectrum interference monitoring system and method for low-frequency time code monitoring system |
| CN112365186A (en) * | 2020-11-27 | 2021-02-12 | 中国电建集团海外投资有限公司 | Health degree evaluation method and system for electric power information system |
| CN113114398A (en) * | 2021-04-14 | 2021-07-13 | 中南大学 | Communication interference existence detection method based on residual connection and dilation convolution |
| CN113569742A (en) * | 2021-07-29 | 2021-10-29 | 西南交通大学 | Broadband electromagnetic interference source identification method based on convolutional neural network |
| CN113868483A (en) * | 2021-12-02 | 2021-12-31 | 国网江苏省电力有限公司苏州供电分公司 | Wireless spectrum interference evidence obtaining analysis method based on alliance chain |
| CN114070679A (en) * | 2021-10-25 | 2022-02-18 | 中国电子科技集团公司第二十九研究所 | Frequency-phase characteristic analysis method for intelligent pulse classification |
| CN114325258A (en) * | 2021-12-03 | 2022-04-12 | 西南交通大学 | Transformer bushing insulation evaluation method considering multiple resonant frequencies |
| CN114839466A (en) * | 2022-05-24 | 2022-08-02 | 温岭市天泰电气有限公司 | EMC electromagnetic compatibility test system for water pump and test method thereof |
| CN115842597A (en) * | 2023-02-09 | 2023-03-24 | 成都华乾科技有限公司 | Black broadcast detection method and system based on multi-source data fusion |
| CN116056244A (en) * | 2023-03-07 | 2023-05-02 | 浙江万胜智能科技股份有限公司 | Public network wireless communication resource scheduling method and system based on remote module |
| CN116125172A (en) * | 2022-12-30 | 2023-05-16 | 北京长鹰恒容电磁科技有限公司 | Electromagnetic environment data acquisition and feature analysis method |
| CN117559673A (en) * | 2024-01-11 | 2024-02-13 | 希格玛电气(珠海)有限公司 | Wireless sensing system based on magnetic resonance energy supply and ring main unit |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102722759A (en) * | 2012-05-17 | 2012-10-10 | 河海大学 | Method for predicting power supply reliability of power grid based on BP neural network |
| CN103812577A (en) * | 2012-11-06 | 2014-05-21 | 西南交通大学 | Method for automatically identifying and learning abnormal radio signal type |
| CN106911603A (en) * | 2017-03-07 | 2017-06-30 | 北京工业大学 | A kind of broadband monitoring pattern Imitating signal modulation style real-time identification method |
| CN108135003A (en) * | 2017-12-25 | 2018-06-08 | 广东海格怡创科技有限公司 | The construction method and system of interference type identification model |
| CN108509911A (en) * | 2018-04-03 | 2018-09-07 | 电子科技大学 | Interference signal recognition methods based on convolutional neural networks |
| US20190158176A1 (en) * | 2016-01-18 | 2019-05-23 | Viavi Solutions, Inc. | Method and apparatus for the detection of distortion or corruption of cellular communication signals |
| CN110197127A (en) * | 2019-05-06 | 2019-09-03 | 安徽继远软件有限公司 | Wireless signal detection and electromagnetic interference categorizing system and method based on deep learning |
-
2020
- 2020-04-15 CN CN202010297105.3A patent/CN111585671B/en not_active Expired - Fee Related
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102722759A (en) * | 2012-05-17 | 2012-10-10 | 河海大学 | Method for predicting power supply reliability of power grid based on BP neural network |
| CN103812577A (en) * | 2012-11-06 | 2014-05-21 | 西南交通大学 | Method for automatically identifying and learning abnormal radio signal type |
| US20190158176A1 (en) * | 2016-01-18 | 2019-05-23 | Viavi Solutions, Inc. | Method and apparatus for the detection of distortion or corruption of cellular communication signals |
| CN106911603A (en) * | 2017-03-07 | 2017-06-30 | 北京工业大学 | A kind of broadband monitoring pattern Imitating signal modulation style real-time identification method |
| CN108135003A (en) * | 2017-12-25 | 2018-06-08 | 广东海格怡创科技有限公司 | The construction method and system of interference type identification model |
| CN108509911A (en) * | 2018-04-03 | 2018-09-07 | 电子科技大学 | Interference signal recognition methods based on convolutional neural networks |
| CN110197127A (en) * | 2019-05-06 | 2019-09-03 | 安徽继远软件有限公司 | Wireless signal detection and electromagnetic interference categorizing system and method based on deep learning |
Cited By (20)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112165365A (en) * | 2020-09-29 | 2021-01-01 | 封开低频时码授时台 | Wireless spectrum interference monitoring system and method for low-frequency time code monitoring system |
| CN112365186A (en) * | 2020-11-27 | 2021-02-12 | 中国电建集团海外投资有限公司 | Health degree evaluation method and system for electric power information system |
| CN113114398A (en) * | 2021-04-14 | 2021-07-13 | 中南大学 | Communication interference existence detection method based on residual connection and dilation convolution |
| CN113114398B (en) * | 2021-04-14 | 2022-01-28 | 中南大学 | Communication interference existence detection method based on residual connection and dilation convolution |
| CN113569742A (en) * | 2021-07-29 | 2021-10-29 | 西南交通大学 | Broadband electromagnetic interference source identification method based on convolutional neural network |
| CN114070679A (en) * | 2021-10-25 | 2022-02-18 | 中国电子科技集团公司第二十九研究所 | Frequency-phase characteristic analysis method for intelligent pulse classification |
| CN113868483A (en) * | 2021-12-02 | 2021-12-31 | 国网江苏省电力有限公司苏州供电分公司 | Wireless spectrum interference evidence obtaining analysis method based on alliance chain |
| CN113868483B (en) * | 2021-12-02 | 2022-03-25 | 国网江苏省电力有限公司苏州供电分公司 | Wireless spectrum interference evidence obtaining analysis method based on alliance chain |
| CN114325258A (en) * | 2021-12-03 | 2022-04-12 | 西南交通大学 | Transformer bushing insulation evaluation method considering multiple resonant frequencies |
| CN114325258B (en) * | 2021-12-03 | 2022-07-19 | 西南交通大学 | Transformer bushing insulation evaluation method considering multiple resonant frequencies |
| CN114839466A (en) * | 2022-05-24 | 2022-08-02 | 温岭市天泰电气有限公司 | EMC electromagnetic compatibility test system for water pump and test method thereof |
| CN114839466B (en) * | 2022-05-24 | 2023-02-28 | 温岭市天泰电气有限公司 | EMC electromagnetic compatibility test system for water pump and test method thereof |
| CN116125172A (en) * | 2022-12-30 | 2023-05-16 | 北京长鹰恒容电磁科技有限公司 | Electromagnetic environment data acquisition and feature analysis method |
| CN116125172B (en) * | 2022-12-30 | 2023-08-11 | 北京长鹰恒容电磁科技有限公司 | Electromagnetic environment data acquisition and feature analysis method |
| CN115842597A (en) * | 2023-02-09 | 2023-03-24 | 成都华乾科技有限公司 | Black broadcast detection method and system based on multi-source data fusion |
| CN115842597B (en) * | 2023-02-09 | 2023-05-02 | 成都华乾科技有限公司 | Black broadcast detection method and system based on multi-source data fusion |
| CN116056244A (en) * | 2023-03-07 | 2023-05-02 | 浙江万胜智能科技股份有限公司 | Public network wireless communication resource scheduling method and system based on remote module |
| CN116056244B (en) * | 2023-03-07 | 2023-08-25 | 浙江万胜智能科技股份有限公司 | Public network wireless communication resource scheduling method and system based on remote module |
| CN117559673A (en) * | 2024-01-11 | 2024-02-13 | 希格玛电气(珠海)有限公司 | Wireless sensing system based on magnetic resonance energy supply and ring main unit |
| CN117559673B (en) * | 2024-01-11 | 2024-03-26 | 希格玛电气(珠海)有限公司 | Wireless sensing system based on magnetic resonance energy supply and ring main unit |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111585671B (en) | 2022-06-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111585671B (en) | Electric power LTE wireless private network electromagnetic interference monitoring and identifying method | |
| CN111428561B (en) | Broadband electromagnetic interference source identification method and system, storage medium and equipment | |
| CN107729916B (en) | ISODATA-based interference source classification and identification algorithm | |
| CN102404058B (en) | Electromagnetic wave discrimination device, electromagnetic wave discrimination method, and electromagnetic wave discrimination program | |
| CN101334434A (en) | Electromagnetic environment test system for extracting electromagnetic leakage signal by utilizing wavelet transformation | |
| CN107085171B (en) | A kind of optimization placement method of the superfrequency phased array for substation's shelf depreciation direction finding | |
| Bao et al. | A histogram-based segmentation method for wideband spectrum sensing in cognitive radios | |
| CN105610525B (en) | A kind of broadband compression frequency spectrum sensing method based on sub-band match selection | |
| CN112287796B (en) | Radiation source identification method based on VMD-Teager energy operator | |
| CN113325277A (en) | Partial discharge processing method | |
| CN115618213A (en) | Charger voltage disturbance analysis method, system, equipment and storage medium | |
| CN112688746A (en) | Spectrum prediction method based on space-time data | |
| Huang et al. | FM broadcast monitoring using artificial intelligence | |
| CN110991378B (en) | Individual identification method and device for power amplifier | |
| Xu et al. | Individual radio transmitter identification based on spurious modulation characteristics of signal envelop | |
| CN117169664A (en) | Anti-interference system and method for partial discharge sensor | |
| CN113495193A (en) | Fault diagnosis method based on multi-wavelet transform and cluster analysis | |
| CN112488092B (en) | Navigation frequency band signal type identification method and system based on deep neural network | |
| CN111641934B (en) | Method for estimating electromagnetic signal situation distribution based on vehicle-mounted equipment monitoring data | |
| CN106405341A (en) | Method used for reducing partial discharge ultrahigh frequency signal | |
| Riley et al. | Modelling and measurement of man-made radio noise in the VHF-UHF bands | |
| Le Truong et al. | An Application of Deep Learning YOLOv5 Framework to Intelligent Radio Spectrum Monitoring | |
| US20240003946A1 (en) | Spectrum Analyzer, System and Method for Outputting Data from a Spectrum Analyzer | |
| CN109412718A (en) | Broader frequency spectrum signal detecting method | |
| CN113518049B (en) | Modulation identification method based on fractional low-order polar coordinates and deep learning |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20220610 |