CN116488750A - Electromagnetic interference influence analysis method and system based on neural network - Google Patents
Electromagnetic interference influence analysis method and system based on neural network Download PDFInfo
- Publication number
- CN116488750A CN116488750A CN202310471410.3A CN202310471410A CN116488750A CN 116488750 A CN116488750 A CN 116488750A CN 202310471410 A CN202310471410 A CN 202310471410A CN 116488750 A CN116488750 A CN 116488750A
- Authority
- CN
- China
- Prior art keywords
- frequency
- signal
- interference
- signals
- electromagnetic
- 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.)
- Pending
Links
- 238000004458 analytical method Methods 0.000 title claims abstract description 72
- 238000013528 artificial neural network Methods 0.000 title claims abstract description 41
- 238000004891 communication Methods 0.000 claims abstract description 17
- 238000000034 method Methods 0.000 claims abstract description 15
- 210000002569 neuron Anatomy 0.000 claims description 24
- 238000012806 monitoring device Methods 0.000 claims description 12
- 230000008569 process Effects 0.000 claims description 12
- 238000012545 processing Methods 0.000 claims description 11
- 238000001914 filtration Methods 0.000 claims description 7
- 238000012549 training Methods 0.000 claims description 7
- 230000004913 activation Effects 0.000 claims description 6
- 230000006978 adaptation Effects 0.000 claims description 4
- 230000007613 environmental effect Effects 0.000 claims description 4
- 238000003062 neural network model Methods 0.000 claims description 4
- 238000001228 spectrum Methods 0.000 abstract description 14
- 238000012544 monitoring process Methods 0.000 description 8
- 230000005540 biological transmission Effects 0.000 description 2
- 238000013480 data collection Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000000977 initiatory effect Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 206010035148 Plague Diseases 0.000 description 1
- 241000607479 Yersinia pestis Species 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000001276 controlling effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000008520 organization Effects 0.000 description 1
- 230000001105 regulatory effect Effects 0.000 description 1
- 230000000630 rising effect Effects 0.000 description 1
Classifications
-
- 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
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/10—Pre-processing; Data cleansing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/048—Activation functions
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04B—TRANSMISSION
- H04B17/00—Monitoring; Testing
- H04B17/30—Monitoring; Testing of propagation channels
- H04B17/309—Measuring or estimating channel quality parameters
- H04B17/345—Interference values
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/06—Management of faults, events, alarms or notifications
- H04L41/0631—Management of faults, events, alarms or notifications using root cause analysis; using analysis of correlation between notifications, alarms or events based on decision criteria, e.g. hierarchy, tree or time analysis
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/08—Configuration management of networks or network elements
- H04L41/0894—Policy-based network configuration management
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/14—Network analysis or design
- H04L41/145—Network analysis or design involving simulating, designing, planning or modelling of a network
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/16—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks using machine learning or artificial intelligence
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/02—Preprocessing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/02—Preprocessing
- G06F2218/04—Denoising
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/12—Classification; Matching
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D30/00—Reducing energy consumption in communication networks
- Y02D30/70—Reducing energy consumption in communication networks in wireless communication networks
Abstract
The invention discloses an electromagnetic interference influence analysis method and system based on a neural network, wherein the system comprises a device management module, a strategy setting module, an interference analysis module and a result display module; the method comprises the following steps: 1) Acquiring a current signal and an environment electromagnetic signal of the frequency-using device; 2) Identifying a current signal of the frequency-consuming device; 3) Acquiring a valid signal; 4) Recording as an interference signal; 5) Obtaining a standby signal; 6) Recording the available signal; 7) And obtaining and outputting the recommended frequency. According to the invention, the model based on the neural network is used for replacing artificial analysis and judgment, so that the problem cause can be rapidly and effectively analyzed, effective solving measures and suggestions are provided, the communication working efficiency can be improved, and the utilization rate of the frequency spectrum can be greatly improved.
Description
Technical Field
The invention relates to the technical field of algorithm model training, in particular to an electromagnetic interference influence analysis method and system based on a neural network.
Background
Electromagnetic interference refers to that the working electronic equipment is interfered by electromagnetic signals sent by other surrounding working electronic equipment, so that the working electronic equipment cannot normally communicate. Frequency modulation is one way to avoid interference, which from the beginning plagues the radio. Regulatory bodies have long been managing spectrum so that different radio users in an emerging wireless ecosystem can be assigned different dedicated frequencies. While this avoids the problems of detecting transmission conditions and changing frequencies in use, the spectrum utilization is very low because part of the spectrum is idle. Today, the demand for limited radio spectrum resources is rising. Over the past few years, wireless data transmission has grown at a rate of about 50% per year, mainly because people are increasingly watching video and browsing social media on smartphones.
To meet this requirement, we have to allocate spectrum as efficiently as possible, which means that wireless technology cannot have an exclusive frequency and the available spectrum has to be shared. If the problem cause can be rapidly and effectively analyzed when the frequency interference or other problems occur through the artificial intelligent model algorithm, effective solving measures and suggestions are provided, so that the communication working efficiency can be improved, and the utilization rate of the frequency spectrum can be greatly improved.
Disclosure of Invention
Aiming at the defects of the prior art, the invention aims to provide the electromagnetic interference influence analysis method and system based on the neural network, which can analyze the problem of frequency interference, can rapidly and effectively analyze the cause of the problem by replacing artificial analysis and judgment by a model based on the neural network, and provide effective solving measures and suggestions, thereby not only improving the communication working efficiency, but also greatly improving the utilization rate and the utilization rate of frequency spectrum.
In order to solve the technical problems, the technical scheme adopted by the invention is as follows: an electromagnetic interference influence analysis method based on a neural network is characterized by comprising the following steps of: the method comprises the following steps:
1) Acquiring a current signal and an environment electromagnetic signal of the frequency-using device;
2) Identifying the current signal of the frequency-using equipment in the acquired environmental electromagnetic signal, and marking the current signal as f0;
3) Calculating to obtain a noise threshold according to the intensity of the current signal of the frequency-using equipment and the noise proportional coefficient, comparing the intensity of the electromagnetic signal in the collected environment with the noise threshold to obtain an electromagnetic signal with the intensity larger than the noise threshold, and marking the electromagnetic signal except f0 as effective signals f 1-fn; and then performing steps 4) and/or 5);
4) Analyzing whether the frequency of the effective signal obtained in the step 3) causes interference to the frequency of the frequency using equipment by using an interference signal judgment model; if not, repeating the step; if yes, recording an effective signal which causes interference to the current signal of the frequency-using equipment as an interference signal, extracting a plurality of interference signals with the highest possibility, and outputting the frequency of the interference signals as an interference signal frequency fx which is suggested to be adjusted;
5) Analyzing and processing the effective signal obtained in the step 3) by utilizing an interference analysis model based on a neural network to obtain a standby signal f 0';
6) Inputting the frequency of the standby signal obtained in the step 5) into an interference signal judgment model, judging whether each effective signal obtained in the step 3) causes interference to the standby signal, and returning to the step 5) if yes; if not, recording the standby signal as a usable signal;
7) Comparing the available signal obtained in the step 6) with the set frequency using plan and frequency using rule, judging whether the available signal is in the frequency using plan and meets the frequency using rule, if so, recording the frequency of the signal as the recommended frequency using frequency, and outputting the frequency; otherwise, repeating steps 5), 6), 7).
Further, the interference signal judgment model is as follows:
calculating the frequency of the current signal f0 of the frequency using device and the frequencies of the effective signals f 1-fn by using an m-order harmonic, a second-order intermodulation formula, a third-order intermodulation formula, a fourth-order intermodulation formula and a fifth-order intermodulation formula, wherein:
the m-th harmonic formula: f0 = mfn;
second order intermodulation formula: f0 =f1±f2;
third-order intermodulation formula: f0 =2f1±f2; f0 =f1±2f2; f0 =f1±f2±f3;
fourth order intermodulation formula: f0 =3f1±f2; f0 =f1±3f2; f0 =2f1±2f2;
five-order intermodulation equation: f0 =4f1±f2; f0 =f1±4f2; f0 =3f1±2f2; f0 =2f1±3f2;
wherein: the frequency of the current signal f0 of the frequency-using equipment is f0, and the frequencies of the effective signals f 1-fn are corresponding to f 1-fn;
when any interference judging formula is established, the interference to the frequency of the current signal f0 of the frequency-using equipment is caused, the frequencies involved in the interference judging formula are all interference frequencies, and the signal corresponding to the frequencies is recorded as an interference signal;
the steps are repeated until the effective signals f 1-fn are all called for a plurality of times, and a plurality of interference signals are obtained.
Further, among the plurality of interference signals, a plurality of interference signals having the highest signal strength and highest frequency are recorded as the interference signal having the highest probability.
Further, in step 5), the process of obtaining the standby signal by using the interference analysis model based on the neural network is as follows:
s 1) randomly extracting k effective signals from the effective signals obtained in the step 3);
s 2) inputting the frequencies of the extracted k effective signals into a trained neural network-based interference analysis model to obtain a frequency which is not interfered by the group of effective signals, and recording the frequency as the frequency of a standby signal f 0'.
Further, in step 6), when step 5) is repeated, k effective signals are randomly extracted again from the remaining signals.
Further, in step 7), repeating steps 5), 6) and 7) until all the effective signals are analyzed to obtain a plurality of available signals which are located in the frequency using plan and meet the frequency using rule, then performing noise analysis on the available signals which are located in the frequency using plan and meet the frequency using rule to obtain the available signal with the lowest noise, and outputting the frequency of the signal as the recommended frequency using frequency.
Further, the interference analysis model is a neural network model comprising three layers of neural networks, wherein: the first layer is an input layer with k neurons, the second layer is an intermediate layer with p neurons, and the third layer is an input layer or an output layer with 1 neuron;
the activation function activation between network layers adopts a linear rectification function relu, and finally, the cross entropy of an output tensor and a target tensor is calculated to be used as the loss of a model, and rmsprop is used as an optimizer of the model;
in the training process, after k training frequency data are input to the neurons of the first layer, simultaneously inputting an undisturbed frequency to the neurons of the third layer so as to train the neurons of the second layer;
in the working process, after the frequencies of k effective signals are input to the neurons of the first layer, the second layer is processed according to the trained operation model, and the third layer outputs a new frequency which is not interfered by the input k effective signals, namely the frequency of the standby signal.
An electromagnetic interference influence analysis system based on the analysis method is characterized in that: the system comprises a device management module, a strategy setting module, an interference analysis module and a result display module;
the device management module is used for being connected with the frequency-using device and the electromagnetic environment monitoring device to acquire electromagnetic signals in the frequency-using device and the environment, carrying out data acquisition and control on the connected device, and then transmitting the acquired data to the interference analysis module;
the strategy setting module is used for setting a frequency using plan and a frequency using rule;
the interference analysis module comprises a noise filtering module, an interference signal judging model and an interference analysis model based on a neural network; the electromagnetic signals transmitted by the equipment management module are filtered by the noise filtering module to obtain effective signals, and then the interference signal judgment model is used for judging whether the frequencies of the effective signals cause interference to the frequencies of the frequency-using equipment; if yes, one path of effective signals causing interference are recorded as interference signals, then a plurality of interference signals with the highest possibility are extracted, recorded as interference signal frequency recommended to be adjusted, and output; the other path of the frequency of the effective signal is input into an interference analysis model based on a neural network to obtain the frequency of the standby signal, the frequency of the effective signal and the frequency of the standby signal are input into an interference signal judgment model to judge whether the standby signal is interfered by the effective signal, and if the standby signal is not interfered, the standby signal is recorded as an available signal; comparing the frequency of the available signal with a frequency plan and a frequency rule, if the condition is met, recording the available signal as a suggested frequency and outputting the suggested frequency;
the result display module is used for displaying the data collected by the interference analysis module through the equipment management module, the set frequency using plan, the frequency using rule, the suggested frequency using frequency and the suggested adjusted interference signal frequency.
Further, the device management module is in communication connection with the frequency-using device and the electromagnetic environment monitoring device through the Internet of things, and comprises a device information management module, a device communication protocol adaptation module, a data acquisition module, a data processing module and an information interface module.
Further, the electromagnetic environment monitoring device comprises a frequency monitoring device.
Compared with the prior art, the invention has the following advantages:
1. according to the scheme, the problem of frequency interference is automatically analyzed, and reasonable frequency suggestions are given, so that the problem of field communication can be rapidly checked and solved, and the cause of the problem can be rapidly and effectively analyzed; meanwhile, artificial intelligence can be used for replacing artificial analysis and judgment, effective solving measures and suggestions are provided, the communication work efficiency can be improved, the utilization rate and the utilization rate of frequency spectrum can be greatly improved, meanwhile, the technical requirements on the frequency-using professional technology of people can be reduced, and the business can be rapidly developed on the frequency-using work of communication in various industries.
2. The frequency of the interference signal can be analyzed, so that a supervision and management organization can monitor whether the frequency is illegal or not according to the frequency spectrum plan designed at the beginning, and meanwhile, the frequency plan can be quickly adjusted by continuously analyzing the feedback result, so that different radio users in the emerging wireless ecological system can be distributed to different special frequencies.
3. Meanwhile, the problem that part of the frequency spectrum is idle and the frequency spectrum utilization rate is low is solved; the analysis of the frequency interference problem by the neural network analysis algorithm tool can effectively and dynamically adjust the use of limited radio frequency spectrum resources, and continuously correct and adjust the algorithm according to the actual problem solving result, so that the analysis result is more and more accurate, and the sustainable optimization is realized.
Drawings
FIG. 1 is a flow chart of the present invention.
FIG. 2 is an analysis flow chart of a neural network-based disturbance analysis model.
Fig. 3 is a functional block diagram of an interference analysis model.
Fig. 4 is a flowchart of the operation of performing interference judgment on the current signal of the frequency-using device by using the interference judgment model.
Fig. 5 is a flowchart of the operation of performing interference judgment on a standby signal by using an interference judgment model.
Detailed Description
The invention will be further described with reference to the drawings and examples.
Example 1: referring to fig. 1-5, an electromagnetic interference influence analysis method based on a neural network includes the following steps:
1) The current signal of the frequency-taking device and the ambient electromagnetic signal (electromagnetic signal present in the environment) are obtained.
2) Identifying the current signal of the frequency-using equipment in the acquired environmental electromagnetic signal, and marking the current signal as f0; because the signals of the frequency-using equipment are also in the environment, the signals of the frequency-using equipment in the collected environment electromagnetic signals need to be screened out, and the influence on subsequent processing is avoided.
3) Calculating to obtain a noise threshold according to the intensity of the current signal of the frequency using equipment and a noise proportion coefficient, wherein the noise proportion coefficient is a critical signal-to-noise ratio which does not affect the frequency using state and is usually 0.4-0.5; then comparing the intensity of the electromagnetic signals in the collected environment with a noise threshold value to obtain electromagnetic signals with the intensity larger than the noise threshold value, and marking the electromagnetic signals except f0 as effective signals f 1-fn; and then performing steps 4) and/or 5).
4) Analyzing whether the frequency of the effective signal obtained in the step 3) causes interference to the frequency of the frequency using equipment by using an interference signal judgment model; if not, repeating the step; if yes, recording an effective signal which causes interference to the current signal of the frequency-using equipment as an interference signal, extracting a plurality of interference signals with the highest possibility, and outputting the frequency of the interference signals as an interference signal frequency fx which is suggested to be adjusted. In practical application, after the interference signals with the highest possibility are obtained, the frequencies of the interference signals can be adjusted to ensure that the frequencies of the frequency-using equipment are not interfered any more, so that the normal operation of the frequency-using equipment is ensured.
The interference signal judgment model is as follows:
calculating the frequency of the current signal f0 and the frequencies of the effective signals f 1-fn of the frequency using equipment by using an m-order harmonic wave, a second-order intermodulation formula, a third-order intermodulation formula, a fourth-order intermodulation formula, a fifth-order intermodulation formula or other electromagnetic interference type calculation formulas, wherein:
the m-th harmonic formula: f0 = mfn;
second order intermodulation formula: f0 =f1±f2;
third-order intermodulation formula: f0 =2f1±f2; f0 =f1±2f2; f0 =f1±f2±f3;
fourth order intermodulation formula: f0 =3f1±f2; f0 =f1±3f2; f0 =2f1±2f2;
five-order intermodulation equation: f0 =4f1±f2; f0 =f1±4f2; f0 =3f1±2f2; f0 =2f1±3f2;
wherein: the frequency of the current signal f0 of the frequency-using equipment is f0, and the frequencies of the effective signals f 1-fn are corresponding to f 1-fn;
when any interference judging formula is established, the interference is caused to the frequency of the current signal f0 of the frequency using device, the frequencies involved in the interference judging formula are all interference frequencies, and the signal corresponding to the frequencies is recorded as an interference signal.
The steps are repeated until the effective signals f 1-fn are all called for a plurality of times, and a plurality of interference signals are obtained.
And carrying out mathematical statistics on the interference signals, and recording a plurality of interference signals with the maximum signal intensity and the highest frequency as the interference signal with the highest possibility.
5) And 3) analyzing and processing the effective signal obtained in the step 3) by using the trained interference analysis model based on the neural network to obtain a standby signal f 0'.
The process for acquiring the standby signal by using the interference analysis model based on the neural network comprises the following steps:
the process of obtaining the standby signal by using the interference analysis model based on the neural network comprises the following steps:
s 1) randomly extracting k effective signals from the effective signals obtained in the step 3);
s 2) inputting the frequencies of the extracted k effective signals into a trained neural network-based interference analysis model to obtain a frequency which is not interfered by the group of effective signals, and recording the frequency as the frequency of a standby signal f 0'.
Specifically, the interference analysis model is a neural network model, is built based on an artificial neural network library keras, and comprises three layers of neural networks, wherein: the first layer is an input layer with k neurons, the second layer is an intermediate layer with p neurons, and the third layer is an input layer or an output layer with 1 neuron.
The activation function activation between network layers adopts a linear rectification function relu, and finally, the cross entropy of the output tensor and the target tensor is calculated to be used as the loss of a model, and rmsprop is used as an optimizer of the model.
In the training process, k training frequency data are input to the neurons of the first layer, and then an undisturbed frequency is input to the neurons of the third layer at the same time, so that the neurons of the second layer are trained, namely, the p neurons of the second layer in the trained neural network are known.
In the working process, after the frequencies of k effective signals are input to the neurons of the first layer, the second layer is processed according to the trained operation model, and the third layer outputs a new frequency which is not interfered by the input k effective signals, namely the frequency of the standby signal.
As one implementation, in the present example, the first layer of the neural network model has 10 neurons, and the second layer has 64 neurons; i.e. take k=10, p=64; in step 5, the number of effective signals extracted randomly is also 10.
6) Inputting the frequency of the standby signal obtained in the step 5) into an interference signal judging model, judging whether each effective signal obtained in the step 3) causes interference on the standby signal, if so, returning to the step 5), and randomly extracting k effective signals from the rest signals again when the step 5) is repeated, namely, the extracted signals are not repeated each time. If not, the standby signal f 0' is recorded as a usable signal.
7) Comparing the available signal obtained in the step 6) with the set frequency using plan and frequency using rule, judging whether the available signal is in the frequency using plan and meets the frequency using rule, if so, recording the frequency of the signal as the recommended frequency using frequency, and outputting the frequency; otherwise, repeating steps 5), 6), 7).
By adopting the scheme, the environmental electromagnetic signals can be rapidly analyzed, and the recommended frequency of the frequency-using equipment is given in the shortest time, so that the analysis and processing efficiency can be effectively improved.
Example 2, unlike example 1,
5) Analyzing and processing the effective signal obtained in the step 3) by using a trained interference analysis model based on a neural network to obtain a standby signal f 0'; specifically:
s 1) randomly extracting k effective signals from the effective signals obtained in the step 3);
s 2) inputting the frequency of the extracted n effective signals into a trained neural network-based interference analysis model to obtain a frequency which is not interfered by the group of effective signals, and recording the frequency as the frequency of a standby signal f 0'.
6) Inputting the frequency of the standby signal obtained in the step 5) into an interference signal judging model, judging whether each effective signal obtained in the step 3) causes interference on the standby signal, if so, returning to the step 5), and randomly extracting k effective signals from the rest signals again when the step 5) is repeated, namely, the extracted signals are not repeated each time. If not, the standby signal f 0' is recorded as a usable signal.
7) Comparing the available signal obtained in the step 6) with the set frequency using plan and the frequency using rule, judging whether the available signal is in the frequency using plan and meets the frequency using rule, if so, recording the available signal; otherwise, repeating the steps 5), 6) and 7) until all the effective signals are analyzed to obtain a plurality of available signals which are positioned in the frequency using plan and meet the frequency using rule, then carrying out noise analysis on the available signals which are positioned in the frequency using plan and meet the frequency using rule to obtain the available signal with the lowest noise, and taking the frequency of the available signal as the recommended frequency and outputting the frequency.
By adopting the scheme, the environment electromagnetic signals can be fully (completely) analyzed, and the recommended frequency with the minimum possibility of interference is given, so that the working stability of the frequency equipment can be effectively improved.
The invention also discloses an electromagnetic interference influence analysis system based on the analysis method, which comprises a device management module, a strategy setting module, an interference analysis module and a result display module.
The equipment management module is used for being connected with the frequency-using equipment and the electromagnetic environment monitoring equipment to collect signals of the frequency-using equipment and electromagnetic signals in the environment, and carrying out data collection and control (controlling collection signals) on the connected equipment, and then transmitting the collected data to the interference analysis module. In practice, the electromagnetic environment monitoring device comprises a frequency monitoring device. As optimization, the device management module also collects data information of the frequency-using device and the detection device, specifically, the device management module is in communication connection with the frequency-using device and the electromagnetic environment monitoring device through the internet of things, and the device management module comprises a device information management module, a device communication protocol adaptation module, a data collection module, a data processing module and an information interface module. After the device management module establishes connection with the devices (the frequency-using device and the monitoring device), the device information management module configures basic information of the devices, wherein the basic information comprises the device type, the device name, the device acquisition parameters, the device IP, the device port and the device protocol. After the information of the monitoring equipment (fixed monitoring station or mobile monitoring machine, etc.) is configured in the equipment information management module, the monitoring equipment is accessed into the same network as the system through the Ethernet, so that the system can automatically identify the monitoring equipment. The device communication protocol adaptation module is driven by the loading device, so that the device communication protocol can be adapted, and the communication format, the communication content and the like of the device can be identified from the communication packet sent by the device to the system. The data acquisition module is used for initiating a data acquisition instruction to the monitoring equipment after the system identifies the equipment and can normally communicate with the equipment, and feeding back the acquired data to the data acquisition module according to the instruction requirement after the monitoring equipment receives the instruction. The data processing module internally processes the acquired original data into data meeting the analysis requirement of the system application, namely, the data is converted into data which can be identified and processed by the intelligent analysis module. The information interface module is responsible for receiving instructions needing to be subjected to data acquisition from other modules, initiating a request to the data acquisition module according to the instructions, and carrying out data acquisition by the data acquisition module; and then, the data processed by the data processing module is transmitted to the intelligent analysis module through an API interface of the system internal standard.
The strategy setting module is used for setting a frequency using plan and a frequency using rule.
The interference analysis module comprises a noise filtering module, an interference signal judging model and an interference analysis model based on a neural network.
The electromagnetic signals transmitted by the equipment management module are filtered by the noise filtering module to obtain effective signals, the noise filtering module calculates a noise threshold according to the intensity of the signals of the frequency-using equipment and the noise proportion coefficient, and then the signals with the intensity lower than the threshold are filtered to obtain the effective signals. When implemented, the process may be implemented by a filter or oscilloscope, or the like.
Then, judging whether the frequency of the effective signal causes interference to the frequency of the frequency-using equipment or not through an interference signal judging model; if yes, then:
and recording the effective signal causing interference as an interference signal, extracting a plurality of interference signals with the highest possibility, recording the interference signals as recommended interference signal frequencies, and outputting the recommended interference signals.
The other path of the frequency of the effective signal is input into an interference analysis model based on a neural network to obtain the frequency of the standby signal, the frequency of the effective signal and the frequency of the standby signal are input into an interference signal judgment model to judge whether the standby signal is interfered by the effective signal, and if the standby signal is not interfered, the standby signal is recorded as an available signal; and comparing the frequency of the available signal with the frequency using plan and the frequency using rule, and if the condition is met, recording the available signal as the suggested frequency using frequency and outputting.
The result display module is used for displaying the data collected by the interference analysis module through the equipment management module, the set frequency using plan, the frequency using rule, the suggested frequency using frequency and the suggested adjusted interference signal frequency.
Finally, it should be noted that the above embodiments are only for illustrating the technical solution of the present invention and not for limiting the technical solution, and those skilled in the art should understand that modifications and equivalents may be made to the technical solution of the present invention without departing from the spirit and scope of the present invention, and all such modifications and equivalents are included in the scope of the claims.
Claims (10)
1. An electromagnetic interference influence analysis method based on a neural network is characterized by comprising the following steps of: the method comprises the following steps:
1) Acquiring a current signal and an environment electromagnetic signal of the frequency-using device;
2) Identifying the current signal of the frequency-using equipment in the acquired environmental electromagnetic signal, and marking the current signal as f0;
3) Calculating to obtain a noise threshold according to the intensity of the current signal of the frequency-using equipment and the noise proportional coefficient, comparing the intensity of the electromagnetic signal in the collected environment with the noise threshold to obtain an electromagnetic signal with the intensity larger than the noise threshold, and marking the electromagnetic signal except f0 as effective signals f 1-fn; and then performing steps 4) and/or 5);
4) Analyzing whether the frequency of the effective signal obtained in the step 3) causes interference to the frequency of the frequency using equipment by using an interference signal judgment model; if not, repeating the step; if yes, recording an effective signal which causes interference to the current signal of the frequency-using equipment as an interference signal, extracting a plurality of interference signals with the highest possibility, and outputting the frequency of the interference signals as an interference signal frequency fx which is suggested to be adjusted;
5) Analyzing and processing the effective signal obtained in the step 3) by utilizing an interference analysis model based on a neural network to obtain a standby signal f 0';
6) Inputting the frequency of the standby signal obtained in the step 5) into an interference signal judgment model, judging whether each effective signal obtained in the step 3) causes interference to the standby signal, and returning to the step 5) if yes; if not, recording the standby signal as a usable signal;
7) Comparing the available signal obtained in the step 6) with the set frequency using plan and frequency using rule, judging whether the available signal is in the frequency using plan and meets the frequency using rule, if so, recording the frequency of the signal as the recommended frequency using frequency, and outputting the frequency; otherwise, repeating steps 5), 6), 7).
2. The neural network-based electromagnetic interference impact analysis method according to claim 1, wherein: the interference signal judgment model is as follows:
calculating the frequency of the current signal f0 of the frequency using device and the frequencies of the effective signals f 1-fn by using an m-order harmonic, a second-order intermodulation formula, a third-order intermodulation formula, a fourth-order intermodulation formula and a fifth-order intermodulation formula, wherein:
the m-th harmonic formula: f0 = mfn;
second order intermodulation formula: f0 =f1±f2;
third-order intermodulation formula: f0 =2f1±f2; f0 =f1±2f2; f0 =f1±f2±f3;
fourth order intermodulation formula: f0 =3f1±f2; f0 =f1±3f2; f0 =2f1±2f2;
five-order intermodulation equation: f0 =4f1±f2; f0 =f1±4f2; f0 =3f1±2f2; f0 =2f1±3f2;
wherein: the frequency of the current signal f0 of the frequency-using equipment is f0, and the frequencies of the effective signals f 1-fn are corresponding to f 1-fn;
when any interference judging formula is established, the interference to the frequency of the current signal f0 of the frequency-using equipment is caused, the frequencies involved in the interference judging formula are all interference frequencies, and the signal corresponding to the frequencies is recorded as an interference signal;
the steps are repeated until the effective signals f 1-fn are all called for a plurality of times, and a plurality of interference signals are obtained.
3. The neural network-based electromagnetic interference impact analysis method according to claim 2, wherein: and recording a plurality of interference signals with the highest signal intensity and highest frequency as the interference signal with the highest possibility.
4. The electromagnetic interference influence analysis method based on the neural network according to claim 1 or 2, characterized in that: in step 5), the process of acquiring the standby signal by using the interference analysis model based on the neural network is as follows:
s 1) randomly extracting k effective signals from the effective signals obtained in the step 3);
s 2) inputting the frequencies of the extracted k effective signals into a trained neural network-based interference analysis model to obtain a frequency which is not interfered by the group of effective signals, and recording the frequency as the frequency of a standby signal f 0'.
5. The neural network-based electromagnetic interference impact analysis method of claim 4, wherein: in step 6), when step 5) is repeated, k effective signals are randomly extracted again from the remaining signals.
6. The neural network-based electromagnetic interference impact analysis method of claim 5, wherein: in step 7), repeating the steps 5), 6) and 7) until all the effective signals are analyzed to obtain a plurality of available signals which are positioned in the frequency using plan and meet the frequency using rule, then carrying out noise analysis on the available signals which are positioned in the frequency using plan and meet the frequency using rule to obtain the available signal with the lowest noise, and outputting the frequency of the signal as the recommended frequency using frequency.
7. The neural network-based electromagnetic interference impact analysis method of claim 4, wherein: the interference analysis model is a neural network model comprising three layers of neural networks, wherein: the first layer is an input layer with k neurons, the second layer is an intermediate layer with p neurons, and the third layer is an input layer or an output layer with 1 neuron;
the activation function activation between network layers adopts a linear rectification function relu, and finally, the cross entropy of an output tensor and a target tensor is calculated to be used as the loss of a model, and rmsprop is used as an optimizer of the model;
in the training process, after k training frequency data are input to the neurons of the first layer, simultaneously inputting an undisturbed frequency to the neurons of the third layer so as to train the neurons of the second layer;
in the working process, after the frequencies of k effective signals are input to the neurons of the first layer, the second layer is processed according to the trained operation model, and the third layer outputs a new frequency which is not interfered by the input k effective signals, namely the frequency of the standby signal.
8. An electromagnetic interference influence analysis system based on the analysis method according to any one of claims 1 to 7, characterized in that: the system comprises a device management module, a strategy setting module, an interference analysis module and a result display module;
the device management module is used for being connected with the frequency-using device and the electromagnetic environment monitoring device to acquire electromagnetic signals in the frequency-using device and the environment, carrying out data acquisition and control on the connected device, and then transmitting the acquired data to the interference analysis module;
the strategy setting module is used for setting a frequency using plan and a frequency using rule;
the interference analysis module comprises a noise filtering module, an interference signal judging model and an interference analysis model based on a neural network; the electromagnetic signals transmitted by the equipment management module are filtered by the noise filtering module to obtain effective signals, and then the interference signal judgment model is used for judging whether the frequencies of the effective signals cause interference to the frequencies of the frequency-using equipment; if yes, one path of effective signals causing interference are recorded as interference signals, then a plurality of interference signals with the highest possibility are extracted, recorded as interference signal frequency recommended to be adjusted, and output; the other path of the frequency of the effective signal is input into an interference analysis model based on a neural network to obtain the frequency of the standby signal, the frequency of the effective signal and the frequency of the standby signal are input into an interference signal judgment model to judge whether the standby signal is interfered by the effective signal, and if the standby signal is not interfered, the standby signal is recorded as an available signal; comparing the frequency of the available signal with a frequency plan and a frequency rule, if the condition is met, recording the available signal as a suggested frequency and outputting the suggested frequency;
the result display module is used for displaying the data collected by the interference analysis module through the equipment management module, the set frequency using plan, the frequency using rule, the suggested frequency using frequency and the suggested adjusted interference signal frequency.
9. The electromagnetic interference impact analysis system of claim 8, wherein: the device management module is in communication connection with the frequency-using device and the electromagnetic environment monitoring device through the Internet of things, and comprises a device information management module, a device communication protocol adaptation module, a data acquisition module, a data processing module and an information interface module.
10. The electromagnetic interference impact analysis system of claim 8, wherein: the electromagnetic environment monitoring device includes a frequency monitoring device.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310471410.3A CN116488750A (en) | 2023-04-27 | 2023-04-27 | Electromagnetic interference influence analysis method and system based on neural network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310471410.3A CN116488750A (en) | 2023-04-27 | 2023-04-27 | Electromagnetic interference influence analysis method and system based on neural network |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116488750A true CN116488750A (en) | 2023-07-25 |
Family
ID=87213592
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310471410.3A Pending CN116488750A (en) | 2023-04-27 | 2023-04-27 | Electromagnetic interference influence analysis method and system based on neural network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116488750A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117353833A (en) * | 2023-09-22 | 2024-01-05 | 恩平市天行电子科技有限公司 | Wireless signal receiving method and related device based on interference detection |
| CN117806914A (en) * | 2024-02-29 | 2024-04-02 | 潍坊鼎好信息科技有限公司 | Computer fault monitoring and alarming system |
-
2023
- 2023-04-27 CN CN202310471410.3A patent/CN116488750A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117353833A (en) * | 2023-09-22 | 2024-01-05 | 恩平市天行电子科技有限公司 | Wireless signal receiving method and related device based on interference detection |
| CN117806914A (en) * | 2024-02-29 | 2024-04-02 | 潍坊鼎好信息科技有限公司 | Computer fault monitoring and alarming system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116488750A (en) | Electromagnetic interference influence analysis method and system based on neural network | |
| CN104396188B (en) | System and method for carrying out basic reason analysis to mobile network property problem | |
| CN101605067B (en) | Network behaviour active analyzing and diagnosing method | |
| CN114630352B (en) | Fault monitoring method and device for access equipment | |
| CN107786994B (en) | User perception quality difference analysis method and system for end-to-end wireless service | |
| US20200134421A1 (en) | Assurance of policy based alerting | |
| CN110460454B (en) | Intelligent network equipment port fault prediction method based on deep learning | |
| CN106686264A (en) | Method and system for fraud call screening and analyzing | |
| CN110891283A (en) | Small base station monitoring device and method based on edge calculation model | |
| CN103490849A (en) | Method and device for analyzing signaling traffic | |
| Krishnaswamy et al. | Data-driven learning to predict wan network traffic | |
| CN111124852A (en) | Fault prediction method and system based on BMC health management module | |
| CN114189310A (en) | Unmanned aerial vehicle measurement and control signal accurate interference method based on signal reconnaissance and prediction | |
| CN116800586A (en) | Method for diagnosing data communication faults of telecommunication network | |
| CN116032692A (en) | Intelligent Internet of things gateway and Internet of things system based on same | |
| CN116723136B (en) | Network data detection method applying FCM clustering algorithm | |
| CN111090585B (en) | Crowd-sourcing task closing time automatic prediction method based on crowd-sourcing process | |
| CN117440018A (en) | Network camera equipment fortune pipe platform based on thing networking | |
| CN113204332B (en) | Intelligent household equipment control program generation system and method | |
| CN105099745B (en) | A kind of tracking and device of operation flow | |
| US11540234B2 (en) | Automated narrow peak interference severity estimation | |
| WO2022019728A1 (en) | Method and system for dynamic threshold detection for key performance indicators in communication networks | |
| DE602004002477D1 (en) | TEST SYSTEM AND METHOD FOR A MOBILE RADIO NETWORK | |
| CN117033922A (en) | Electromagnetic environment influence analysis method and system based on artificial intelligence | |
| CN113677027A (en) | Method and system for predicting future transmission of node based on machine 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 |