CN116184088A - Electromagnetic spectrum characteristic-based electromagnetic radiation emission system fault detection method - Google Patents
Electromagnetic spectrum characteristic-based electromagnetic radiation emission system fault detection method Download PDFInfo
- Publication number
- CN116184088A CN116184088A CN202310204992.9A CN202310204992A CN116184088A CN 116184088 A CN116184088 A CN 116184088A CN 202310204992 A CN202310204992 A CN 202310204992A CN 116184088 A CN116184088 A CN 116184088A
- Authority
- CN
- China
- Prior art keywords
- electromagnetic
- fault
- fre
- spectrum
- emission
- 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
- 230000005670 electromagnetic radiation Effects 0.000 title claims abstract description 55
- 238000001228 spectrum Methods 0.000 title claims abstract description 31
- 238000001514 detection method Methods 0.000 title claims abstract description 25
- 238000012360 testing method Methods 0.000 claims abstract description 90
- 238000000295 emission spectrum Methods 0.000 claims abstract description 62
- 230000005855 radiation Effects 0.000 claims abstract description 46
- 230000007613 environmental effect Effects 0.000 claims abstract description 18
- 238000012549 training Methods 0.000 claims abstract description 10
- 238000000034 method Methods 0.000 claims description 13
- 238000013473 artificial intelligence Methods 0.000 claims description 6
- 238000013528 artificial neural network Methods 0.000 claims description 5
- 238000007906 compression Methods 0.000 claims description 3
- 238000010801 machine learning Methods 0.000 claims description 3
- 238000012216 screening Methods 0.000 claims description 3
- 241000736839 Chara Species 0.000 claims description 2
- 230000003595 spectral effect Effects 0.000 claims description 2
- 238000000411 transmission spectrum Methods 0.000 claims description 2
- 239000002699 waste material Substances 0.000 claims description 2
- 238000013024 troubleshooting Methods 0.000 abstract description 2
- 238000003066 decision tree Methods 0.000 description 7
- 230000005540 biological transmission Effects 0.000 description 4
- 238000013527 convolutional neural network Methods 0.000 description 3
- 230000007547 defect Effects 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000007477 logistic regression Methods 0.000 description 2
- 230000002093 peripheral effect Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 238000012706 support-vector machine Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000006835 compression Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000005284 excitation Effects 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
Images
Classifications
-
- 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
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R29/00—Arrangements for measuring or indicating electric quantities not covered by groups G01R19/00 - G01R27/00
- G01R29/08—Measuring electromagnetic field characteristics
- G01R29/0807—Measuring electromagnetic field characteristics characterised by the application
- G01R29/0814—Field measurements related to measuring influence on or from apparatus, components or humans, e.g. in ESD, EMI, EMC, EMP testing, measuring radiation leakage; detecting presence of micro- or radiowave emitters; dosimetry; testing shielding; measurements related to lightning
-
- 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
-
- 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
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
- Y04S10/52—Outage or fault management, e.g. fault detection or location
Landscapes
- Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Electromagnetism (AREA)
- Testing Electric Properties And Detecting Electric Faults (AREA)
Abstract
The invention discloses a fault detection method of an electromagnetic radiation emission system based on electromagnetic spectrum characteristics, which comprises the following steps: s1, determining M common fault states of a test frequency band and an electromagnetic radiation emission system, and testing to obtain N groups of background environmental noise; s2, under the mth fault state, testing to obtain the radiation emission amplitude of N groups of electromagnetic radiation emission systems; s3, extracting N groups of emission spectrum electromagnetic characteristics under the mth fault state; s4, obtaining the emission electromagnetic spectrum of each group of fault states under M fault states; s5, updating N groups of emission spectrum electromagnetic characteristics under each fault state; s6, constructing and training a fault identification model; s7, fault detection of the electromagnetic radiation emission system is carried out by using the mature fault recognition model. According to the invention, the electromagnetic radiation emission characteristics of the equipment and the corresponding relation of the equipment are utilized to train the fault identification model, so that the fault detection method is used for fault detection of the electromagnetic radiation emission system, the difficulty of fault detection is reduced, and the troubleshooting period is shortened.
Description
Technical Field
The invention relates to electromagnetic radiation, in particular to an electromagnetic radiation emission system fault detection method based on electromagnetic spectrum characteristics.
Background
For electromagnetic radiation emission systems comprising a plurality of electronic devices (or sub-systems), the individual electronic devices are often distributed in different locations of the system, for example, in the case of aircraft, the electronic devices (or sub-systems) are all centrally mounted in the equipment bay in the middle, bottom or tail of the aircraft, or in the interior of the cockpit, etc.
The space resources in the electromagnetic radiation emission system are precious and short, the equipment cabin for placing the electronic equipment is quite narrow, and the electronic equipment is closely distributed in the equipment cabin. In such a narrow space range, electromagnetic radiation emission signals generated by different devices mutually influence and are aliased, so that when all the devices are started, it is difficult to make electromagnetic radiation emission characteristics of a specific position correspond to corresponding devices nearby the position one by one.
The electronic device is internally composed of various core circuit structures and other peripheral functional circuits. The excitation source signals and other functional signals generated by the internal circuitry may be emitted into the environment in the form of electromagnetic radiation, particularly high frequency signals such as those generated by clocks, I/O lines and internal switches. In addition, processing defects of the printed circuit board or design defects of the circuit itself, as well as additional peripherals, will also result in a large amount of electromagnetic emissions.
Because the position and the subordinate type of the electronic equipment are not clear, when the electromagnetic radiation emission system fails, the electronic equipment is generally manually judged and checked one by one, and the electronic equipment also has long period, high requirement on testers, low test automation degree and the like, so that the existing electromagnetic emission source detection means cannot meet the failure detection requirement of the electromagnetic radiation emission system.
Disclosure of Invention
The invention aims to overcome the defects of the prior art and provides a fault detection method of an electromagnetic radiation emission system based on electromagnetic spectrum characteristics, which is used for training a fault identification model by utilizing the corresponding relation between the electromagnetic radiation emission characteristics of equipment and the equipment, so that the mature model is obtained and then used for fault detection of the electromagnetic radiation emission system, the difficulty of fault detection is reduced, and the troubleshooting period is shortened.
The aim of the invention is realized by the following technical scheme: an electromagnetic radiation emission system fault detection method based on electromagnetic spectrum characteristics comprises the following steps:
s1, determining M common fault states of a test frequency band and an electromagnetic radiation emission system, and testing to obtain N groups of background environmental noise
S2, under the mth fault state, testing to obtain the radiation emission amplitude of the N groups of electromagnetic radiation emission systems
S3, extracting N groups of emission spectrum electromagnetic characteristics according to background environment noise and the radiation emission amplitude of the electromagnetic radiation emission system in the mth fault state;
s4, repeatedly executing the steps S2-S3 when m=1, 2, & gt, so as to obtain the emission electromagnetic spectrum of each group of fault states under M fault states;
s5, extracting a simplified emission spectrum electromagnetic feature set under each fault state, updating N groups of emission spectrum electromagnetic features under the fault state, and simultaneously recording all test frequency points contained in the simplified emission spectrum electromagnetic feature sets under M fault states;
s6, constructing a fault identification model based on an artificial intelligent algorithm, taking the updated N groups of emission spectrum electromagnetic characteristics of each fault state as samples, and taking the fault type as a sample label;
training a fault recognition model by using the constructed samples and sample labels, and obtaining a mature fault recognition model after training all groups of emission spectrum sample characteristics in the fault state in M;
s7, fault detection of the electromagnetic radiation emission system is carried out by using the mature fault recognition model.
The beneficial effects of the invention are as follows: (1) The scheme of the invention considers the influence of environmental interference and adopts corresponding processing means, thus having strong applicability;
(2) The invention compresses the dimension of the spectrum data to be processed and lightens the burden of the artificial intelligent algorithm classifier.
Drawings
FIG. 1 is a flow chart of the method of the present invention;
FIG. 2 is a schematic illustration of a single radiation emission characteristic of a device set in different fault conditions in an embodiment;
FIG. 3 is a graph showing radiation emission characteristics of a device set under different fault conditions in an embodiment;
FIG. 4 is a schematic diagram of a decision tree under the full-sample condition in the embodiment.
Detailed Description
The technical solution of the present invention will be described in further detail with reference to the accompanying drawings, but the scope of the present invention is not limited to the following description.
For electronic devices, electromagnetic radiation emissions are generated either intentionally or unintentionally. And electromagnetic radiation emission is an inherent property of electronic devices, and its internal structure, composition principle, working state, etc. are related. Therefore, the electromagnetic radiation emission of the electronic equipment is different, and the radiation emission and the tested products in different states are in one-to-one mapping relation. Thus, even though there are similar portions of the radiation emissions of the same type or model of electronic device and system, the radiation emissions are different from one electronic device to the next at the microscopic level. The method also means that the type and the working state of the tested object can be identified in a targeted manner on the basis of obtaining the emission characteristics of the electronic electromagnetic radiation, and finally the purpose of identifying the state of the equipment according to the electromagnetic radiation is achieved. Namely, fault location of the equipment is completed by utilizing the one-to-one correspondence relation between the electromagnetic emission characteristics of the equipment and the equipment, and specifically:
as shown in fig. 1, a fault detection method of an electromagnetic radiation emission system based on electromagnetic spectrum characteristics includes the following steps:
s1, determining M common fault states of a test frequency band and an electromagnetic radiation emission system, and testing to obtain N groups of background environmental noise
The electromagnetic radiation emission system comprises Q devices, namely a device 1, a device 2, a … and a device Q;
in the common M fault states, each fault state corresponds to a different combination of devices that fail, that is, in each fault state, it is clearly known which devices fail and which devices are normal, so only the fault state needs to be known, for example, fault detection can be completed:
| fault state | |
| State | |
| 1 | Only |
| |
|
| … | … |
| State m | |
| … | … |
| State M | … |
The test frequency band is a vector of length K and is marked as:
Fre＝(fre 1 ,fre 2 ,...,fre k ,...,fre K )；
wherein ,frek Represents the kth test frequency point, k=1, 2.
The process of testing N sets of background ambient noise includes:
s101, in a test frequency band Fre= (Fre 1 ,fre 2 ,...,fre k ,...,fre K ) Respectively carrying out background environmental noise test under each frequency point to obtain background environmental noise;
s102, repeatedly executing the test in the step S101 for N times to obtain N groups of background environmental noise, which is recorded as:
wherein ,
the results from the nth background ambient noise test are shown, n=1, 2, N;
S2, under the mth fault state, testing to obtain the radiation emission amplitude of the N groups of electromagnetic radiation emission systems
S201, in the test frequency band Fre= (Fre 1 ,fre 2 ,...,fre k ,...,fre K ) The radiation emission amplitude of the magnetic radiation emission system is tested at each frequency point to obtain a radiation emission amplitude test result;
s202, repeatedly executing the test in the step S201 for N times to obtain N groups of radiation emission amplitude test results, wherein the test results are recorded as follows:
wherein ,
the result of the N-th radiation emission amplitude test is shown, n=1, 2,. -%, N;
wherein 
Representing the results measured at the kth frequency point during the nth radiation emission amplitude test.
S3, extracting N groups of emission spectrum electromagnetic characteristics according to background environment noise and the radiation emission amplitude of the electromagnetic radiation emission system in the mth fault state;
s301, testing result of nth radiation emission amplitude in mth state
Extract significantly higher than background noise +.>
The test frequency point corresponding to the element of (c) is used as the emission spectrum electromagnetic characteristic of the nth group test:
a1, for
The kth element->
If it is->
The difference between the kth element in (a) is greater than a set threshold, then consider +.>
Obviously higher than background noise, the corresponding test frequency point k is added into the set +.>
In (a) and (b);
a2, repeating step A1 at k=1, 2..k, resulting in emission spectrum electromagnetic features:
wherein K' represents the electromagnetic characteristics of the emission spectrum
The number of frequency points contained in the data; />
S302, repeating step S301 when n=1, 2, & gt, and obtaining N sets of emission spectrum electromagnetic features.
S4, repeatedly executing the steps S2-S3 when m=1, 2, & gt, so as to obtain the emission electromagnetic spectrum of each group of fault states under M fault states;
s5, extracting a simplified emission spectrum electromagnetic feature set under each fault state, updating N groups of emission spectrum electromagnetic features under the fault state, and simultaneously recording all test frequency points contained in the simplified emission spectrum electromagnetic feature sets under M fault states;
s501. at m=1, 2,.. all test frequency points contained in the N groups of emission spectrum electromagnetic characteristics in the mth state are selected, recording the test frequency points with the occurrence frequency greater than 0.9 xN, and adding the test frequency points into the same set to obtain an emission spectrum electromagnetic characteristic set of a state M
Wherein j represents the number of test frequency points contained in the emission spectrum electromagnetic feature set of the state m;
s502, compressing the electromagnetic spectrum feature set in the mth fault state according to the electromagnetic spectrum feature sets of the emission spectrum in all M states, wherein the compression process follows the following three principles:
(1) The compressed electromagnetic spectrum features should be able to effectively distinguish all fault states of the device, the number of features not being lower than
wherein />
Is rounded upwards;
(2) For the electromagnetic signature of the emission spectrum that exists in all M fault states, from the emission spectrum signature set fre in the mth state m Removing the waste residues;
(3) When different electromagnetic spectrum characteristics are completely identical in different states, only one electromagnetic spectrum characteristic is required to be reserved;
for fre m Any two test frequency points fre a 、fre b ；
Traversing the emission spectrum feature set of M fault states will contain the test frequency bin fre a Is added to the set M in a fault state corresponding to the emission spectrum characteristic set a In (a) and (b);
traversing the emission spectrum feature set of M fault states will contain the test frequency bin fre b Is added to the set M in a fault state corresponding to the emission spectrum characteristic set a In (a) and (b);
if M a ＝M b Then the spectral feature point fre a ，fre b At fre m One from fre and the other from fre m Delete in the middle;
after (1) - (3), obtaining a simplified emission spectrum electromagnetic feature set
wherein />
The dimension of the required features can be reduced by compression, thereby greatly reducing the training complexity of the artificial intelligence algorithm.
S503, updating the electromagnetic characteristics of the emission spectrum of the nth group of tests in the mth fault state, wherein the updated result is as follows:
s504, repeatedly executing the steps S502-S503 when n=1, 2, & gt, and obtaining N groups of updated emission spectrum electromagnetic characteristics under the mth fault state;
s505. when m=1, 2,., repeating step S504 to obtain N sets of emission spectrum electromagnetic characteristics after each fault state update in M fault states;
s506, recording a set formed by all test frequency points contained in the electromagnetic characteristic set of the simplified emission spectrum under M fault states:
s6, constructing a fault identification model based on an artificial intelligent algorithm, taking the updated N groups of emission spectrum electromagnetic characteristics of each fault state as samples, and taking the fault type as a sample label;
training a fault recognition model by using the constructed samples and sample labels, and obtaining a mature fault recognition model after training all groups of emission spectrum sample characteristics in the fault state in M;
the artificial intelligence algorithm comprises, but is not limited to, a machine learning algorithm or a neural network algorithm, and the training of the model can be realized by constructing a classifier model by using the algorithms; for example, the machine learning algorithm may employ one of logistic regression (Logistic Regression), naive Bayes (Naive Bayes), nearest neighbors (K-Nearest Neighbors), decision trees (Decision Tree), support vector machines (Support Vector Machines); the neural network algorithm may employ convolutional neural networks (Convolutional Neural Networks, CNN), deep neural networks (Deep Neural Networks, DNN), and the like.
S7, fault detection of the electromagnetic radiation emission system is carried out by using the mature fault recognition model.
S701 when the electromagnetic radiation emission system fails, the electromagnetic radiation emission system is in the test frequency band Fre= (Fre 1 ,fre 2 ,...,fre k ,...,fre K ) The radiation emission amplitude of the magnetic radiation emission system is tested at each frequency point to obtain the radiation emission amplitude test result under the current fault;
s702, selecting any group of background environmental noise, comparing the background environmental noise with the radiation emission amplitude test result under the current fault under each frequency point, screening out test frequency points with the difference between the radiation emission amplitude and the background environmental noise being greater than a set threshold value, and forming the emission spectrum electromagnetic characteristics of the current fault:
fre 0-chara ：fre 0-chara ＝[fre′ 1 ,fre′ 2 ,...fre′ k′ ]；
wherein k' represents fre 0-chara The number of test frequency points included;
s703, carrying out electromagnetic characteristic fre on the emission spectrum of the current fault 0-chara Set fre composed of all test frequency points contained in electromagnetic characteristic set of transmission spectrum simplified under M fault states Chara Intersection is calculated, and the following steps are obtained:
s704. Will
And sending the fault state into a mature fault recognition model, and taking the fault state output by the mature fault recognition model as a system fault detection result.
In the embodiment of the present application, a specific fault detection procedure is described taking an example that only one of the 6 devices cannot normally operate.
(1) Test phase
For 6 devices, there are 6 different test states, namely: the device 1 does not work, and the other five devices work; the device 2 does not operate, the other five devices operate … the device 6 does not operate, and the other five devices operate. All of the six operating conditions were tested in 30 groups. The single test results in each state are shown as solid lines in fig. 2.
According to the method, the characteristic frequency points of six devices in different fault states can be obtained as shown in the following figure 2 "+";
(2) Feature screening stage
To further compress the effect of random noise on the selection of a transmission feature, the number of occurrences of a certain transmission feature in the same fault state is counted, and if the probability of occurrence of the transmission feature is greater than 90%, we regard it as a transmission feature of the fault state. Finally, we can obtain the radiation emission characteristic distribution in each fault state as shown in fig. 3.
It is seen that when equipment of class 3 fails, there are fewer radiation emission characteristics picked up from the entire aircraft equipment bay, only 8, and for other classes of equipment, there are up to 20 radiation emission characteristics. Since we further use an artificial intelligence algorithm, the artificial intelligence algorithm is essentially a probability statistic, if the characteristics of the sample are too many, this will result in a large demand of the algorithm for the sample. Therefore, to further compress the data volume, we further tailor the radiation characteristics under different fault conditions. The basis of the clipping is as follows: a. the radiation emission characteristics for all 6 fault conditions are not sufficient to distinguish the 6 fault conditions, and are therefore screened out of the final emission characteristics (e.g., 1.201GHz in fig. 3 is present in all 6 conditions); b. for two different emission characteristics to behave consistently in different device failure states, we only need to reserve one of them (e.g., 300MHz and 1.15GHz in fig. 3 are both present in the 1,2,3,5,6 states); c. theoretically only 3 carefully selected radiation emission characteristics are needed to identify 8 different fault conditions. In summary, we have chosen five orphan signal radiation characteristic quantities as radiation emission characteristics, f1, f2, f3, f4, f5, in order to compress the number of radiation emission characteristics on the one hand, and to guarantee redundancy on the other hand.
The one-to-one correspondence between these five electromagnetic radiation characteristics and the fault condition is shown in the table below.
| |
|
|
|
|
|
| f1 | f2 | f3 | f4 | f5 | |
| Failure of the |
0 | 0 | 0 | 1 | 0 |
| Failure of |
1 | 1 | 1 | 1 | 1 |
| Failure of |
1 | 1 | 1 | 1 | 0 |
| Failure of |
1 | 1 | 1 | 0 | 0 |
| Failure of the |
1 | 1 | 0 | 0 | 0 |
| Failure of the |
1 | 0 | 0 | 0 | 0 |
Wherein 1 is the feature that the frequency point is the corresponding fault state, and 0 is the feature that the frequency point is not the corresponding fault state;
it should be noted that the feature of a certain type of fault is not necessarily related to the feature of a single test, taking the fault of the device 1 as an example, for example, 1351MHz does not belong to the feature of the device 1 when the fault of the device 1, but the feature 1351MHz is included in a certain test when the fault of the device 1 occurs, so that in order to build a more accurate prediction model, an artificial intelligence algorithm needs to be further introduced.
(3) Feature identification stage
Based on the principle, the corresponding logic of the decision tree algorithm is realized through programming. In order to ensure the fault prediction accuracy, all test data are used as samples to train a decision tree algorithm, and the trained decision tree structure is shown in fig. 4, wherein x1, x2, x3, x4 and x5 correspond to radiation characteristics 1-5 in each group of test data in table 6. Taking the 1 st group of test data as an example under the condition of equipment failure state one, the characteristic vector is [0, 1,0], when deciding, x1=0 <0.5 is started from the root node, so that the next layer of nodes enter leftwards from the root node, and the decision node is finally reached at the sub-node layer x3=0 < 0.5. The accuracy of the equipment fault state prediction result under the decision tree can reach 95%.
While the foregoing description illustrates and describes a preferred embodiment of the present invention, it is to be understood that the invention is not limited to the form disclosed herein, but is not to be construed as limited to other embodiments, but is capable of use in various other combinations, modifications and environments and is capable of changes or modifications within the spirit of the invention described herein, either as a result of the foregoing teachings or as a result of the knowledge or skill of the relevant art. And that modifications and variations which do not depart from the spirit and scope of the invention are intended to be within the scope of the appended claims.
Claims (9)
1. A fault detection method of an electromagnetic radiation emission system based on electromagnetic spectrum features is characterized in that: the method comprises the following steps:
s1, determining M common fault states of a test frequency band and an electromagnetic radiation emission system, and testing to obtain N groups of background environmental noise
S2, under the mth fault state, testing to obtain the radiation emission amplitude of the N groups of electromagnetic radiation emission systems
S3, extracting N groups of emission spectrum electromagnetic characteristics according to background environment noise and the radiation emission amplitude of the electromagnetic radiation emission system in the mth fault state;
s4, repeatedly executing the steps S2-S3 when m=1, 2, & gt, so as to obtain the emission electromagnetic spectrum of each group of fault states under M fault states;
s5, extracting a simplified emission spectrum electromagnetic feature set under each fault state, updating N groups of emission spectrum electromagnetic features under the fault state, and simultaneously recording all test frequency points contained in the simplified emission spectrum electromagnetic feature sets under M fault states;
s6, constructing a fault identification model based on an artificial intelligent algorithm, taking the updated N groups of emission spectrum electromagnetic characteristics of each fault state as samples, and taking the fault type as a sample label;
training a fault recognition model by using the constructed samples and sample labels, and obtaining a mature fault recognition model after training all groups of emission spectrum sample characteristics in the fault state in M;
s7, fault detection of the electromagnetic radiation emission system is carried out by using the mature fault recognition model.
2. A method for detecting faults in an electromagnetic radiation emitting system based on characteristics of the electromagnetic spectrum as claimed in claim 1, wherein: the electromagnetic radiation emission system in step S1 includes Q devices, i.e., device 1, device 2, …, and device Q;
each of the common M fault conditions described in step S1 corresponds to a different combination of devices that have failed.
3. A method for detecting faults in an electromagnetic radiation emitting system based on characteristics of the electromagnetic spectrum as claimed in claim 1, wherein: the test frequency band in step S1 is a vector of length K, and is noted as:
Fre＝(fre 1 ,fre 2 ,...,fre k ,...,fre K )；
wherein ,frek Represents the kth test frequency point, k=1, 2.
4. A method for detecting faults in an electromagnetic radiation emitting system based on characteristics of the electromagnetic spectrum as claimed in claim 1, wherein: the process of testing the N groups of background environmental noise in the step S1 comprises the following steps:
s101, in a test frequency band Fre= (Fre 1 ,fre 2 ,...,fre k ,...,fre K ) Respectively carrying out background environmental noise test under each frequency point to obtain background environmental noise;
s102, repeatedly executing the test in the step S101 for N times to obtain N groups of background environmental noise, which is recorded as:
wherein ,
the results from the nth background ambient noise test are shown, n=1, 2, N;
5. A method for detecting faults in an electromagnetic radiation emitting system based on characteristics of the electromagnetic spectrum as claimed in claim 1, wherein: the step S2 includes the steps of:
s201, in the test frequency band Fre= (Fre 1 ,fre 2 ,...,fre k ,...,fre K ) The radiation emission amplitude of the magnetic radiation emission system is tested at each frequency point to obtain a radiation emission amplitude test result;
s202, repeatedly executing the test in the step S201 for N times to obtain N groups of radiation emission amplitude test results, wherein the test results are recorded as follows:
wherein ,
the result of the N-th radiation emission amplitude test is shown, n=1, 2,. -%, N;
wherein 
Representing the results measured at the kth frequency point during the nth radiation emission amplitude test.
6. A method for detecting faults in an electromagnetic radiation emitting system based on characteristics of the electromagnetic spectrum as claimed in claim 1, wherein: said step S3 comprises the sub-steps of:
s301, testing result of nth radiation emission amplitude in mth state
Extract significantly higher than background noise +.>
The test frequency point corresponding to the element of (c) is used as the emission spectrum electromagnetic characteristic of the nth group test:
a1, for
The kth element->
If it is->
The difference between the kth element in (a) is greater than a set threshold, then consider +.>
Obviously higher than background noise, the corresponding test frequency point k is added into the set +.>
In (a) and (b);
a2, repeating step A1 at k=1, 2..k, resulting in emission spectrum electromagnetic features:
wherein K' represents the electromagnetic characteristics of the emission spectrum
The number of frequency points contained in the data;
s302, repeating step S301 when n=1, 2, & gt, and obtaining N sets of emission spectrum electromagnetic features.
7. The electromagnetic radiation emission system fault detection method based on electromagnetic spectrum characteristics of claim 6, wherein: the step S5 includes:
s501. at m=1, 2,.. all test frequency points contained in the N groups of emission spectrum electromagnetic characteristics in the mth state are selected, recording the test frequency points with the occurrence frequency greater than 0.9 xN, and adding the test frequency points into the same set to obtain an emission spectrum electromagnetic characteristic set of a state M
Wherein j represents the number of test frequency points contained in the emission spectrum electromagnetic feature set of the state m;
s502, compressing the electromagnetic spectrum feature set in the mth fault state according to the electromagnetic spectrum feature sets of the emission spectrum in all M states, wherein the compression process follows the following three principles:
(1) The compressed electromagnetic spectrum features should be able to effectively distinguish all fault states of the device, the number of features not being lower than
wherein />
Is rounded upwards;
(2) For the electromagnetic signature of the emission spectrum that exists in all M fault states, from the emission spectrum signature set fre in the mth state m Removing the waste residues;
(3) When different electromagnetic spectrum characteristics are completely identical in different states, only one electromagnetic spectrum characteristic is required to be reserved;
for fre m Any two test frequency points fre a 、fre b ；
Traversing M faultsThe emission spectrum feature set of the state will contain the test frequency point fre a Is added to the set M in a fault state corresponding to the emission spectrum characteristic set a In (a) and (b);
traversing the emission spectrum feature set of M fault states will contain the test frequency bin fre b Is added to the set M in a fault state corresponding to the emission spectrum characteristic set a In (a) and (b);
if M a ＝M b Then the spectral feature point fre a ，fre b At fre m One from fre and the other from fre m Delete in the middle;
after (1) - (3), obtaining a simplified emission spectrum electromagnetic feature set
wherein 
S503, updating the electromagnetic characteristics of the emission spectrum of the nth group of tests in the mth fault state, wherein the updated result is as follows:
s504, repeatedly executing the steps S502-S503 when n=1, 2, & gt, and obtaining N groups of updated emission spectrum electromagnetic characteristics under the mth fault state;
s505. when m=1, 2,., repeating step S504 to obtain N sets of emission spectrum electromagnetic characteristics after each fault state update in M fault states;
s506, recording a set formed by all test frequency points contained in the electromagnetic characteristic set of the simplified emission spectrum under M fault states:
8. the electromagnetic radiation emission system fault detection method based on electromagnetic spectrum characteristics of claim 6, wherein: the step S7 includes:
s701 when the electromagnetic radiation emission system fails, the electromagnetic radiation emission system is in the test frequency band Fre= (Fre 1 ,fre 2 ,...,fre k ,...,fre K ) The radiation emission amplitude of the magnetic radiation emission system is tested at each frequency point to obtain the radiation emission amplitude test result under the current fault;
s702, selecting any group of background environmental noise, comparing the background environmental noise with the radiation emission amplitude test result under the current fault under each frequency point, screening out test frequency points with the difference between the radiation emission amplitude and the background environmental noise being greater than a set threshold value, and forming the emission spectrum electromagnetic characteristics of the current fault:
fre 0-chara ：fre 0-chara ＝[fre 1 ′,fre′ 2 ,...fre′ k′ ]；
wherein k' represents fre 0-chara The number of test frequency points included;
s703, carrying out electromagnetic characteristic fre on the emission spectrum of the current fault 0-chara Set fre composed of all test frequency points contained in electromagnetic characteristic set of transmission spectrum simplified under M fault states Chara Intersection is calculated, and the following steps are obtained:
s704. Will
And sending the fault state into a mature fault recognition model, and taking the fault state output by the mature fault recognition model as a system fault detection result.
9. A method for detecting faults in an electromagnetic radiation emitting system based on characteristics of the electromagnetic spectrum as claimed in claim 1, wherein: the artificial intelligence algorithm includes, but is not limited to, a machine learning algorithm or a neural network algorithm.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310204992.9A CN116184088B (en) | 2023-03-06 | 2023-03-06 | Electromagnetic spectrum characteristic-based electromagnetic radiation emission system fault detection method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310204992.9A CN116184088B (en) | 2023-03-06 | 2023-03-06 | Electromagnetic spectrum characteristic-based electromagnetic radiation emission system fault detection method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116184088A true CN116184088A (en) | 2023-05-30 |
| CN116184088B CN116184088B (en) | 2024-04-12 |
Family
ID=86434373
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310204992.9A Active CN116184088B (en) | 2023-03-06 | 2023-03-06 | Electromagnetic spectrum characteristic-based electromagnetic radiation emission system fault detection method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116184088B (en) |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US4775839A (en) * | 1985-05-21 | 1988-10-04 | Korona Messtechnik Gossau | Control apparatus for the electronic detection in a.c. power transmission lines of fault locations causing power losses |
| DE102006053970A1 (en) * | 2006-11-16 | 2008-05-21 | Adc Automotive Distance Control Systems Gmbh | Object e.g. automatic-masking object, object characteristic and object position detecting method for use in driver assistance system, involves determining amplitude gradients of received electromagnetic radiation |
| CN101701986A (en) * | 2009-10-27 | 2010-05-05 | 中国舰船研究设计中心 | System for pre-testing and diagnosing electro magnetic interference of electronic equipment and method thereof |
| CN105044520A (en) * | 2015-08-06 | 2015-11-11 | 西安电子科技大学 | Method and device for measuring electromagnetic emission characteristics of electronic device on site |
| CN106526380A (en) * | 2016-11-18 | 2017-03-22 | 北京航空航天大学 | Electromagnetic emission element detection and analysis system |
| CN110082609A (en) * | 2019-05-06 | 2019-08-02 | 中国人民解放军海军航空大学 | Portable airborne communication equipment electromagnet radiation detection instrument |
| CN112363021A (en) * | 2020-11-13 | 2021-02-12 | 重庆大学 | Distributed line fault detection and positioning system and method |
| CN112924749A (en) * | 2021-02-04 | 2021-06-08 | 西安电子科技大学 | Unsupervised counterstudy electromagnetic spectrum abnormal signal detection method |
| US20210215750A1 (en) * | 2018-05-18 | 2021-07-15 | Enics Ag | Method and system for fault detection |
| RU2752281C1 (en) * | 2020-06-29 | 2021-07-26 | Межрегиональное общественное учреждение "Институт инженерной физики" | Method for detecting covert information leakage paths in technical means for reception, processing, storage and transmission of information |
| CN113899948A (en) * | 2021-12-08 | 2022-01-07 | 成都中星世通电子科技有限公司 | System and method for quickly extracting electromagnetic spectrum target characteristic data |
-
2023
- 2023-03-06 CN CN202310204992.9A patent/CN116184088B/en active Active
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US4775839A (en) * | 1985-05-21 | 1988-10-04 | Korona Messtechnik Gossau | Control apparatus for the electronic detection in a.c. power transmission lines of fault locations causing power losses |
| DE102006053970A1 (en) * | 2006-11-16 | 2008-05-21 | Adc Automotive Distance Control Systems Gmbh | Object e.g. automatic-masking object, object characteristic and object position detecting method for use in driver assistance system, involves determining amplitude gradients of received electromagnetic radiation |
| CN101701986A (en) * | 2009-10-27 | 2010-05-05 | 中国舰船研究设计中心 | System for pre-testing and diagnosing electro magnetic interference of electronic equipment and method thereof |
| CN105044520A (en) * | 2015-08-06 | 2015-11-11 | 西安电子科技大学 | Method and device for measuring electromagnetic emission characteristics of electronic device on site |
| CN106526380A (en) * | 2016-11-18 | 2017-03-22 | 北京航空航天大学 | Electromagnetic emission element detection and analysis system |
| US20210215750A1 (en) * | 2018-05-18 | 2021-07-15 | Enics Ag | Method and system for fault detection |
| CN110082609A (en) * | 2019-05-06 | 2019-08-02 | 中国人民解放军海军航空大学 | Portable airborne communication equipment electromagnet radiation detection instrument |
| RU2752281C1 (en) * | 2020-06-29 | 2021-07-26 | Межрегиональное общественное учреждение "Институт инженерной физики" | Method for detecting covert information leakage paths in technical means for reception, processing, storage and transmission of information |
| CN112363021A (en) * | 2020-11-13 | 2021-02-12 | 重庆大学 | Distributed line fault detection and positioning system and method |
| CN112924749A (en) * | 2021-02-04 | 2021-06-08 | 西安电子科技大学 | Unsupervised counterstudy electromagnetic spectrum abnormal signal detection method |
| CN113899948A (en) * | 2021-12-08 | 2022-01-07 | 成都中星世通电子科技有限公司 | System and method for quickly extracting electromagnetic spectrum target characteristic data |
Non-Patent Citations (2)
| Title |
|---|
| DONGLIN SU; SHAOXIONG CAI; YAOYAO LI; WEIMIN LI; XIAOJING DIAO: "A Novel Equivalent Construction Method Applying to Radar EMS Threshold Test Under Multi-Source Heterogeneous Electromagnetic Environment", IEEE TRANSACTIONS ON ELECTROMAGNETIC COMPATIBILITY, vol. 63, no. 2021, 31 December 2021 (2021-12-31), pages 1910 - 1920 * |
| 吕冬翔，苏东林: "被试品辐射发射试验点位对测试结果影响", 北京航空航天大学学报, vol. 43, no. 2017, 31 January 2017 (2017-01-31), pages 100 - 106 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116184088B (en) | 2024-04-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107907799B (en) | Method and system for identifying partial discharge defect type based on convolutional neural network | |
| US9834317B2 (en) | Method for identifying a piece of defective equipment in an aircraft | |
| CN108389197A (en) | Transmission line of electricity defect inspection method based on deep learning | |
| Liu et al. | Effective algorithm for detecting community structure in complex networks based on GA and clustering | |
| CN111199244B (en) | Data classification method and device, storage medium and electronic device | |
| CN111490897B (en) | Network fault analysis method and system for complex network | |
| CN112910811B (en) | Blind modulation identification method and device under unknown noise level condition based on joint learning | |
| CN107830996B (en) | Fault diagnosis method for aircraft control surface system | |
| CN110991610B (en) | Probability determination method for nondeterministic problem | |
| CN116577677A (en) | Discharging test system and method for retired power battery | |
| CN116184088B (en) | Electromagnetic spectrum characteristic-based electromagnetic radiation emission system fault detection method | |
| CN112507605A (en) | Power distribution network anomaly detection method based on AnoGAN | |
| CN114356641A (en) | Incremental software defect prediction method, system, equipment and storage medium | |
| KR20210100028A (en) | Method of examining specimens and system thereof | |
| CN112149845A (en) | Intelligent operation and maintenance method based on big data and machine learning | |
| CN116224091B (en) | Battery cell fault detection method and device, electronic equipment and storage medium | |
| US20080315892A1 (en) | Methods and apparatus using one or more supernodes when testing for shorts between nodes of a circuit assembly | |
| EP3748549B1 (en) | Learning device and learning method | |
| Masich et al. | Identification of cut-points in test parameters for classification of industrial products | |
| CN112183737A (en) | Firefly algorithm and CNN-based high-voltage cable partial discharge mode identification method | |
| CN110874839A (en) | Wafer graph extraction method and extraction system thereof | |
| CN110784887A (en) | Method for detecting number of abnormal signal sources in gridding radio signal monitoring system | |
| CN115684835B (en) | Power distribution network fault diagnosis method, device, equipment and storage medium | |
| CN113867172B (en) | Avionics system fault simulation verification platform and method | |
| US20240219453A1 (en) | Test system for detecting faults in multiple devices of the same type |
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 |