CN117077066A - Waveform abnormality detection method, waveform abnormality detection device, electronic device and storage medium - Google Patents
Waveform abnormality detection method, waveform abnormality detection device, electronic device and storage medium Download PDFInfo
- Publication number
- CN117077066A CN117077066A CN202311345102.2A CN202311345102A CN117077066A CN 117077066 A CN117077066 A CN 117077066A CN 202311345102 A CN202311345102 A CN 202311345102A CN 117077066 A CN117077066 A CN 117077066A
- Authority
- CN
- China
- Prior art keywords
- waveform
- time domain
- waveform data
- data
- target
- 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
- 238000001514 detection method Methods 0.000 title claims abstract description 100
- 230000005856 abnormality Effects 0.000 title claims abstract description 36
- 230000002159 abnormal effect Effects 0.000 claims abstract description 46
- 230000009466 transformation Effects 0.000 claims abstract description 38
- 238000000034 method Methods 0.000 claims abstract description 36
- 238000012549 training Methods 0.000 claims abstract description 25
- 230000001131 transforming effect Effects 0.000 claims abstract description 17
- 238000012545 processing Methods 0.000 abstract description 8
- 230000006870 function Effects 0.000 description 29
- 238000010586 diagram Methods 0.000 description 13
- 238000004891 communication Methods 0.000 description 8
- 238000004590 computer program Methods 0.000 description 7
- 238000004422 calculation algorithm Methods 0.000 description 6
- 238000006243 chemical reaction Methods 0.000 description 5
- 230000008569 process Effects 0.000 description 5
- 238000004364 calculation method Methods 0.000 description 4
- 230000008602 contraction Effects 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- 230000003287 optical effect Effects 0.000 description 3
- 230000000630 rising effect Effects 0.000 description 3
- 238000012360 testing method Methods 0.000 description 3
- 238000013519 translation Methods 0.000 description 3
- 238000012795 verification Methods 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000012512 characterization method Methods 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 230000001788 irregular Effects 0.000 description 2
- 239000011159 matrix material Substances 0.000 description 2
- 230000002547 anomalous effect Effects 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 230000000717 retained effect Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000001953 sensory effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/2433—Single-class perspective, e.g. one-against-all classification; Novelty detection; Outlier detection
-
- 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
- G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
- G06F18/2131—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods based on a transform domain processing, e.g. wavelet transform
-
- 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
- G06F2123/00—Data types
- G06F2123/02—Data types in the time domain, e.g. time-series data
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Measurement Of Mechanical Vibrations Or Ultrasonic Waves (AREA)
Abstract
The application relates to the field of data processing, and provides a waveform abnormality detection method, a waveform abnormality detection device, electronic equipment and a storage medium, wherein the method comprises the following steps: acquiring time domain waveform data to be detected; transforming the time domain waveform data to be detected from the time domain to the frequency domain to obtain a correlation coefficient, wherein the correlation coefficient represents the correlation between the time domain waveform data to be detected and a reference waveform adopted in the transformation; obtaining target waveform data based on the correlation coefficient and the reference waveform; inputting the target waveform data into a detection model to obtain a detection result of the target waveform data, wherein the detection result is used for representing whether the time domain waveform data to be detected is abnormal waveform data or not; the detection model is obtained by training a model to be trained by using time domain waveform sample data with a normal waveform data sample label and a time domain waveform sample data with an abnormal waveform data sample label. The problem of the correlation technique low to unusual waveform judgement inefficiency is solved, the high efficiency of waveform anomaly detection has been realized.
Description
Technical Field
The present application relates to the field of data processing, and in particular, to a method and apparatus for detecting waveform anomalies, an electronic device, and a storage medium.
Background
Before the notebook computer leaves the factory, whether the waveform of the key point electric signal in the circuit board is abnormal or not is usually detected. The related technology mainly detects whether the waveform has abnormality or not by manpower, and has lower efficiency. Therefore, how to improve the efficiency of waveform abnormality detection is a technical problem to be solved.
Disclosure of Invention
The application provides a waveform abnormality detection method, a waveform abnormality detection device, electronic equipment and a storage medium, which are used for at least solving the technical problems in the prior art.
The application provides a waveform abnormality detection method, which comprises the following steps:
acquiring time domain waveform data to be detected;
transforming the time domain waveform data to be detected from the time domain to the frequency domain to obtain a correlation coefficient, wherein the correlation coefficient represents the correlation between the time domain waveform data to be detected and a reference waveform adopted in the transformation;
obtaining target waveform data based on the correlation coefficient and the reference waveform;
inputting the target waveform data into a detection model to obtain a detection result of the target waveform data, wherein the detection result is used for representing whether the time domain waveform data to be detected is abnormal waveform data or not; the detection model is obtained by training a model to be trained by using time domain waveform sample data with a normal waveform data sample label and a time domain waveform sample data with an abnormal waveform data sample label.
In the above scheme, the transforming the waveform data of the time domain to be measured from the time domain to the frequency domain to obtain the correlation coefficient includes:
and carrying out wavelet transformation on the time domain waveform data to be detected to obtain at least one wavelet coefficient, and taking the at least one wavelet coefficient as a correlation coefficient.
In the above scheme, the acquiring the time domain waveform data to be measured includes:
acquiring initial time domain waveform data;
based on a preset interception condition, intercepting the initial time domain waveform data to obtain time domain waveform data to be detected.
In the above scheme, the obtaining the target waveform data based on the correlation coefficient and the reference waveform includes:
obtaining a target array based on the correlation coefficient, wherein the target array represents a set of correlation coefficients associated with the time domain waveform data characteristics to be detected;
and obtaining target waveform data based on the target array and the reference waveform.
In the above scheme, the obtaining the target waveform data based on the target array and the reference waveform includes:
determining a target correlation coefficient in a target array;
and obtaining target waveform data based on the target correlation coefficient and the reference waveform.
In the above scheme, the detection model is obtained by training a model to be trained by using time domain waveform sample data with a normal waveform data sample tag and a time domain waveform sample data with an abnormal waveform data sample tag, and includes:
Transforming the time domain waveform sample data from the time domain to the frequency domain to obtain a correlation coefficient, wherein the correlation coefficient represents the correlation between the time domain waveform sample data and a reference waveform adopted in the transformation;
obtaining target waveform sample data based on the correlation coefficient and the reference waveform;
inputting target waveform sample data and sample labels of the target waveform sample data into a model to be trained, and training the model to be trained to obtain a detection model;
the detection model is used for detecting whether the time domain waveform data to be detected is abnormal waveform data or not.
In the above scheme, the transforming the time domain to the frequency domain is performed on the time domain waveform sample data to obtain a correlation coefficient, including:
and carrying out wavelet transformation on the time domain waveform sample data to obtain at least one wavelet coefficient, and taking the at least one wavelet coefficient as a correlation coefficient.
The application provides a waveform abnormality detection device, which comprises:
the first acquisition unit is used for acquiring time domain waveform data to be detected;
the transformation unit is used for transforming the time domain waveform data to be measured from the time domain to the frequency domain to obtain a correlation coefficient, and the correlation coefficient represents the correlation between the time domain waveform data to be measured and a reference waveform adopted in the transformation;
A second acquisition unit for acquiring target waveform data based on the correlation coefficient and the reference waveform;
the detection unit is used for inputting the target waveform data into a detection model to obtain a detection result of the target waveform data, and the detection result is used for representing whether the time domain waveform data to be detected is abnormal waveform data or not; the detection model is obtained by training a model to be trained by using time domain waveform sample data with a normal waveform data sample label and a time domain waveform sample data with an abnormal waveform data sample label.
The application provides an electronic device, comprising:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the methods of the present application.
The present application provides a non-transitory computer readable storage medium storing computer instructions for causing a computer to perform the method of the present application.
According to the method, the time domain waveform data to be detected is obtained, the time domain to frequency domain transformation is carried out on the time domain waveform data to be detected, the correlation coefficient is obtained, the correlation coefficient represents the correlation between the time domain waveform data to be detected and the reference waveform adopted in the transformation, the target waveform data is obtained based on the correlation coefficient and the reference waveform, the target waveform data is input into the detection model, the detection result of the target waveform data is obtained, and the detection that the time domain waveform data to be detected is abnormal waveform data or normal waveform data is achieved. The detection model is obtained by training a model to be trained by using time domain waveform sample data with a normal waveform data sample label and a time domain waveform sample data with an abnormal waveform data sample label.
The waveform data abnormality or normal detection flow provided by the application is an automatic implementation flow, is simple and not complex to implement, solves the problem of low abnormal waveform judgment efficiency in the related technology, and realizes the high efficiency of waveform abnormality detection.
It should be understood that the description in this section is not intended to identify key or critical features of the embodiments of the application or to delineate the scope of the application. Other features of the present application will become apparent from the description that follows.
Drawings
The above, as well as additional purposes, features, and advantages of exemplary embodiments of the present application will become readily apparent from the following detailed description when read in conjunction with the accompanying drawings. Several embodiments of the present application are illustrated by way of example, and not by way of limitation, in the figures of the accompanying drawings and in which:
in the drawings, the same or corresponding reference numerals indicate the same or corresponding parts.
Fig. 1 shows a schematic implementation flow diagram of a waveform abnormality detection method according to an embodiment of the present application;
fig. 2 shows a second implementation flow chart of the waveform abnormality detection method according to the embodiment of the present application;
FIG. 3 is a schematic diagram of time domain waveform data to be measured according to an embodiment of the present application;
FIG. 4 shows a wavelet transform diagram I of an embodiment of the present application;
FIG. 5 shows a second wavelet transform schematic diagram of an embodiment of the present application;
FIG. 6 is a schematic diagram of an implementation flow of a training method of a detection model according to an embodiment of the present application;
FIG. 7 is a schematic diagram of normal time domain waveform sample data according to an embodiment of the present application;
FIG. 8 is a schematic diagram of target waveform sample data corresponding to normal time domain waveform sample data according to an embodiment of the present application;
FIG. 9 is a schematic diagram of anomalous time domain waveform sample data in accordance with an embodiment of the application;
FIG. 10 is a schematic diagram of target waveform sample data corresponding to abnormal time domain waveform sample data according to an embodiment of the present application;
fig. 11 is a schematic diagram showing the constitution of a waveform abnormality detecting apparatus according to an embodiment of the present application;
fig. 12 is a schematic diagram showing a composition structure of an electronic device according to an embodiment of the present application.
Detailed Description
In order to make the objects, features and advantages of the present application more comprehensible, the technical solutions according to the embodiments of the present application will be clearly described in the following with reference to the accompanying drawings, and it is obvious that the described embodiments are only some embodiments of the present application, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
It can be understood that before the notebook computer leaves the factory, it will generally detect whether there is an abnormality in the waveform of the electrical signal of the key point on the circuit board, for example, detect whether there is an abnormality in the voltage waveform of the key point. In the related art, whether an abnormality exists in a waveform is detected mainly manually. Specifically, the parameters of the waveform are measured, and whether the measured parameters meet the specification is checked manually. This manual verification scheme requires relying on the experience of the tester and has low verification efficiency. Moreover, whether the waveform is an abnormal waveform is determined by judging whether the parameters accord with the specification, so that details of the waveform are difficult to pay attention to, and missed judgment and misjudgment are easy to occur. The maximum voltage and the minimum voltage of the waveform are measured, and the waveform is manually judged to be a normal waveform when the maximum voltage and the minimum voltage of the waveform meet the specification. However, when there is a slight abnormality in the waveform, the waveform is not perceived by a person, and even if the maximum voltage and the minimum voltage meet the specification, the waveform has a potential abnormality risk, so that the accuracy of manual verification can be greatly reduced, and the efficiency of waveform abnormality detection can be affected to a certain extent.
In the embodiment of the application, the time domain waveform data to be measured is obtained, the time domain to frequency domain transformation is carried out on the time domain waveform data to be measured, the correlation coefficient is obtained, the correlation coefficient represents the correlation relation between the time domain waveform data to be measured and the reference waveform adopted in the transformation, the target waveform data is obtained based on the correlation coefficient and the reference waveform, the target waveform data is input into the detection model, the detection result of the target waveform data is obtained, and the detection result is used for representing whether the time domain waveform data to be measured is abnormal waveform data or not; the detection model is obtained by training a model to be trained by using time domain waveform sample data with a normal waveform data sample label and a time domain waveform sample data with an abnormal waveform data sample label. The implementation process is not complicated, the problem of low judging efficiency of the abnormal waveform in the related technology is solved, and the high efficiency of waveform abnormality detection is realized. In addition, the waveform data abnormality or normal detection flow provided by the application is an automatic implementation flow, and compared with the scheme of manually detecting in the related art, the waveform data abnormality or normal detection flow can pay attention to the details of the waveform, and is not easy to miss judgment and misjudgment.
The waveform abnormality detection method according to the embodiment of the present application is described in detail below.
An embodiment of the present application provides a method for detecting waveform anomalies, as shown in fig. 1, the method includes:
s101: and obtaining time domain waveform data to be detected.
In this step, the time domain waveform data to be (detected) is waveform data for which it is necessary to detect whether it is abnormal. And obtaining the time domain waveform data to be detected by reading the time domain waveform data to be detected. In practical application, the time domain waveform data to be measured can be read through an automatic program, and then the time domain waveform data to be measured is obtained. In this step, the read waveform data is time domain data.
S102: and transforming the time domain waveform data to be detected from the time domain to the frequency domain to obtain a correlation coefficient, wherein the correlation coefficient represents the correlation between the time domain waveform data to be detected and a reference waveform adopted in the transformation.
In the step, a time domain-to-frequency domain conversion algorithm is adopted to convert waveform data of a time domain to be detected from the time domain to the frequency domain. When the conversion scheme is executed, a reference waveform is pre-selected or set, and the time domain to frequency domain transformation is carried out on the data of the time domain to be detected based on the reference waveform, so that a correlation coefficient representing the correlation between the data of the time domain to be detected and the reference waveform is obtained. The number of the correlation coefficients may be one, two or more, preferably a plurality.
Where the number of correlation coefficients is two or more, it can be understood that: the time domain waveform data to be detected is transformed from the time domain to the frequency domain, namely the time domain waveform data to be detected is essentially split into a plurality of sections to perform characteristic analysis. Since there may be a difference in waveform trend for each section, a correlation coefficient is calculated for each section in the present application. The correlation coefficient calculated for all the sections is a set of the correlation coefficients calculated for each section. From this point of view, the number of correlation coefficients is two or more.
In the application, the correlation of the correlation coefficient characterization can be the similarity between each section of the time domain waveform data to be measured and the reference waveform. The similarity determines the similarity of the characteristics between each section of the reference waveform and the time domain waveform data to be measured. The larger the correlation coefficient is, the higher the similarity between the section of the time domain waveform data to be measured and the reference waveform is, namely the higher the similarity of the characteristics between the section and the reference waveform is. The smaller the correlation coefficient is, the lower the similarity between the section of the time domain waveform data to be measured and the reference waveform is, namely the lower the similarity of the characteristics between the section and the reference waveform is.
S103: and obtaining target waveform data based on the correlation coefficient and the reference waveform.
In this step, the target waveform data is waveform data input to the detection model. The target waveform data in the application is synthesized waveform data with the overall characteristic similarity exceeding a certain preset threshold value with the time domain waveform data to be detected. The similarity exceeding a certain preset threshold value can be regarded as high in similarity with the overall characteristics of the time domain waveform data to be detected.
Based on the correlation coefficient representing the similarity between each section of the time domain waveform data to be measured and the reference waveform, the synthesized waveform data with the overall characteristic similarity exceeding a certain preset threshold value with the time domain waveform data to be measured is obtained, and the characteristics of the time domain waveform data to be measured can be better analyzed.
S104: inputting the target waveform data into a detection model to obtain a detection result of the target waveform data, wherein the detection result is used for representing whether the time domain waveform data to be detected is abnormal waveform data or not; the detection model is obtained by training a model to be trained by using time domain waveform sample data with a normal waveform data sample label and a time domain waveform sample data with an abnormal waveform data sample label.
In this step, the detection model is a model for detecting whether the time domain waveform data to be detected is abnormal waveform data. The detection model is obtained by training a model to be trained by using time domain waveform sample data with normal and abnormal waveform data sample labels. And inputting the target waveform data into a detection model to obtain a detection result of whether the time domain waveform data to be detected is abnormal waveform data.
In the scheme shown in S101 to S104, a correlation coefficient representing a correlation between time domain waveform data to be measured and a reference waveform used in the transformation is obtained by transforming the time domain waveform data to be measured from the time domain to the frequency domain, target waveform data is obtained based on the correlation coefficient, and the target waveform data is input into a detection model to obtain a detection result of whether the time domain waveform data to be measured is abnormal waveform data. The implementation process is not complicated, the problem of low judging efficiency of the abnormal waveform in the related technology is solved, and the high efficiency of waveform abnormality detection is realized. In addition, the waveform data abnormality or normal detection flow provided by the application is an automatic implementation flow, and compared with the scheme of manually detecting in the related art, the waveform data abnormality or normal detection flow is not easy to miss judgment and misjudgment.
In an alternative solution, as shown in fig. 2, the transforming the waveform data of the time domain to the frequency domain to obtain the correlation coefficient includes:
s202: and carrying out wavelet transformation on the time domain waveform data to be detected to obtain at least one wavelet coefficient, and taking the at least one wavelet coefficient as a correlation coefficient.
In the application, a wavelet transformation algorithm is adopted to carry out wavelet transformation on the waveform data of the time domain to be measured. It is understood that the wavelet transform algorithm is one of the time domain to frequency domain conversion algorithms.
And carrying out wavelet transformation on the time domain waveform data to be detected to obtain at least one wavelet coefficient. It will be appreciated that the wavelet function is a waveform of finite duration with an average value of 0. The wavelet function is typically irregular, asymmetric. The wavelet transformation is to use the time domain waveform data to be measured as a standard, and at least one wavelet coefficient is obtained by utilizing translation transformation and expansion transformation of a wavelet function, wherein the wavelet coefficient is used for characterizing the similarity degree between each section of the time domain waveform data to be measured and the wavelet function (used as a reference waveform).
Specifically, as shown in fig. 3, the abscissa represents time and the ordinate represents amplitude. Fig. 3 shows time domain waveform data to be measured. Fig. 4 shows that the wavelet coefficients are calculated from the starting position of the time domain waveform data to be measured when the wavelet is not stretched. And after shifting rightwards by a certain time unit, calculating the wavelet coefficient again, shifting again, and the like until the wavelet is shifted to the end position of the time domain waveform data to be detected. Fig. 5 shows that when the wavelet is expanded by 1 time, the wavelet coefficients are calculated from the start position of the time domain waveform data to be measured until the wavelet is shifted to the end position of the time domain waveform data to be measured.
In fig. 5, the expansion of the wavelet is taken as an example by 1 time, and the expansion of the wavelet may be 3 times, 4 times or more, which is not particularly limited in the present application. Wherein the wavelet coefficients are calculated by the formula (1) and the formula (2):
Formula (1)
Formula (2)
In the foregoing formulas (1) and (2),is continuous time domain waveform data to be measured. />Time is indicated. />Representing wavelet coefficients. />Representing the wavelet function or wavelet selected. />Representing the offset (e.g., time units of translation). />Represents the maximum value of the amount of expansion (e.g., a is 1 when the wavelet is expanded 1 time). />Representation->Is a complex conjugate of (a) and (b).Represents a pair of ++in the (- ≡infinity) interval>Integration is performed.
According to the method, the time domain waveform data to be detected can be split into a plurality of sections by performing wavelet transformation on the time domain waveform data to be detected, and the wavelet coefficient of each section is calculated. In colloquial terms, wavelet coefficients represent the degree of similarity of each segment to the wavelet function characteristics. The calculation of the wavelet coefficients can better extract the local characteristics of each section of the time domain waveform data to be measured, and further better analyze the overall characteristics or the whole characteristics of the time domain waveform data to be measured.
In an alternative solution, the acquiring time domain waveform data to be measured includes:
acquiring initial time domain waveform data;
based on a preset interception condition, intercepting the initial time domain waveform data to obtain time domain waveform data to be detected.
In the present application, the initial time domain waveform data is the acquired initial complete time domain waveform data. Since a complete waveform data generally includes a flat section and a non-flat section. When there is a rise or fall in waveform data within a section, the section may be regarded as an uneven section. Typically, anomalies (e.g., a rising or falling period) will only occur in the non-flat section. It makes sense to detect whether the waveform in the non-flat section is normal or abnormal. Based on this, in the present application, the gentle waveform data in the acquired complete time domain waveform data is deleted, and the waveform data in the gentle section is retained. The reserved waveform data is the time domain waveform data to be detected obtained by intercepting the initial time domain waveform data.
In the application, the section which is unlikely to be abnormal in the initial time domain waveform data is discarded and not detected, and the section which is likely to be abnormal is intercepted and used as the time domain waveform data to be detected for detection, so that the data calculation amount can be greatly reduced, and the detection efficiency is improved.
In an alternative solution, the obtaining the target waveform data based on the correlation coefficient and the reference waveform includes:
Obtaining a target array based on the correlation coefficient, wherein the target array represents a set of correlation coefficients associated with the time domain waveform data characteristics to be detected;
and obtaining target waveform data based on the target array and the reference waveform.
In the application, at least one wavelet coefficient is stored in a target array as a set of correlation coefficients representing characteristic correlations (characteristic similarity degree) with each section of time domain waveform data to be measured. It will be appreciated that the target array is a two-dimensional array and can be considered as a coefficient matrix. The wavelet coefficients in the matrix represent the correlation (similarity) between the wavelet functions under each expansion and contraction amount and each section of the time domain waveform data to be measured. For example, table 1 may be represented as a representation of a target array. As shown in table 1, 9 wavelet coefficients A1-A3, b1-b3, and c1-c3 are stored in the target array, and represent the degree of similarity between the wavelet function and the time domain waveform data to be measured in the A1-A2 section, the degree of similarity between the wavelet function and the A2-A3 section, and the degree of similarity between the wavelet function and the A3-A4 section when the wavelet function is not stretched (the wavelet function is G (x)), and the expansion is doubled (the wavelet function is G (2 x)), and the expansion is doubled (the wavelet function is G (3 x)).
TABLE 1
In the application, at least one wavelet coefficient obtained by wavelet transformation is stored in an array. The method can intuitively list the similarity of wavelet functions with different expansion and contraction amounts and each section of the time domain waveform data to be tested, and provides a data base for accurately obtaining final target waveform data.
In an alternative solution, the obtaining the target waveform data based on the target array and the reference waveform includes:
determining a target correlation coefficient in a target array;
and obtaining target waveform data based on the target correlation coefficient and the reference waveform.
In the application, under each section of the time domain waveform data to be detected, the wavelet coefficients with different expansion amounts and the wavelet coefficients with highest similarity between the sections are regarded as the target correlation coefficients under the sections, namely, the selection of the target correlation coefficients corresponding to the different sections is realized. The selected target correlation coefficient is the characteristic similarity degree when the characteristic of the wavelet of the expansion quantity is closest to the characteristic of the time domain waveform data to be measured in the section.
Referring to table 1, assuming that the value of a3 is the largest among three wavelet coefficients A1-a3 under the A1-A2 section, a3 may be regarded as one target correlation coefficient. Namely, in the section A1-A2, the characteristic of the wavelet G (3 x) with the target correlation coefficient a3 corresponding to the expansion amount is closest to the characteristic of the time domain waveform data to be detected, and the characteristic similarity is highest. Similarly, of the three wavelet coefficients b1-b3 in the A2-A3 section, b1 has the largest value, and b1 can be regarded as a target correlation coefficient. Namely, in the section A2-A3, the characteristic of the wavelet G (x) of the target correlation coefficient b1 corresponding to the amount of expansion is closest to the characteristic of the time domain waveform data to be measured. Of the three wavelet coefficients c1-c3 under the A3-A4 section, c2 has the largest value, then c2 can be regarded as a target correlation coefficient. Namely, in the section A3-A4, the characteristic of the wavelet G (2 x) of the target correlation coefficient c2 corresponding to the expansion amount is closest to the characteristic of the time domain waveform data to be measured. The target correlation coefficient of each segment is used as the weight of the wavelet function of the corresponding expansion amount, and the target correlation coefficient is multiplied by the wavelet function of the corresponding expansion amount, such as a3×g (3 x), b1×g (x) and c2×g (2 x). Finally, the target correlation coefficient of each section is multiplied by the wavelet function of the corresponding expansion and contraction amount, and then the target waveform data, such as target waveform data H (x) =a3×g (3 x) +b1×g (x) +c2×g (2 x), is obtained after addition. It is understood that the target waveform data is a waveform fitted or synthesized according to the wavelet function of the target correlation coefficient and its corresponding expansion/contraction amount, and such a waveform can be regarded as synthesized waveform data. In the application, a wavelet function with highest similarity with each section in the time domain waveform data to be detected is utilized to fit a synthesized waveform data. Because the synthesized waveform data is synthesized by the wavelet function representing the target correlation coefficient closest to the characteristics of each section of the time domain waveform data to be detected and the corresponding expansion amount, the characteristics of the synthesized waveform data can be maximally close to the characteristics of the time domain waveform data to be detected.
According to the method, the target correlation coefficient and the reference waveform are utilized to obtain the target waveform data, the purpose that the characteristic of the synthesized waveform data is closest to the characteristic of each section of the time domain waveform data to be measured and the wavelet function corresponding to the characteristic of the time domain waveform data to be measured are utilized to fit the synthesized waveform data, and the characteristic of the synthesized waveform data can be closest to the characteristic of the time domain waveform data to be measured to the greatest extent. The accuracy of waveform abnormality detection is improved.
In an alternative solution, the detection model is obtained by training a model to be trained by using time domain waveform sample data with a normal waveform data sample tag and a time domain waveform sample data with an abnormal waveform data sample tag, as shown in fig. 6, and includes:
s601: transforming the time domain waveform sample data from the time domain to the frequency domain to obtain a correlation coefficient, wherein the correlation coefficient represents the correlation between the time domain waveform sample data and a reference waveform adopted in the transformation;
in this step, a time domain to frequency domain conversion algorithm is used to convert the time domain to frequency domain waveform sample data. A reference waveform is pre-selected or set when the conversion scheme is performed, and the time domain waveform sample data is transformed from the time domain to the frequency domain based on the reference waveform, so as to obtain a correlation coefficient representing a correlation between the time domain waveform sample data and the reference waveform. The number of the correlation coefficients may be one, two or more, preferably a plurality.
Where the number of correlation coefficients is two or more, it can be understood that: the transformation from time domain to frequency domain is carried out on the same time domain waveform sample data, namely the same time domain waveform sample data is split into a plurality of sections to carry out characteristic analysis. Since there may be a difference in waveform trend for each section, a correlation coefficient is calculated for each section in the present application. The correlation coefficient calculated for all the sections is a set of the correlation coefficients calculated for each section. From this point of view, the number of correlation coefficients is two or more.
In the present application, the correlation of the correlation coefficient characterization may be a similarity between each section of the time domain waveform sample data and the reference waveform. The degree of similarity determines the degree of similarity of features between the segments of the reference waveform and the time domain waveform sample data in the present application. The larger the correlation coefficient, the higher the similarity between the section of the time domain waveform sample data and the reference waveform, i.e. the higher the similarity of the features between the section and the reference waveform. The smaller the correlation coefficient, the lower the similarity between the segment of the time domain waveform sample data and the reference waveform, i.e. the lower the similarity of the features between the two.
S602: obtaining target waveform sample data based on the correlation coefficient and the reference waveform;
in this step, the target waveform sample data is waveform data input to the model to be trained. The target waveform sample data in the application is synthesized waveform data with the overall characteristic similarity exceeding a certain preset threshold value with the time domain waveform sample data.
Based on the correlation coefficient representing the similarity between each section of the time domain waveform sample data and the reference waveform, the synthesized waveform data with the overall characteristic similarity exceeding a certain preset threshold value is obtained, and the characteristics of the time domain waveform sample data can be better analyzed.
S603: inputting target waveform sample data and sample labels of the target waveform sample data into a model to be trained, and training the model to be trained to obtain a detection model; the detection model is used for detecting whether the time domain waveform data to be detected is abnormal waveform data or not.
In the step, the detection model is obtained by training a model to be trained by using target waveform sample data with a normal waveform data sample tag and target waveform sample data with an abnormal waveform data sample tag. Fig. 7 and 8 show normal time-domain waveform sample data and corresponding target waveform sample data, respectively, and in general, there should be only one abrupt point in a falling interval (or rising interval) of one normal time-domain waveform sample data, and there should be only one peak value in the corresponding target waveform sample data. Referring to fig. 9 and 10, the time-domain waveform sample data has two peaks with similar peak values in the corresponding target waveform sample data in one rising section (or falling section). That is, fig. 9 and 10 show abnormal time domain waveform sample data and corresponding target waveform sample data, respectively. Sample data of the target waveform with a normal waveform data sample label and a sample data of the target waveform with an abnormal waveform data sample label are mixed by 80%: the 20% proportion distinguishes a training data set and a test data set, the training data set is used for training a model to be trained, the test data set is used for testing the classification performance of a detection model obtained through training, and the detection accuracy of the detection model can be improved. The target waveform sample data with normal and abnormal labels are adopted to train the model to be trained, and whether the waveform data in the time domain to be detected is abnormal data or not can be detected by utilizing the detection model obtained through training.
According to the method and the device, the model to be trained is trained by utilizing the target waveform sample data with the normal and abnormal labels, so that whether the waveform data in the time domain to be detected is abnormal data or not can be detected by utilizing the detection model obtained through training. Compared with the scheme of relying on manual experience and manually repeatedly checking in the related art, the method improves the detection efficiency and ensures the detection accuracy.
In an alternative solution, the transforming the time domain to frequency domain on the time domain waveform sample data to obtain a correlation coefficient includes:
and carrying out wavelet transformation on the time domain waveform sample data to obtain at least one wavelet coefficient, and taking the at least one wavelet coefficient as a correlation coefficient.
In the application, at least one wavelet coefficient is obtained by performing wavelet transform on time-domain waveform sample data. It will be appreciated that the wavelet function is a waveform of finite duration with an average value of 0. And the wavelet function is typically irregular, asymmetric. The wavelet transformation is to use time domain waveform sample data as standard, and utilize translation transformation and expansion transformation of wavelet function to obtain at least one wavelet coefficient, and the wavelet coefficient is used for representing similarity degree of each section of the time domain waveform sample data and the wavelet function. The calculation method of the wavelet coefficients refers to the foregoing formula (1) and formula (2), and is not repeated.
In the application, the time domain waveform sample data can be divided into a plurality of sections by performing wavelet transform on the time domain waveform sample data, and the wavelet coefficient of each section can be calculated. In colloquial terms, wavelet coefficients represent the degree of similarity of each segment to the wavelet function characteristics. The calculation of the wavelet coefficients can better extract the local characteristics of each section of the time domain waveform sample data, and further better analyze the overall characteristics or the whole characteristics of the time domain waveform sample data.
An embodiment of the present application provides a waveform abnormality detection apparatus, as shown in fig. 11, including:
a first obtaining unit 1101, configured to obtain time domain waveform data to be measured;
the transformation unit 1102 is configured to perform a transformation from a time domain to a frequency domain on the time domain waveform data to be measured, so as to obtain a correlation coefficient, where the correlation coefficient represents a correlation between the time domain waveform data to be measured and a reference waveform used in the transformation;
a second obtaining unit 1103, configured to obtain target waveform data based on the correlation coefficient and the reference waveform;
the detection unit 1104 is configured to input the target waveform data to a detection model, and obtain a detection result of the target waveform data, where the detection result is used to characterize whether the time domain waveform data to be detected is abnormal waveform data; the detection model is obtained by training a model to be trained by using time domain waveform sample data with a normal waveform data sample label and a time domain waveform sample data with an abnormal waveform data sample label.
In an alternative solution, the transforming unit 1102 is configured to perform wavelet transform on the time domain waveform data to be measured to obtain at least one wavelet coefficient, and use the at least one wavelet coefficient as a correlation coefficient.
In an alternative, the first obtaining unit 1101 is configured to obtain initial time domain waveform data; based on a preset interception condition, intercepting the initial time domain waveform data to obtain time domain waveform data to be detected.
In an optional solution, the second obtaining unit 1103 is configured to obtain a target array, based on the correlation coefficient, where the target array characterizes a set of correlation coefficients associated with the time domain waveform data feature to be measured; and obtaining target waveform data based on the target array and the reference waveform.
In an optional solution, the second obtaining unit 1103 is configured to determine a target correlation coefficient in the target array; and obtaining target waveform data based on the target correlation coefficient and the reference waveform.
In an alternative solution, the detecting unit 1104 is configured to perform a transform from the time domain to the frequency domain on the time domain waveform sample data, so as to obtain a correlation coefficient, where the correlation coefficient characterizes a correlation between the time domain waveform sample data and a reference waveform used in the transform; obtaining target waveform sample data based on the correlation coefficient and the reference waveform; inputting target waveform sample data and sample labels of the target waveform sample data into a model to be trained, and training the model to be trained to obtain a detection model; the detection model is used for detecting whether the time domain waveform data to be detected is abnormal waveform data or not.
In an alternative, the detecting unit 1104 is configured to perform wavelet transform on the time domain waveform sample data to obtain at least one wavelet coefficient, and use the at least one wavelet coefficient as a correlation coefficient.
It should be noted that, since the principle of solving the problem of the device according to the embodiment of the present application is similar to that of the foregoing waveform abnormality detection method, the implementation process, implementation principle and beneficial effect of the device may be described with reference to the implementation process, implementation principle and beneficial effect of the foregoing method, and the repetition is omitted.
According to an embodiment of the present application, the present application also provides an electronic device and a readable storage medium.
FIG. 12 shows a schematic block diagram of an example electronic device 1200 that may be used to implement an embodiment of the application. Electronic device 1200 is intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device 1200 may also represent various forms of mobile apparatuses, such as personal digital processing, cellular telephones, smartphones, wearable devices, and other similar computing apparatuses. The components shown herein, their connections and relationships, and their functions, are meant to be exemplary only, and are not meant to limit implementations of the applications described and/or claimed herein.
As shown in fig. 12, the electronic device 1200 includes a computing unit 1201 that can perform various appropriate actions and processes according to a computer program stored in a Read Only Memory (ROM) 1202 or a computer program loaded from a storage unit 1208 into a Random Access Memory (RAM) 1203. In the RAM1203, various programs and data required for the operation of the electronic device 1200 may also be stored. The computing unit 1201, the ROM1202, and the RAM1203 are connected to each other via a bus 1204. An input/output (I/O) interface 1205 is also connected to the bus 1204.
Various components in the electronic device 1200 are connected to the I/O interface 1205, including: an input unit 1206 such as a keyboard, mouse, etc.; an output unit 1207 such as various types of displays, speakers, and the like; a storage unit 1208 such as a magnetic disk, an optical disk, or the like; and a communication unit 1209, such as a network card, modem, wireless communication transceiver, etc. The communication unit 1209 allows the electronic device 1200 to exchange information/data with other devices through a computer network, such as the internet, and/or various telecommunications networks.
The computing unit 1201 may be a variety of general and/or special purpose processing components having processing and computing capabilities. Some examples of computing unit 1201 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various specialized Artificial Intelligence (AI) computing chips, various computing units running machine learning model algorithms, digital Signal Processors (DSPs), and any suitable processor, controller, microcontroller, etc. The computing unit 1201 performs the respective methods and processes described above, for example, the waveform abnormality detection method. For example, in some embodiments, the waveform anomaly detection method may be implemented as a computer software program tangibly embodied on a machine-readable medium, such as storage unit 1208. In some embodiments, part or all of the computer program may be loaded and/or installed onto the electronic device 1200 via the ROM1202 and/or the communication unit 1209. When a computer program is loaded into the RAM1203 and executed by the computing unit 1201, one or more steps of the waveform abnormality detection method described above may be performed. Alternatively, in other embodiments, the computing unit 1201 may be configured to perform the waveform anomaly detection method by any other suitable means (e.g., by means of firmware).
Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuitry, field Programmable Gate Arrays (FPGAs), application Specific Integrated Circuits (ASICs), application Specific Standard Products (ASSPs), systems-on-a-chip (SOCs), complex Programmable Logic Devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs, the one or more computer programs may be executed and/or interpreted on a programmable system including at least one programmable processor, which may be a special purpose or general-purpose programmable processor, that may receive data and instructions from, and transmit data and instructions to, a storage system, at least one input device, and at least one output device.
Program code for carrying out methods of the present application may be written in any combination of one or more programming languages. These program code may be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus such that the program code, when executed by the processor or controller, causes the functions/operations specified in the flowchart and/or block diagram to be implemented. The program code may execute entirely on the machine, partly on the machine, as a stand-alone software package, partly on the machine and partly on a remote machine or entirely on the remote machine or server.
In the context of the present application, a machine-readable medium may be a tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. The machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and pointing device (e.g., a mouse or trackball) by which a user can provide input to the computer. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic input, speech input, or tactile input.
The systems and techniques described here can be implemented in a computing system that includes a background component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such background, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), wide Area Networks (WANs), and the internet.
The computer system may include a client and a server. The client and server are typically remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server may be a cloud server, a server of a distributed system, or a server incorporating a blockchain.
It should be appreciated that various forms of the flows shown above may be used to reorder, add, or delete steps. For example, the steps described in the present application may be performed in parallel, sequentially, or in a different order, so long as the desired results of the technical solution disclosed in the present application can be achieved, and are not limited herein.
Furthermore, the terms "first," "second," and the like, are used for descriptive purposes only and are not to be construed as indicating or implying a relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include at least one such feature. In the description of the present application, the meaning of "a plurality" is two or more, unless explicitly defined otherwise.
The foregoing is merely illustrative of the present application, and the present application is not limited thereto, and any person skilled in the art will readily recognize that variations or substitutions are within the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.
Claims (10)
1. A method for detecting waveform anomalies, the method comprising:
acquiring time domain waveform data to be detected;
transforming the time domain waveform data to be detected from the time domain to the frequency domain to obtain a correlation coefficient, wherein the correlation coefficient represents the correlation between the time domain waveform data to be detected and a reference waveform adopted in the transformation;
obtaining target waveform data based on the correlation coefficient and the reference waveform;
inputting the target waveform data into a detection model to obtain a detection result of the target waveform data, wherein the detection result is used for representing whether the time domain waveform data to be detected is abnormal waveform data or not; the detection model is obtained by training a model to be trained by using time domain waveform sample data with a normal waveform data sample label and a time domain waveform sample data with an abnormal waveform data sample label.
2. The method of claim 1, wherein transforming the waveform data from the time domain to the frequency domain to obtain the correlation coefficient comprises:
and carrying out wavelet transformation on the time domain waveform data to be detected to obtain at least one wavelet coefficient, and taking the at least one wavelet coefficient as a correlation coefficient.
3. The method of claim 1, wherein the acquiring time domain waveform data to be measured comprises:
Acquiring initial time domain waveform data;
based on a preset interception condition, intercepting the initial time domain waveform data to obtain time domain waveform data to be detected.
4. A method according to any one of claims 1 to 3, wherein the obtaining target waveform data based on the correlation coefficient and the reference waveform comprises:
obtaining a target array based on the correlation coefficient, wherein the target array represents a set of correlation coefficients associated with the time domain waveform data characteristics to be detected;
and obtaining target waveform data based on the target array and the reference waveform.
5. The method of claim 4, wherein the obtaining target waveform data based on the target array and a reference waveform comprises:
determining a target correlation coefficient in a target array;
and obtaining target waveform data based on the target correlation coefficient and the reference waveform.
6. A method according to any one of claims 1 to 3, wherein the detection model is derived from training a model to be trained from time-domain waveform sample data with normal waveform data sample labels and with abnormal waveform data sample labels, comprising:
transforming the time domain waveform sample data from the time domain to the frequency domain to obtain a correlation coefficient, wherein the correlation coefficient represents the correlation between the time domain waveform sample data and a reference waveform adopted in the transformation;
Obtaining target waveform sample data based on the correlation coefficient and the reference waveform;
inputting target waveform sample data and sample labels of the target waveform sample data into a model to be trained, and training the model to be trained to obtain a detection model;
the detection model is used for detecting whether the time domain waveform data to be detected is abnormal waveform data or not.
7. The method of claim 6, wherein said transforming the time domain to frequency domain of the time domain waveform sample data to obtain the correlation coefficient comprises:
and carrying out wavelet transformation on the time domain waveform sample data to obtain at least one wavelet coefficient, and taking the at least one wavelet coefficient as a correlation coefficient.
8. A waveform abnormality detection apparatus, characterized by comprising:
the first acquisition unit is used for acquiring time domain waveform data to be detected;
the transformation unit is used for transforming the time domain waveform data to be measured from the time domain to the frequency domain to obtain a correlation coefficient, and the correlation coefficient represents the correlation between the time domain waveform data to be measured and a reference waveform adopted in the transformation;
a second acquisition unit for acquiring target waveform data based on the correlation coefficient and the reference waveform;
The detection unit is used for inputting the target waveform data into a detection model to obtain a detection result of the target waveform data, and the detection result is used for representing whether the time domain waveform data to be detected is abnormal waveform data or not; the detection model is obtained by training a model to be trained by using time domain waveform sample data with a normal waveform data sample label and a time domain waveform sample data with an abnormal waveform data sample label.
9. An electronic device, comprising:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-7.
10. A non-transitory computer readable storage medium storing computer instructions for causing a computer to perform the method of any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311345102.2A CN117077066B (en) | 2023-10-17 | 2023-10-17 | Waveform abnormality detection method, waveform abnormality detection device, electronic device and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311345102.2A CN117077066B (en) | 2023-10-17 | 2023-10-17 | Waveform abnormality detection method, waveform abnormality detection device, electronic device and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117077066A true CN117077066A (en) | 2023-11-17 |
| CN117077066B CN117077066B (en) | 2024-03-12 |
Family
ID=88706577
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311345102.2A Active CN117077066B (en) | 2023-10-17 | 2023-10-17 | Waveform abnormality detection method, waveform abnormality detection device, electronic device and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117077066B (en) |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1920594A (en) * | 2006-05-16 | 2007-02-28 | 中国科学院研究生院 | Wavelet reinforcement based compound aperture radar image method for detecting ship object |
| CN101012746A (en) * | 2006-12-26 | 2007-08-08 | 大庆油田有限责任公司 | Method for prediction of oil well annular tube damage and detecting instrument for implementing the method |
| JP2009300114A (en) * | 2008-06-10 | 2009-12-24 | Toshiba Corp | Waveform display apparatus and waveform display method |
| CN111259269A (en) * | 2020-01-10 | 2020-06-09 | 上海海事大学 | Abnormal point detection method, apparatus and storage medium based on time series data |
| WO2021056724A1 (en) * | 2019-09-23 | 2021-04-01 | 平安科技（深圳）有限公司 | Anomaly detection method and apparatus, electronic device and storage medium |
| CN115186711A (en) * | 2022-07-12 | 2022-10-14 | 联宝(合肥)电子科技有限公司 | Test signal processing method of target device and electronic device |
| CN116304805A (en) * | 2023-02-15 | 2023-06-23 | 合肥联宝信息技术有限公司 | Training method and device of waveform detection model and electronic equipment |
| CN116415161A (en) * | 2023-04-17 | 2023-07-11 | 中交第四航务工程局有限公司 | Fitting complementation method for geological drilling detection and different physical wave detection data of string-shaped karst cave |
| WO2023184918A1 (en) * | 2022-03-31 | 2023-10-05 | 苏州浪潮智能科技有限公司 | Image anomaly detection method, apparatus and system, and readable storage medium |
-
2023
- 2023-10-17 CN CN202311345102.2A patent/CN117077066B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1920594A (en) * | 2006-05-16 | 2007-02-28 | 中国科学院研究生院 | Wavelet reinforcement based compound aperture radar image method for detecting ship object |
| CN101012746A (en) * | 2006-12-26 | 2007-08-08 | 大庆油田有限责任公司 | Method for prediction of oil well annular tube damage and detecting instrument for implementing the method |
| JP2009300114A (en) * | 2008-06-10 | 2009-12-24 | Toshiba Corp | Waveform display apparatus and waveform display method |
| WO2021056724A1 (en) * | 2019-09-23 | 2021-04-01 | 平安科技（深圳）有限公司 | Anomaly detection method and apparatus, electronic device and storage medium |
| CN111259269A (en) * | 2020-01-10 | 2020-06-09 | 上海海事大学 | Abnormal point detection method, apparatus and storage medium based on time series data |
| WO2023184918A1 (en) * | 2022-03-31 | 2023-10-05 | 苏州浪潮智能科技有限公司 | Image anomaly detection method, apparatus and system, and readable storage medium |
| CN115186711A (en) * | 2022-07-12 | 2022-10-14 | 联宝(合肥)电子科技有限公司 | Test signal processing method of target device and electronic device |
| CN116304805A (en) * | 2023-02-15 | 2023-06-23 | 合肥联宝信息技术有限公司 | Training method and device of waveform detection model and electronic equipment |
| CN116415161A (en) * | 2023-04-17 | 2023-07-11 | 中交第四航务工程局有限公司 | Fitting complementation method for geological drilling detection and different physical wave detection data of string-shaped karst cave |
Non-Patent Citations (2)
| Title |
|---|
| 宋彦坡;彭小奇;: "一种基于小波分析的异常数据样本检测与修复方法", 小型微型计算机系统, no. 02, pages 135 - 139 * |
| 张晔;魏然;谷延锋;严萌;: "基于小波变换的光谱异常特征分析及提取技术研究", 新型工业化, no. 01, pages 41 - 48 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117077066B (en) | 2024-03-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Schulz et al. | REDFIT: estimating red-noise spectra directly from unevenly spaced paleoclimatic time series | |
| CN108880931B (en) | Method and apparatus for outputting information | |
| CN108344895B (en) | Signal detection method and device | |
| CN111191671A (en) | Electrical appliance waveform detection method and system, electronic equipment and storage medium | |
| CN117290679A (en) | Running state detection method and device of current transformer and electronic equipment | |
| CN117077066B (en) | Waveform abnormality detection method, waveform abnormality detection device, electronic device and storage medium | |
| CN117593115A (en) | Feature value determining method, device, equipment and medium of credit risk assessment model | |
| CN111784042B (en) | Power utilization node safety risk prediction method and device and storage medium | |
| CN108037420B (en) | Cable joint fault detection equipment based on traveling wave method | |
| US7877219B2 (en) | System and method for analyzing a signal displaying a non-monotonic transition | |
| CN116610912A (en) | Quick detection method and system for electric energy quality based on lifting wavelet and FFT | |
| CN115794473A (en) | Root cause alarm positioning method, device, equipment and medium | |
| CN114764949A (en) | Living body detection method and device | |
| CN114168586A (en) | Abnormal point detection method and device | |
| CN111026989B (en) | Page loading time detection method and device and electronic equipment | |
| EP2799893B1 (en) | Adaptive Frequency-Domain Windowing | |
| CN109783745B (en) | Method, device and computer equipment for personalized typesetting of pages | |
| CN109409232B (en) | Noise source detection method, noise source detection device, computer equipment and storage medium | |
| CN116302897B (en) | Data set establishing method and device, electronic equipment and storage medium | |
| CN111710347A (en) | Audio data analysis method, electronic device and storage medium | |
| CN112527622A (en) | Performance test result analysis method and device | |
| US6697766B2 (en) | System and method for detecting and characterizing gaussian pulses | |
| CN114549941B (en) | Model testing method and device and electronic equipment | |
| CN108318778B (en) | Cable joint fault detection device with self-updating simulation data | |
| CN116684063A (en) | Detection method, detection device, detection equipment and storage medium |
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 |