CN113160110A - Industrial data anomaly detection method and device, terminal device and storage medium - Google Patents
Industrial data anomaly detection method and device, terminal device and storage medium Download PDFInfo
- Publication number
- CN113160110A CN113160110A CN202011493678.XA CN202011493678A CN113160110A CN 113160110 A CN113160110 A CN 113160110A CN 202011493678 A CN202011493678 A CN 202011493678A CN 113160110 A CN113160110 A CN 113160110A
- Authority
- CN
- China
- Prior art keywords
- data
- sample
- category
- detected
- industrial
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 37
- 238000003860 storage Methods 0.000 title claims description 15
- 230000007547 defect Effects 0.000 claims abstract description 69
- 230000002159 abnormal effect Effects 0.000 claims abstract description 41
- 238000004590 computer program Methods 0.000 claims description 24
- 238000000034 method Methods 0.000 claims description 24
- 238000013507 mapping Methods 0.000 claims description 4
- 230000005856 abnormality Effects 0.000 claims description 3
- 238000004364 calculation method Methods 0.000 claims description 3
- 230000008859 change Effects 0.000 claims description 3
- 238000013524 data verification Methods 0.000 claims description 3
- 238000012937 correction Methods 0.000 claims description 2
- 238000012217 deletion Methods 0.000 claims description 2
- 230000037430 deletion Effects 0.000 claims description 2
- 238000010586 diagram Methods 0.000 description 6
- 230000006870 function Effects 0.000 description 5
- 238000012545 processing Methods 0.000 description 5
- 238000004422 calculation algorithm Methods 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000013135 deep learning Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 239000004744 fabric Substances 0.000 description 3
- 238000004891 communication Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000009977 dual effect Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000009776 industrial production Methods 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 229910000831 Steel Inorganic materials 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000004069 differentiation Effects 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 239000002184 metal Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000012827 research and development Methods 0.000 description 1
- 238000000638 solvent extraction Methods 0.000 description 1
- 239000010959 steel Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012706 support-vector machine Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
- G06T7/001—Industrial image inspection using an image reference approach
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10004—Still image; Photographic image
- G06T2207/10012—Stereo images
Abstract
The invention provides an industrial data anomaly detection method, which comprises the steps of firstly, acquiring data of a standard industrial product and acquiring data of an abnormal industrial product; secondly, the data of the standard industrial product is rechecked, and the data of the abnormal industrial product is rechecked; then, calculating and obtaining a high density area and a low density area of the data; identifying the category of the defect sample by dividing the low-density area; and finally, acquiring data of a sample to be detected, and determining the category of the sample to be detected. In the embodiment of the invention, the data are verified to ensure the consistency of the data, so that the defect classification is more accurate when the defects of the industrial products are classified, and the classes of the defect samples are identified by classifying the low-density areas, so that the classes of the defects can be effectively classified; and when the defect detection is carried out on the sample to be detected, the defect type of the sample to be detected can be accurately determined.
Description
Technical Field
The invention relates to the field of machine learning, in particular to a small sample industrial data anomaly detection method and device, terminal equipment and a storage medium.
Background
With the development of the industry in China, the development of industrial automation is more and more rapid. In an industrial production line, the defect detection of a product is an essential step, and the monitoring effect and accuracy affect the performance, efficiency and profit of industrial production. Most of the existing defect detection is in a manual mode, so that a large amount of labor is wasted, errors are easy to occur during detection, particularly small defects are high in error rate and can cause certain damage to vision, and therefore, the research and development of powerful intelligent defect detection technologies are increasingly important.
The deep learning technology is relatively mature at present, has strong universality and robustness, can detect various defects, increases the industrial utilization rate, and becomes an industrialized technology. At present, the defect detection can be quickly and accurately realized by using an algorithm based on deep learning, the application range is wide, the method can be flexibly applied to the production processes of various industries such as buildings, metal firmware, cloth silk fabrics and the like, a better practical effect can be generally obtained, but large data support is required. However, in a defect detection scenario, a large number of defect samples are difficult to obtain, and only a small number of defect samples and a large number of normal samples are obtained, so that unbalanced data is obtained. In this case, the defect detection using a general machine learning algorithm is not effective. For example, a defect sample with a small sample size is trained by using deep learning, which easily causes overfitting; the hyperplane biased to the normal sample set is easily obtained by using a standard support vector machine algorithm, so that the normal samples near the decision hyperplane are identified as defect samples and the like. Therefore, data processing for small samples and unbalanced data sets is of great importance for industrial defect detection.
Disclosure of Invention
In view of the above, the present invention provides a method, an apparatus, an electronic device and a readable storage medium for detecting industrial data anomaly; the data of the abnormal industrial products are effectively screened out by cleaning and density dividing the data of the standard industrial products and the data of the abnormal industrial products, and the defect classification of the abnormal data is effectively realized by further dividing the data of the low-density area, so that the defect of the sample to be detected is quickly classified.
The embodiment of the invention provides an industrial data anomaly detection method which is characterized by comprising the following steps:
acquiring data of the standard industrial product;
acquiring data of the abnormal industrial product;
re-checking the data of the standard industrial product, and re-checking the data of the abnormal industrial product;
calculating and obtaining a high density region and a low density region of the data;
dividing the low-density area, and identifying the category of the defect sample;
acquiring data of a sample to be detected, and determining the category of the sample to be detected.
Further, the data of the standard industrial product is rechecked; re-verifying the data of the abnormal industrial product, further comprising: and performing format content correction and duplicate information deletion on the acquired data of the standard industrial product and/or the acquired data of the abnormal industrial product.
Further, calculating and obtaining a high density region and a low density region of the data further comprises: and mapping the acquired data of the standard industrial product and the acquired data of the abnormal industrial product to a high-dimensional space, and determining the high-density area and the low-density area through the distance value between the data.
Further, the determining of the high density region and the low density region further includes enclosing the high density region in a hypersphere, and taking data of the high density region as standard industrial product data, and data located outside the hypersphere is data of an abnormal industrial product.
Further, the dividing the low-density area and identifying the category of the defect sample further includes: initializing a category center, dividing a low-density area into a plurality of areas, taking each area as a category, and randomly selecting a sample in each category as the category center as an initial point;
establishing a label for each defect sample according to the principle that the distance from the initial point is minimum;
calculating the mean value of all samples in the area as the center of the category;
repeating the steps, knowing that the center change of the category is small, and finishing the classification of the category.
Further, the method further comprises: constructing a hypersphere for each defect sample category, and calculating the distance to the hypersphere of the defect sample category.
Further, when judging whether the sample to be detected has defects, determining the type of the sample to be detected, further comprising: acquiring data of a sample to be detected in a three-dimensional scanning or image recognition mode; and the acquired sample data to be detected is consistent with the data of the standard industrial product and the data type of the abnormal industrial product, the distance from the sample data to be detected to the hypersphere is calculated, and the distance between the sample data to be detected and the hypersphere is compared with the distance between the sample data to be detected and the defect sample type to determine the defect type of the sample to be detected.
A second aspect of an embodiment of the present invention provides an industrial data abnormality detection apparatus, including:
the data acquisition module is used for acquiring the data of the standard industrial product and acquiring the data of the abnormal industrial product;
a data verification module; for re-verifying the data of the standard industrial article; re-verifying the data of the abnormal industrial product;
the calculation module is used for calculating and obtaining the high-density area and the low-density area;
and the classification module is used for dividing the low-density area and identifying the category of the defect sample.
And the judging module is used for judging the category of the sample to be detected and determining the category of the sample to be detected by calculating the distance from the sample to be detected to the hypersphere.
A third aspect of an embodiment of the present invention provides a terminal device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, where the processor implements the steps of the industrial data anomaly detection method according to the first aspect when executing the computer program.
A third aspect of embodiments of the present invention provides a computer-readable storage medium, which stores a computer program, wherein the computer program, when executed by a processor, implements the steps of the industrial data anomaly detection method according to the first aspect.
According to the technical scheme, the embodiment of the invention has the following advantages:
in the embodiment of the invention, firstly, the data of the standard industrial product is obtained, and the data of the abnormal industrial product is obtained; secondly, the data of the standard industrial product is rechecked, and the data of the abnormal industrial product is rechecked; then, calculating and obtaining a high density area and a low density area of the data; identifying the category of the defect sample by dividing the low-density area; and finally, acquiring data of a sample to be detected, and determining the category of the sample to be detected. In the embodiment of the invention, the data are verified to ensure the consistency of the data, so that the defect classification is more accurate when the defects of the industrial products are classified, and the classes of the defect samples are identified by classifying the low-density areas, so that the classes of the defects can be effectively classified; and when the defect detection is carried out on the sample to be detected, the defect type of the sample to be detected can be accurately determined.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the embodiments or the prior art descriptions will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without inventive exercise.
FIG. 1 is a flow chart of a first embodiment of a method for industrial data anomaly detection according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of a hypersphere constructed in an industrial data anomaly detection method according to an embodiment of the present invention;
FIG. 3 is a flowchart of step 105 of a method for detecting industrial data anomalies according to an embodiment of the present invention;
FIG. 4a is a schematic diagram of low density region division in an industrial data anomaly detection method according to an embodiment of the present invention;
FIG. 4b is a schematic diagram of hypersphere division in an industrial data anomaly detection method according to an embodiment of the present invention;
fig. 5 is a schematic diagram of an industrial data exception apparatus according to an embodiment of the present invention.
Fig. 6 is a schematic diagram of a terminal device according to an embodiment of the present invention.
Detailed Description
In the following description, for purposes of explanation and not limitation, specific details are set forth, such as particular system structures, techniques, etc. in order to provide a thorough understanding of the embodiments of the invention. It will be apparent, however, to one skilled in the art that the present invention may be practiced in other embodiments that depart from these specific details. In other instances, detailed descriptions of well-known systems, devices, circuits, and methods are omitted so as not to obscure the description of the present invention with unnecessary detail.
The embodiment of the invention provides an industrial data anomaly detection method, an industrial data anomaly detection device, terminal equipment and a computer storage medium, which effectively solve the defect detection of small sample industrial products.
Referring to fig. 1, a first embodiment of an industrial data anomaly detection method according to an embodiment of the present invention includes:
specifically, the data of the standard industrial product is obtained by detecting an image of the standard industrial product or by three-dimensionally scanning the standard industrial product.
102, acquiring data of the abnormal industrial product;
specifically, the data of the abnormal industrial products are acquired by detecting collected images of various abnormal industrial products or by three-dimensionally scanning standard industrial products.
103, rechecking the data of the standard industrial product; re-verifying the data of the abnormal industrial product;
specifically, the purpose of re-checking the data is to delete duplicate information, correct existing errors, and ensure data consistency. The process of data re-checking mainly comprises deleting repeated values of data, eliminating unreasonable data and correcting self-contradictory contents of the data; processing missing values in the data, judging the principle of the missing values, and filling the missing values with data; and (3) checking the format contents to keep the format contents consistent, correcting the format content problems in the data, and correcting the data under the conditions of different data types, inconsistent time and date formats and the like.
specifically, the method comprises the steps of mapping acquired data of a standard industrial product and acquired data of an abnormal industrial product to a high-dimensional space, wherein the data is the similarity between the distance integral correlation between the data of the standard industrial product and the data of the standard industrial product; thus, after mapping to the high-dimensional space, the distances are closer, and a corresponding high-density region appears.
The data of the abnormal industrial products are different in abnormal conditions, and the data of the abnormal industrial products are different in similarity, so that the distance between the mapped abnormal industrial products and the standard industrial products is large, and corresponding low-density areas can appear after the abnormal industrial products are mapped to a high-dimensional space.
Enclosing the data of the high-density area in a hypersphere, wherein the data positioned in the hypersphere is the data of a standard industrial product, and the data positioned outside the hypersphere is the data of an abnormal industrial product; taking two-dimensional data as an example, as shown in fig. 2, the inner circle is normal sample data, and the outer circle is defect sample data.
Specifically, the manner of constructing the hypersphere is as follows:
a hypersphere with center c and radius R is minimized so that the positive type points are all contained within this sphere. The model is as follows:
where C is a penalty parameter and ξ is a relaxation variable, i.e. allowing a portion of the positive samples to be out of the hypersphere.
The dual problem of the original optimization problem is obtained by using a Lagrange multiplier method, and the problem is a quadratic programming problem.
And solving the dual problem of the original problem according to a quadratic programming problem solving method. And then obtaining the center and the radius of the hypersphere, and constructing the hypersphere which can basically contain all the positive sample points.
And 105, dividing the low-density area, and identifying the type of the defect sample.
Specifically, the low-density area partitioned in step 104 is partitioned into defect types of the abnormal industrial data samples in the low-density area, and the method for partitioning the defect types is as follows:
(A1) initializing a category center, dividing a low-density area into a plurality of areas, taking each area as a category, and randomly selecting a sample in each category as the category center, namely an initial point;
(A2) labeling each defect sample according to the principle that the distance from the selected initial point is minimum;
(A3) the mean of all sample points in the region is calculated as the new center for the class.
(A4) And repeating the steps A2 and A3 until the change of the category center is small, and finishing the classification of the categories.
106, constructing a hypersphere for each defect sample category, and calculating the distance to the hypersphere of the defect sample category;
specifically, a hypersphere is constructed for each defect sample category, the distance between the defect sample category and the center of the hypersphere is calculated, and the distance between the defect sample categories is stored.
And 107, detecting data of a sample to be detected, calculating the distance from the sample to be detected to the hypersphere, and determining the category of the sample to be detected.
Specifically, when the sample to be detected needs to be judged whether to have defects, the data of the sample to be detected is obtained in a three-dimensional scanning or image recognition mode; and the acquired sample data to be detected is consistent with the data of the standard industrial product and the data type of the abnormal industrial product, the distance from the sample data to be detected to the hypersphere is calculated, and the distance is compared with the distance of the defect sample type to determine the defect type of the sample to be detected.
Further, when the distance from the sample to be detected to the hypersphere is judged, and the type of the sample to be detected is determined, the distance from the sample to be detected to the hypersphere is compared with the distance from the sample to be detected to the type of the defect, a threshold interval is set, when the difference value between the distance from the sample to be detected to the hypersphere and the distance from the sample to be detected to the type of the defect is within the threshold interval, the sample to be detected is of the defect type, and if the difference value is not within the threshold interval, other corresponding defect types are matched; and if the hypersphere distance of the sample to be detected cannot be matched in the current defect types, dividing the sample to be detected into new types for storage.
In the embodiment of the invention, the data of the standard industrial product and the data of the abnormal industrial product are divided into the high-density area and the low-density area to determine the differentiation boundary, and the category of the defect sample is identified by further dividing the low-density area; the method can be used for detecting the defect samples in the fields of cloth, liquid crystal screens, mobile phone screens, steel surfaces and the like.
An embodiment of an industrial data anomaly detection apparatus according to an embodiment of the present invention includes:
a data acquisition module 201, configured to acquire data of the standard industrial product and acquire data of the abnormal industrial product;
a data verification module 202; for re-verifying the data of the standard industrial article; re-verifying the data of the abnormal industrial product;
the calculation module 203 calculates and obtains the high-density area and the low-density area;
and the classification module 204 is used for dividing the low-density area and identifying the category of the defect sample.
The judging module 205 is configured to judge the category of the sample to be detected, and determine the category of the sample to be detected by calculating a distance from the sample to be detected to the hypersphere.
An embodiment of the present invention further provides a terminal device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, where the processor implements the steps of any industrial data anomaly detection method shown in fig. 1 to 3 when executing the computer program.
An embodiment of the present invention further provides a computer-readable storage medium, which stores a computer program, and when the computer program is executed by a processor, the computer program implements the steps of any one of the industrial data anomaly detection methods shown in fig. 1 to 3.
Fig. 6 is a schematic diagram of a terminal device according to an embodiment of the present invention. As shown in fig. 6, the terminal device 5 of this embodiment includes: a processor 50, a memory 51 and a computer program 52 stored in said memory 51 and executable on said processor 50. The processor 50, when executing the computer program 52, implements the steps in the embodiments of the robot wake-up method described above, such as the steps 101 to 104 shown in fig. 1. Alternatively, the processor 50, when executing the computer program 52, implements the functions of each module/unit in the above-mentioned device embodiments, for example, the functions of the modules 201 to 204 shown in fig. 5.
The computer program 52 may be divided into one or more modules/units, which are stored in the memory 51 and executed by the processor 50 to accomplish the present invention. The one or more modules/units may be a series of computer program instruction segments capable of performing specific functions, which are used to describe the execution process of the computer program 52 in the terminal device 5.
The terminal device 5 may be various types of computing devices such as a mobile phone, a desktop computer, a notebook, a palm computer, and a cloud server. The terminal device may include, but is not limited to, a processor 50, a memory 51. It will be understood by those skilled in the art that fig. 5 is only an example of the terminal device 5, and does not constitute a limitation to the terminal device 5, and may include more or less components than those shown, or combine some components, or different components, for example, the terminal device 5 may further include an input-output device, a network access device, a bus, etc.
The Processor 50 may be a Central Processing Unit (CPU), other general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), an off-the-shelf Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic, discrete hardware components, etc. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
The memory 51 may be an internal storage unit of the terminal device 5, such as a hard disk or a memory of the terminal device 5. The memory 51 may also be an external storage device of the terminal device 5, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), and the like, which are provided on the terminal device 5. Further, the memory 51 may also include both an internal storage unit and an external storage device of the terminal device 5. The memory 51 is used for storing the computer program and other programs and data required by the terminal device. The memory 51 may also be used to temporarily store data that has been output or is to be output.
It will be apparent to those skilled in the art that, for convenience and brevity of description, only the above-mentioned division of the functional units and modules is illustrated, and in practical applications, the above-mentioned function distribution may be performed by different functional units and modules according to needs, that is, the internal structure of the apparatus is divided into different functional units or modules to perform all or part of the above-mentioned functions. Each functional unit and module in the embodiments may be integrated in one processing unit, or each unit may exist alone physically, or two or more units are integrated in one unit, and the integrated unit may be implemented in a form of hardware, or in a form of software functional unit. In addition, specific names of the functional units and modules are only for convenience of distinguishing from each other, and are not used for limiting the protection scope of the present application.
It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described systems, apparatuses and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
In the above embodiments, the descriptions of the respective embodiments have respective emphasis, and reference may be made to the related descriptions of other embodiments for parts that are not described or illustrated in a certain embodiment.
Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
In the embodiments provided in the present invention, it should be understood that the disclosed apparatus and method may be implemented in other ways. For example, the above-described system embodiments are merely illustrative, and for example, the division of the modules or units is only one logical division, and there may be other divisions when actually implemented, for example, a plurality of units or components may be combined or may be integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, all or part of the flow of the method according to the embodiments of the present invention may also be implemented by a computer program, which may be stored in a computer-readable storage medium, and when the computer program is executed by a processor, the steps of the method embodiments may be implemented. Wherein the computer program comprises computer program code, which may be in the form of source code, object code, an executable file or some intermediate form, etc. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, usb disk, removable hard disk, magnetic disk, optical disk, computer Memory, Read-Only Memory (ROM), Random Access Memory (RAM), electrical carrier wave signals, telecommunications signals, software distribution medium, and the like. It should be noted that the computer readable medium may contain other components which may be suitably increased or decreased as required by legislation and patent practice in jurisdictions, for example, in some jurisdictions, computer readable media which may not include electrical carrier signals and telecommunications signals in accordance with legislation and patent practice.
The above-mentioned embodiments are only used for illustrating the technical solutions of the present invention, and not for limiting the same; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; such modifications and substitutions do not substantially depart from the spirit and scope of the embodiments of the present invention, and are intended to be included within the scope of the present invention.
Claims (10)
1. An industrial data anomaly detection method, comprising:
acquiring data of a standard industrial product;
acquiring data of abnormal industrial products;
re-checking the data of the standard industrial product, and re-checking the data of the abnormal industrial product;
calculating and obtaining a high density region and a low density region of the data;
dividing the low-density area, and identifying the category of the defect sample;
acquiring data of a sample to be detected, and determining the category of the sample to be detected.
2. The industrial data anomaly detection method according to claim 1, characterized in that said standard industrial article data is re-checked; re-verifying the data of the abnormal industrial product, further comprising: and performing format content correction and duplicate information deletion on the acquired data of the standard industrial product and/or the acquired data of the abnormal industrial product.
3. The industrial data anomaly detection method of claim 1, wherein calculating and obtaining high density regions and low density regions of said data further comprises: and mapping the acquired data of the standard industrial product and the acquired data of the abnormal industrial product to a high-dimensional space, and determining the high-density area and the low-density area through the distance value between the data.
4. The industrial data abnormality detection method according to claim 3, wherein the determination of the high-density region and the low-density region further includes enclosing the high-density region in a hypersphere, and using data of the high-density region as standard industrial product data, and data located outside the hypersphere is data of an abnormal industrial product.
5. The method for detecting industrial data anomalies according to claim 1, wherein the classifying the low-density regions to identify the category of the defect samples further comprises: initializing a category center, dividing a low-density area into a plurality of areas, taking each area as a category, and randomly selecting a sample in each category as the category center as an initial point;
establishing a label for each defect sample according to the principle that the distance from the initial point is minimum;
calculating the mean value of all samples in the area as the center of the category;
repeating the steps, knowing that the center change of the category is small, and finishing the classification of the category.
6. The industrial data anomaly detection method according to claim 5, said method further comprising: constructing a hypersphere for each defect sample category, and calculating the distance to the hypersphere of the defect sample category.
7. The method for detecting industrial data abnormality according to claim 1, wherein determining the category of the sample to be detected when judging whether the sample to be detected has a defect, further comprises: acquiring data of a sample to be detected in a three-dimensional scanning or image recognition mode; and the acquired sample data to be detected is consistent with the data of the standard industrial product and the data type of the abnormal industrial product, the distance from the sample data to be detected to the hypersphere is calculated, and the distance between the sample data to be detected and the hypersphere is compared with the distance between the sample data to be detected and the defect sample type to determine the defect type of the sample to be detected.
8. An industrial data anomaly detection device characterized in that:
the data acquisition module is used for acquiring the data of the standard industrial product and acquiring the data of the abnormal industrial product;
a data verification module; for re-verifying the data of the standard industrial article; re-verifying the data of the abnormal industrial product;
the calculation module is used for calculating and obtaining the high-density area and the low-density area;
and the classification module is used for dividing the low-density area and identifying the category of the defect sample.
And the judging module is used for judging the category of the sample to be detected and determining the category of the sample to be detected by calculating the distance from the sample to be detected to the hypersphere.
9. A terminal device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that the processor implements the steps of the industrial data anomaly detection method according to any one of claims 1 to 7 when executing the computer program.
10. A computer-readable storage medium, in which a computer program is stored which, when being executed by a processor, carries out the steps of the industrial data anomaly detection method according to any one of claims 1 to 7.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011493678.XA CN113160110A (en) | 2020-12-17 | 2020-12-17 | Industrial data anomaly detection method and device, terminal device and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011493678.XA CN113160110A (en) | 2020-12-17 | 2020-12-17 | Industrial data anomaly detection method and device, terminal device and storage medium |
Publications (1)
Publication Number | Publication Date |
---|---|
CN113160110A true CN113160110A (en) | 2021-07-23 |
Family
ID=76882604
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202011493678.XA Pending CN113160110A (en) | 2020-12-17 | 2020-12-17 | Industrial data anomaly detection method and device, terminal device and storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113160110A (en) |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105894036A (en) * | 2016-04-19 | 2016-08-24 | 武汉大学 | Image feature template matching method being applied to detection of mobile phone screen defects |
US20170193078A1 (en) * | 2016-01-06 | 2017-07-06 | International Business Machines Corporation | Hybrid method for anomaly Classification |
CN108945514A (en) * | 2018-06-19 | 2018-12-07 | 中国航空工业集团公司北京长城航空测控技术研究所 | A kind of condition detection method based on aircraft parameter data |
CN109724994A (en) * | 2017-10-30 | 2019-05-07 | 东莞理工学院 | FPC golden finger surface defects detection system and method based on AOI technology |
CN111145175A (en) * | 2020-01-10 | 2020-05-12 | 惠州光弘科技股份有限公司 | SMT welding spot defect detection method based on iForest model verification |
CN111652319A (en) * | 2020-06-09 | 2020-09-11 | 创新奇智(广州)科技有限公司 | Cloth defect detection method and device |
CN111709907A (en) * | 2020-04-26 | 2020-09-25 | 江南大学 | Cloth defect detection method based on One-Class deep support vector description |
-
2020
- 2020-12-17 CN CN202011493678.XA patent/CN113160110A/en active Pending
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20170193078A1 (en) * | 2016-01-06 | 2017-07-06 | International Business Machines Corporation | Hybrid method for anomaly Classification |
CN105894036A (en) * | 2016-04-19 | 2016-08-24 | 武汉大学 | Image feature template matching method being applied to detection of mobile phone screen defects |
CN109724994A (en) * | 2017-10-30 | 2019-05-07 | 东莞理工学院 | FPC golden finger surface defects detection system and method based on AOI technology |
CN108945514A (en) * | 2018-06-19 | 2018-12-07 | 中国航空工业集团公司北京长城航空测控技术研究所 | A kind of condition detection method based on aircraft parameter data |
CN111145175A (en) * | 2020-01-10 | 2020-05-12 | 惠州光弘科技股份有限公司 | SMT welding spot defect detection method based on iForest model verification |
CN111709907A (en) * | 2020-04-26 | 2020-09-25 | 江南大学 | Cloth defect detection method based on One-Class deep support vector description |
CN111652319A (en) * | 2020-06-09 | 2020-09-11 | 创新奇智(广州)科技有限公司 | Cloth defect detection method and device |
Non-Patent Citations (1)
Title |
---|
李建国等: "高效的混合聚类算法及其在异常检测中的应用", 《计算机应用》 * |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109886928B (en) | Target cell marking method, device, storage medium and terminal equipment | |
CN110909712B (en) | Moving object detection method and device, electronic equipment and storage medium | |
CN109697468B (en) | Sample image labeling method and device and storage medium | |
CN108955901B (en) | Infrared temperature measurement method and system and terminal equipment | |
WO2023130717A1 (en) | Image positioning method and apparatus, computer device and storage medium | |
CN113449703B (en) | Quality control method and device for environment online monitoring data, storage medium and equipment | |
CN114169381A (en) | Image annotation method and device, terminal equipment and storage medium | |
CN114414935A (en) | Automatic positioning method and system for feeder fault area of power distribution network based on big data | |
CN112014413A (en) | Mobile phone glass cover plate window area defect detection method based on machine vision | |
WO2023029491A1 (en) | Panel array short circuit detection method and apparatus, electronic device, and storage medium | |
CN113963033B (en) | Power equipment abnormality detection method and system based on artificial intelligence | |
CN112085721A (en) | Damage assessment method, device and equipment for flooded vehicle based on artificial intelligence and storage medium | |
CN111626360A (en) | Method, device, equipment and storage medium for detecting fault type of boiler | |
CN114881996A (en) | Defect detection method and device | |
CN108960246B (en) | Binarization processing device and method for image recognition | |
CN107316296A (en) | A kind of method for detecting change of remote sensing image and device based on logarithmic transformation | |
CN111680680B (en) | Target code positioning method and device, electronic equipment and storage medium | |
CN113723467A (en) | Sample collection method, device and equipment for defect detection | |
CN108564571B (en) | Image area selection method and terminal equipment | |
CN113160110A (en) | Industrial data anomaly detection method and device, terminal device and storage medium | |
CN114913350B (en) | Material duplicate checking method, device, equipment and storage medium | |
Liu et al. | A real-time and precise ellipse detector via edge screening and aggregation | |
CN117392042A (en) | Defect detection method, defect detection apparatus, and storage medium | |
CN115063473A (en) | Object height detection method and device, computer equipment and storage medium | |
CN111401383B (en) | Target frame estimation method, system, device and medium based on image detection |
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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210723 |
|
RJ01 | Rejection of invention patent application after publication |