Layout wiring checking method based on machine learning

Abstract

The invention discloses a layout wiring checking method based on machine learning, and relates to the technical field of power grid distribution line single line diagrams. The method comprises the following steps: step 1, constructing a checking model of a basic target, and perfecting the checking model by adopting a machine learning process, so that the checking model effectively integrates historical data, and according to the layout and wiring checking method based on machine learning, the historical data is effectively integrated through the checking model, so that the checking efficiency is improved; the problems that a checking model cannot fully learn knowledge borne by historical data and the model excessively learns noise information in the historical data are avoided, the accuracy of data collection is improved, a multi-dimensional checking means is used under the condition that a checking rule is solidified, the problems of single checking angle, incomplete checking and the like in the past are technically solved, and the checking efficiency is improved. A more comprehensive checking technical means is provided for checking the distribution network model; intelligent verification is carried out according to a specified rule, and friendly and clear verification and analysis result display are provided while less / no manual intervention is realized.

Description

Technical Field

[0001] The present invention relates to the technical field of single-line diagrams of power grid distribution lines, and in particular to a layout and wiring verification method based on machine learning. Background Art

[0002] At present, the distribution network diagram and single-line diagram verification tools used by various units are mostly developed from the perspective of distribution network automation system and production system to solve the problem of receiving functional position (production system) and diagram interaction file (distribution network automation system) of the system. The verification perspective is single and the verification information is incomplete. The distribution network single-line diagram verification tools used by various units are based on business applications. They are used to verify the terminal data provided by the GIS platform after it is converted into "cooked data" in the system. They cannot perform verification and verification on the GIS platform source data. The verification results cannot be deeply integrated with the power grid GIS platform, nor can they be linked with the GIS layout. The problem location is limited to the business system and it is difficult to trace the source. The identification and layout of the single-line diagram model have different requirements for the establishment of the model due to the different map requirements of various professions.

[0003] This project intends to improve the efficiency of GIS data quality verification and map adjustment through machine learning technology, promote departmental collaboration and lean management of data quality improvement work, and provide auxiliary tools for electronic transfer of basic information rectification, GIS single-line diagram adjustment, and scheduling review. Summary of the invention

[0004] 1. Technical issues to be resolved

[0005] In view of the deficiencies in the prior art, the present invention provides a layout and routing verification method based on machine learning, which solves the problems mentioned in the above background technology.

[0006] (II) Technical solution

[0007] To achieve the above objectives, the present invention is implemented through the following technical solutions: a layout and routing verification method based on machine learning, comprising:

[0008] Step 1: construct a verification model of the basic target, and use a machine learning process to improve the verification model so that the verification model can effectively integrate historical data and detect fault points in the machine learning process, wherein the basic target is specifically a single-line diagram of a power distribution line of a power grid;

[0009] Step 2: extracting a low-light image of a single-line diagram of a power distribution line of a power grid, performing enhancement processing on the image, and setting verification rules so that the single-line diagram of the power distribution line of a power grid can be automatically verified and displayed, wherein the specific method of the enhancement processing is image feature enhancement;

[0010] Step three: Establish a verification rule base from multiple perspectives, solidify the verification rule base, analyze the verification results of the power grid distribution line single-line diagram, and synchronously display the reviewer's information, wherein the verification rule base is a comparison database.

[0011] As an improved technical solution, the machine learning process is used in step 1 to improve the verification model, so that the verification model can effectively integrate historical data in the following specific ways:

[0012] S1: First, the collected historical data is marked as Hj, where j is the collection sequence number of the historical data, and then a machine learning data standard YH is established. In the process of collecting historical data Hj, data that meets the standard data YH is automatically identified and stored;

[0013] S2: Then verify the collected standard data YH, randomly select a data segment SH from the standard data YH, and search the data segment SH. If they are consistent, the standard data YH is valid. If there is one inconsistency with the previous data, all standard data YH need to be verified, and the data that is consistent before and after the verification is retained.

[0014] As an improved technical solution, the specific method of detecting the fault point in the machine learning process in the step one is: using a Gaussian mixture model to make the data set obey a certain special distribution or probability model, and then judging whether the data is an abnormal point by comparing the deviation between the data and the distribution, setting a judgment value PC, if the deviation exceeds the judgment value PC, it is judged as an abnormal point, otherwise, it is a normal point.

[0015] As an improved technical solution, the specific method of extracting the low-light image of the single-line diagram of the power grid distribution line in step 2 and enhancing it is as follows:

[0016] Extract from the texture features and frequency domain features of the image. The specific formula is as follows:

[0017]

[0018] In the formula, P represents the overall mean of the image, B n The random variable representing the pixel reflection value, F(B n ) represents the image histogram, n represents the number of image pixels, the larger the image mean P is, the brighter the image is, and vice versa, the smaller P is, the darker the image is.

[0019] As an improved technical solution, the low-illumination image enhancement processing method is to adopt an illumination component optimization method.

[0020] As an improved technical solution, the specific method of analyzing the verification result of the power grid distribution line single-line diagram in step 3 is:

[0021] P1: First, the single-line diagram of the power distribution line is obtained through the server interface, and then the verification data standard TR is set, the obtained single-line diagram of the power distribution line is compared with the verification data standard TR, and the difference data is marked and recorded as CH;

[0022] P2: The data that has passed the verification is then repaired with reference to the difference data CH for auxiliary data repair, and the repaired power grid distribution line single-line diagram is stored in the file library. When the power grid distribution line single-line diagram is compared with the verification data standard TR and is consistent, it is directly stored in the file library.

[0023] As an improved technical solution, when the information of the reviewers is synchronously displayed in step three, the reviewer may be one person or multiple people. When conducting a second review, the number of reviewers and the review time are synchronously displayed.

[0024] As an improved technical solution, when the obtained single-line diagram of the power distribution line of the power grid is compared with the verification data standard TR in P1, manual verification or automatic verification is adopted.

[0025] (III) Beneficial effects

[0026] The present invention provides a layout and routing verification method based on machine learning. Compared with the prior art, it has the following beneficial effects:

[0027] This layout and routing verification method based on machine learning effectively integrates historical data through the verification model to avoid the verification model failing to fully learn the knowledge carried by the historical data, and the model over-learning the noise information in the historical data, thereby improving the accuracy of data collection. It also uses multi-dimensional verification methods when the verification rules are solidified, technically solving the previous problems of single verification angle and incomplete verification, and providing a more comprehensive verification technology for distribution network model verification. It also conducts intelligent verification according to specified rules to reduce / avoid manual intervention while providing a friendly and clear display of verification and analysis results. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] Figure 1 A flow chart of a layout and routing verification method based on machine learning shown in an embodiment of the present application;

[0029] Figure 2 This is a schematic diagram of the structure of an electronic device shown in an embodiment of the present application. DETAILED DESCRIPTION

[0030] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0031] See also Figure 1-Figure 2 , the embodiment of the present invention provides four technical solutions:

[0032] Embodiment 1

[0033] A layout and routing verification method based on machine learning, comprising:

[0034] Step 1: Construct a verification model for the basic target, and use the machine learning process to improve the verification model so that the verification model can effectively integrate historical data and detect fault points in the machine learning process. The basic target is specifically the single-line diagram of the power distribution line of the power grid. In step 1, the verification model is improved by using the machine learning process so that the verification model can effectively integrate historical data in the following specific ways:

[0035] S1: First, the collected historical data is marked as Hj, where j is the collection sequence number of the historical data, and then a machine learning data standard YH is established. In the process of collecting historical data Hj, data that meets the standard data YH is automatically identified and stored;

[0036] S2: Then verify the collected standard data YH, randomly select a data segment SH from the standard data YH, and search the data segment SH. If they are consistent, the standard data YH is valid. If there is one inconsistency with the previous data, all standard data YH need to be verified, and the data that is consistent before and after the verification is retained.

[0037] The specific method of detecting the fault points in the machine learning process in step 1 is: using a Gaussian mixture model to make the data set obey a special distribution or probability model, and then judging whether the data is an abnormal point by comparing the deviation between the data and the distribution, setting the judgment value PC, if the deviation exceeds the judgment value PC, it is judged as an abnormal point, otherwise, it is a normal point.

[0038] Step 2: extract the low-light image of the power grid distribution line single-line diagram, enhance it, and set the verification rules so that the power grid distribution line single-line diagram performs automatic verification and display, wherein the specific method of the enhancement processing is image feature enhancement; the specific method of extracting the low-light image of the power grid distribution line single-line diagram and enhancing it in step 2 is:

[0039] Extract from the texture features and frequency domain features of the image. The specific formula is as follows:

[0040]

[0041] In the formula, P represents the overall mean of the image, B n The random variable representing the pixel reflectance value, F(B n ) represents the image histogram, n represents the number of image pixels, the larger the image mean P is, the brighter the image is, and vice versa, the smaller P is, the darker the image is. The low-light image enhancement processing method is to use the illumination component optimization method.

[0042] Step 3: Establish a verification rule base with multiple perspectives, solidify the verification rule base, analyze the verification results of the power grid distribution line single-line diagram, and synchronously display the information of the reviewer. The verification rule base is a comparison database. The specific method of analyzing the verification results of the power grid distribution line single-line diagram in step 3 is:

[0043] P1: First, the power grid distribution line single-line diagram is obtained through the server interface, and then the verification data standard TR is set, and the obtained power grid distribution line single-line diagram is compared with the verification data standard TR, and the difference data is marked and recorded as CH; when the obtained power grid distribution line single-line diagram is compared with the verification data standard TR in P1, manual verification or automatic verification is adopted;

[0044] P2: The data that has passed the verification is then repaired with reference to the difference data CH for auxiliary data repair, and the repaired power grid distribution line single-line diagram is stored in the file library. When the power grid distribution line single-line diagram is compared with the verification data standard TR and is consistent, it is directly stored in the file library.

[0045] When the information of the reviewer is displayed synchronously in step 3, the reviewer may be one person or multiple people. When conducting a second review, the number of reviewers and the review time are displayed synchronously.

[0046] Embodiment 2

[0047] A layout and routing verification method based on machine learning, comprising:

[0048] Step 1: Construct a verification model for the basic target, and use the machine learning process to improve the verification model so that the verification model can effectively integrate historical data and detect fault points in the machine learning process. The basic target is specifically the single-line diagram of the power distribution line of the power grid. In step 1, the verification model is improved by using the machine learning process so that the verification model can effectively integrate historical data in the following specific ways:

[0049] S1: First, the collected historical data is marked as Hj, where j is the collection sequence number of the historical data, and then a machine learning data standard YH is established. In the process of collecting historical data Hj, data that meets the standard data YH is automatically identified and stored;

[0050] S2: Then verify the collected standard data YH, randomly select a data segment SH from the standard data YH, and search the data segment SH. If they are consistent, the standard data YH is valid. If there is one inconsistency with the previous data, all standard data YH need to be verified, and the data that is consistent before and after the verification is retained.

[0051] The specific method of detecting the fault points in the machine learning process in step 1 is: using a Gaussian mixture model to make the data set obey a special distribution or probability model, and then judging whether the data is an abnormal point by comparing the deviation between the data and the distribution, setting the judgment value PC, if the deviation exceeds the judgment value PC, it is judged as an abnormal point, otherwise, it is a normal point.

[0052] Step 2: extract the low-light image of the power grid distribution line single-line diagram, enhance it, and set the verification rules so that the power grid distribution line single-line diagram performs automatic verification and display, wherein the specific method of the enhancement processing is image feature enhancement; the specific method of extracting the low-light image of the power grid distribution line single-line diagram and enhancing it in step 2 is:

[0053] Extract from the texture features and frequency domain features of the image. The specific formula is as follows:

[0054]

[0055] In the formula, P represents the overall mean of the image, B n The random variable representing the pixel reflectance value, F(B n ) represents the image histogram, n represents the number of image pixels, the larger the image mean P is, the brighter the image is, and vice versa, the smaller P is, the darker the image is. The low-light image enhancement processing method is to use the illumination component optimization method.

[0056] Embodiment 3

[0057] A layout and routing verification method based on machine learning, comprising:

[0058] Step 1: construct a verification model of the basic target, and use a machine learning process to improve the verification model so that the verification model can effectively integrate historical data and detect fault points in the machine learning process, wherein the basic target is specifically a single-line diagram of a power distribution line of a power grid;

[0059] Step 2: extracting a low-light image of a single-line diagram of a power distribution line of a power grid, performing enhancement processing on the image, and setting verification rules so that the single-line diagram of the power distribution line of a power grid can be automatically verified and displayed, wherein the specific method of the enhancement processing is image feature enhancement;

[0060] Step three: Establish a verification rule base from multiple perspectives, solidify the verification rule base, analyze the verification results of the power grid distribution line single-line diagram, and synchronously display the reviewer's information, wherein the verification rule base is a comparison database.

[0061] Meanwhile, the contents not described in detail in this specification belong to the prior art known to those skilled in the art.

[0062] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0063] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

[0064] Embodiment 4

[0065] Corresponding to the aforementioned application function implementation method embodiment, the present application also provides an electronic device and corresponding embodiments.

[0066] See also Figure 2 , the electronic device 1000 includes a memory 1010 and a processor 1020 .

[0067] The processor 1020 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or the processor may be any conventional processor, etc.

[0068] The memory 1010 may include various types of storage units, such as system memory, read-only memory (ROM), and permanent storage devices. Among them, ROM can store static data or instructions required by the processor 1020 or other modules of the computer. The permanent storage device may be a readable and writable storage device. The permanent storage device may be a non-volatile storage device that does not lose the stored instructions and data even after the computer is powered off. In some embodiments, the permanent storage device uses a large-capacity storage device (such as a magnetic or optical disk, flash memory) as a permanent storage device. In some other embodiments, the permanent storage device may be a removable storage device (such as a floppy disk, optical drive). The system memory may be a readable and writable storage device or a volatile readable and writable storage device, such as a dynamic random access memory. The system memory may store some or all instructions and data required by the processor at run time. In addition, the memory 1010 may include any combination of computer-readable storage media, including various types of semiconductor memory chips (DRAM, SRAM, SDRAM, flash memory, programmable read-only memory), and disks and / or optical disks may also be used. In some embodiments, the memory 1010 may include a readable and / or writable removable storage device, such as a laser disc (CD), a read-only digital versatile disc (such as a DVD-ROM, a double-layer DVD-ROM), a read-only Blu-ray disc, an ultra-density optical disc, a flash memory card (such as an SD card, a mini SD card, a Micro-SD card, etc.), a magnetic floppy disk, etc. The computer-readable storage medium does not include carrier waves and transient electronic signals transmitted wirelessly or wired.

[0069] The memory 1010 stores executable codes, and when the executable codes are processed by the processor 1020 , the processor 1020 can execute part or all of the methods described above.

[0070] The scheme of the present application has been described in detail above with reference to the accompanying drawings. In the above embodiments, the description of each embodiment has its own emphasis. For the part that is not described in detail in a certain embodiment, refer to the relevant description of other embodiments. Those skilled in the art should also know that the actions and modules involved in the description are not necessarily required for the present application. In addition, it can be understood that the steps in the method of the embodiment of the present application can be adjusted in order, merged and deleted according to actual needs, and the modules in the device of the embodiment of the present application can be merged, divided and deleted according to actual needs.

[0071] In addition, the method according to the present application may also be implemented as a computer program or a computer program product, which includes computer program code instructions for executing some or all of the steps in the above method of the present application.

[0072] Alternatively, the present application can also be implemented as a non-temporary machine-readable storage medium (or computer-readable storage medium, or machine-readable storage medium) on which executable code (or computer program, or computer instruction code) is stored. When the executable code (or computer program, or computer instruction code) is executed by a processor of an electronic device (or electronic device, server, etc.), the processor executes part or all of the steps of the above-mentioned method according to the present application.

[0073] Those skilled in the art will further appreciate that the various illustrative logical blocks, modules, circuits, and algorithm steps described in connection with the application herein may be implemented as electronic hardware, computer software, or combinations of both.

[0074] The flow chart and block diagram in the accompanying drawings show the possible architecture, function and operation of the system and method according to multiple embodiments of the present application. In this regard, each square box in the flow chart or block diagram can represent a part of a module, a program segment or a code, and the part of the module, the program segment or the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two continuous square boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or the flow chart, and the combination of the square boxes in the block diagram and / or the flow chart can be implemented with a dedicated hardware-based system that performs the specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0075] The embodiments of the present application have been described above, and the above description is exemplary, not exhaustive, and is not limited to the disclosed embodiments. Many modifications and changes will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The selection of terms used herein is intended to best explain the principles of the embodiments, practical applications, or improvements to the technology in the market, or to enable other persons of ordinary skill in the art to understand the embodiments disclosed herein.

Claims

1. A layout and routing verification method based on machine learning, characterized in that: include: Step 1: construct a verification model of the basic target, and use a machine learning process to improve the verification model so that the verification model can effectively integrate historical data and detect fault points in the machine learning process, wherein the basic target is specifically a single-line diagram of a power distribution line of a power grid; Step 2: extracting a low-light image of a power grid distribution line single-line diagram, performing enhancement processing on it, and setting verification rules so that the power grid distribution line single-line diagram performs automatic verification and display, wherein the specific method of the enhancement processing is image feature enhancement; Step three: Establish a verification rule base from multiple perspectives, solidify the verification rule base, analyze the verification results of the power grid distribution line single-line diagram, and synchronously display the reviewer's information, wherein the verification rule base is a comparison database.

2. The layout and routing verification method based on machine learning according to claim 1, characterized in that: In the step 1, the machine learning process is used to improve the verification model, so that the verification model can effectively integrate the historical data in the following specific manner: S1: First, the collected historical data is marked as Hj, where j is the collection sequence number of the historical data, and then a machine learning data standard YH is established. In the process of collecting historical data Hj, data that meets the standard data YH is automatically identified and stored; S2: Then verify the collected standard data YH, randomly select a data segment SH from the standard data YH, and search the data segment SH. If they are consistent, the standard data YH is valid. If there is one inconsistency with the previous data, all standard data YH need to be verified, and the data that is consistent before and after the verification is retained.

3. The layout and routing verification method based on machine learning according to claim 1, characterized in that: The specific method for detecting the fault point in the machine learning process in the step 1 is: using a Gaussian mixture model to make the data set obey a certain special distribution or probability model, and then judging whether the data is an abnormal point by comparing the deviation between the data and the distribution, setting a judgment value PC, if the deviation exceeds the judgment value PC, it is judged as an abnormal point, otherwise, it is a normal point.

4. The layout and routing verification method based on machine learning according to claim 1, characterized in that: The specific method of extracting the low-light image of the single-line diagram of the power grid distribution line in the step 2 and performing enhancement processing on it is as follows: Extract from the texture features and frequency domain features of the image. The specific formula is as follows: In the formula, P represents the overall mean of the image, B n The random variable representing the pixel reflectance value, F(B n ) represents the image histogram, n represents the number of image pixels, the larger the image mean P is, the brighter the image is, and vice versa, the smaller P is, the darker the image is.

5. The layout and routing verification method based on machine learning according to claim 4, characterized in that: The low-illumination image enhancement processing method is to adopt an illumination component optimization method.

6. The layout and routing verification method based on machine learning according to claim 1, characterized in that: The specific method of analyzing the verification result of the power grid distribution line single-line diagram in step 3 is: P1: First, the single-line diagram of the power distribution line is obtained through the server interface, and then the verification data standard TR is set, the obtained single-line diagram of the power distribution line is compared with the verification data standard TR, and the difference data is marked and recorded as CH; P2: The data that has passed the verification is then repaired with reference to the difference data CH for auxiliary data repair, and the repaired power grid distribution line single-line diagram is stored in the file library. When the power grid distribution line single-line diagram is compared with the verification data standard TR and is consistent, it is directly stored in the file library.

7. The layout and routing verification method based on machine learning according to claim 1, characterized in that: When the information of the reviewers is synchronously displayed in step three, the reviewer may be one person or multiple persons. When the second review is conducted, the number of reviewers and the review time are synchronously displayed.

8. The layout and routing verification method based on machine learning according to claim 1, characterized in that: When the obtained single-line diagram of the power distribution line of the power grid is compared with the verification data standard TR in P1, manual verification or automatic verification is adopted.

Images