CN115861173A - Automatic detection system and method for accuracy of optical splitter resources based on digital twin and AI - Google Patents
Automatic detection system and method for accuracy of optical splitter resources based on digital twin and AI Download PDFInfo
- Publication number
- CN115861173A CN115861173A CN202211326888.9A CN202211326888A CN115861173A CN 115861173 A CN115861173 A CN 115861173A CN 202211326888 A CN202211326888 A CN 202211326888A CN 115861173 A CN115861173 A CN 115861173A
- Authority
- CN
- China
- Prior art keywords
- information
- module
- optical splitter
- twin
- characteristic
- 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
Images
Landscapes
- Optical Communication System (AREA)
Abstract
The invention discloses a system and a method for automatically detecting the accuracy of optical splitter resources based on digital twin and AI, wherein the system comprises the following steps: a digital twin module: carrying out digital twin modeling on the optical splitter equipment; a twinning construction module: generating a construction scheme, a twin ecological model after construction and a relevant characteristic value change condition; an image acquisition module: acquiring image information of a port panel of light splitting equipment; an image analysis module: extracting port states and characteristic information of the optical splitting equipment; a port change labeling module: analyzing and marking the change condition of the port state of the optical splitting equipment, and extracting a characteristic value and the change condition of the characteristic value; reality & twinning check module: verifying the change condition of the characteristic value of the optical splitter, and judging the resource use accuracy of the optical splitter; abnormal occupation warning module: and prompting further field rechecking for the optical splitter with abnormal verification. Automatic identification of light splitting equipment resources and violation early warning are achieved.
Description
Technical Field
The invention belongs to the technical field of optical splitting equipment, and particularly relates to an automatic detection system and method for optical splitter resource accuracy based on digital twins and AI.
Background
At present, optical broadband services mainly depend on optical splitting equipment as peripheral access equipment for carrying. However, the optical splitter is a passive optical power distribution device, cannot automatically collect the port occupation state, and can only perform resource accuracy management by means of field check and manual recording of maintenance personnel. Although staff is required to shoot the optical splitting equipment in the optical width service opening process, the optical width service opening process only needs manual examination and check, the workload is large, and the check rate is low.
The target detection technology based on deep learning is widely applied to the field of computer vision in recent years, the characteristics are not required to be artificially designed, only corresponding models are required to be trained aiming at different detection scenes, and the detection precision and the generalization are greatly improved. With the upgrading of video monitoring equipment and the improvement of terminal photographing performance, the wide application and popularization of the acquisition and transmission of high-definition videos/images enable the detail recognition degree in the videos/images to be remarkably improved, and powerful support is provided for the accuracy and feasibility of automatic image recognition of light splitting equipment.
With the wide popularization of the digital twin technology, the method also relates to the field of equipment management, and for optical splitter equipment with a large number of ports, the accuracy management of optical splitter resources can be effectively improved by performing twin management through the digital twin technology.
Disclosure of Invention
The invention aims to solve the technical problem of providing a system and a method for automatically detecting the accuracy of optical splitter resources based on digital twins and AI (artificial intelligence) to realize automatic identification and violation early warning of optical splitter resources.
In order to achieve the technical purpose, the technical scheme adopted by the invention is as follows:
spectrometer resource accuracy automatic check out system based on digit twin and AI includes: the system comprises a digital twinning module, a twinning construction module, an image acquisition module, an image analysis module, a port change marking module, a reality & twinning check module and an abnormal occupation alarm module;
wherein, the digital twin module: performing digital twinning modeling on information of the spectrometer equipment by a digital twinning technology;
a twinning construction module: based on the digital twin module, combined with construction work order information, simulation construction is carried out on the digital twin model of the optical splitter to generate a construction scheme, and a corresponding constructed twin ecological model and a relevant characteristic value change condition are generated;
an image acquisition module: acquiring image information of a port panel of the light splitting equipment through a monitoring camera or an acquisition terminal, and uploading the image information to an image analysis module;
an image analysis module: identifying the collected video or image through a video/image analysis server, and extracting and recording port state and characteristic information of the light splitting equipment;
a port change labeling module: analyzing and marking the change condition of the port state of the optical splitting equipment and extracting the characteristic value and the change condition of the characteristic value by combining the port state and the characteristic information of the optical splitting equipment analyzed and extracted in the current video or image with the state and the characteristic information in the previous image;
reality & twinning check module: verifying the change condition of the characteristic values of the optical splitter, which are acquired by the image analysis module, on the basis of the on-site optical splitter characteristic value data and the port change marking module, the characteristic values of the optical splitter in the digital twin module and the characteristic value change condition data generated by the twin construction module, and judging the use accuracy of the optical splitter resources;
abnormal occupation warning module: and for the optical splitter with abnormal use of the optical splitter resource in the verification, the responsible person of the optical splitter is inquired in a related manner, and related workers are prompted to carry out further on-site recheck.
In order to optimize the technical scheme, the specific measures adopted further comprise:
the information of the optical splitter device includes basic information, port states, port characteristics, line sequence states, line sequence tags, and line sequence characteristic information.
The port states of the optical splitting device comprise idle, occupied and shielding states.
In the reality and twin checking module, the characteristic information in reality and twin is compared on the basis, and if the characteristic information is consistent, no abnormity is judged; if the actual and twin characteristics change, carrying out intelligent verification to find abnormal occupation conditions; for the problem that the machine cannot finish accurate identification, feeding back manual work for checking, and simultaneously optimizing a machine algorithm; and judging the accuracy of the resource use of the real optical splitter through information verification.
The automatic detection method for the accuracy of the optical splitter resources based on the digital twin and AI, which is realized by the system, is characterized by comprising the following steps of:
the method comprises the following steps: the digital twinning module carries out digital twinning modeling on information of the optical splitter equipment through a digital twinning technology to generate an optical splitter model in an operating state, and supports the extraction of characteristic values by modifying characteristic parameters to participate in the accuracy verification work of videos/images;
step two: the image acquisition module acquires port video information of the light splitting device in real time through the video monitoring device and sends the acquired video stream information to the video analysis server.
Step three: in a video analysis server, analyzing and processing a video, completing extraction of characteristic information of the light splitting equipment and identification of a port state of the light splitting equipment, and sending the related characteristic information of the light splitting equipment and the port use state information to a port change labeling module to realize port change labeling;
step four: the reality and twin checking module sends the characteristic parameter information of the on-site optical splitter image/video acquired in the step three to the digital twin server to complete twin setting and generate twin optical splitter characteristic information under a corresponding scene, and performs information checking on the real image/video characteristic information and the twin optical splitter characteristic information after scene revision;
step five: and the abnormal occupation warning module acquires corresponding constructor information through the basic information of the light splitting equipment aiming at the condition that the step four analysis finds that the abnormality exists, and sends related abnormal warning to prompt the constructor to carry out on-site recheck.
The characteristic parameters comprise environment, angle, illumination, visibility and shielding parameters;
the characteristic information of the light splitting device is divided into two parts, one part is the characteristic information of the light splitter, and the other part is the relevant characteristic information of the environment where the current light splitter is located and the collection angle during collection.
The fourth step comprises: comparing the characteristic information in reality and twins on a basis, and judging whether the characteristic information is consistent or not; carrying out intelligent verification on the change of the real and twin characteristics through error analysis, simulation judgment and a machine identification algorithm, and finding out abnormal occupation conditions; for the problem that the machine cannot finish accurate identification, feeding back manual work for checking, and simultaneously optimizing a machine algorithm; and checking the accuracy of the resource use through information check, and if the abnormality is found, synchronizing the information to the abnormal occupation module.
The automatic detection method for the accuracy of the optical splitter resource based on the digital twin and AI realized by the system is characterized in that the accuracy inspection step of the optical splitter construction comprises the following steps:
the method comprises the following steps: the digital twinning module carries out digital twinning modeling on information of the optical splitter equipment through a digital twinning technology to generate an optical splitter model in an operating state, and supports the extraction of characteristic values by modifying characteristic parameters to participate in the accuracy verification work of videos/images;
step two: when the construction work order information is generated, the twin construction module calls the optical splitter model in the running state from the digital twin service, construction simulation is carried out on the optical splitter model according to the work order content, the generation of the optimal construction scheme is completed, the optical splitter model in the design state and the generation of the related characteristic value are generated, the extraction of the running state > the characteristic value in the design state and the change condition thereof is completed by modifying the characteristic parameters, and the verification work of the accuracy of the construction is participated;
step three: before and after construction, the image acquisition module acquires port video information of the light splitting equipment in real time through the video monitoring equipment and sends the acquired video stream information to the video analysis server;
step four: the image analysis module analyzes and processes the images before and after construction in the video analysis server, extracts the characteristic information of the light splitting equipment and identifies the port use state information of the light splitting equipment, and sends the related characteristic information of the light splitting equipment and the port use state information to the port change marking module for carrying out port change marking service;
step five: the reality & twin checking module sends the characteristic information of the on-site optical splitter image/video acquired in the fourth step to the digital twin/twin construction module to complete twin setting and generate twin optical splitter characteristic information and characteristic value change information under a corresponding scene, and performs information checking on the characteristic information and characteristic value change information of the real image/video and the twin optical splitter characteristic information and characteristic value change information after scene revision to check the construction accuracy, and if abnormal construction is found, performs information synchronization on the abnormal occupation module;
step six: and aiming at the condition that the abnormal occupation is found by the step four analysis, the abnormal occupation alarming module acquires corresponding constructor information through the basic information of the light splitting equipment, sends related abnormal alarming information and promotes the workers to carry out on-site recheck.
The invention has the following beneficial effects:
1. the method has the advantages that AI video/image analysis capability is introduced, construction records of the optical splitter are correlated, automatic detection of construction compliance of the optical splitter is realized, the resource condition of the optical splitter can be automatically identified, manual inspection is replaced, intelligent management of port resources is realized, the network safety production service level is improved, the purposes of reducing operation cost and improving efficiency are realized, and the problems that the port state of an inaccurate optical splitter cannot be put into operation and used, the silencing cost is huge, illegal construction operation of important optical splitters cannot be found in time and the like are solved;
2. the method comprises the steps of extracting characteristic information such as environment and collection angle when information collection is carried out on the optical splitter through image/video analysis, simulating the characteristic information in a twin model, extracting corresponding twin characteristic information, checking the influence of the environment and collection state of the optical splitter, guaranteeing the accuracy of information verification, and eliminating the state difference of the optical splitter in the twin environment and the optical splitter in real collection.
3. The method introduces a digital twinning technology, carries out digital twinning on splitter resources, realizes judgment of splitter resource use accuracy by checking and verifying twinning simulation of splitter current conditions and actually acquired video images, completes accuracy identification and management of splitter equipment resources, and avoids the problem that abnormal alarm is caused by errors generated in identification of dense ports of the splitters under the conditions of port shielding, low monitoring pixels and the like.
4. The twinning simulation of construction is completed by relying on digital twinning and combining a construction work order, the generation of an optimal construction scheme is carried out, and the guidance on site construction and the verification on the construction result are carried out; through the simulation of the construction work order, the characteristic value variable quantity generated by the optimal execution scheme is generated, the image characteristic value variable quantity of video/image acquisition before and after construction is verified, early warning artificial verification is carried out when the image characteristic value variable quantity exceeds the fault tolerance, and the construction accuracy is guaranteed.
Drawings
FIG. 1 is a diagram of the system for automatically detecting the resource accuracy of a spectrometer based on digital twin and AI according to the present invention;
FIG. 2 is a logic diagram of the system for automatically detecting the accuracy of the resources of the optical splitter based on the digital twin and AI according to the present invention;
FIG. 3 is a logic diagram of splitter resource accuracy check in accordance with the present invention;
FIG. 4 is a logic diagram of the accuracy inspection of the construction of the optical splitter according to the present invention.
Detailed Description
Embodiments of the present invention are described in further detail below with reference to the accompanying drawings.
Example 1
As shown in fig. 1-2, the automatic detection system for the accuracy of the optical splitter resource based on the digital twin and AI of the present invention comprises: the system comprises a digital twinning module, a twinning construction module, an image acquisition module, an image analysis module, a port change marking module, a reality & twinning check module and an abnormal occupation alarm module;
wherein, the digital twin module: by means of a digital twinning technology, digital twinning modeling is carried out on information of the splitter equipment, and support is provided for twinning construction and twinning verification;
a twinning construction module: by means of the digital twin module, simulation construction is carried out on the digital twin model of the optical splitter in combination with construction work order information, a construction scheme is generated, a corresponding constructed twin ecological model and relevant characteristic value change conditions are generated, on-site and twin verification is carried out after on-site construction is supported, and construction accuracy is guaranteed;
the twin construction module is used for preferentially carrying out construction simulation on the twin model when a construction order is generated, generating an optimal construction scheme and generating a corresponding twin state, recording the characteristic change condition after construction, and providing help for twin verification and verification of construction accuracy after site construction;
an image acquisition module: acquiring image information of a port panel of the light splitting equipment through a monitoring camera or an acquisition terminal, and transmitting the image information to a video/image analysis server;
an image analysis module: after the video/image analysis server acquires the video/image of the asset entity, the port state and the characteristic information of the light splitting equipment are extracted and recorded by identifying the acquired video or image;
a port change labeling module: analyzing and marking the change condition of the port state of the optical splitting equipment by combining the port state and the characteristic information of the optical splitting equipment analyzed and extracted in the video or image with the state and the characteristic information in the previous image, and extracting a characteristic value and the change condition of the characteristic value for performing reality and twin verification;
reality & twinning check module: verifying the change condition of the characteristic values of the optical splitter, which are acquired by the image analysis module, on the basis of the on-site optical splitter characteristic value data and the port change marking module, the characteristic values of the optical splitter in the digital twin module and the characteristic value change condition data generated by the twin construction module, and judging the use accuracy of the optical splitter resources;
abnormal occupation warning module: and for the optical splitter with abnormal use of the optical splitter resource in the verification, the responsible person of the optical splitting equipment is inquired in an associated manner, and the related staff is prompted to carry out further on-site recheck.
In an embodiment, the information of the optical splitter device includes basic information, port states, port characteristics, line sequence states, line sequence tags, and line sequence characteristic information.
The port states of the optical splitting equipment comprise idle, occupied and shielding states.
In the reality and twin checking module, the characteristic information in reality and twin is compared on the basis, and if the characteristic information is consistent, no abnormity is judged; if the actual and twin characteristics change, intelligent verification is carried out through error analysis, simulation judgment, a machine recognition algorithm and the like to find abnormal occupation conditions; for the problem that the machine cannot finish accurate identification, feeding back manual work for checking, and simultaneously optimizing a machine algorithm; and judging the accuracy of the resource use of the real optical splitter through information verification.
Example 2
As shown in fig. 3, according to the method for automatically detecting the accuracy of the optical splitter resource based on the digital twin and the AI implemented by the system, the step of checking the accuracy of the optical splitter resource includes:
the method comprises the following steps: the digital twin module carries out digital twin modeling on basic information, port states, port characteristics, line sequence states, line sequence labels, line sequence characteristics and other related information of the optical splitter equipment through a digital twin technology to generate an optical splitter model in a running state, and supports the completion of characteristic value extraction through modification of characteristic parameters such as environment, angle, illumination, visibility and shielding, and the participation of the optical splitter model and the accuracy verification of videos/images.
Step two: the image acquisition module acquires port video information of the light splitting device in real time through the video monitoring device and sends the acquired video stream information to the video analysis server.
Step three: the image analysis module analyzes and processes the video in the video analysis server, extracts the characteristic information of the light splitting equipment and identifies the port use state information of the light splitting equipment, and sends the related characteristic information of the light splitting equipment and the port use state information to the port change labeling module to perform port change labeling service.
The characteristic information of the light splitting device is divided into two parts, one part is the characteristic information of the light splitter, and the other part is the relevant characteristic information such as the environment where the current light splitter is located and the collection angle during collection.
The invention does not limit the specific characteristic range of the light splitting equipment, and the collected two parts of characteristics are subject to the requirements of setting characteristic values of environment and the like and generating effective verifiable twin characteristic information by meeting the requirements of digital twin service/twin construction service;
the port use state information of the optical splitting device includes but is not limited to information such as occupation, idle state, shielding and line sequence trend characteristics of the port, so as to meet the requirement of change marking.
Step four: and the reality and twin checking module sends the characteristic information of the scene image/video acquired in the step three, such as environment, angle, illumination, visibility, shielding and the like to the digital twin server to complete twin setting and generate twin characteristic information under a corresponding scene, and performs information checking on the characteristic information of the real image/video and the twin characteristic information of the scene after revision.
In the information verification, the characteristic information in reality and twin is subjected to basic comparison, and the judgment of the consistency of the characteristic information is abnormal;
carrying out intelligent verification on the change of the real and twin characteristics through error analysis, simulation judgment, a machine recognition algorithm and the like, and finding out abnormal occupation conditions;
and feeding back manual work for checking the problem that the machine cannot finish accurate identification, and optimizing a machine algorithm. And checking the accuracy of the resource use through information check, and if the abnormality is found, synchronizing the information to the abnormal occupation module.
Step five: and the abnormal occupation warning module acquires corresponding constructor information through the basic information of the light splitting equipment aiming at the condition that the step four analysis finds that the abnormality exists, and sends related abnormal warning to prompt the constructor to carry out on-site recheck.
The invention does not limit the specific connotation of the abnormal alarm information, and particularly meets the use requirements of workers.
Example 3
As shown in fig. 4, according to the automatic detection method for the accuracy of the optical splitter resource based on the digital twin and the AI implemented by the system, the step of checking the accuracy of the optical splitter construction includes:
the method comprises the following steps: the digital twinning module carries out digital twinning modeling on basic information, port states, port characteristics, line sequence states, line sequence labels, line sequence characteristics and other related information of the optical splitter equipment through a digital twinning technology to generate an optical splitter model in a running state, and supports the completion of characteristic value extraction through modification of characteristic parameters such as environment, angle, illumination, visibility and shielding, and participates in the accuracy verification work of videos/images.
Step two: when the construction work order information is generated, the twin construction module calls the optical splitter model in the running state from the digital twin service, construction simulation is carried out on the optical splitter model according to the work order content, the generation of the optimal construction scheme is completed, the optical splitter model in the design state and the generation of related characteristic values are generated, the extraction of the characteristic values in the running state > the design state and the change conditions thereof is completed by modifying the characteristic parameters of environment, angle, illumination, visibility, shielding and the like, and the accuracy verification work of the participation and construction is carried out.
Step three: before and after construction, the image acquisition module acquires port video information of the light splitting equipment in real time through the video monitoring equipment and sends the acquired video stream information to the video analysis server.
Step four: and the image analysis module analyzes and processes the images before and after construction in the video analysis server, extracts the characteristic information of the light splitting equipment and identifies the port use state information of the light splitting equipment, and sends the related characteristic information of the light splitting equipment and the port use state information to the port change labeling module for port change labeling service.
The characteristic information of the light splitting equipment is divided into two parts, one part is the characteristic information of the light splitter, and the other part is the relevant characteristic information such as the environment where the current light splitter is located and the collection angle during collection;
the invention does not limit the specific characteristic range of the light splitting equipment, and the collected two parts of characteristics are subject to the requirements of setting characteristic values of environment and the like and generating effective verifiable twin characteristic information by meeting the requirements of digital twin service/twin construction service;
the port use state information of the optical splitting device includes but is not limited to information such as occupation, idle state, shielding and line sequence trend characteristics of the port, so as to meet the requirement of change marking.
Step five: and the reality and twin checking module sends the characteristic information of the image/video of the optical splitter before and after the construction of the site, which is acquired in the fourth step, to the digital twin/twin construction server, so that twin setting is completed, twin characteristic information and characteristic value change information under a corresponding scene are generated, information checking is carried out on the characteristic information and the characteristic value change information of the image/video of the reality and the twin characteristic information and the characteristic value change information of the optical splitter after the scene is revised, the construction accuracy is checked, and if abnormal construction is found, information synchronization is carried out on the abnormal occupation module.
Step six: and aiming at the condition that the step four analysis shows that the abnormity exists, the abnormal occupation alarming module acquires corresponding constructor information through the light splitting equipment basic information, sends related abnormal alarming information and promotes the workers to carry out on-site recheck.
The invention does not limit the specific connotation of the abnormal alarm information, and particularly meets the use requirements of workers.
The above is only a preferred embodiment of the present invention, and the protection scope of the present invention is not limited to the above-mentioned embodiments, and all technical solutions belonging to the idea of the present invention belong to the protection scope of the present invention. It should be noted that modifications and embellishments within the scope of the invention may be made by those skilled in the art without departing from the principle of the invention.
Claims (8)
1. Automatic detection system of optical splitter resource accuracy based on digit twin and AI, its characterized in that includes: the system comprises a digital twinning module, a twinning construction module, an image acquisition module, an image analysis module, a port change marking module, a reality & twinning checking module and an abnormal occupation warning module;
wherein, the digital twin module: performing digital twinning modeling on information of the spectrometer equipment through a digital twinning technology;
a twinning construction module: based on the digital twin module, combined with construction work order information, simulation construction is carried out on the digital twin model of the optical splitter to generate a construction scheme, and a corresponding constructed twin ecological model and a relevant characteristic value change condition are generated;
an image acquisition module: acquiring image information of a port panel of the light splitting equipment through a monitoring camera or an acquisition terminal, and uploading the image information to an image analysis module;
an image analysis module: identifying the collected video or image through a video/image analysis server, and extracting and recording port state and characteristic information of the light splitting equipment;
a port change labeling module: analyzing and marking the change condition of the port state of the optical splitting equipment and extracting the characteristic value and the change condition of the characteristic value by combining the port state and the characteristic information of the optical splitting equipment analyzed and extracted in the current video or image with the state and the characteristic information in the previous image;
reality & twinning check module: verifying the change condition of the characteristic values of the optical splitter obtained by the image analysis module and the port change marking module, the characteristic values of the optical splitter in the digital twin module and the change condition data of the characteristic values generated by the twin construction module, and judging the use accuracy of the optical splitter resources;
abnormal occupation warning module: and for the optical splitter with abnormal use of the optical splitter resource in the verification, the responsible person of the optical splitting equipment is inquired in an associated manner, and the related staff is prompted to carry out further on-site recheck.
2. The automatic digital twin and AI-based optical splitter resource accuracy detection system of claim 1, wherein the information of the optical splitter device includes basic information, port status, port characteristics, line order status, line order tags, line order characteristic information.
3. The automatic digital twin and AI-based splitter resource accuracy detection system of claim 1, wherein the splitter device port states include idle, occupied, and occluded states.
4. The automatic detection system for the accuracy of the resources of the optical splitter based on the digital twin and the AI according to claim 1, wherein in the reality & twin verification module, the characteristic information in the reality and the twin is compared on the basis, and if the characteristic information is consistent, it is determined that there is no abnormality; if the actual and twin characteristics change, carrying out intelligent verification to find abnormal occupation conditions; for the problem that the machine cannot finish accurate identification, feeding back manual work for checking, and simultaneously optimizing a machine algorithm; and judging the accuracy of the resource use of the real optical splitter through information verification.
5. The method for automatically detecting the accuracy of the optical splitter resources based on the digital twin and AI according to any one of the claims 1-4, wherein the step of checking the accuracy of the optical splitter resources comprises:
the method comprises the following steps: the digital twinning module carries out digital twinning modeling on information of the optical splitter equipment through a digital twinning technology to generate an optical splitter model in an operating state, and supports the extraction of characteristic values by modifying characteristic parameters to participate in the accuracy verification work of videos/images;
step two: the image acquisition module acquires port video information of the light splitting device in real time through the video monitoring device and sends the acquired video stream information to the video analysis server.
Step three: in a video analysis server, analyzing and processing a video, completing extraction of characteristic information of the light splitting equipment and identification of a port state of the light splitting equipment, and sending the related characteristic information of the light splitting equipment and the port use state information to a port change labeling module to realize port change labeling;
step four: the reality and twin checking module sends the characteristic parameter information of the on-site optical splitter image/video acquired in the step three to the digital twin server to complete twin setting and generate twin optical splitter characteristic information under a corresponding scene, and performs information checking on the real image/video characteristic information and the twin optical splitter characteristic information after scene revision;
step five: and the abnormal occupation warning module acquires corresponding constructor information through the basic information of the light splitting equipment aiming at the condition that the step four analysis finds that the abnormality exists, and sends related abnormal warning to prompt the constructor to carry out on-site recheck.
6. The automatic detection method for the accuracy of the optical splitter resource based on the digital twin and the AI as claimed in claim 5, wherein the characteristic parameters include environment, angle, illumination, visibility, and occlusion parameters;
the characteristic information of the light splitting device is divided into two parts, one part is the characteristic information of the light splitter, and the other part is the relevant characteristic information of the environment where the current light splitter is located and the collection angle during collection.
7. The automatic detection method for the accuracy of the digital twin and AI-based splitter resource as defined in claim 5, wherein the fourth step comprises: comparing the characteristic information in reality and twins on a basis, and judging whether the characteristic information is consistent or not; carrying out intelligent verification on the change of the real and twin characteristics through error analysis, simulation judgment and a machine identification algorithm, and finding out abnormal occupation conditions; for the problem that the machine cannot finish accurate identification, feeding back manual work for checking, and simultaneously optimizing a machine algorithm; and checking the accuracy of the resource use through information check, and if an abnormality is found, synchronizing the information to the abnormal occupation module.
8. The method for automatically detecting the accuracy of the optical splitter resources based on the digital twin and AI according to any one of the systems of claims 1-4, wherein the step of checking the accuracy of the optical splitter construction comprises the following steps:
the method comprises the following steps: the digital twinning module carries out digital twinning modeling on information of the optical splitter equipment through a digital twinning technology to generate an optical splitter model in an operating state, and supports the extraction of characteristic values by modifying characteristic parameters to participate in the accuracy verification work of videos/images;
step two: when the construction work order information is generated, the twin construction module calls the optical splitter model in the running state from the digital twin service, construction simulation is carried out on the optical splitter model according to the work order content, the generation of the optimal construction scheme is completed, the optical splitter model in the design state and the generation of the related characteristic value are generated, the extraction of the running state > the characteristic value in the design state and the change condition thereof is completed by modifying the characteristic parameters, and the verification work of the accuracy of the construction is participated;
step three: before and after construction, the image acquisition module acquires port video information of the light splitting equipment in real time through the video monitoring equipment and sends the acquired video stream information to the video analysis server;
step four: the image analysis module analyzes and processes the images before and after construction in the video analysis server, extracts the characteristic information of the light splitting equipment and identifies the port use state information of the light splitting equipment, and sends the related characteristic information of the light splitting equipment and the port use state information to the port change marking module for carrying out port change marking service;
step five: the reality & twin checking module sends the characteristic information of the on-site optical splitter image/video acquired in the fourth step to the digital twin/twin construction module to complete twin setting and generate twin optical splitter characteristic information and characteristic value change information under a corresponding scene, and performs information checking on the characteristic information and characteristic value change information of the real image/video and the twin optical splitter characteristic information and characteristic value change information after scene revision to check the construction accuracy, and if abnormal construction is found, performs information synchronization on the abnormal occupation module;
step six: and aiming at the condition that the step four analysis shows that the abnormity exists, the abnormal occupation alarming module acquires corresponding constructor information through the light splitting equipment basic information, sends related abnormal alarming information and promotes the workers to carry out on-site recheck.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211326888.9A CN115861173A (en) | 2022-10-26 | 2022-10-26 | Automatic detection system and method for accuracy of optical splitter resources based on digital twin and AI |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211326888.9A CN115861173A (en) | 2022-10-26 | 2022-10-26 | Automatic detection system and method for accuracy of optical splitter resources based on digital twin and AI |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115861173A true CN115861173A (en) | 2023-03-28 |
Family
ID=85661951
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211326888.9A Pending CN115861173A (en) | 2022-10-26 | 2022-10-26 | Automatic detection system and method for accuracy of optical splitter resources based on digital twin and AI |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115861173A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116567686A (en) * | 2023-07-10 | 2023-08-08 | 亚信科技（中国）有限公司 | Method, apparatus, device, medium and program product for constructing digital twin network |
| CN117394945A (en) * | 2023-12-11 | 2024-01-12 | 中国电信股份有限公司深圳分公司 | Method, device and equipment for detecting ports of optical splitters based on multivariate algorithm |
-
2022
- 2022-10-26 CN CN202211326888.9A patent/CN115861173A/en active Pending
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116567686A (en) * | 2023-07-10 | 2023-08-08 | 亚信科技（中国）有限公司 | Method, apparatus, device, medium and program product for constructing digital twin network |
| CN116567686B (en) * | 2023-07-10 | 2023-09-12 | 亚信科技（中国）有限公司 | Method, apparatus, device, medium and program product for constructing digital twin network |
| CN117394945A (en) * | 2023-12-11 | 2024-01-12 | 中国电信股份有限公司深圳分公司 | Method, device and equipment for detecting ports of optical splitters based on multivariate algorithm |
| CN117394945B (en) * | 2023-12-11 | 2024-03-08 | 中国电信股份有限公司深圳分公司 | Method, device and equipment for detecting ports of optical splitters based on multivariate algorithm |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| TWI741505B (en) | Topology processing method, device and system | |
| CN115861173A (en) | Automatic detection system and method for accuracy of optical splitter resources based on digital twin and AI | |
| CN108964995A (en) | Log correlation analysis method based on time shaft event | |
| CN113095132B (en) | Neural network based gas field identification method, system, terminal and storage medium | |
| CN111797725A (en) | Equipment state detection method, device and system | |
| CN101771582A (en) | Safety monitoring correlation analysis method based on state machine | |
| CN111695493A (en) | Method and system for detecting hidden danger of power transmission line | |
| CN115269438A (en) | Automatic testing method and device for image processing algorithm | |
| CN112733147A (en) | Equipment safety management method and system | |
| CN115880631A (en) | Power distribution station fault identification system, method and medium | |
| CN106874306A (en) | People information portrait Compare System Key Performance Indicator evaluating method | |
| CN117171694B (en) | Distribution scene safety identification system based on AI technology | |
| CN117114420B (en) | Image recognition-based industrial and trade safety accident risk management and control system and method | |
| CN110543149A (en) | Aviation seat bullet loading and unloading auxiliary system based on intelligent glasses and use method | |
| CN115426363B (en) | Data acquisition method and terminal of intelligent plate processing factory | |
| CN117037059A (en) | Equipment management method and device based on inspection monitoring and electronic equipment | |
| CN114120462B (en) | Self-adaptive pushing system and method for labor service real-name system data based on supervision platform | |
| CN114416417A (en) | System abnormity monitoring method, device, equipment and storage medium | |
| CN114066181A (en) | Intelligent state evaluation system for thermal equipment | |
| CN115185792A (en) | Fault hardware processing method, device and system | |
| CN114387564A (en) | Head-knocking engine-off pumping-stopping detection method based on YOLOv5 | |
| CN110087066B (en) | One-key automatic inspection method applied to online inspection | |
| CN115394025A (en) | Monitoring method, monitoring device, electronic equipment and storage medium | |
| CN112132819A (en) | Communication network management monitoring method based on artificial intelligence | |
| KR102619578B1 (en) | AI-based structure damage determination training data expansion service system and method for providing structure damage determination service |
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 |