Cable tunnel intelligent operation and maintenance method and device based on digital twinborn technology

Abstract

The embodiment of the invention discloses a cable tunnel intelligent operation and maintenance method and device based on a digital twinning technology. A specific embodiment of the method comprises the steps of obtaining a point cloud data set and a tunnel drawing; constructing an initial three-dimensional cable tunnel model according to the point cloud data set and the tunnel drawing; according to each sensor arranged in the target cable tunnel, real-time sensing data corresponding to each sensor is obtained, and each piece of real-time sensing data is obtained; generating cable operation analysis information for the target cable tunnel according to the real-time sensing data; generating a cable twinborn model for the target cable tunnel according to the real-time sensing data and the cable operation analysis information; and executing at least one operation and maintenance processing task by using the cable twinning model. According to the implementation mode, the cable twinborn model can be accurately generated, so that intelligent operation and maintenance of the cable tunnel are realized, and cable accidents are avoided.

Description

Technical Field

[0001] The embodiments of the present disclosure relate to the field of computer technology, and specifically to a method and device for intelligent operation and maintenance of a cable tunnel based on digital twin technology. Background Art

[0002] At present, with the continuous development of intelligence, the maintenance of cable tunnels is also moving towards intelligence. For the operation and maintenance of cable tunnels, the usual method is: first, multiple sensors are set up in the cable tunnel. Then, by receiving multiple real-time data sent by multiple sensors, it is manually determined whether multiple sensors detect abnormal information for the cable tunnel based on the multiple real-time data, which is convenient for subsequent operation and maintenance processing.

[0003] However, when the above method is used to perform operation and maintenance of cable tunnels, the following technical problems often occur:

[0004] It requires manual real-time observation of multiple real-time data corresponding to multiple sensors, which not only wastes a lot of manpower and material resources, but also fails to efficiently realize real-time anomaly detection, resulting in the inability to carry out subsequent operation and maintenance work synchronously, and possible cable accidents.

[0005] The above information disclosed in this Background section is only for enhancement of understanding of the background of the inventive concept and therefore it may contain information that does not form the prior art that is already known in this country to a person of ordinary skill in the art. Summary of the invention

[0006] The content of this disclosure is used to introduce concepts in a brief form, which will be described in detail in the detailed implementation section below. The content of this disclosure is not intended to identify the key features or essential features of the technical solution claimed for protection, nor is it intended to limit the scope of the technical solution claimed for protection.

[0007] Some embodiments of the present disclosure propose an intelligent operation and maintenance method and device for a cable tunnel based on digital twin technology to solve one or more of the technical problems mentioned in the above background technology section.

[0008] In a first aspect, some embodiments of the present disclosure provide an intelligent operation and maintenance method for a cable tunnel based on digital twin technology, including: obtaining a point cloud dataset and tunnel drawings for a target cable tunnel; constructing an initial three-dimensional cable tunnel model based on the point cloud dataset and the tunnel drawings; obtaining real-time perception data corresponding to each sensor installed in the target cable tunnel to obtain each real-time perception data, wherein each real-time perception data includes: cable current, voltage, temperature, ambient temperature, humidity and gas concentration; generating cable operation analysis information for the target cable tunnel based on each real-time perception data; generating a cable twin model for the target cable tunnel based on each real-time perception data and the cable operation analysis information; and performing at least one operation and maintenance processing task for the target cable tunnel using the cable twin model.

[0009] In a second aspect, some embodiments of the present disclosure provide an intelligent operation and maintenance device for a cable tunnel based on digital twin technology, comprising: a first acquisition unit, configured to acquire a point cloud data set and a tunnel drawing for a target cable tunnel; a construction unit, configured to construct an initial three-dimensional cable tunnel model based on the point cloud data set and the tunnel drawing; a second acquisition unit, configured to acquire real-time perception data corresponding to each sensor installed in the target cable tunnel, and obtain each real-time perception data, wherein each real-time perception data includes: cable current, voltage, temperature, ambient temperature, humidity and gas concentration; a first generation unit, configured to generate cable operation analysis information for the target cable tunnel based on the each real-time perception data; a second generation unit, configured to generate a cable twin model for the target cable tunnel based on the each real-time perception data and the cable operation analysis information; an execution unit, configured to use the cable twin model to execute at least one operation and maintenance processing task for the target cable tunnel.

[0010] In a third aspect, some embodiments of the present disclosure provide an electronic device comprising: one or more processors; a storage device on which one or more programs are stored, and when the one or more programs are executed by the one or more processors, the one or more processors implement the method described in any implementation manner in the first aspect.

[0011] In a fourth aspect, some embodiments of the present disclosure provide a computer-readable medium having a computer program stored thereon, wherein when the program is executed by a processor, the method described in any implementation manner in the first aspect is implemented.

[0012] The above-mentioned various embodiments of the present disclosure have the following beneficial effects: through the intelligent operation and maintenance method of the cable tunnel based on the digital twin technology of some embodiments of the present disclosure, the cable twin model is accurately generated to realize the intelligent operation and maintenance of the cable tunnel, and the cable accident is avoided. Specifically, the reason for the inefficiency of the operation and maintenance of the relevant cable tunnel is that it is necessary to manually observe the multiple real-time data corresponding to the multiple sensors in real time, which not only wastes a lot of manpower and material resources, but also cannot efficiently realize real-time abnormal detection, resulting in the inability to carry out subsequent operation and maintenance work synchronously, and cable accidents may occur. Based on this, the intelligent operation and maintenance method of the cable tunnel based on the digital twin technology of some embodiments of the present disclosure, first, obtains the point cloud data set and tunnel drawings for the target cable tunnel, so as to comprehensively determine the tunnel structure and tunnel scene information of the target cable tunnel from a two-dimensional perspective and a three-dimensional perspective, so as to facilitate the subsequent accurate generation of the initial three-dimensional cable tunnel model. Then, according to the above-mentioned point cloud data set and the above-mentioned tunnel drawings, the initial three-dimensional cable tunnel model can be accurately constructed to generate tunnel scene information that preliminarily reflects the relevant target cable tunnel. Then, according to each sensor installed in the target cable tunnel, the real-time sensing data corresponding to each sensor is obtained to obtain each real-time sensing data, so as to understand the real-time status of the tunnel in the target cable tunnel and determine whether there is an abnormal problem in the target cable tunnel. Then, according to each real-time sensing data, the cable operation analysis information for the target cable tunnel can be accurately generated, so as to determine the operation status of the target cable tunnel and summarize all aspects, so as to understand the abnormal problems of the target cable tunnel in real time. Among them, each real-time sensing data includes: cable current, voltage, temperature, ambient temperature, humidity and gas concentration. Furthermore, according to each real-time sensing data and the cable operation analysis information, a cable twin model for the target cable tunnel can be accurately generated, so as to realize the intelligent display and analysis of the operation status corresponding to the cable tunnel by using the cable twin model. Finally, the cable twin model is used to perform at least one operation and maintenance processing task for the target cable tunnel in real time to ensure the efficiency of operation and maintenance processing. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] The above and other features, advantages and aspects of the embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. Throughout the accompanying drawings, the same or similar reference numerals represent the same or similar elements. It should be understood that the drawings are schematic and that components and elements are not necessarily drawn to scale.

[0014] Figure 1 It is a flowchart of some embodiments of the intelligent operation and maintenance method of a cable tunnel based on the digital twin technology according to the present disclosure;

[0015] Figure 2It is a structural schematic diagram of some embodiments of the intelligent operation and maintenance device for a cable tunnel based on the digital twin technology according to the present disclosure;

[0016] Figure 3 It is a schematic diagram of the structure of an electronic device suitable for implementing some embodiments of the present disclosure. DETAILED DESCRIPTION

[0017] Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as being limited to the embodiments set forth herein. On the contrary, these embodiments are provided to provide a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are only for exemplary purposes and are not intended to limit the scope of protection of the present disclosure.

[0018] It should also be noted that, for ease of description, only the parts related to the invention are shown in the drawings. In the absence of conflict, the embodiments and features in the embodiments of the present disclosure can be combined with each other.

[0019] It should be noted that the concepts such as "first" and "second" mentioned in the present disclosure are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.

[0020] It should be noted that the modifications of "one" and "plurality" mentioned in the present disclosure are illustrative rather than restrictive, and those skilled in the art should understand that unless otherwise clearly indicated in the context, it should be understood as "one or more".

[0021] The names of the messages or information exchanged between multiple devices in the embodiments of the present disclosure are only used for illustrative purposes and are not used to limit the scope of these messages or information.

[0022] The present disclosure will be described in detail below with reference to the accompanying drawings and in conjunction with embodiments.

[0023] refer to Figure 1 , shows a process 100 of some embodiments of the cable tunnel intelligent operation and maintenance method based on digital twin technology according to the present disclosure. The cable tunnel intelligent operation and maintenance method based on digital twin technology includes the following steps:

[0024] Step 101, obtaining a point cloud data set and tunnel drawings for a target cable tunnel.

[0025] In some embodiments, the execution subject of the above-mentioned intelligent operation and maintenance method of cable tunnels based on digital twin technology can obtain the point cloud data set and tunnel drawings for the target cable tunnel through a wired connection or a wireless connection. Among them, the target cable tunnel can be a cable tunnel for daily cable status detection. The point cloud data can be three-dimensional laser point cloud data. The point cloud data set can be obtained through a related point cloud collection device. The tunnel drawings can be high-precision BIM modeling of the cable tunnel to achieve a 1:1 reconstruction of the cable tunnel scene accuracy.

[0026] Here, the point cloud data set and tunnel drawings can provide an intuitive visualization of the cable tunnel distribution direction, the number of cables laid, and the internal equipment.

[0027] Step 102: construct an initial three-dimensional cable tunnel model based on the point cloud data set and the tunnel drawing.

[0028] In some embodiments, the execution entity may construct an initial three-dimensional cable tunnel model based on the point cloud data set and the tunnel drawings. The initial three-dimensional cable tunnel model may reflect the spatial arrangement relationship between the cables and the devices in the target cable tunnel. The initial three-dimensional cable tunnel model may be a three-dimensional cable tunnel model that has not yet been connected to the relevant cable data, analysis data, and equipment data. The three-dimensional cable tunnel model may be a digital twin model based on cables. That is, the initial three-dimensional cable tunnel model may be a data twin model based on cables that has not yet been connected to data. In practice, there is a corresponding digital twin platform for the digital twin model.

[0029] Step 103, according to each sensor installed in the target cable tunnel, real-time sensing data corresponding to each sensor is acquired to obtain each real-time sensing data.

[0030] In some embodiments, the execution subject may obtain the real-time sensing data corresponding to each sensor according to each sensor installed in the target cable tunnel, and obtain each real-time sensing data. The real-time sensing data include: cable current, voltage, temperature, ambient temperature, humidity and gas concentration. In practice, each sensor may include but is not limited to at least one of the following: cable current sensing sensor, voltage sensor, temperature sensor, ambient temperature sensor, humidity sensor.

[0031] Step 104: Generate cable operation analysis information for the target cable tunnel based on the above-mentioned real-time sensing data.

[0032] In some embodiments, the execution subject may generate cable operation analysis information for the target cable tunnel according to the real-time sensing data. The cable operation analysis information may characterize the operation status of the cable. For example, the cable operation analysis information may include: status information characterizing normal operation of the cable, and status information characterizing abnormal operation of the cable.

[0033] As an example, the execution subject may generate cable operation analysis information for the target cable tunnel according to the real-time sensing data by using a data analysis method. For example, the data analysis method may be a data analysis method based on machine learning.

[0034] Step 105: Generate a cable twin model for the target cable tunnel based on the above-mentioned real-time sensing data and the above-mentioned cable operation analysis information.

[0035] In some embodiments, the execution subject may generate a cable twin model for the target cable tunnel according to the real-time sensing data and the cable operation analysis information. The cable operation analysis information may be an analysis result after analyzing various scenarios of the target cable tunnel. For example, if the scenario is a gas detection scenario, the cable operation analysis information may include: gas flow analysis information and gas content information. If the scenario is a personnel detection scenario, the cable operation analysis information may include: personnel flow analysis information and cable personnel operation information.

[0036] Step 106: Use the cable twin model to perform at least one operation and maintenance task for the target cable tunnel.

[0037] In some embodiments, the execution subject may use the cable twin model to execute at least one operation and maintenance task for the target cable tunnel. The operation and maintenance task may be a task that executes a corresponding operation and maintenance operation according to a dispatch instruction. The dispatch instruction may be an instruction that instructs the cable twin model to execute a related operation. For example, the dispatch instruction may be a valve closing instruction.

[0038] In some optional implementations of some embodiments, the at least one operation and maintenance processing task mentioned above includes: a real-time gas detection task, a real-time personnel detection task, a first real-time patrol task based on a track-mounted robot, a fire simulation task, and a second real-time patrol task based on augmented reality glasses. Among them, the real-time gas detection task may be a task of performing gas detection in real time. In practice, gas detection may be oxygen detection or toxic gas detection. The real-time personnel detection task may be a task of performing target personnel detection in real time. The target personnel may be a person invading the cable area. The first real-time patrol task based on a track-mounted robot may be a task of instructing the track-mounted robot to perform a real-time patrol operation. The fire simulation task may be a task of performing a fire simulation. The second real-time patrol task based on augmented reality glasses may be a task of performing real-time patrol based on augmented reality glasses.

[0039] Optionally, the above-mentioned using the above-mentioned cable twin model to perform at least one processing task for the above-mentioned target cable tunnel may include the following steps:

[0040] The first step is to, in response to receiving the real-time gas detection information for the target cable tunnel, use the cable twin model to start at least one gas-related detection device in the target cable tunnel to perform the real-time gas detection task. The gas-related detection device may be a device associated with gas detection. For example, the gas-related detection device may be, but is not limited to, at least one of the following: ventilation equipment, lighting equipment, gas content detection equipment, sampling equipment.

[0041] In the second step, in response to receiving the personnel detection information for the above-mentioned target cable tunnel, the cable twin model is used to start at least one personnel-related detection device in the above-mentioned target cable tunnel to perform the above-mentioned real-time personnel detection task. Among them, the personnel detection information can be a personnel detection instruction. In practice, the personnel detection instruction can be an instruction to detect the target personnel. The personnel-related detection device in at least one personnel-related detection device can be a device associated with personnel detection of the target personnel. For example, the personnel-related detection device can be but is not limited to at least one of the following: a camera device, an audio device, and a camera support device.

[0042] The third step is to, in response to receiving the first real-time patrol information for the target cable tunnel, start the track-type robot using the cable twin model to perform the first real-time patrol task for the target cable tunnel. The first real-time patrol information may be an instruction to perform a real-time patrol using the track-type robot.

[0043] In step 4, in response to receiving the second real-time patrol information for the target cable tunnel, the cable twin model and the augmented reality glasses are used to perform a second real-time patrol task for the target cable tunnel. The second real-time patrol information may be an instruction to wear augmented reality glasses for real-time patrol.

[0044] In step 5, in response to receiving the fire simulation information for the target cable tunnel, the firefighting robot is started using the cable twin model to perform the fire simulation task for the target cable tunnel. The fire simulation information may be an instruction to perform a fire simulation process. The firefighting robot may be a robot that performs a firefighting task.

[0045] In some optional implementations of some embodiments, after step 106, the steps further include:

[0046] The first step is to obtain, in response to the detection of abnormal information displayed by the cable twin model, which characterizes the existence of abnormalities in the various real-time data in the target cable tunnel, an infrared imaging video of the cable set in the target cable tunnel within a predetermined time period taken by an infrared camera, and an optical imaging video of the cable set within the preset time period taken by an optical camera. The predetermined time period can be the previous historical time period of the corresponding moment of the currently detected abnormal information. For example, the current corresponding moment of the detected abnormal information is "16:00". The predetermined time period can be "12". The cables in the cable set are cables located in the corresponding area of ​​the target cable tunnel.

[0047] In the second step, the infrared imaging video and the optical imaging video are subjected to frame extraction processing every predetermined number to obtain an infrared imaging image sequence and an optical imaging image sequence. For example, the predetermined number may be "2".

[0048] The third step is to input each optical imaging image in the above optical imaging image sequence into a pre-trained first cable identification information generation model to generate a cable location information set and a cable type information set corresponding to the above cable set, and obtain a cable location information set sequence and a cable type information set sequence.

[0049] The first cable identification information generation model may be a neural network model for generating cable identification information. The cable identification information may include: cable position information and cable type information. For example, the first cable identification information generation model may be a YOLO model. The cable position information may be the position coordinates of the cable pixel position in the image. The cable type information may be the cable information model of the cable in the image.

[0050] The fourth step is to generate the position association relationship information between the cables in the cable set and the cable type information corresponding to the cables according to the cable position information set sequence and the cable type information set sequence.

[0051] As an example, the execution entity may aggregate and deduplicate the cable location information set sequence and the cable type information set sequence to generate the location association relationship information between the cables in the cable set and the cable type information corresponding to the cables.

[0052] The fifth step is to input the positional association relationship information between the infrared imaging image and each of the cables into a pre-trained second cable identification information generation model for each infrared imaging image in the infrared imaging image sequence, so as to generate each infrared image cable position information corresponding to each of the cables and each infrared cable type information corresponding to each of the cables.

[0053] The second cable identification information generation model may be a model that outputs corresponding cable identification information when the input is an infrared imaging image. In practice, the second cable identification information generation model may be a YOLO model. The infrared image cable position information may be the cable position coordinates of the cable in the infrared imaging image. The infrared cable type information may be the cable type information of the cable in the infrared imaging image.

[0054] The sixth step is to input the infrared imaging image, the corresponding infrared image cable position information and the corresponding infrared cable type information of each infrared imaging image into a pre-trained cable anomaly detection model for each infrared imaging image in the above infrared imaging image sequence to generate cable anomaly prediction information for each cable in the above infrared imaging image.

[0055] The cable anomaly detection model may be a neural network model for detecting whether a cable is abnormal. That is, the cable anomaly detection model may be a model for generating cable anomaly prediction information. In practice, the cable anomaly detection model may be a cable temperature classification neural network model based on cable type. In practice, the cable anomaly detection model may be a multi-layer serially connected convolutional neural network model. The cable anomaly prediction information may characterize the cable anomaly prediction of each cable.

[0056] The seventh step is to generate cable anomaly information corresponding to each cable in the above cable set according to the obtained cable anomaly prediction information sequence.

[0057] As an example, the execution entity may summarize the cable anomalies of the individual cable anomaly prediction information in the cable anomaly prediction information set sequence according to the cable dimension, so as to generate individual cable anomaly information corresponding to each cable.

[0058] In some optional implementations of some embodiments, the step of inputting each optical imaging image in the optical imaging image sequence into the first cable identification information generation model to generate a cable location information set and a cable type information set corresponding to the cable set may include the following steps:

[0059] The first step is to perform image preprocessing on the optical imaging image to obtain a preprocessed image.

[0060] As an example, the above execution subject can perform image grayscale processing on the optical imaging image to obtain a pre-processed image.

[0061] In the second step, the preprocessed image is input into the first scale feature extraction model, the second scale feature extraction model and the third scale feature extraction model included in the first cable identification information generation model to generate the first image feature information, the second image feature information and the third image feature information accordingly. The feature scale corresponding to the first image feature information is larger than the feature scale corresponding to the second image feature information, and the feature scale corresponding to the second image feature information is larger than the feature scale corresponding to the third image feature information. The first scale feature extraction model, the second scale feature extraction model and the third scale feature extraction model can be models for extracting features based on the vector scale of the output vector. The first scale feature extraction model, the second scale feature extraction model and the third scale feature extraction model can be feature extraction models of convolutional neural networks with different corresponding layers and multiple layers connected in series.

[0062] In the third step, the second image feature information is downsampled at a first scale and upsampled at a first scale to obtain first downsampled feature information and first upsampled feature information, wherein the feature scale corresponding to the first downsampled feature information is the same as the feature scale corresponding to the third image feature information, and the feature scale corresponding to the first upsampled feature information is the same as the feature scale corresponding to the first image feature information.

[0063] The fourth step is to perform corresponding multiplication of the first down-sampling feature information and the first coefficient matrix to obtain the first multiplied feature information. The first coefficient matrix is ​​a trainable and updateable network parameter matrix.

[0064] The fifth step is to multiply the first up-sampled feature information with the second coefficient matrix to obtain second multiplied feature information. The second coefficient matrix is ​​a trainable and updateable network parameter matrix.

[0065] In the sixth step, the first multiplied feature information and the first image feature information are fused to generate first fused feature information.

[0066] As an example, the execution entity may perform feature information splicing on the first multiplication feature information and the first image feature information to generate spliced ​​feature information as the first fusion feature information.

[0067] In the seventh step, the second multiplied feature information and the second image feature information are fused to generate second fused feature information.

[0068] In the eighth step, the first fusion feature information is input into the fourth scale feature extraction model included in the first cable identification information generation model to generate fourth image feature information.

[0069] In the ninth step, the first image feature information is input into the fifth scale feature extraction model included in the first cable identification information generation model to generate fifth image feature information, wherein the feature scale corresponding to the fifth scale feature extraction model is smaller than the feature scale corresponding to the fourth scale feature extraction model.

[0070] In the tenth step, the second fusion feature information is input into the sixth scale feature extraction model included in the first cable identification information generation model to generate sixth image feature information. The feature scale corresponding to the sixth scale feature extraction model is smaller than the feature scale corresponding to the fifth scale feature extraction model.

[0071] In the eleventh step, the fourth image feature information is downsampled by a second scale and a third scale to obtain second downsampled feature information and third downsampled feature information, wherein the feature scale corresponding to the second downsampled feature information is the same as the feature scale corresponding to the fifth image feature information, and the feature scale corresponding to the third downsampled feature information is the same as the feature scale corresponding to the sixth image feature information.

[0072] In the twelfth step, the second down-sampled feature information is correspondingly multiplied by the third coefficient matrix to obtain third multiplied feature information, wherein the third coefficient matrix is ​​a trainable and updateable network parameter matrix.

[0073] In the thirteenth step, the third down-sampling feature information is correspondingly multiplied with the fourth coefficient matrix to obtain fourth multiplied feature information. The fourth coefficient matrix is ​​a trainable and updateable network parameter matrix.

[0074] In the fourteenth step, the third multiplied feature information and the fifth image feature information are fused to generate third fused feature information.

[0075] In the fifteenth step, the fourth multiplied feature information and the sixth image feature information are fused to generate fourth fused feature information.

[0076] In the sixteenth step, the fourth image feature information is input into the seventh scale feature extraction model included in the first cable identification information generation model to generate the seventh image feature information.

[0077] Step 17: Input the third fusion feature information into the eighth scale feature extraction model included in the first cable identification information generation model to generate eighth image feature information. The feature scale corresponding to the eighth scale feature extraction model is smaller than the feature scale corresponding to the seventh scale feature extraction model.

[0078] Step 18: input the fourth fusion feature information into the ninth scale feature extraction model included in the first cable identification information generation model to generate ninth image feature information, wherein the feature scale corresponding to the ninth scale feature extraction model is smaller than the feature scale corresponding to the eighth scale feature extraction model;

[0079] In step 19, the ninth image feature information is subjected to second scale upsampling and third scale upsampling to obtain second upsampled feature information and third upsampled feature information, wherein the feature scale corresponding to the second downsampled feature information is the same as the feature scale corresponding to the seventh image feature information, and the feature scale corresponding to the third upsampled feature information is the same as the feature scale corresponding to the ninth image feature information.

[0080] In the twentieth step, the second up-sampling feature information is correspondingly multiplied by the fifth coefficient matrix to obtain fifth multiplied feature information, wherein the fifth coefficient matrix is ​​a trainable and updateable network parameter matrix.

[0081] In the 21st step, the third up-sampled feature information is correspondingly multiplied by the sixth coefficient matrix to obtain the sixth multiplied feature information. The sixth coefficient matrix is ​​a trainable and updateable network parameter matrix.

[0082] Optionally, the step of inputting each optical imaging image in the optical imaging image sequence into a first cable identification information generation model to generate a cable location information set and a cable type information set corresponding to the cable set further includes the following steps:

[0083] In the first step, the fifth multiplied feature information, the sixth multiplied feature information and the ninth image feature information are input into the multi-head attention mechanism model included in the first cable identification information generation model to generate attention feature information. The multi-head attention mechanism model can be a Transformer model.

[0084] The second step is to input the attention feature information into the cable information generation layer included in the first cable identification information generation model to generate a cable location information set and a cable type information set corresponding to the cable set. The cable information generation layer can be a fully connected layer with multiple layers of serial connections.

[0085] As one of the invention points, the second technical problem in the background technology is solved: "When generating cable identification information based on optical imaging, the feature information extracted is not comprehensive and rich enough, resulting in the subsequent cable identification information being not accurate enough." Based on this, the present invention uses the first coefficient matrix, the second coefficient matrix, the third coefficient matrix, the fourth coefficient matrix and the fifth coefficient matrix to make the feature information of each scale to be diversified and fused to obtain fused feature information. Finally, the multi-head attention mechanism model and the cable information generation layer are used to accurately generate the cable location information set and the cable type information set corresponding to the above cable set.

[0086] In some optional implementations of some embodiments, the steps further include:

[0087] The above-mentioned execution entity can send the cable abnormality information corresponding to the above-mentioned each cable to the above-mentioned cable twin model, and according to the cable abnormality information corresponding to the above-mentioned each cable, the above-mentioned cable twin model instructs the target robot to travel to the corresponding cable to perform deep abnormality detection of the cable.

[0088] In some optional implementations of some embodiments, the generating of the cable abnormality information corresponding to each cable in the cable set according to the obtained cable abnormality prediction information sequence may include the following steps:

[0089] The first step is to adjust the cable anomaly prediction information of the cable anomaly prediction information set sequence to generate a cable anomaly prediction information sequence for each cable, thereby obtaining a cable anomaly prediction information sequence set.

[0090] In the second step, for each cable anomaly prediction information sequence in the cable anomaly prediction information sequence set, the following generation steps are performed:

[0091] Sub-step 1: determine the cable abnormality prediction information characterizing the cable temperature abnormality in the above-mentioned cable abnormality prediction information sequence as the target cable abnormality prediction information, and obtain at least one target cable abnormality prediction information.

[0092] Sub-step 2: determining a ratio value between the number of information corresponding to the at least one target cable anomaly prediction information and the number of information corresponding to the cable anomaly prediction information sequence.

[0093] Sub-step 3, in response to determining that the number ratio is less than a predetermined value, generating cable abnormality information indicating that the cable corresponding to the cable abnormality prediction information sequence has no abnormality. For example, the predetermined value may be 70%.

[0094] In a third step, in response to determining that the number ratio value is greater than or equal to the predetermined value, cable abnormality information is generated, indicating that an abnormality exists in the cable corresponding to the cable abnormality prediction information sequence.

[0095] In some optional implementations of some embodiments, the cable location information in the cable location information set sequence corresponds to the cable type information in the cable type information set sequence, and the cable location information is pixel area location information. The pixel area location information may be location information of a pixel area location in an image.

[0096] Optionally, the generating of the position association relationship information between the cables in the cable set and the cable type information corresponding to the cables according to the cable position information set sequence and the cable type information set sequence may include the following steps:

[0097] The first step is to determine the actual cable position information corresponding to each cable position information in the cable position information set sequence to obtain the cable actual position information set sequence, wherein the cable actual position information may be the actual cable position in the coordinate system established in reality corresponding to the image position information.

[0098] The second step is to determine the area location information corresponding to the target area. The area location information may be the actual area location range corresponding to the target cable area. The area location information may be in the form of coordinates.

[0099] The third step is to remove the cable actual location information whose location information is not within the above-mentioned regional location information from the above-mentioned cable actual location information set sequence to obtain the cable location information set after removal.

[0100] The fourth step is to perform cable information removal processing on the above-mentioned cable position information set after removal to obtain at least one cable information.

[0101] As an example, the execution subject may perform cable information deduplication processing on the cable position information set after removal to obtain at least one piece of cable information.

[0102] The fifth step is to determine the position association relationship information between the cables and the cable type information corresponding to the cables according to the at least one cable position information and the at least one cable type information corresponding to the at least one cable information.

[0103] As an example, the execution entity may aggregate at least one cable position information and at least one corresponding cable type information to generate position association relationship information between the cables and cable type information corresponding to the cables.

[0104] Optionally, the above-mentioned determination of the actual cable location information corresponding to each cable location information in the above-mentioned cable location information set sequence may include the following steps:

[0105] The first step is to determine the optical imaging image corresponding to the above cable position information as the target optical imaging image, wherein the target optical imaging image may be an optical imaging image that only includes the corresponding cable information.

[0106] The second step is to obtain an image-region correspondence transformation model between the above-mentioned target optical imaging image and the actual target cable region. The image-region correspondence transformation model can be a 3D coordinate transformation model. The image-region correspondence transformation model represents the transformation relationship between image pixels and each coordinate in the actual coordinate system.

[0107] The third step is to use the above-mentioned image and region correspondence transformation model to determine the pixel transformation information corresponding to the pixel region position information corresponding to the above-mentioned cable position information as the actual cable position information.

[0108] The above-mentioned various embodiments of the present disclosure have the following beneficial effects: through the intelligent operation and maintenance method of the cable tunnel based on the digital twin technology of some embodiments of the present disclosure, the cable twin model is accurately generated to realize the intelligent operation and maintenance of the cable tunnel, and the cable accident is avoided. Specifically, the reason for the inefficiency of the operation and maintenance of the relevant cable tunnel is that it is necessary to manually observe the multiple real-time data corresponding to the multiple sensors in real time, which not only wastes a lot of manpower and material resources, but also cannot efficiently realize real-time abnormal detection, resulting in the inability to carry out subsequent operation and maintenance work synchronously, and cable accidents may occur. Based on this, the intelligent operation and maintenance method of the cable tunnel based on the digital twin technology of some embodiments of the present disclosure, first, obtains the point cloud data set and tunnel drawings for the target cable tunnel, so as to comprehensively determine the tunnel structure and tunnel scene information of the target cable tunnel from a two-dimensional perspective and a three-dimensional perspective, so as to facilitate the subsequent accurate generation of the initial three-dimensional cable tunnel model. Then, according to the above-mentioned point cloud data set and the above-mentioned tunnel drawings, the initial three-dimensional cable tunnel model can be accurately constructed to generate tunnel scene information that preliminarily reflects the relevant target cable tunnel. Then, according to each sensor installed in the target cable tunnel, the real-time sensing data corresponding to each sensor is obtained to obtain each real-time sensing data, so as to understand the real-time status of the tunnel in the target cable tunnel and determine whether there is an abnormal problem in the target cable tunnel. Then, according to each real-time sensing data, the cable operation analysis information for the target cable tunnel can be accurately generated, so as to determine the operation status of the target cable tunnel and summarize all aspects, so as to understand the abnormal problems of the target cable tunnel in real time. Among them, each real-time sensing data includes: cable current, voltage, temperature, ambient temperature, humidity and gas concentration. Furthermore, according to each real-time sensing data and the cable operation analysis information, a cable twin model for the target cable tunnel can be accurately generated, so as to realize the intelligent display and analysis of the operation status corresponding to the cable tunnel by using the cable twin model. Finally, the cable twin model is used to perform at least one operation and maintenance processing task for the target cable tunnel in real time to ensure the efficiency of operation and maintenance processing.

[0109] Further references Figure 2 As an implementation of the methods shown in the above figures, the present disclosure provides some embodiments of a cable tunnel intelligent operation and maintenance device based on digital twin technology. These device embodiments are similar to Figure 1 Corresponding to the method embodiments shown, the intelligent operation and maintenance device for cable tunnels based on digital twin technology can be specifically applied to various electronic devices.

[0110] like Figure 2As shown, a cable tunnel intelligent operation and maintenance device 200 based on digital twin technology includes: a first acquisition unit 201, a construction unit 202, a second acquisition unit 203, a first generation unit 204, a second generation unit 205 and an execution unit 206. Among them, the first acquisition unit 201 is configured to acquire a point cloud data set and a tunnel drawing for the target cable tunnel; the construction unit 202 is configured to construct an initial three-dimensional cable tunnel model based on the above point cloud data set and the above tunnel drawing; the second acquisition unit 203 is configured to acquire the real-time perception data corresponding to each sensor installed in the above target cable tunnel, and obtain each real-time perception data, wherein the above each real-time perception data includes: cable current, voltage, temperature, ambient temperature, humidity and gas concentration; the first generation unit 204 is configured to generate cable operation analysis information for the above target cable tunnel according to the above each real-time perception data; the second generation unit 205 is configured to generate a cable twin model for the above target cable tunnel according to the above each real-time perception data and the above cable operation analysis information; the execution unit 206 is configured to use the above cable twin model to perform at least one operation and maintenance processing task for the above target cable tunnel.

[0111] It can be understood that the units recorded in the cable tunnel intelligent operation and maintenance device 200 based on digital twin technology are similar to the reference Figure 1 Therefore, the operations, features and beneficial effects described above for the method are also applicable to the intelligent operation and maintenance device 200 for cable tunnels and the units contained therein, and will not be described in detail here.

[0112] Reference below Figure 3 , which shows a structural schematic diagram of an electronic device (eg, an electronic device) 300 suitable for implementing some embodiments of the present disclosure. Figure 3 The electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0113] like Figure 3 As shown, the electronic device 300 may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 301, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 302 or a program loaded from a storage device 308 into a random access memory (RAM) 303. In the RAM 303, various programs and data required for the operation of the electronic device 300 are also stored. The processing device 301, the ROM 302, and the RAM 303 are connected to each other via a bus 304. An input / output (I / O) interface 305 is also connected to the bus 304.

[0114] Typically, the following devices may be connected to the I / O interface 305: input devices 306 including, for example, a touch screen, a touch pad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; output devices 307 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; storage devices 308 including, for example, a magnetic tape, a hard disk, etc.; and communication devices 309. The communication devices 309 may allow the electronic device 300 to communicate with other devices wirelessly or by wire to exchange data. Although Figure 3 The electronic device 300 is shown with various devices, but it should be understood that it is not required to implement or possess all the devices shown. More or fewer devices may be implemented or possessed instead. Figure 3 Each block shown in the figure may represent one device, or may represent multiple devices as required.

[0115] In particular, according to some embodiments of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, some embodiments of the present disclosure include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In some such embodiments, the computer program can be downloaded and installed from the network through the communication device 309, or installed from the storage device 308, or installed from the ROM 302. When the computer program is executed by the processing device 301, the above-mentioned functions defined in the method of some embodiments of the present disclosure are executed.

[0116] It should be noted that the computer-readable medium in some embodiments of the present disclosure may be a computer-readable signal medium or a computer-readable storage medium or any combination of the two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In some embodiments of the present disclosure, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device or device. In some embodiments of the present disclosure, the computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, in which a computer-readable program code is carried. This propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. The computer readable signal medium may also be any computer readable medium other than a computer readable storage medium, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer readable medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0117] In some embodiments, the client and the server may communicate using any currently known or future developed network protocol such as HTTP (HyperText Transfer Protocol), and may be interconnected with any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), an internet (e.g., the Internet), and a peer-to-peer network (e.g., an ad hoc peer-to-peer network), as well as any currently known or future developed network.

[0118] The computer-readable medium may be included in the electronic device; or it may exist independently without being assembled into the electronic device. The computer-readable medium carries one or more programs. When the one or more programs are executed by the electronic device, the electronic device: obtains a point cloud data set and a tunnel drawing for the target cable tunnel; constructs an initial three-dimensional cable tunnel model based on the point cloud data set and the tunnel drawing; obtains real-time sensing data corresponding to each sensor installed in the target cable tunnel, and obtains each real-time sensing data, wherein each real-time sensing data includes: cable current, voltage, temperature, ambient temperature, humidity and gas concentration; generates cable operation analysis information for the target cable tunnel based on each real-time sensing data; generates a cable twin model for the target cable tunnel based on each real-time sensing data and the cable operation analysis information; and uses the cable twin model to perform at least one operation and maintenance processing task for the target cable tunnel.

[0119] Computer program code for performing the operations of some embodiments of the present disclosure may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0120] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present disclosure. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some implementations as replacements, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession 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 flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0121] The units described in some embodiments of the present disclosure may be implemented by software or hardware. The units described may also be set in a processor, for example, may be described as: a processor includes a first acquisition unit, a construction unit, a second acquisition unit, a first generation unit, a second generation unit and an execution unit. The names of these units do not constitute a limitation on the units themselves in some cases, for example, the first acquisition unit may also be described as "a unit for acquiring a point cloud data set and a tunnel drawing for a target cable tunnel".

[0122] The functions described above herein may be performed at least in part by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), and the like.

[0123] The above descriptions are only some preferred embodiments of the present disclosure and an explanation of the technical principles used. Those skilled in the art should understand that the scope of the invention involved in the embodiments of the present disclosure is not limited to the technical solutions formed by a specific combination of the above-mentioned technical features, but should also cover other technical solutions formed by any combination of the above-mentioned technical features or their equivalent features without departing from the above-mentioned inventive concept. For example, the above-mentioned features are replaced with the technical features with similar functions disclosed in the embodiments of the present disclosure (but not limited to) and the technical solutions formed.

Claims

1. A cable tunnel intelligent operation and maintenance method based on digital twin technology, comprising: Obtain point cloud datasets and tunnel drawings for the target cable tunnel; constructing an initial three-dimensional cable tunnel model according to the point cloud data set and the tunnel drawing; According to each sensor installed in the target cable tunnel, real-time sensing data corresponding to each sensor is acquired to obtain each real-time sensing data, wherein each real-time sensing data includes: cable current, voltage, temperature, ambient temperature, humidity and gas concentration; Generate cable operation analysis information for the target cable tunnel according to the various real-time sensing data; Generate a cable twin model for the target cable tunnel according to the various real-time sensing data and the cable operation analysis information; Utilizing the cable twin model, at least one operation and maintenance task for the target cable tunnel is performed.

2. The method according to claim 1, wherein: The at least one operation and maintenance processing task includes: a real-time gas detection task, a real-time personnel detection task, a first real-time patrol task based on a track-mounted robot, a fire simulation task, and a second real-time patrol task based on augmented reality glasses; and The utilizing the cable twin model to perform at least one processing task for the target cable tunnel comprises: In response to receiving the real-time gas detection information for the target cable tunnel, using the cable twin model, starting at least one gas-related detection device in the target cable tunnel to perform the real-time gas detection task; In response to receiving personnel detection information for the target cable tunnel, using the cable twin model, starting at least one personnel-related detection device in the target cable tunnel to perform the real-time personnel detection task; In response to receiving first real-time patrol information for the target cable tunnel, using the cable twin model, starting the track-mounted robot to perform a first real-time patrol mission for the target cable tunnel; In response to receiving second real-time patrol information for the target cable tunnel, using the cable twin model and the augmented reality glasses to perform a second real-time patrol task for the target cable tunnel; In response to receiving the fire simulation information for the target cable tunnel, the firefighting robot is activated using the cable twin model to perform a fire simulation task for the target cable tunnel.

3. The method according to claim 1, wherein: The method further comprises: In response to detecting abnormal information displayed by the cable twin model indicating that various real-time data in the target cable tunnel are abnormal, obtaining an infrared imaging video of the cable set in the target cable tunnel within a predetermined time period shot by an infrared camera, and obtaining an optical imaging video of the cable set within the preset time period shot by an optical camera; Perform frame extraction processing on the infrared imaging video and the optical imaging video at predetermined intervals to obtain an infrared imaging image sequence and an optical imaging image sequence; Inputting each optical imaging image in the optical imaging image sequence into a pre-trained first cable identification information generation model to generate a cable position information set and a cable type information set corresponding to the cable set, thereby obtaining a cable position information set sequence and a cable type information set sequence; Generate position association relationship information between the cables in the cable set and cable type information corresponding to the cables according to the cable position information set sequence and the cable type information set sequence; For each infrared imaging image in the infrared imaging image sequence, inputting the position association relationship information between the infrared imaging image and each cable into a pre-trained second cable identification information generation model to generate each infrared image cable position information corresponding to each cable and each infrared cable type information corresponding to each cable; For each infrared imaging image in the infrared imaging image sequence, the infrared imaging image, the corresponding infrared image cable position information and the corresponding infrared cable type information are input into a pre-trained cable anomaly detection model to generate cable anomaly prediction information for each cable in the infrared imaging image; According to the obtained cable anomaly prediction information sequence, cable anomaly information corresponding to each cable in the cable set is generated.

4. The method according to claim 3, wherein: The method further comprises: The cable abnormality information corresponding to each cable is sent to the cable twin model, and based on the cable abnormality information corresponding to each cable, the cable twin model instructs the target robot to travel to the corresponding cable to perform in-depth abnormality detection of the cable.

5. The method according to claim 4, wherein: The generating, according to the obtained cable anomaly prediction information sequence, cable anomaly information corresponding to each cable in the cable set comprises: Performing cable anomaly prediction information adjustment on the cable anomaly prediction information set sequence to generate a cable anomaly prediction information sequence for each cable, thereby obtaining a cable anomaly prediction information sequence set; For each cable anomaly prediction information sequence in the cable anomaly prediction information sequence set, the following generation steps are performed: Determine the cable abnormality prediction information in the cable abnormality prediction information sequence that characterizes the cable temperature abnormality as the target cable abnormality prediction information, and obtain at least one target cable abnormality prediction information; Determine a ratio value between the number of information corresponding to the at least one target cable anomaly prediction information and the number of information corresponding to the cable anomaly prediction information sequence; In response to determining that the number ratio value is less than a predetermined value, generating cable abnormality information indicating that there is no abnormality in the cable corresponding to the cable abnormality prediction information sequence; In response to determining that the number ratio value is greater than or equal to the predetermined value, cable abnormality information is generated, indicating that an abnormality exists in the cable corresponding to the cable abnormality prediction information sequence.

6. The method according to claim 5, wherein: There is a corresponding relationship between the cable position information in the cable position information set sequence and the cable type information in the cable type information set sequence, and the cable position information is pixel area position information; as well as The step of generating the position association relationship information between the cables in the cable set and the cable type information corresponding to the cables according to the cable position information set sequence and the cable type information set sequence comprises: Determine the cable actual position information corresponding to each cable position information in the cable position information set sequence to obtain the cable actual position information set sequence; Determine the area location information corresponding to the target area; Remove the cable actual location information whose location information is not within the area location information from the cable actual location information set sequence to obtain a cable location information set after removal; Performing cable information removal processing on the removed cable position information set to obtain at least one cable information; According to at least one cable position information and at least one cable type information corresponding to the at least one cable information, position association relationship information between the cables and cable type information corresponding to the cables are determined.

7. The method according to claim 6, wherein: The determining the actual cable location information corresponding to each cable location information in the cable location information set sequence comprises: Determine an optical imaging image corresponding to the cable position information as a target optical imaging image; Acquire an image-region correspondence transformation model between the target optical imaging image and the actual target cable region; The image and region correspondence transformation model is used to determine pixel transformation information corresponding to the pixel region position information corresponding to the cable position information as the actual cable position information.

8. An intelligent operation and maintenance device for a cable tunnel based on digital twin technology, comprising: A first acquisition unit is configured to acquire a point cloud data set and a tunnel drawing for a target cable tunnel; A construction unit configured to construct an initial three-dimensional cable tunnel model according to the point cloud data set and the tunnel drawing; A second acquisition unit is configured to acquire real-time sensing data corresponding to each sensor installed in the target cable tunnel to obtain each real-time sensing data, wherein each real-time sensing data includes: cable current, voltage, temperature, ambient temperature, humidity and gas concentration; A first generating unit is configured to generate cable operation analysis information for the target cable tunnel according to the respective real-time sensing data; A second generating unit is configured to generate a cable twin model for the target cable tunnel according to the respective real-time sensing data and the cable operation analysis information; An execution unit is configured to use the cable twin model to execute at least one operation and maintenance processing task for the target cable tunnel.

9. An electronic device, comprising: one or more processors; a storage device having one or more programs stored thereon, When the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1 to 7.

10. A computer readable medium having a computer program stored thereon, wherein: When the program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images