A fire warning method for intelligent cables

Through the combination of cable feature perception module and early warning module, cable image and operation feature information are analyzed, and the distribution field is built for fire trend analysis, which solves the problem of inaccurate and timely cable fire warning in the existing technology, and achieves a more accurate and timely Early warning.

CN118840818BActive Publication Date: 2024-12-03JIANGSU DAYUAN ELECTRONIC TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411311557.7
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-09-20
Publication Date
2024-12-03
Estimated Expiration
2044-09-20

AI Technical Summary

Technical Problem

In the prior art, cable fire warnings are not accurate and timely enough, making it difficult to comprehensively monitor the cable status, resulting in the expansion of fire accidents.

Method used

The cable image is collected through the cable feature perception module, the arc sag and density are analyzed, and the insulation aging and load analysis is carried out in combination with the operation feature information, the insulation aging distribution field and the operation load distribution field are built, and the early warning module is used to analyze and make decisions on fire trends and make decisions. Early warning.

Benefits of technology

Improve the accuracy and timeliness of cable fire warnings to ensure the safe operation of the cable.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118840818B_ABST
    Figure CN118840818B_ABST
Patent Text Reader

Abstract

The present invention discloses a fire warning method for an intelligent cable, and relates to the technical field of fire warning. The method comprises: collecting a cable image on a target cable, and analyzing the sag and density; performing insulation aging analysis according to the cable image, and obtaining insulation aging information; collecting operation characteristic information, performing operation load analysis, and obtaining operation load information; performing adaptive adjustment on the insulation aging information and the operation load information according to the sag and density, obtaining adjusted insulation aging information and adjusted operation load information, and constructing and rendering to obtain the insulation aging distribution field and the operation load distribution field on the target cable; performing fire trend analysis according to the insulation aging distribution field and the operation load distribution field, obtaining the fire trend analysis results, and making decision warnings. The method solves the technical problem that the cable fire warning in the prior art is not accurate and timely enough, and achieves the technical effect of improving the accuracy and timeliness of the cable fire warning.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of fire early warning, and in particular to a fire early warning method for an intelligent cable. Background Art

[0002] With the rapid development of modern power networks, cables, as an important carrier of power transmission, are crucial to the operation of the entire power system in terms of safety and stability. However, during long-term operation, cables are prone to fire accidents due to various factors such as insulation aging and overload, posing a serious threat to people's lives and property. Traditional cable fire warning methods often rely on a single monitoring parameter, which makes it difficult to accurately judge the trend of the fire, and untimely warnings can easily lead to the expansion of accidents. Therefore, there is a need for an intelligent cable fire warning method that can comprehensively and accurately monitor the cable status and timely warn of fires, so as to achieve comprehensive monitoring of the cable status and accurate judgment of the fire trend, and provide strong guarantees for the safe operation of the cable. Summary of the invention

[0003] The embodiment of the present application provides a fire warning method for an intelligent cable, which solves the technical problem in the prior art that cable fire warning is not accurate and timely enough.

[0004] In view of the above problems, an embodiment of the present application provides a fire warning method for an intelligent cable.

[0005] The present application embodiment provides a fire warning method for an intelligent cable, the method comprising:

[0006] The cable feature sensing module collects cable images of multiple parts on the target cable, and analyzes multiple sags and multiple densities of the multiple parts;

[0007] Perform insulation aging analysis on the multiple parts according to the multiple cable images to obtain multiple insulation aging information;

[0008] Collecting the operation characteristic information of the multiple parts through the operation characteristic perception module, performing operation load analysis on the multiple parts, and obtaining multiple operation load information, wherein the operation characteristic information includes current load information and temperature information;

[0009] Adaptively adjust the multiple insulation aging information and the multiple operating load information according to the multiple sags and the multiple densities to obtain multiple adjusted insulation aging information and multiple adjusted operating load information, and construct and render to obtain the insulation aging distribution field and the operating load distribution field on the target cable;

[0010] Through the early warning module, a fire trend analysis is performed according to the insulation aging distribution field and the operating load distribution field, the fire trend analysis results are obtained, and a decision-making early warning is performed.

[0011] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0012] Through the cable feature perception module, the cable images of multiple parts on the target cable are collected, and the multiple sags and multiple densities of the multiple parts are analyzed. According to the multiple cable images, the insulation aging analysis of the multiple parts is performed to obtain multiple insulation aging information. Through the operation feature perception module, the operation feature information of the multiple parts is collected, and the operation load analysis of the multiple parts is performed to obtain multiple operation load information, wherein the operation feature information includes current load information and temperature information. According to the multiple sags and multiple densities, the multiple insulation aging information and the multiple operation load information are adaptively adjusted to obtain multiple adjusted insulation aging information and multiple adjusted operation load information, and the insulation aging distribution field and the operation load distribution field on the target cable are constructed and rendered. Through the early warning module, according to the insulation aging distribution field and the operation load distribution field, the fire trend analysis is performed to obtain the fire trend analysis results, and the decision-making early warning is performed. The technical problem that the cable fire early warning in the prior art is not accurate and timely is solved, and the technical effect of improving the accuracy and timeliness of the cable fire early warning is achieved. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0014] Figure 1 A schematic flow chart of a fire warning method for an intelligent cable provided in an embodiment of the present application;

[0015] Figure 2 A schematic diagram of a flow chart of performing insulation aging analysis of multiple parts in a fire warning method of an intelligent cable provided in an embodiment of the present application;

[0016] Figure 3 A schematic diagram of a flow chart of operating load analysis of multiple parts in a fire warning method for an intelligent cable provided in an embodiment of the present application. DETAILED DESCRIPTION

[0017] The embodiment of the present application solves the technical problem in the prior art that cable fire warning is not accurate and timely enough by providing a fire warning method for an intelligent cable.

[0018] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0019] It should be noted that the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or server that includes a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or modules that are not explicitly listed or are inherent to these processes, methods, products or devices.

[0020] Embodiment 1

[0021] like Figure 1 As shown, an embodiment of the present application provides a fire warning method for an intelligent cable, the method is applied to a fire warning device for an intelligent cable, the device includes a cable feature sensing module, an operation feature sensing module and a warning module, wherein the method includes:

[0022] The cable feature sensing module collects cable images of multiple parts on the target cable, and analyzes multiple sags and multiple densities of the multiple parts;

[0023] An intelligent cable fire warning device integrates a cable feature sensing module, an operation feature sensing module and a warning module. It can collect various status information of the cable in real time and perform fire trend analysis, thereby achieving timely fire warning.

[0024] The cable feature perception module is responsible for collecting cable images of multiple parts on the target cable. These images can intuitively reflect the appearance of the cable, including the arrangement, bending, connection and other physical characteristics of the cable. After obtaining the cable image, the cable feature perception module will conduct a detailed analysis of multiple sags and multiple densities of multiple parts in the image. Sag is the degree of bending of the cable. The greater the sag, the greater the degree of mechanical damage to the insulation layer inside the cable, and the higher the probability of fire. Density refers to the density of the cable. The denser the cable, the higher the temperature and the greater the load, and the higher the probability of fire. Generally speaking, the sag of the part hanging down in the middle of the cable is large, and the part fixed on the edge of the pole tower is similar to other cables and has a high density.

[0025] Furthermore, the cable feature sensing module collects cable images of multiple parts on the target cable, and analyzes multiple sags and multiple densities of the multiple parts, including:

[0026] The cable feature sensing module is used to collect cable images of multiple parts of the target cable;

[0027] Splicing and fusing multiple cable images to obtain an overall cable image of the target cable;

[0028] Acquire a set of sample cable overall images, identify the curvature of the multiple parts in each sample cable overall image and the distance between the cable and other cables, process and identify to obtain multiple sample sag sets and multiple sample density sets, wherein the curvature and sag are positively correlated, and the cable distance and density are negatively correlated;

[0029] A cable feature identifier is constructed by using the sample cable overall image set, multiple sample sag sets, and multiple sample density sets;

[0030] Based on the cable feature identifier, the overall image of the cable is identified to obtain multiple sags and multiple densities of the multiple parts.

[0031] The cable feature perception module starts an image acquisition device, such as a high-definition camera, to acquire images of multiple parts of the target cable. Since the cable may span a large area, a single image may not be able to fully display its entire appearance. Therefore, the multiple cable images acquired are spliced ​​and fused to form a complete cable image. In order to train the cable feature identifier, a set of sample cable images is first acquired. Then, multiple parts of the cable in each sample image are identified, including their curvature and distance from other cables. Curvature is positively correlated with sag, while the distance between cables is negatively correlated with density. After processing, these features are identified and form multiple sample sag sets and multiple sample density sets. A cable feature identifier is constructed based on the sample cable image set, multiple sample sag sets, and multiple sample density sets. The identifier learns the features of sag and density in the cable image and can accurately identify these features in subsequent analysis. After the cable feature identifier is constructed, the cable image is identified based on the cable feature identifier. Through identification, multiple sag and multiple density information of multiple parts of the cable are obtained.

[0032] Perform insulation aging analysis on the multiple parts according to the multiple cable images to obtain multiple insulation aging information;

[0033] Based on multiple cable images collected by the cable feature sensing module, insulation aging analysis of multiple parts is performed to obtain multiple insulation aging information. The insulation aging information includes the insulation aging level of each cable part, the specific value or description of the aging degree, etc.

[0034] Furthermore, if Figure 2As shown, according to the multiple cable images, insulation aging analysis of the multiple parts is performed to obtain multiple insulation aging information, including:

[0035] Based on the cable aging detection data records, a sample cable image set is obtained, and according to the number and width of cracks on the cable surface in each sample cable image, the evaluation mark is obtained to obtain a sample insulation aging information set;

[0036] The sample cable image set and the sample insulation aging information set are used to construct an insulation aging identifier, and the multiple cable images are identified to obtain the multiple insulation aging information.

[0037] According to the cable aging detection data records, a series of sample cable images are collected, and these sample images cover cables with different aging degrees. For each sample cable image, two key features, the number and width of cracks on the cable surface, are extracted. Through image processing technology, the number and width of cracks on the cable surface in the image are automatically detected and measured. According to the number and width of cracks, the insulation aging degree of each sample is evaluated and identified to form a sample insulation aging information set. Using the sample cable image set and the corresponding sample insulation aging information set, an insulation aging identifier is constructed. The insulation aging identifier uses machine learning or deep learning algorithms to learn the mapping relationship between the features in the sample data and the insulation aging degree, so as to accurately identify the insulation aging degree in the new cable image. After the insulation aging identifier is constructed, it can be applied to actual cable image recognition. By inputting multiple cable images, the insulation aging identifier will automatically analyze the features in the image and output the insulation aging information of each cable image.

[0038] Collecting the operation characteristic information of the multiple parts through the operation characteristic perception module, performing operation load analysis on the multiple parts, and obtaining multiple operation load information, wherein the operation characteristic information includes current load information and temperature information;

[0039] The operation characteristic perception module collects the operation characteristic information of multiple parts on the target cable through its built-in various sensors and devices. The operation characteristic information includes current load information and temperature information, which reflects the load state and temperature change of the cable during operation. Based on the operation characteristic information of multiple parts, the operation load analysis is performed to obtain multiple operation load information, including the load degree and temperature distribution of each part.

[0040] Furthermore, if Figure 3 As shown, the operation characteristic information of the multiple parts is collected through the operation characteristic perception module, and the operation load analysis of the multiple parts is performed to obtain multiple operation load information, including:

[0041] The current load information and temperature information of the plurality of parts are collected by the operation characteristic sensing module to obtain a plurality of operation characteristic information;

[0042] Based on the operation load detection record of the cable, a sample operation characteristic information set is obtained, and according to the damage rate of the cable under different operation characteristic information, the sample operation load information set is obtained by evaluation;

[0043] The sample operation characteristic information set and the sample operation load information set are used to construct a cable load analyzer, and the multiple operation characteristic information are identified to obtain multiple operation load information.

[0044] The operation characteristic perception module will collect the current load information and temperature information of multiple parts of the target cable in real time. This information directly reflects the load status of the cable during operation. Based on the operation load detection record of the cable, a sample operation characteristic information set is obtained. The sample operation characteristic information set contains the current load and temperature information of the cable under different load states. According to historical data and expert experience, the mapping relationship between the operation characteristic information and the cable damage rate is established through analysis, so as to evaluate and obtain the sample operation load information set according to the damage rate of the cable under different operation characteristic information. A cable load analyzer is constructed using the sample operation characteristic information set and the corresponding sample operation load information set. The cable load analyzer often uses machine learning or deep learning algorithms to accurately identify and analyze new operation characteristic information by learning the association between the features in the sample data and the load information. After the cable load analyzer is constructed, it is applied to the actual cable operation characteristic information identification. By inputting multiple operation characteristic information, the cable load analyzer will automatically analyze the characteristics of this information and output the corresponding operation load information, including the load degree of the cable, possible overload risk, etc.

[0045] Adaptively adjust the multiple insulation aging information and the multiple operating load information according to the multiple sags and the multiple densities to obtain multiple adjusted insulation aging information and multiple adjusted operating load information, and construct and render to obtain the insulation aging distribution field and the operating load distribution field on the target cable;

[0046] According to the sag and density, the insulation aging information and the operating load information are adjusted to obtain multiple adjusted insulation aging information and multiple adjusted operating load information, wherein the greater the sag and density, the greater the adjusted insulation aging information and operating load information. Using the multiple adjusted insulation aging information and the multiple adjusted operating load information, the insulation aging distribution field and the operating load distribution field on the target cable are constructed, the insulation aging distribution field shows the insulation aging degree of different parts of the cable, and the operating load distribution field shows the load conditions of different parts of the cable.

[0047] Furthermore, according to the multiple sags and the multiple densities, the multiple insulation aging information and the multiple operating load information are adaptively adjusted to obtain multiple adjusted insulation aging information and multiple adjusted operating load information, including:

[0048] Based on the cable aging detection data records and load detection data records, a sample sag set and a sample density set are obtained;

[0049] Based on the influence of different sags on insulation aging and the influence of different densities on cable loads, a set of sample insulation adjustment coefficients and a set of sample load adjustment coefficients are obtained, wherein the size of the insulation adjustment coefficient is positively correlated with the size of the sag;

[0050] The sample sag set and the sample insulation adjustment coefficient set are used to construct an insulation adjustment classification branch, the sample density set and the sample load adjustment coefficient set are used to construct a load adjustment classification branch, and the cable feature adjustment classifier is obtained by combining the insulation adjustment classification branch;

[0051] Based on the cable feature adjustment classifier, classification is performed according to the multiple sags and multiple densities to obtain multiple insulation adjustment coefficients and multiple load adjustment coefficients, and adjustment calculations are performed on the multiple insulation aging information and multiple operating load information to obtain multiple adjusted insulation aging information and multiple adjusted operating load information.

[0052] From the cable aging detection data record, extract a sample sag set, which reflects the hanging state of the cable under different conditions. From the cable load detection data record, extract a sample density set, which describes the compactness of the cable arrangement. Analyze the influence of different sags on insulation aging, and determine the correlation between sag and insulation aging. Based on this correlation, formulate a sample insulation adjustment coefficient set, in which the size of the insulation adjustment coefficient is positively correlated with the size of the sag. This means that as the sag increases, the insulation aging adjustment coefficient will also increase accordingly. Similarly, analyze the influence of different densities on cable load, and determine the correlation between density and cable load. Based on this correlation, formulate a sample load adjustment coefficient set, which reflects the degree of influence of density on cable load. Using machine learning or deep learning technology, based on the sample sag set and the sample insulation adjustment coefficient set, construct an insulation adjustment classification branch, which can predict the corresponding insulation adjustment coefficient based on the given sag data. Similarly, a load adjustment classification branch is constructed using a sample density set and a sample load adjustment coefficient set. The load adjustment classification branch can predict the corresponding load adjustment coefficient based on the given density data. The insulation adjustment classification branch and the load adjustment classification branch are combined to form a complete cable feature adjustment classifier. The cable feature adjustment classifier can process sag and density data at the same time and output the corresponding insulation adjustment coefficient and load adjustment coefficient. The cable feature adjustment classifier is applied to classify the multiple sags and multiple densities actually monitored. According to the classification results, multiple insulation adjustment coefficients and multiple load adjustment coefficients are obtained. Based on the multiple insulation adjustment coefficients and multiple load adjustment coefficients, the original multiple insulation aging information and multiple operating load information are adjusted and calculated. Specifically, each insulation aging information is multiplied by the corresponding insulation adjustment coefficient to obtain the adjusted insulation aging information; similarly, each operating load information is multiplied by the corresponding load adjustment coefficient to obtain the adjusted operating load information.

[0053] Furthermore, constructing and rendering to obtain the insulation aging distribution field and the operating load distribution field on the target cable includes:

[0054] Based on the multiple adjusted insulation aging information and the multiple adjusted operation load information, respectively constructing a basic insulation aging distribution and a basic operation load distribution of the target cable;

[0055] Based on the basic insulation aging distribution and the basic operating load distribution, supplementary rendering is performed to obtain the insulation aging distribution field and the operating load distribution field, wherein the insulation aging distribution includes insulation aging information of all parts on the target cable.

[0056] Based on multiple adjusted insulation aging information, the basic insulation aging distribution of the target cable is constructed. The basic insulation aging distribution divides the cable into different areas or segments, and each area or segment corresponds to an adjusted insulation aging information value. Similarly, using multiple adjusted operating load information, the basic operating load distribution of the target cable is constructed. The basic operating load distribution also divides the cable into different areas or segments, and each area or segment corresponds to an adjusted operating load information value. Based on the basic insulation aging distribution and the basic operating load distribution, supplementary rendering is performed to obtain the insulation aging distribution field and the operating load distribution field.

[0057] Furthermore, based on the basic insulation aging distribution and the basic operation load distribution, supplementary rendering is performed to obtain the insulation aging distribution field and the operation load distribution field, including:

[0058] Based on the detection data records of the cable, a sample basic insulation aging distribution set and a sample basic operating load distribution set are obtained, and a sample insulation aging distribution field set and a sample operating load distribution field set are obtained;

[0059] Based on the generative adversarial network, an insulation aging generator, an operating load generator, an insulation aging discriminator, and an operating load discriminator are constructed;

[0060] The sample basic insulation aging distribution set and the sample basic operation load distribution set are combined with random noise to input the insulation aging generator and the operation load generator to generate a trained insulation aging distribution field and an operation load distribution field, and discriminant training is performed based on the insulation aging discriminator and the operation load discriminator until the convergence condition is met, and an insulation field rendering channel and a load field rendering channel are obtained;

[0061] The basic insulation aging distribution and the basic operation load distribution are input into the insulation field rendering channel and the load field rendering channel to generate the insulation aging distribution field and the operation load distribution field.

[0062] From the detection data record of the cable, a sample basic insulation aging distribution set and a sample basic operating load distribution set are extracted. These sets contain the insulation aging distribution and operating load distribution data of the cable under different conditions. At the same time, a sample insulation aging distribution field set and a sample operating load distribution field set are obtained. These sets provide examples of real distribution fields for training the generative adversarial network. The insulation aging generator receives random noise and a sample basic insulation aging distribution as input to generate a candidate image of the insulation aging distribution field. The operating load generator receives random noise and a sample basic operating load distribution as input to generate a candidate image of the operating load distribution field. The insulation aging discriminator receives the real insulation aging distribution field and the candidate image generated by the generator, and judges its authenticity. The operating load discriminator receives the real operating load distribution field and the candidate image generated by the generator, and judges its authenticity. During the training process, the sample basic insulation aging distribution and random noise are input into the insulation aging generator to generate a candidate image of the insulation aging distribution field. The insulation aging discriminator receives the candidate image and the real insulation aging distribution field and returns the discrimination result. Through back propagation, the parameters of the generator and the discriminator are updated to minimize the discriminator's ability to correctly distinguish between real images and generated images. Similarly, the sample basic operating load distribution and random noise are input into the operating load generator to generate candidate images of the operating load distribution field. The operating load discriminator receives the candidate image and the real operating load distribution field and returns the discrimination result. Through back propagation, the parameters of the generator and the discriminator are updated. Repeat the above process until the convergence condition is met, such as reaching the preset number of training rounds or the discriminator cannot further improve the discrimination ability. After the training of the generative adversarial network is completed, the insulation aging generator and the operating load generator will be used as the insulation field rendering channel and the load field rendering channel, which can generate the corresponding insulation aging distribution field and the operating load distribution field according to the input basic insulation aging distribution and basic operating load distribution. The basic insulation aging distribution and the basic operating load distribution are input into the insulation field rendering channel and the load field rendering channel to generate the final insulation aging distribution field and the operating load distribution field.

[0063] Through the early warning module, a fire trend analysis is performed according to the insulation aging distribution field and the operating load distribution field, the fire trend analysis results are obtained, and a decision-making early warning is performed.

[0064] After obtaining the insulation aging distribution field and operating load distribution field of the cable, the early warning module can be used to analyze the fire trend and make decision warnings based on the analysis results.

[0065] Furthermore, the early warning module performs fire trend analysis according to the insulation aging distribution field and the operating load distribution field to obtain fire trend analysis results, including:

[0066] Based on the fire data records of the cable, obtain a sample insulation aging distribution field set and a sample operating load distribution field set, and obtain a sample fire probability set and a sample fire point set;

[0067] The sample insulation aging distribution field set and the sample operating load distribution field set are used as input, and the sample fire probability set and the sample fire point set are used as output to construct a fire trend analyzer, perform fire trend analysis and prediction on the insulation aging distribution field and the operating load distribution field, and obtain predicted fire probability and predicted fire point as fire trend analysis results.

[0068] From the fire data records of the cable, extract the sample insulation aging distribution field set and the sample operating load distribution field set of historical fire events. These distribution field sets reflect the insulation aging and operating load status of the cable before the fire. At the same time, obtain the sample fire probability set and the sample fire point set corresponding to these distribution field sets. The fire probability set contains the probability of fire occurrence corresponding to each sample, while the fire point set records the specific location of the fire. Use machine learning or deep learning algorithms, such as neural networks, random forests, etc. to build a fire trend analyzer. The fire trend analyzer will learn the patterns and features extracted from historical data to predict the fire trend under new insulation aging distribution fields and operating load distribution fields. Take the sample insulation aging distribution field set and the sample operating load distribution field set as input features, and the sample fire probability set and the sample fire point set as output targets to train the fire trend analyzer. Through the iterative training process, continuously adjust the parameters and weights of the fire trend analyzer to minimize the prediction error. Monitor the performance indicators during the training process, such as accuracy, recall rate, F1 score, etc., to ensure that the performance of the fire trend analyzer reaches the expected level. After the fire trend analyzer is trained, it is applied to the new insulation aging distribution field and operating load distribution field data. The fire trend analyzer will output the predicted fire probability and predicted fire point as the fire trend analysis result.

[0069] In summary, the embodiments of the present application have at least the following technical effects:

[0070] Through the cable feature perception module, the cable images of multiple parts on the target cable are collected, and the multiple sags and multiple densities of the multiple parts are analyzed. According to the multiple cable images, the insulation aging analysis of the multiple parts is performed to obtain multiple insulation aging information. Through the operation feature perception module, the operation feature information of the multiple parts is collected, and the operation load analysis of the multiple parts is performed to obtain multiple operation load information, wherein the operation feature information includes current load information and temperature information. According to the multiple sags and multiple densities, the multiple insulation aging information and the multiple operation load information are adaptively adjusted to obtain multiple adjusted insulation aging information and multiple adjusted operation load information, and the insulation aging distribution field and the operation load distribution field on the target cable are constructed and rendered. Through the early warning module, according to the insulation aging distribution field and the operation load distribution field, the fire trend analysis is performed to obtain the fire trend analysis results, and the decision-making early warning is performed. The technical problem that the cable fire early warning in the prior art is not accurate and timely is solved, and the technical effect of improving the accuracy and timeliness of the cable fire early warning is achieved.

[0071] It should be noted that the above-mentioned sequence of the embodiments of the present application is only for description and does not represent the advantages and disadvantages of the embodiments. And the above-mentioned specific embodiments of this specification are described. Other embodiments are within the scope of the attached claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0072] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application shall be included in the protection scope of the present application.

[0073] This specification and drawings are merely exemplary illustrations of the present application and are deemed to cover any and all modifications, variations, combinations or equivalents within the scope of the present application. Obviously, a person skilled in the art may make various modifications and variations to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalents, the present application intends to include these modifications and variations.

Claims

1. A fire warning method for an intelligent cable, characterized in that: The method is applied to a fire warning device of an intelligent cable, the device comprising a cable feature sensing module, an operation feature sensing module and a warning module, and the method comprises: The cable feature sensing module collects cable images of multiple parts on the target cable, and analyzes multiple sags and multiple densities of the multiple parts; Perform insulation aging analysis on the multiple parts according to the multiple cable images to obtain multiple insulation aging information; Collecting the operation characteristic information of the multiple parts through the operation characteristic perception module, performing operation load analysis on the multiple parts, and obtaining multiple operation load information, wherein the operation characteristic information includes current load information and temperature information; Adaptively adjust the multiple insulation aging information and the multiple operating load information according to the multiple sags and the multiple densities to obtain multiple adjusted insulation aging information and multiple adjusted operating load information, and construct and render to obtain the insulation aging distribution field and the operating load distribution field on the target cable; Through the early warning module, according to the insulation aging distribution field and the operating load distribution field, a fire trend analysis is performed, the fire trend analysis result is obtained, and a decision-making early warning is performed; The cable feature sensing module is used to collect cable images of multiple parts of the target cable, and multiple sags and multiple densities of the multiple parts are analyzed, including: The cable feature sensing module is used to collect cable images of multiple parts of the target cable; Splicing and fusing multiple cable images to obtain an overall cable image of the target cable; Acquire a set of sample cable overall images, identify the curvature of the multiple parts in each sample cable overall image and the distance between the cable and other cables, process and identify to obtain multiple sample sag sets and multiple sample density sets, wherein the curvature and sag are positively correlated, and the cable distance and density are negatively correlated; A cable feature identifier is constructed by using the sample cable overall image set, multiple sample sag sets, and multiple sample density sets; Based on the cable feature identifier, the overall image of the cable is identified to obtain multiple sags and multiple densities of the multiple parts; According to the multiple sags and the multiple densities, the multiple insulation aging information and the multiple operating load information are adaptively adjusted to obtain multiple adjusted insulation aging information and multiple adjusted operating load information, including: Based on the cable aging detection data records and load detection data records, a sample sag set and a sample density set are obtained; Based on the influence of different sags on insulation aging and the influence of different densities on cable loads, a set of sample insulation adjustment coefficients and a set of sample load adjustment coefficients are obtained, wherein the size of the insulation adjustment coefficient is positively correlated with the size of the sag; The sample sag set and the sample insulation adjustment coefficient set are used to construct an insulation adjustment classification branch, the sample density set and the sample load adjustment coefficient set are used to construct a load adjustment classification branch, and the cable feature adjustment classifier is obtained by combining the insulation adjustment classification branch; Based on the cable feature adjustment classifier, classification is performed according to the multiple sags and multiple densities to obtain multiple insulation adjustment coefficients and multiple load adjustment coefficients, and adjustment calculations are performed on the multiple insulation aging information and multiple operating load information to obtain multiple adjusted insulation aging information and multiple adjusted operating load information.

2. The method according to claim 1, characterized in that According to the plurality of cable images, insulation aging analysis of the plurality of parts is performed to obtain a plurality of insulation aging information, including: Based on the cable aging detection data records, a sample cable image set is obtained, and according to the number and width of cracks on the cable surface in each sample cable image, the evaluation mark is obtained to obtain a sample insulation aging information set; The sample cable image set and the sample insulation aging information set are used to construct an insulation aging identifier, and the multiple cable images are identified to obtain the multiple insulation aging information.

3. The method according to claim 1, characterized in that The operation characteristic information of the multiple parts is collected through the operation characteristic perception module, and the operation load analysis of the multiple parts is performed to obtain multiple operation load information, including: The current load information and temperature information of the plurality of parts are collected by the operation characteristic sensing module to obtain a plurality of operation characteristic information; Based on the operation load detection record of the cable, a sample operation characteristic information set is obtained, and according to the damage rate of the cable under different operation characteristic information, the sample operation load information set is obtained by evaluation; The sample operation characteristic information set and the sample operation load information set are used to construct a cable load analyzer, and the multiple operation characteristic information are identified to obtain multiple operation load information.

4. The method according to claim 1, characterized in that: Construct rendering to obtain the insulation aging distribution field and operating load distribution field on the target cable, including: Based on the multiple adjusted insulation aging information and the multiple adjusted operation load information, respectively constructing a basic insulation aging distribution and a basic operation load distribution of the target cable; Based on the basic insulation aging distribution and the basic operating load distribution, supplementary rendering is performed to obtain the insulation aging distribution field and the operating load distribution field, wherein the insulation aging distribution includes insulation aging information of all parts on the target cable.

5. The method according to claim 4, characterized in that Based on the basic insulation aging distribution and the basic operation load distribution, supplementary rendering is performed to obtain the insulation aging distribution field and the operation load distribution field, including: Based on the detection data records of the cable, a sample basic insulation aging distribution set and a sample basic operating load distribution set are obtained, and a sample insulation aging distribution field set and a sample operating load distribution field set are obtained; Based on the generative adversarial network, an insulation aging generator, an operating load generator, an insulation aging discriminator, and an operating load discriminator are constructed; The sample basic insulation aging distribution set and the sample basic operation load distribution set are combined with random noise to input the insulation aging generator and the operation load generator to generate a trained insulation aging distribution field and an operation load distribution field, and discriminant training is performed based on the insulation aging discriminator and the operation load discriminator until the convergence condition is met, and an insulation field rendering channel and a load field rendering channel are obtained; The basic insulation aging distribution and the basic operation load distribution are input into the insulation field rendering channel and the load field rendering channel to generate the insulation aging distribution field and the operation load distribution field.

6. The method according to claim 1, characterized in that Through the early warning module, a fire trend analysis is performed according to the insulation aging distribution field and the operating load distribution field to obtain a fire trend analysis result, including: Based on the fire data records of the cable, obtain a sample insulation aging distribution field set and a sample operating load distribution field set, and obtain a sample fire probability set and a sample fire point set; The sample insulation aging distribution field set and the sample operating load distribution field set are used as input, and the sample fire probability set and the sample fire point set are used as output to construct a fire trend analyzer, perform fire trend analysis and prediction on the insulation aging distribution field and the operating load distribution field, and obtain predicted fire probability and predicted fire point as fire trend analysis results.