Cable tunnel monitoring management system based on big data

Abstract

The invention discloses a cable tunnel monitoring management system based on big data, relates to the technical field of cable tunnels, solves the problem of poor monitoring effect of an existing cable tunnel monitoring management system, and comprises an image data module which is used for carrying out infrared image analysis on each monitoring sub-region to obtain cable tunnel image monitoring data, and sending the cable tunnel image monitoring data to a server; the electric power data module is used for carrying out electric power data monitoring on each monitoring sub-region according to the cable tunnel image monitoring data to obtain cable tunnel electric power monitoring data, and the environment data module is used for carrying out environment data monitoring on each monitoring sub-region according to the cable tunnel image monitoring data to obtain cable tunnel environment monitoring data and sending the cable tunnel environment monitoring data to the monitoring sub-region. And the monitoring management module is used for carrying out area monitoring early warning on each monitoring sub-area according to the cable tunnel image monitoring data, the cable tunnel power monitoring data and the cable tunnel environment monitoring data. The cable tunnel monitoring system can improve the comprehensiveness and accuracy of cable tunnel monitoring management.

Description

Technical Field

[0001] The present invention belongs to the technical field of cable tunnels and relates to big data technology, in particular to a cable tunnel monitoring and management system based on big data. Background Art

[0002] The existing cable tunnel monitoring and management system has the following specific defects when performing cable tunnel monitoring and management: The existing cable tunnel monitoring and management system mainly monitors the appearance damage of cable lines through monitoring images and manual inspections, which has the problems of low appearance monitoring efficiency and poor accuracy of monitoring results; 2. The existing cable tunnel monitoring and management system can only monitor the power of cable tunnels in a single environment, and cannot change the external environment of the cable line within the monitoring cycle to conduct more comprehensive monitoring, which leads to the lack of comprehensiveness of the monitoring results.

[0003] To this end, we propose a cable tunnel monitoring and management system based on big data. Summary of the invention

[0004] In view of the deficiencies in the prior art, the purpose of the present invention is to provide a cable tunnel monitoring and management system based on big data. The present invention is based on dividing the cable tunnel into several monitoring sub-areas and marking a tunnel real-time monitoring cycle, performing infrared image analysis on each monitoring sub-area in the tunnel real-time monitoring cycle, and obtaining the image monitoring abnormality coefficient corresponding to each monitoring sub-area to obtain the cable tunnel image monitoring data, performing power data monitoring on each monitoring sub-area according to the cable tunnel image monitoring data, and obtaining the cable power monitoring coefficient corresponding to each monitoring sub-area to obtain the cable tunnel power monitoring data, performing environmental data monitoring on each monitoring sub-area according to the cable tunnel image monitoring data, and obtaining the tunnel environment monitoring coefficient corresponding to each monitoring sub-area to obtain the cable tunnel environment monitoring data, and performing regional monitoring early warning on each monitoring sub-area according to the cable tunnel image monitoring data, the cable tunnel power monitoring data and the cable tunnel environment monitoring data.

[0005] In order to achieve the above purpose, the present invention adopts the following technical solution: a cable tunnel monitoring and management system based on big data, and the specific working process of each module is as follows: Image data module: used to divide the cable tunnel into several monitoring sub-areas, mark a tunnel real-time monitoring cycle, perform infrared image analysis on each monitoring sub-area in the tunnel real-time monitoring cycle, obtain the image monitoring anomaly coefficient corresponding to each monitoring sub-area, and obtain the cable tunnel image monitoring data; Power data module: used to monitor the power data of each monitoring sub-area according to the cable tunnel image monitoring data, and obtain the cable power monitoring coefficient corresponding to each monitoring sub-area to obtain the cable tunnel power monitoring data; Environmental data module: used to monitor the environmental data of each monitoring sub-area according to the cable tunnel image monitoring data, and obtain the tunnel environmental monitoring coefficient corresponding to each monitoring sub-area to obtain the cable tunnel environmental monitoring data; Monitoring management module: used to perform regional monitoring and early warning for each monitoring sub-area based on the cable tunnel image monitoring data, cable tunnel power monitoring data and cable tunnel environment monitoring data.

[0006] Furthermore, the image data module acquires the cable tunnel image monitoring data as follows: In the process of monitoring the cable tunnel, the time value corresponding to the current moment is marked as the first characteristic time point, the time point corresponding to the characteristic monitoring duration before the first characteristic time point is marked as the second characteristic time point, and the period between the first characteristic time point and the second characteristic time point is marked as the tunnel real-time monitoring period; The interior of the cable tunnel is divided into a plurality of monitoring sub-areas, and one monitoring sub-area is randomly selected from the divided monitoring sub-areas as a target monitoring sub-area to obtain monitoring area division data; Create a cable infrared image recognition model; Obtain infrared monitoring video of the target monitoring sub-area within the real-time monitoring period of the tunnel, obtain the target infrared monitoring video, and intercept the target infrared monitoring into a plurality of monitoring intercepted images by frame; Use the cable infrared image recognition model to recognize each intercepted monitoring image, obtain multiple first-type cable infrared images and second-type cable infrared images, and obtain the number of first-type cable infrared images to obtain the number of abnormal images; The number of intercepted surveillance images captured by the target infrared surveillance is obtained to obtain the total number of periodic images, and the ratio of the number of abnormal images to the total number of periodic images is calculated to obtain the image surveillance abnormality coefficient corresponding to the target surveillance sub-area; Repeat the process of obtaining the image monitoring anomaly coefficient corresponding to the target monitoring sub-area, respectively obtain the image monitoring anomaly coefficient corresponding to each monitoring sub-area, and obtain multiple image monitoring anomaly coefficients; The tunnel real-time monitoring cycle, monitoring area division data and multiple image monitoring anomaly coefficients are defined as the cable tunnel image monitoring data.

[0007] Furthermore, the image data module creates a cable infrared image recognition model, as follows: Using data crawler technology, a number of tunnel cable infrared images are crawled using tunnel cable as a keyword to obtain multiple tunnel cable infrared images; The acquired plurality of tunnel cable infrared images are divided into first type cable infrared images and second type cable infrared images to obtain cable infrared image marking data; The cable infrared image labeled data is divided into a cable infrared image training set and a cable infrared image test set according to the image training and testing ratio; Create an image recognition model through an existing artificial intelligence platform, and train the image recognition model using the cable infrared image training set until every medical cable infrared image in the cable infrared image training set is trained by the image recognition model; The image recognition model is tested using the cable infrared image test set, and the recognition accuracy is obtained. When the recognition accuracy is greater than or equal to the target recognition accuracy, the image recognition model training is completed and the cable infrared image recognition model is obtained. When the recognition accuracy is less than the target recognition accuracy, the cable infrared image training set is continued to be used to train the image recognition model until the recognition accuracy is greater than or equal to the target recognition accuracy.

[0008] Furthermore, the image data module acquires the cable infrared image marking data as follows: Randomly select one tunnel cable infrared image from multiple cable infrared images as a sample cable infrared image; In the sample cable infrared image, the image area covered by the cable is marked to obtain the cable coverage area, and several feature rectangles are marked in the cable coverage area, and the vertices of each feature rectangle are marked as cable feature points to obtain multiple cable feature points; In the sample cable infrared image, the brightness value corresponding to each cable feature point is obtained respectively to obtain multiple feature point brightness values, and a reference brightness value is set, and the cable feature points whose feature point brightness values ​​are greater than or equal to the reference brightness value are classified as first-category feature points, and the cable feature points whose feature point brightness values ​​are less than the reference brightness value are classified as second-type feature points; Classify the feature rectangles in the sample cable infrared image where all four vertices are first-category feature points as first-category feature rectangles; classify the feature rectangles in the sample cable infrared image where the second-type feature points exist among the four vertices as second-category feature rectangles; Acquire the number of characteristic rectangles in the infrared image of the sample cable to obtain the number value of characteristic rectangles, acquire the number of first-type characteristic rectangles in the infrared image of the sample cable to obtain the number value of hotspot rectangles, calculate the ratio of the number value of hotspot rectangles to the number value of characteristic rectangles, and obtain the hotspot rectangle feature ratio; The number of cable feature points in the sample cable infrared image is obtained to obtain the number of cable feature points, the number of first category feature points in the sample cable infrared image is obtained to obtain the number of cable hot spots, and the ratio of the number of cable hot spots to the number of cable feature points is calculated to obtain the cable hot spot feature ratio; The hotspot rectangle feature ratio and the cable hotspot feature ratio are calculated to obtain the image infrared anomaly coefficient corresponding to the sample cable infrared image; The image infrared anomaly coefficient corresponding to the sample cable infrared image is calculated. The specific formula is as follows: ; Among them, Hwy is the image infrared anomaly coefficient corresponding to the sample cable infrared image, Jxt is the hotspot rectangle feature ratio, and Rdt is the cable hotspot feature ratio; Repeat the process of obtaining the image infrared anomaly coefficient corresponding to the sample cable infrared image, respectively obtain the image infrared anomaly coefficient corresponding to each tunnel cable infrared image, and obtain multiple image infrared anomaly coefficients; An image infrared anomaly coefficient threshold is obtained, and a numerical comparison is performed between multiple image infrared anomaly coefficients and the image infrared anomaly coefficient threshold; when the image infrared anomaly coefficient of a certain tunnel cable infrared image is greater than or equal to the image infrared anomaly coefficient threshold, the cable infrared image of the tunnel is classified as a first type of cable infrared image; when the image infrared anomaly coefficient of a certain tunnel cable infrared image is less than the image infrared anomaly coefficient threshold, the cable infrared image of the tunnel is classified as a second type of cable infrared image, and the cable infrared image marking data is obtained.

[0009] Furthermore, the power data module acquires the cable tunnel power monitoring data, as follows: Acquire cable tunnel image monitoring data, and acquire tunnel real-time monitoring cycle and monitoring area division data according to the cable tunnel image monitoring data; Divide the data according to the monitoring area to obtain the target monitoring sub-area; Perform power data monitoring on the target monitoring sub-area in the tunnel real-time monitoring cycle to obtain the regional power monitoring coefficient corresponding to the target monitoring sub-area; The details are as follows: Acquire the tunnel cables of the target monitoring sub-area to obtain a plurality of tunnel cables, and sequentially name the plurality of cables acquired as a first tunnel cable to a dth tunnel cable; Acquiring a first cable transmission loss by monitoring the power transmission loss of the first tunnel cable; Repeat the process of obtaining the first cable transmission loss, respectively obtain the cable transmission losses corresponding to the second tunnel cable to the d-th tunnel cable, and obtain the transmission losses of the second cable to the d-th cable; Respectively obtain reference circuit transmission losses corresponding to the first tunnel cable to the dth tunnel cable, and obtain reference transmission losses of the first cable to the dth cable; The regional power monitoring coefficient corresponding to the target monitoring sub-area is obtained by calculating the transmission loss of the first cable to the transmission loss of the dth cable and the reference transmission loss of the first cable to the reference transmission loss of the dth cable; Calculate the regional power monitoring coefficient corresponding to the target monitoring sub-area. The specific formula is as follows: ; Among them, Qjk is the regional power monitoring coefficient corresponding to the target monitoring sub-area, Hshi is the i-th cable transmission loss, Hsji is the i-th cable benchmark transmission loss, and d is the number of tunnel cables corresponding to the target monitoring sub-area; Repeat the process of acquiring the regional power monitoring coefficient corresponding to the target monitoring sub-area, and acquire the cable power monitoring coefficient corresponding to each monitoring sub-area respectively to obtain the cable tunnel power monitoring data.

[0010] Furthermore, the power data module acquires the first cable transmission loss as follows: Acquire the line connection position in the first tunnel cable to obtain multiple line connection positions, deploy a circuit environment test box for each line connection position, and use the circuit environment test box to cover each line connection position; The circuit environment test boxes in the first tunnel cable are named the first environment test box to the cth environment test box in sequence; Use the circuit environment test box to set up several different test deployment environments, and the ambient temperature value and ambient humidity value corresponding to each test deployment environment are different, and arbitrarily select one test deployment environment from the multiple test deployment environments set as a sample deployment environment; Under the sample deployment environment, the line voltage data corresponding to the first environmental test box to the cth environmental test box in the first tunnel cable are respectively acquired to obtain the first test voltage value to the cth test voltage value; The environmental cable transmission loss corresponding to the sample deployment environment is obtained by calculating the first test voltage value to the cth test voltage value; The environmental cable transmission loss corresponding to the sample deployment environment is calculated using the following formula: ; Wherein, Hds is the environmental cable transmission loss corresponding to the sample deployment environment, Vcsi is the i-th test voltage value, Vcs(i-1) is the i-1-th test voltage value, and c is the quantity value corresponding to the circuit environment test box; Repeat the process of obtaining the environmental cable transmission loss corresponding to the sample deployment environment, obtain the environmental circuit transmission loss corresponding to each test deployment environment respectively, obtain multiple environmental circuit transmission losses, and calculate the average of the multiple environmental circuit transmission losses obtained to obtain the first cable transmission loss.

[0011] Furthermore, the environmental data module acquires the cable tunnel environmental monitoring data, as follows: Acquire cable tunnel image monitoring data, and acquire tunnel real-time monitoring cycle and monitoring area division data according to the cable tunnel image monitoring data; Divide the data according to the monitoring area to obtain the target monitoring sub-area; Perform environmental data monitoring on the target monitoring sub-area in the tunnel real-time monitoring cycle to obtain the regional environmental monitoring coefficient corresponding to the target monitoring sub-area; The process of obtaining the regional environmental monitoring coefficient corresponding to the target monitoring sub-area is repeated, and the tunnel environmental monitoring coefficient corresponding to each monitoring sub-area is obtained respectively to obtain the cable tunnel environmental monitoring data.

[0012] Furthermore, the environmental data module obtains the regional environmental monitoring coefficient corresponding to the target monitoring sub-area, as follows: In the target monitoring sub-area, a plurality of sensors of different types are deployed, and the plurality of sensors of different types are named as first type sensors to mth type sensors in sequence; During the real-time monitoring period of the tunnel, numerical values ​​of the monitoring parameters corresponding to each first-type sensor are acquired to obtain a plurality of first-type monitoring parameters, and an average of the acquired plurality of first-type monitoring parameters is calculated to obtain an average value of the first-type monitoring parameters; During the real-time monitoring period of the tunnel, numerical values ​​of the monitoring parameters corresponding to each second-type sensor are acquired to obtain a plurality of second-type monitoring parameters, and an average of the acquired plurality of second-type monitoring parameters is calculated to obtain an average value of the second-type monitoring parameters; Repeat the process of obtaining the average value of the second type of monitoring parameter, respectively obtain the average values ​​of the monitoring parameters corresponding to the third type of sensor to the mth type of sensor, and obtain the average values ​​of the third type of monitoring parameters to the mth type of monitoring parameters; Obtaining first type monitoring parameter reference values ​​to mth type monitoring parameter reference values ​​respectively; The regional environmental monitoring coefficient corresponding to the target monitoring sub-area is obtained by calculating the average value of the first type monitoring parameter to the average value of the m-th type monitoring parameter and the baseline value of the first type monitoring parameter to the baseline value of the m-th type monitoring parameter; Calculate the regional environmental monitoring coefficient corresponding to the target monitoring sub-area. The specific formula is as follows: ; Among them, Hqx is the regional environmental monitoring coefficient corresponding to the target monitoring sub-area, Jcci is the average value of the i-th type monitoring parameter, and Jcji is the benchmark value of the i-th type monitoring parameter.

[0013] Furthermore, the monitoring management module obtains the regional monitoring warning coefficient, as follows: Acquire cable tunnel image monitoring data, and acquire image monitoring anomaly coefficients corresponding to each monitoring sub-area according to the cable tunnel image monitoring data; Acquire the power monitoring data of the cable tunnel, and acquire the regional power monitoring coefficient corresponding to each monitoring sub-area according to the power monitoring data of the cable tunnel; Obtaining cable tunnel environmental monitoring data, and obtaining regional environmental monitoring coefficients corresponding to each monitoring sub-area according to the cable tunnel environmental monitoring data; The image monitoring anomaly coefficient, regional power monitoring coefficient and regional environmental monitoring coefficient corresponding to the same monitoring sub-area are calculated to obtain a regional monitoring warning coefficient; The regional monitoring warning coefficient is calculated, and the specific formula is as follows: ; Among them, Yjx is the regional monitoring warning coefficient, Tyc is the image monitoring anomaly coefficient, Qjk is the regional power monitoring coefficient, and Hqx is the regional environmental monitoring coefficient; Obtain the regional monitoring warning coefficient threshold, compare the regional monitoring warning coefficient with the regional monitoring warning coefficient threshold, and perform monitoring management and warning for each monitoring sub-area based on the numerical comparison result.

[0014] Furthermore, the monitoring management module performs monitoring and early warning on the monitoring sub-area, as follows: Obtaining image monitoring anomaly coefficient threshold, regional power monitoring coefficient threshold and regional environment monitoring coefficient threshold respectively; The image monitoring abnormality coefficient threshold, the regional power monitoring coefficient threshold and the regional environment monitoring coefficient threshold are calculated to obtain the regional monitoring warning coefficient threshold; The regional monitoring warning coefficient threshold is calculated, and the specific formula is as follows: ; Among them, Yjxy is the regional monitoring warning coefficient threshold, Tycy is the image monitoring abnormality coefficient threshold, Qjky is the regional power monitoring coefficient threshold, and Hqxy is the regional environment monitoring coefficient threshold; When the image monitoring anomaly coefficient is greater than or equal to the image monitoring anomaly coefficient threshold, a monitoring anomaly warning is issued for the corresponding monitoring sub-area; When the image monitoring anomaly coefficient is less than the image monitoring anomaly coefficient threshold, the corresponding monitoring sub-area is monitored normally.

[0015] In summary, due to the adoption of the above technical solution, the beneficial effects of the present invention are: 1. The present invention can effectively improve the monitoring efficiency of cable sheath damage and the accuracy of monitoring results by creating a cable infrared image recognition model to periodically monitor the infrared image of the cable tunnel; 2. The present invention uses a circuit environment test box to cover each line connection position, and uses the circuit environment test box to perform diversified deployment of the local external environment of the line connection position, which can effectively improve the comprehensiveness of power data monitoring. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to facilitate understanding by those skilled in the art, the present invention is further described below with reference to the accompanying drawings.

[0017] Figure 1 is the overall system block diagram of the present invention; Figure 2 It is a schematic diagram of the cable coverage area of ​​the present invention; Figure 3 It is a schematic diagram of the circuit environment test box of the present invention. DETAILED DESCRIPTION

[0018] The technical solution of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0019] Embodiment 1 See also Figure 1 , the present invention provides a technical solution: a cable tunnel monitoring and management system based on big data, comprising an image data module, a power data module, an environment data module, a monitoring and management module and a server, wherein the image data module, the power data module, the environment data module and the monitoring and management module are respectively connected to the server, and the server controls the image data module, the power data module, the environment data module and the monitoring and management module respectively; The image data module divides the cable tunnel into several monitoring sub-areas, marks a tunnel real-time monitoring cycle, performs infrared image analysis on each monitoring sub-area in the tunnel real-time monitoring cycle, obtains the image monitoring anomaly coefficient corresponding to each monitoring sub-area, and obtains the cable tunnel image monitoring data; The details are as follows: In the process of monitoring the cable tunnel, the time value corresponding to the current moment is marked as the first characteristic time point, the time point corresponding to the characteristic monitoring duration before the first characteristic time point is marked as the second characteristic time point, and the period between the first characteristic time point and the second characteristic time point is marked as the tunnel real-time monitoring period.

[0020] It should be noted here that: In the present application, as the time value corresponding to the current moment changes, the first characteristic time point and the second characteristic time point also change accordingly, thereby realizing the dynamic update of the tunnel real-time monitoring cycle; In this application, the specific time value corresponding to the feature monitoring duration involved here is specifically 20 minutes; The interior of the cable tunnel is divided into a plurality of monitoring sub-areas, and one monitoring sub-area is randomly selected from the divided monitoring sub-areas as a target monitoring sub-area to obtain monitoring area division data.

[0021] Create a cable infrared image recognition model; The details are as follows: Using data crawler technology, a number of tunnel cable infrared images are crawled using tunnel cable as a keyword to obtain multiple tunnel cable infrared images; The acquired plurality of tunnel cable infrared images are divided into first type cable infrared images and second type cable infrared images to obtain cable infrared image marking data; The details are as follows: Randomly select one tunnel cable infrared image from multiple cable infrared images as a sample cable infrared image; See also Figure 2 , mark the image area covered by the cable in the sample cable infrared image to obtain the cable coverage area, mark several feature rectangles in the cable coverage area, and mark the vertex of each feature rectangle as a cable feature point to obtain multiple cable feature points; It should be noted here that: In this application, the side length of the characteristic rectangle involved here is specifically set to 5 cm; In the sample cable infrared image, the brightness value corresponding to each cable feature point is obtained respectively to obtain multiple feature point brightness values, and a reference brightness value is set, and the cable feature points whose feature point brightness values ​​are greater than or equal to the reference brightness value are classified as first-category feature points, and the cable feature points whose feature point brightness values ​​are less than the reference brightness value are classified as second-type feature points; It should be noted here that: In this application, the reference brightness value involved here is specifically the minimum infrared brightness value corresponding to the circuit damage area in the tunnel historical monitoring data; Classify the feature rectangles whose four vertices in the sample cable infrared image are all first-category feature points as first-category feature rectangles; classify the feature rectangles whose four vertices in the sample cable infrared image have second-type feature points as second-category feature rectangles; Acquire the number of characteristic rectangles in the infrared image of the sample cable to obtain the number value of characteristic rectangles, acquire the number of first-type characteristic rectangles in the infrared image of the sample cable to obtain the number value of hotspot rectangles, calculate the ratio of the number value of hotspot rectangles to the number value of characteristic rectangles, and obtain the hotspot rectangle feature ratio; The number of cable feature points in the sample cable infrared image is obtained to obtain the number of cable feature points, the number of first category feature points in the sample cable infrared image is obtained to obtain the number of cable hot spots, and the ratio of the number of cable hot spots to the number of cable feature points is calculated to obtain the cable hot spot feature ratio; The hotspot rectangle feature ratio and the cable hotspot feature ratio are calculated to obtain the image infrared anomaly coefficient corresponding to the sample cable infrared image; The image infrared anomaly coefficient corresponding to the sample cable infrared image is calculated. The specific formula is as follows: ; Among them, Hwy is the image infrared anomaly coefficient corresponding to the sample cable infrared image, Jxt is the hotspot rectangle feature ratio, and Rdt is the cable hotspot feature ratio.

[0022] Repeat the process of obtaining the image infrared anomaly coefficient corresponding to the sample cable infrared image, respectively obtain the image infrared anomaly coefficient corresponding to each tunnel cable infrared image, and obtain multiple image infrared anomaly coefficients; Obtain an image infrared anomaly coefficient threshold, and perform numerical comparison between multiple image infrared anomaly coefficients and the image infrared anomaly coefficient threshold; when the image infrared anomaly coefficient of a certain tunnel cable infrared image is greater than or equal to the image infrared anomaly coefficient threshold, the cable infrared image of the tunnel is classified as a first type of cable infrared image; when the image infrared anomaly coefficient of a certain tunnel cable infrared image is less than the image infrared anomaly coefficient threshold, the cable infrared image of the tunnel is classified as a second type of cable infrared image, and cable infrared image marking data is obtained; The cable infrared image labeled data is divided into a cable infrared image training set and a cable infrared image test set according to the image training and testing ratio; It should be noted here that: In this application, the image training-test ratio is specifically set to 7:3, that is, the ratio of the number of medical cable infrared images in the cable infrared image training set and the cable infrared image test set is 7:3; Create an image recognition model through an existing artificial intelligence platform, and train the image recognition model using the cable infrared image training set until every medical cable infrared image in the cable infrared image training set is trained by the image recognition model; The image recognition model is tested using the cable infrared image test set, and the recognition accuracy is obtained. When the recognition accuracy is greater than or equal to the target recognition accuracy, the image recognition model training is completed and the cable infrared image recognition model is obtained. When the recognition accuracy is less than the target recognition accuracy, the cable infrared image training set is continued to be used to train the image recognition model until the recognition accuracy is greater than or equal to the target recognition accuracy.

[0023] It should be noted here that: The target recognition accuracy involved here is specifically set to 95% in this application.

[0024] Obtain infrared monitoring video of the target monitoring sub-area within the real-time monitoring period of the tunnel, obtain the target infrared monitoring video, and intercept the target infrared monitoring into a plurality of monitoring intercepted images by frame; It should be noted here that: In itself, the infrared surveillance video is obtained here to periodically monitor the target surveillance sub-area, and at different time points, the specific coverage area of ​​the infrared surveillance video in the target surveillance sub-area is different; Use the cable infrared image recognition model to recognize each intercepted monitoring image, obtain multiple first-type cable infrared images and second-type cable infrared images, and obtain the number of first-type cable infrared images to obtain the number of abnormal images; The number of intercepted surveillance images captured by the target infrared surveillance is obtained to obtain the total number of periodic images, and the ratio of the number of abnormal images to the total number of periodic images is calculated to obtain the image surveillance abnormality coefficient corresponding to the target surveillance sub-area; Repeat the process of obtaining the image monitoring anomaly coefficient corresponding to the target monitoring sub-area, respectively obtain the image monitoring anomaly coefficient corresponding to each monitoring sub-area, and obtain multiple image monitoring anomaly coefficients; The tunnel real-time monitoring cycle, monitoring area division data and multiple image monitoring abnormality coefficients are defined as cable tunnel image monitoring data; The image data module acquires the cable tunnel image monitoring data and transmits it to the power data module, the environment data module and the monitoring management module; The power data module monitors the power data of each monitoring sub-area according to the cable tunnel image monitoring data, and obtains the cable power monitoring coefficient corresponding to each monitoring sub-area to obtain the cable tunnel power monitoring data; The details are as follows: Acquire cable tunnel image monitoring data, and acquire tunnel real-time monitoring cycle and monitoring area division data according to the cable tunnel image monitoring data; Divide the data according to the monitoring area to obtain the target monitoring sub-area; Perform power data monitoring on the target monitoring sub-area in the tunnel real-time monitoring cycle to obtain the regional power monitoring coefficient corresponding to the target monitoring sub-area; The details are as follows: Acquire the tunnel cables of the target monitoring sub-area to obtain a plurality of tunnel cables, and sequentially name the plurality of cables acquired as a first tunnel cable to a dth tunnel cable; It should be noted here that: In this application, d is the quantity value corresponding to the tunnel cable, and d is an integer greater than 0; Acquiring a first cable transmission loss by monitoring the power transmission loss of the first tunnel cable; The details are as follows: See also Figure 3 , obtaining the line connection position in the first tunnel cable to obtain multiple line connection positions, respectively deploying a circuit environment test box for each line connection position, and using the circuit environment test box to cover each line connection position; The circuit environment test boxes in the first tunnel cable are named the first environment test box to the cth environment test box in sequence; It should be noted here that: In this application, the power line connection method involved here is parallel connection; In this application, c is the quantity value corresponding to the circuit environment test box, and c is an integer greater than 0; It should be noted here that: The circuit environment test box involved herein is a closed space container that can change local environmental data. The circuit environment test box involved herein includes power equipment including but not limited to voltage sensors, heaters, humidifiers, and data wireless transmission equipment; Use the circuit environment test box to set up several different test deployment environments, and the ambient temperature value and ambient humidity value corresponding to each test deployment environment are different, and arbitrarily select one test deployment environment from the multiple test deployment environments set as a sample deployment environment; It should be noted here that: The circuit environment test box involved here also has the function of locally adjusting the original tunnel environment. When the original tunnel environment is not conducive to the transmission of power resources at the cable connection, the circuit environment test box automatically adjusts the local environment at the line connection location to make the local environment at the line connection location more suitable for power resource transmission; Under the sample deployment environment, the line voltage data corresponding to the first environmental test box to the cth environmental test box in the first tunnel cable are respectively acquired to obtain the first test voltage value to the cth test voltage value; The environmental cable transmission loss corresponding to the sample deployment environment is obtained by calculating the first test voltage value to the cth test voltage value; The environmental cable transmission loss corresponding to the sample deployment environment is calculated using the following formula: ; Wherein, Hds is the environmental cable transmission loss corresponding to the sample deployment environment, Vcsi is the i-th test voltage value, Vcs(i-1) is the i-1-th test voltage value, and c is the quantity value corresponding to the circuit environment test box; It should be noted here that: In the present application, the i-th test voltage value involved here may be any test voltage value from the first test voltage value to the c-th test voltage value; Repeat the process of obtaining the environmental cable transmission loss corresponding to the sample deployment environment, obtain the environmental circuit transmission loss corresponding to each test deployment environment respectively, obtain multiple environmental circuit transmission losses, and calculate the average of the multiple environmental circuit transmission losses obtained to obtain the first cable transmission loss.

[0025] Repeat the process of obtaining the first cable transmission loss, respectively obtain the cable transmission losses corresponding to the second tunnel cable to the d-th tunnel cable, and obtain the transmission losses of the second cable to the d-th cable; Respectively obtain reference circuit transmission losses corresponding to the first tunnel cable to the dth tunnel cable, and obtain reference transmission losses of the first cable to the dth cable; It should be noted here that: In the present application, the first cable reference transmission loss to the dth cable reference transmission loss referred to herein are respectively the transmission losses from the first tunnel cable to the dth tunnel cable under normal operating conditions; The regional power monitoring coefficient corresponding to the target monitoring sub-area is obtained by calculating the transmission loss of the first cable to the transmission loss of the dth cable and the reference transmission loss of the first cable to the reference transmission loss of the dth cable; Calculate the regional power monitoring coefficient corresponding to the target monitoring sub-area. The specific formula is as follows: ; Among them, Qjk is the regional power monitoring coefficient corresponding to the target monitoring sub-area, Hshi is the i-th cable transmission loss, Hsji is the i-th cable benchmark transmission loss, and d is the number of tunnel cables corresponding to the target monitoring sub-area.

[0026] Repeat the process of obtaining the regional power monitoring coefficient corresponding to the target monitoring sub-area, obtain the cable power monitoring coefficient corresponding to each monitoring sub-area respectively, and obtain the cable tunnel power monitoring data; The power data module acquires the power monitoring data of the cable tunnel and transmits it to the monitoring management module; The environmental data module monitors the environmental data of each monitoring sub-area according to the cable tunnel image monitoring data, and obtains the tunnel environmental monitoring coefficient corresponding to each monitoring sub-area to obtain the cable tunnel environmental monitoring data; Acquire cable tunnel image monitoring data, and acquire tunnel real-time monitoring cycle and monitoring area division data according to the cable tunnel image monitoring data; Divide the data according to the monitoring area to obtain the target monitoring sub-area; Perform environmental data monitoring on the target monitoring sub-area in the tunnel real-time monitoring cycle to obtain the regional environmental monitoring coefficient corresponding to the target monitoring sub-area; The details are as follows: In the target monitoring sub-area, a plurality of sensors of different types are deployed, and the plurality of sensors of different types are named as first type sensors to mth type sensors in sequence; It should be noted here that: In this application, m is the number of types of sensors corresponding to the target monitoring sub-area, and m is an integer greater than 0; In the present application, the first type of sensor involved here may be a smoke sensor, the second type of sensor may be a temperature sensor, the third type of sensor may be a humidity sensor, and the fourth type of sensor may be a vibration sensor; In this application, there can be multiple sensors of each type; During the real-time monitoring period of the tunnel, numerical values ​​of the monitoring parameters corresponding to each first-type sensor are acquired to obtain a plurality of first-type monitoring parameters, and an average of the acquired plurality of first-type monitoring parameters is calculated to obtain an average value of the first-type monitoring parameters; During the real-time monitoring period of the tunnel, numerical values ​​of the monitoring parameters corresponding to each second-type sensor are acquired to obtain a plurality of second-type monitoring parameters, and an average of the acquired plurality of second-type monitoring parameters is calculated to obtain an average value of the second-type monitoring parameters; Repeat the process of obtaining the average value of the second type of monitoring parameter, respectively obtain the average values ​​of the monitoring parameters corresponding to the third type of sensor to the mth type of sensor, and obtain the average values ​​of the third type of monitoring parameters to the mth type of monitoring parameters; Obtaining first type monitoring parameter reference values ​​to mth type monitoring parameter reference values ​​respectively; It should be noted here that: In the present application, the first type monitoring parameter reference value to the mth type monitoring parameter reference value are respectively the monitoring parameter values ​​of the first type sensor to the mth type sensor under normal cable tunnel working conditions; The regional environmental monitoring coefficient corresponding to the target monitoring sub-area is obtained by calculating the average value of the first type monitoring parameter to the average value of the m-th type monitoring parameter and the baseline value of the first type monitoring parameter to the baseline value of the m-th type monitoring parameter; Calculate the regional environmental monitoring coefficient corresponding to the target monitoring sub-area. The specific formula is as follows: ; Among them, Hqx is the regional environmental monitoring coefficient corresponding to the target monitoring sub-area, Jcci is the average value of the i-th type monitoring parameter, and Jcji is the benchmark value of the i-th type monitoring parameter.

[0027] It should be noted here that: In the present application, the i-th type monitoring parameter average value involved here can be any monitoring parameter average value from the first type monitoring parameter average value to the m-th type monitoring parameter average value, and the i-th type monitoring parameter baseline value involved here can be any monitoring parameter baseline value from the first type monitoring parameter baseline value to the m-th type monitoring parameter baseline value.

[0028] Repeat the process of obtaining the regional environmental monitoring coefficient corresponding to the target monitoring sub-area, respectively obtain the tunnel environmental monitoring coefficient corresponding to each monitoring sub-area, and obtain the cable tunnel environmental monitoring data; The environmental data module acquires the cable tunnel environmental monitoring data and transmits it to the monitoring management module.

[0029] The monitoring management module performs regional monitoring and early warning for each monitoring sub-area based on the cable tunnel image monitoring data, cable tunnel power monitoring data, and cable tunnel environment monitoring data; Acquire cable tunnel image monitoring data, and acquire image monitoring anomaly coefficients corresponding to each monitoring sub-area according to the cable tunnel image monitoring data; Acquire the power monitoring data of the cable tunnel, and acquire the regional power monitoring coefficient corresponding to each monitoring sub-area according to the power monitoring data of the cable tunnel; Obtaining cable tunnel environmental monitoring data, and obtaining regional environmental monitoring coefficients corresponding to each monitoring sub-area according to the cable tunnel environmental monitoring data; The image monitoring anomaly coefficient, regional power monitoring coefficient and regional environmental monitoring coefficient corresponding to the same monitoring sub-area are calculated to obtain a regional monitoring warning coefficient; The regional monitoring warning coefficient is calculated, and the specific formula is as follows: ; Among them, Yjx is the regional monitoring warning coefficient, Tyc is the image monitoring anomaly coefficient, Qjk is the regional power monitoring coefficient, and Hqx is the regional environment monitoring coefficient.

[0030] Obtain the regional monitoring warning coefficient threshold, compare the regional monitoring warning coefficient with the regional monitoring warning coefficient threshold, and perform monitoring management and warning for each monitoring sub-region according to the numerical comparison result; The details are as follows: Obtaining image monitoring anomaly coefficient threshold, regional power monitoring coefficient threshold and regional environment monitoring coefficient threshold respectively; It should be noted here that: In the present application, the image monitoring anomaly coefficient threshold, regional power monitoring coefficient threshold, and regional environment monitoring coefficient threshold involved here are respectively the maximum image monitoring anomaly coefficient, the maximum regional power monitoring coefficient, and the maximum regional environment monitoring coefficient corresponding to the normal monitoring sub-area; The image monitoring abnormality coefficient threshold, the regional power monitoring coefficient threshold and the regional environment monitoring coefficient threshold are calculated to obtain the regional monitoring warning coefficient threshold; The regional monitoring warning coefficient threshold is calculated, and the specific formula is as follows: ; Among them, Yjxy is the regional monitoring warning coefficient threshold, Tycy is the image monitoring abnormality coefficient threshold, Qjky is the regional power monitoring coefficient threshold, and Hqxy is the regional environment monitoring coefficient threshold; When the image monitoring anomaly coefficient is greater than or equal to the image monitoring anomaly coefficient threshold, a monitoring anomaly warning is issued for the corresponding monitoring sub-area; When the image monitoring anomaly coefficient is less than the image monitoring anomaly coefficient threshold, the corresponding monitoring sub-area is monitored normally.

[0031] In this application, if corresponding calculation formulas appear, the above calculation formulas are all dimensionless and take their numerical calculations. The weight coefficients, proportional coefficients and other coefficients in the formulas are set to a result value obtained by quantifying each parameter. The size of the weight coefficient and the proportional coefficient can be determined as long as it does not affect the proportional relationship between the parameter and the result value.

[0032] The preferred embodiments of the present invention disclosed above are only used to help explain the present invention. The preferred embodiments do not describe all the details in detail, nor do they limit the invention to only specific implementation methods. Obviously, many modifications and changes can be made according to the content of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the present invention, so that those skilled in the art can understand and use the present invention well. The present invention is limited only by the claims and their full scope and equivalents.

Claims

1. A cable tunnel monitoring and management system based on big data, characterized in that: The system comprises: Image data module: used to divide the cable tunnel into several monitoring sub-areas, mark a tunnel real-time monitoring cycle, perform infrared image analysis on each monitoring sub-area in the tunnel real-time monitoring cycle to obtain multiple image monitoring abnormality coefficients, and obtain cable tunnel image monitoring data; Power data module: used to monitor the power data of each monitoring sub-area according to the cable tunnel image monitoring data, obtain multiple cable power monitoring coefficients, and obtain the cable tunnel power monitoring data; Environmental data module: used to monitor the environmental data of each monitoring sub-area according to the cable tunnel image monitoring data, obtain the monitoring coefficients of multiple tunnel environments, and obtain the cable tunnel environment monitoring data; Monitoring management module: used to conduct regional monitoring and early warning for each monitoring sub-area based on the cable tunnel image monitoring data, cable tunnel power monitoring data and cable tunnel environment monitoring data.

2. A cable tunnel monitoring and management system based on big data according to claim 1, characterized in that: The image data module acquires the cable tunnel image monitoring data as follows: In the process of monitoring the cable tunnel, the time value corresponding to the current moment is marked as the first characteristic time point, and a time point is marked in the time period before the first characteristic time point as the second characteristic time point; the time period between the first characteristic time point and the second characteristic time point is marked as the tunnel real-time monitoring period; The interior of the cable tunnel is divided into a plurality of monitoring sub-areas, and one monitoring sub-area is randomly selected from the divided monitoring sub-areas as a target monitoring sub-area to obtain monitoring area division data; Create a cable infrared image recognition model; Obtain infrared monitoring video of the target monitoring sub-area within the real-time monitoring period of the tunnel, obtain the target infrared monitoring video, and intercept the target infrared monitoring into a plurality of monitoring intercepted images by frame; Use the cable infrared image recognition model to identify each intercepted surveillance image, obtain multiple first-type cable infrared images and second-type cable infrared images based on the recognition, and obtain the number of first-type cable infrared images to obtain the number of abnormal images; The number of images intercepted by the target infrared monitoring is obtained to obtain the total number of periodic images, and the ratio of the number of abnormal images to the total number of periodic images is calculated to obtain the image monitoring abnormality coefficient corresponding to the target monitoring sub-area; The image monitoring anomaly coefficient corresponding to each monitoring sub-area is obtained respectively to obtain a plurality of image monitoring anomaly coefficients; The tunnel real-time monitoring cycle, monitoring area division data and multiple image monitoring anomaly coefficients are defined as the cable tunnel image monitoring data.

3. A cable tunnel monitoring and management system based on big data according to claim 2, characterized in that: The image data module creates a cable infrared image recognition model, as follows: Taking tunnel cable as the keyword, a number of tunnel cable infrared images were crawled using data crawler technology; The acquired plurality of tunnel cable infrared images are divided into first type cable infrared images and second type cable infrared images to obtain cable infrared image marking data; The cable infrared image labeled data is divided into a cable infrared image training set and a cable infrared image test set according to the image training and testing ratio; Create an image recognition model through the artificial intelligence platform and train the image recognition model using the cable infrared image training set; The image recognition model is tested using the cable infrared image test set, and the recognition accuracy is obtained. When the recognition accuracy is greater than or equal to the target recognition accuracy, the training of the image recognition model is completed and the cable infrared image recognition model is obtained. When the recognition accuracy is less than the target recognition accuracy, the cable infrared image training set is continued to be used to train the image recognition model until the recognition accuracy is greater than or equal to the target recognition accuracy.

4. A cable tunnel monitoring and management system based on big data according to claim 3, characterized in that: The image data module acquires the cable infrared image marking data as follows: Selecting one tunnel cable infrared image from the plurality of cable infrared images as a sample cable infrared image; In the sample cable infrared image, the image area covered by the cable is marked to obtain the cable coverage area, a number of feature rectangles are marked in the cable coverage area, and the vertex of each feature rectangle is marked as a cable feature point to obtain a plurality of cable feature points; In the sample cable infrared image, the brightness value corresponding to each cable feature point is obtained to obtain multiple feature point brightness values; Set a reference brightness value, classify the cable feature points whose brightness values ​​are greater than or equal to the reference brightness value as first-category feature points, and classify the cable feature points whose brightness values ​​are less than the reference brightness value as second-category feature points; Classify a feature rectangle whose four vertices are all first-category feature points as a first-category feature rectangle, and classify a feature rectangle whose four vertices are second-category feature points as a second-category feature rectangle; Acquire the number of characteristic rectangles in the infrared image of the sample cable to obtain the number value of characteristic rectangles, acquire the number of first-type characteristic rectangles in the infrared image of the sample cable to obtain the number value of hotspot rectangles, calculate the ratio of the number value of hotspot rectangles to the number value of characteristic rectangles, and obtain the hotspot rectangle feature ratio; The number of cable feature points in the sample cable infrared image is obtained to obtain the number of cable feature points, the number of first category feature points in the sample cable infrared image is obtained to obtain the number of cable hot spots, and the ratio of the number of cable hot spots to the number of cable feature points is calculated to obtain the cable hot spot feature ratio; The hotspot rectangle feature ratio and the cable hotspot feature ratio are calculated to obtain the image infrared anomaly coefficient corresponding to the sample cable infrared image; The specific formula for calculating the image infrared anomaly coefficient corresponding to the sample cable infrared image is as follows: ； Among them, Hwy is the image infrared anomaly coefficient corresponding to the sample cable infrared image, Jxt is the hotspot rectangle feature ratio, and Rdt is the cable hotspot feature ratio; The image infrared anomaly coefficient corresponding to each tunnel cable infrared image is acquired to obtain a plurality of image infrared anomaly coefficients; Obtain an image infrared anomaly coefficient threshold, and perform numerical comparison between multiple image infrared anomaly coefficients and the image infrared anomaly coefficient threshold; if the image infrared anomaly coefficient of the tunnel cable infrared image is greater than or equal to the image infrared anomaly coefficient threshold, the tunnel cable infrared image is classified as a first type of cable infrared image; if the image infrared anomaly coefficient of the tunnel cable infrared image is less than the image infrared anomaly coefficient threshold, the tunnel cable infrared image is classified as a second type of cable infrared image, and the cable infrared image marking data is obtained.

5. The cable tunnel monitoring and management system based on big data according to claim 1 is characterized in that: The power data module acquires the power monitoring data of the cable tunnel, as follows: Acquire cable tunnel image monitoring data, and acquire tunnel real-time monitoring cycle and monitoring area division data according to the cable tunnel image monitoring data; Divide data according to monitoring areas and obtain target monitoring sub-areas; Perform power data monitoring on the target monitoring sub-area in the tunnel real-time monitoring cycle to obtain the regional power monitoring coefficient corresponding to the target monitoring sub-area; The specific acquisition process is as follows: Acquire the tunnel cables of the target monitoring sub-area to obtain a plurality of tunnel cables, and name the obtained plurality of cables as the first tunnel cable to the dth tunnel cable; Acquiring a first cable transmission loss by monitoring the power transmission loss of the first tunnel cable; Repeat the process of obtaining the first cable transmission loss, obtain the cable transmission loss corresponding to the second tunnel cable to the d-th tunnel cable, and obtain the second cable transmission loss to the d-th cable transmission loss; Obtaining a reference circuit transmission loss corresponding to the first tunnel cable to the dth tunnel cable, and obtaining a reference transmission loss of the first cable to a reference transmission loss of the dth cable; Calculate the regional power monitoring coefficients corresponding to different target monitoring sub-areas according to the transmission loss from the first cable to the dth cable and the reference transmission loss from the first cable to the dth cable; The specific formula for calculating the regional power monitoring coefficient for different target monitoring sub-areas is as follows: ； Among them, Qjk is the regional power monitoring coefficient corresponding to the target monitoring sub-area, Hshi is the i-th cable transmission loss, Hsji is the i-th cable benchmark transmission loss, and d is the number of tunnel cables corresponding to the target monitoring sub-area; The cable power monitoring coefficient corresponding to each monitoring sub-area is obtained respectively to obtain the cable tunnel power monitoring data.

6. A cable tunnel monitoring and management system based on big data according to claim 5, characterized in that: The power data module obtains the first cable transmission loss as follows: Acquire the line connection position in the first tunnel cable to obtain multiple line connection positions, deploy a circuit environment test box for each line connection position, and use the circuit environment test box to cover each line connection position; Name the multiple circuit environmental test boxes in the first tunnel cable as the first environmental test box to the cth environmental test box; Use a circuit environment test box to set up several different test deployment environments, and the ambient temperature value and ambient humidity value corresponding to each test deployment environment are different, and arbitrarily select one test deployment environment from the set multiple test deployment environments as a sample deployment environment; Under the sample deployment environment, the line voltage data corresponding to the first environmental test box to the cth environmental test box in the first tunnel cable are obtained to obtain the first test voltage value to the cth test voltage value; Calculate the environmental cable transmission loss corresponding to the sample deployment environment according to the first test voltage value to the cth test voltage value; The specific formula for calculating the cable transmission loss corresponding to the sample deployment environment is as follows: ； Wherein, Hds is the environmental cable transmission loss corresponding to the sample deployment environment, Vcsi is the i-th test voltage value, Vcs(i-1) is the i-1-th test voltage value, and c is the quantity value corresponding to the circuit environment test box; The environmental circuit transmission loss corresponding to each test deployment environment is obtained respectively to obtain multiple environmental circuit transmission losses, and the average of the obtained multiple environmental circuit transmission losses is calculated to obtain the first cable transmission loss.

7. The cable tunnel monitoring and management system based on big data according to claim 1 is characterized in that: The environmental data module acquires the cable tunnel environmental monitoring data, as follows: Acquire cable tunnel image monitoring data, and acquire tunnel real-time monitoring cycle and monitoring area division data according to the cable tunnel image monitoring data; Divide data according to monitoring areas and obtain target monitoring sub-areas; Perform environmental data monitoring on the target monitoring sub-area in the tunnel real-time monitoring cycle to obtain the regional environmental monitoring coefficient corresponding to the target monitoring sub-area; The tunnel environment monitoring coefficient corresponding to each monitoring sub-area is obtained to obtain the cable tunnel environment monitoring data.

8. The cable tunnel monitoring and management system based on big data according to claim 7 is characterized in that: The environmental data module obtains the regional environmental monitoring coefficient corresponding to the target monitoring sub-area, as follows: In the target monitoring sub-area, a plurality of sensors of different types are deployed, and the plurality of sensors of different types are named as first type sensors to mth type sensors in sequence; During the real-time monitoring period of the tunnel, a monitoring parameter corresponding to each first-type sensor is numerically acquired to obtain a plurality of first-type monitoring parameters, and an average of the acquired plurality of first-type monitoring parameters is averaged to obtain an average value of the first-type monitoring parameters; During the real-time monitoring period of the tunnel, the monitoring parameters corresponding to each second-type sensor are numerically acquired to obtain a plurality of second-type monitoring parameters, and the average of the acquired plurality of second-type monitoring parameters is averaged to obtain an average value of the second-type monitoring parameters; Respectively acquiring the average values ​​of the monitoring parameters corresponding to the third type sensor to the mth type sensor, to obtain the average values ​​of the third type monitoring parameters to the mth type monitoring parameters; Obtaining a first type monitoring parameter reference value to an mth type monitoring parameter reference value; Calculate the average value of the first type of monitoring parameters to the average value of the m-th type of monitoring parameters and the baseline value of the first type of monitoring parameters to the baseline value of the m-th type of monitoring parameters to obtain the regional environmental monitoring coefficient corresponding to the target monitoring sub-area; The specific formula for calculating the regional environmental monitoring coefficient corresponding to the target monitoring sub-area is as follows: ； Among them, Hqx is the regional environmental monitoring coefficient corresponding to the target monitoring sub-area, Jcci is the average value of the i-th type monitoring parameter, and Jcji is the benchmark value of the i-th type monitoring parameter.

9. The cable tunnel monitoring and management system based on big data according to claim 1 is characterized in that: The monitoring management module obtains the regional monitoring warning coefficient, as follows: Acquire cable tunnel image monitoring data, and acquire image monitoring anomaly coefficients corresponding to each monitoring sub-area according to the cable tunnel image monitoring data; Acquire the cable tunnel power monitoring data, and acquire the regional power monitoring coefficient corresponding to each monitoring sub-area according to the cable tunnel power monitoring data; Obtaining cable tunnel environmental monitoring data, and obtaining a regional environmental monitoring coefficient corresponding to each monitoring sub-area according to the cable tunnel environmental monitoring data; Calculate the image monitoring anomaly coefficient, regional power monitoring coefficient and regional environmental monitoring coefficient corresponding to the same monitoring sub-area to obtain the regional monitoring warning coefficient; The specific formula for calculating the regional monitoring warning coefficient is as follows: ； Among them, Yjx is the regional monitoring warning coefficient, Tyc is the image monitoring anomaly coefficient, Qjk is the regional power monitoring coefficient, and Hqx is the regional environmental monitoring coefficient; Obtain the regional monitoring warning coefficient threshold, perform numerical comparison between the regional monitoring warning coefficient and the regional monitoring warning coefficient threshold, and perform monitoring management and warning for each monitoring sub-region based on the numerical comparison result.

10. A cable tunnel monitoring and management system based on big data according to claim 9, characterized in that: The monitoring management module performs monitoring and early warning on the monitoring sub-area, as follows: Obtaining image monitoring anomaly coefficient threshold, regional power monitoring coefficient threshold, and regional environment monitoring coefficient threshold; Calculate the regional monitoring warning coefficient threshold according to the image monitoring anomaly coefficient threshold, the regional power monitoring coefficient threshold and the regional environment monitoring coefficient threshold; The specific formula for calculating the regional monitoring warning coefficient threshold is as follows: ； Among them, Yjxy is the regional monitoring warning coefficient threshold, Tycy is the image monitoring abnormality coefficient threshold, Qjky is the regional power monitoring coefficient threshold, and Hqxy is the regional environment monitoring coefficient threshold; If the image monitoring anomaly coefficient is greater than or equal to the image monitoring anomaly coefficient threshold, a monitoring anomaly warning is issued to the corresponding monitoring sub-area; If the image monitoring anomaly coefficient is less than the image monitoring anomaly coefficient threshold, the corresponding monitoring sub-area is monitored normally.

Images