Access equipment evaluation system for industrial network

Abstract

The invention discloses an access equipment evaluation system for an industrial network, which belongs to the field of access equipment evaluation systems and comprises a shell color change acquisition module, an equipment installation data acquisition module, a data analysis module, a preset data import module, an evaluation module and a visual notification module. The shell color change acquisition module acquires shell color change data of each access device through a camera, and sends the acquired data to the data analysis module; the equipment installation data acquisition module is used for acquiring current installation data of each access equipment and sending the installation data to the data analysis module, the installation data comprises equipment connection part information and shell inclination angle information, the equipment connection part information is acquired by an ultrasonic detector, and the shell inclination angle information is acquired by the data analysis module; and the inclination angle information of the shell is collected by the camera. According to the invention, the aging state of the external shell of the equipment can be accurately evaluated.

Description

Technical Field

[0001] The present invention relates to the field of access equipment evaluation, and in particular to an access equipment evaluation system for industrial networks. Background Art

[0002] Industrial cybersecurity refers to a set of technical, administrative, and physical measures taken to protect industrial control systems (ICS), Industrial Internet of Things (IIoT) devices, and critical infrastructure (such as power, water, transportation, and manufacturing) from cyberattacks, data leaks, malware infections, and other threats. It aims to ensure the availability, integrity, and confidentiality of industrial environments and prevent production disruptions, equipment damage, data leaks, or personal safety risks caused by cyberattacks.

[0003] In industrial network security, access devices are a key component in ensuring the stable operation of industrial networks and data security. Therefore, in order to ensure the stable operation of access devices, it is necessary to regularly evaluate the aging status of access devices. Existing patent 201710603416.6 is an electrical equipment aging assessment method based on device current ID. It provides a field current detection terminal that is set at the power socket of the electrical equipment and is used to obtain the current signal of the electrical equipment, and a remote storage and calculation module that matches the field current detection terminal. When the current signal of the electrical equipment uploaded by the field circuit detection terminal reaches a preset number, the average value of the rated number of current signal sampling values ​​is continuously taken. The aging level is determined based on this average value, and this average value is used as the standard data for the next electrical equipment identification. Similarly, after the next identification is completed, the aging level is determined based on the next average value.

[0004] Existing access device evaluation systems suffer from the following issues: they typically focus on whether the device's internal electrical parameters are standard, but ignore the degree of aging of the device's external casing, making it impossible to accurately assess the aging status of the device's external casing. Therefore, those skilled in the art have provided an access device evaluation system for industrial networks to address the issues raised in the background technology above. Summary of the Invention

[0005] In response to the shortcomings of the prior art, the present invention provides an access device evaluation system for an industrial network, comprising a housing color change acquisition module, an equipment installation data acquisition module, a data analysis module, a preset data import module, an evaluation module, and a visual notification module;

[0006] The shell color change acquisition module collects the shell color change data of each access device through a camera, and sends the collected data to the data analysis module; the device installation data acquisition module is used to collect the current installation data of each access device, and sends the installation data to the data analysis module, wherein the installation data includes the device connection part information and the shell inclination angle information, the device connection part information is collected by an ultrasonic detector, and the shell inclination angle information is collected by a camera; the preset data import module is used to import preset data into the data analysis module and the evaluation module; the data analysis module is used to receive all data for analysis, and output the analysis results to the evaluation module; the evaluation module performs evaluation based on the received analysis results, and packages the analysis results and the evaluation results and sends them to the visual notification module.

[0007] As a further solution of the present invention: the specific process of the data analysis module analyzing the data sent by the shell color change acquisition module is:

[0008] By image recognition, the area where the color of the access device shell changes is marked as Ai, where i=1···n, where n is a positive integer, and image recognition is performed on Ai to determine whether it is a coating peeling area;

[0009] If Ai is a coating peeling area, a first image analysis model is established to perform image analysis on Ai to determine whether the current coating peeling area is peeling due to scratches. If the current coating peeling area is peeling due to scratches, the corresponding Ai is planned to the first cluster; if the current coating peeling area is not peeling due to scratches, the corresponding Ai is planned to the second cluster.

[0010] If Ai is not a coating peeling area, a second image analysis model is established to perform image analysis on Ai to determine whether Ai has changed color due to natural aging. If Ai has changed color due to natural aging, Ai is assigned to the third cluster; if Ai has not changed color due to natural aging, Ai is assigned to the fourth cluster.

[0011] As a further solution of the present invention: the specific analysis process of the first image analysis model is:

[0012] Perform image recognition analysis on the current coating peeling area Ai to determine whether Ai has scratches. If Ai has scratches, it means that Ai has the first significant feature;

[0013] Identify the shape of the current coating peeling area Ai and determine whether Ai is an irregular flake. If Ai is not an irregular flake, it means that Ai has the second significant feature.

[0014] Extract the edge contour of the current coating peeling area Ai and divide the edge contour of Ai into several sub-contours;

[0015] Count the number of all sub-contours, mark them as M, and perform image recognition on each sub-contour;

[0016] If the edge of the sub-contour is sharp and clearly demarcated from the unpeeled area, the sub-contour is planned to the first sequence;

[0017] If the edge of the sub-contour is a straight line or a broken line, the sub-contour is planned to the second sequence;

[0018] If there are burrs or debris left on the edge of the sub-contour, the sub-contour will be planned to the third sequence;

[0019] Count the number of sub-contours in the first sequence, marked as m1, count the number of sub-contours in the second sequence, marked as m2, and count the number of sub-contours in the third sequence, marked as m3;

[0020] Calculate the characteristic weight value W = (m1 + m2 + m3) / 3M of the current coating peeling area Ai;

[0021] Compare the feature weight value W with the preset weight value w. If W≥w, it means that Ai has the third significant feature; if W<w, it means that Ai does not have the third significant feature;

[0022] If the current coating peeling area Ai has any two of the first significant feature, the second significant feature, and the third significant feature, it means that the current coating peeling area Ai is peeling due to scratches. Otherwise, it means that the current coating peeling area Ai is not peeling due to scratches.

[0023] As a further solution of the present invention: the specific analysis process of the second image analysis model is:

[0024] Extract the texture features of Ai and determine whether the texture continuity of Ai is destroyed. If the texture continuity of Ai is not destroyed, it means that Ai has the fourth significant feature;

[0025] Extract the edge contour of Ai and divide the edge contour of Ai into several sub-segments;

[0026] Calculate the color difference on both sides of the sub-segment through image recognition analysis, mark it as X, and compare X with the preset color difference x. If X < x, plan the sub-segment to the fourth sequence; if X ≥ x, plan the sub-segment to the fifth sequence;

[0027] Count the number of sub-segments in the fourth sequence, marked as Y1, and count the number of sub-segments in the fifth sequence, marked as Y2. If Y1>Y2, it means that Ai has the fifth significant feature.

[0028] Extract the regional image of Ai and divide it into several sub-images, count the number of all sub-images, mark them as Z, and perform image recognition on each sub-image;

[0029] If there is a crack in the sub-image, the sub-image is planned to the sixth sequence;

[0030] If there is deformation in the sub-image, the sub-image is planned to the seventh sequence;

[0031] If there is a corrosion pit in the sub-image, the sub-image is planned to the eighth sequence;

[0032] Count the number of sub-images in the sixth sequence, marked as z1, count the number of sub-images in the second sequence, marked as z2, and count the number of sub-images in the third sequence, marked as z3;

[0033] Calculate the feature weight value of Ai Q = (z1 + z2 + z3) / 3Z;

[0034] Compare the feature weight value Q with the preset weight value q. If Q < q, it means that Ai has the sixth significant feature; if Q ≥ q, it means that Ai does not have the sixth significant feature.

[0035] If Ai has any two of the fourth, fifth, and sixth significant characteristics, it means that the current color change of Ai is due to natural aging; otherwise, it means that the current color change of Ai is not due to natural aging.

[0036] As a further solution of the present invention: the specific process of the data analysis module analyzing the data sent by the device installation data acquisition module is:

[0037] The ultrasonic detector uses ultrasonic waves to detect the tightness of each preset connection part of the access device. The ultrasonic waves will be reflected or scattered at the loose parts to determine whether there is any looseness;

[0038] The loose connection parts detected by the ultrasonic detector are marked as Bi, where i=1···n, where n is a positive integer. The connection parts are divided into three types according to their types: wired interface parts, card interface parts, and installation fastening parts;

[0039] Each loose connection Bi is divided into the fifth cluster if the connection is a wired interface, the sixth cluster if the connection is a card interface, and the seventh cluster if the connection is a mounting fastening portion.

[0040] Perform image recognition on the shell tilt angle image captured by the camera to determine whether the shell of the currently connected device is tilted. If so, proceed to the next step. If not, output that the shell installation angle is normal;

[0041] The shell tilt mode in the shell tilt angle image is determined by image recognition analysis, wherein the shell tilt mode includes the shell and the installation base tilting at the same time, the shell tilting but the installation base not tilting, and the shell not tilting but the installation base tilting.

[0042] As a further solution of the present invention: the specific evaluation process of the evaluation module is:

[0043] Construct a shell aging degree assessment sub-model and output the shell aging degree assessment results;

[0044] Obtain the shell aging assessment results for each access device, establish a purchasing staff assessment sub-model, and evaluate the purchasing staff's work;

[0045] Construct an equipment stability assessment sub-model and output the equipment stability assessment results;

[0046] Obtain the stability assessment results of each access device, establish an installation staff assessment sub-model, and evaluate the work of the installation staff.

[0047] As a further solution of the present invention, the specific evaluation process of the shell aging degree evaluation sub-model is as follows:

[0048] Count the number of Ai in the first cluster, marked as C1, and calculate the total area of ​​all Ai in the first cluster, marked as D1;

[0049] Count the number of Ai in the second cluster, marked as C2, and calculate the total area of ​​all Ai in the second cluster, marked as D2;

[0050] Count the number of Ai in the third cluster, marked as C3, and calculate the total area of ​​all Ai in the third cluster, marked as D3;

[0051] Count the number of Ai in the fourth cluster, marked as C4, and calculate the total area of ​​all Ai in the fourth cluster, marked as D4;

[0052] Calculate the shell aging degree weight value V1 = 60% * (C1 / c1 + C2 / c2 + C3 / c3 + C4 / c4) + 40% * (D1 / d1 + D2 / d2 + D3 / d3 + D4 / d4), where c1, c2, c3, c4, d1, d2, d3, and d4 are all preset values;

[0053] The shell aging degree weight value V1 is compared with the preset weight value v1. If V1>v1, it means that the shell aging degree of the access device is abnormal. If V1≤v1, it means that the shell aging degree of the access device is normal.

[0054] As a further solution of the present invention: the specific evaluation process of the procurement employee evaluation sub-model is as follows:

[0055] Obtain all access devices with abnormal shell aging and the corresponding purchasing personnel;

[0056] Count the total number of access devices with abnormal shell aging corresponding to the purchasing personnel, marked as E;

[0057] The total amount of the corresponding access equipment purchased by the purchasing personnel is counted and marked as F;

[0058] Calculate the weight of this procurement task: V2 = 45% * (E / e) + 55% * (F / f), where e and f are both preset values.

[0059] The weight value V2 is compared with the preset weight value v2. If V2>v2, it means that there is an abnormality in the work of the buyer this time. If V2≤v2, it means that the work of the buyer this time is normal.

[0060] As a further solution of the present invention: the specific evaluation process of the stability evaluation sub-model is as follows:

[0061] Count the number of Bi in the fifth cluster, marked as G1, count the number of Bi in the sixth cluster, marked as G2, count the number of Bi in the seventh cluster, marked as G3;

[0062] If the housing of the currently connected device is not tilted, the output weighting factor P=1; if the housing of the currently connected device and the installation base are tilted at the same time, the output weighting factor P=2; if the housing of the currently connected device is tilted but the installation base is not tilted, the output weighting factor P=1.5; if the housing of the currently connected device is not tilted but the installation base is tilted, the output weighting factor P=1.2;

[0063] Calculate the device stability weight V3 = P*(G1 / g1+G2 / g2+G3 / g3), where g1, g2, and g3 are all preset values;

[0064] The device stability weight value V3 is compared with the preset weight value v3. If V3>v3, it means that the stability of the access device is abnormal. If V3≤v3, it means that the stability of the access device is normal.

[0065] As a further solution of the present invention: the specific evaluation process of installing the employee evaluation sub-model is:

[0066] Obtain all access devices with abnormal stability and the corresponding installers;

[0067] Count the total number of access devices with abnormal stability corresponding to the installer, marked as K;

[0068] Compare K with the preset value k. If K>k, it means that the installer is working abnormally. If K≤k, it means that the installer is working abnormally.

[0069] The beneficial effects of the present invention are embodied in:

[0070] 1. This application analyzes the color changes of the shell of the access device to quickly evaluate the aging status of the access device. In order to improve the accuracy of the evaluation results, an in-depth analysis is performed on the areas of each color change on the device shell. The type of each color change area is first analyzed, which makes the subsequent calculation of the comprehensive aging status of the shell more representative.

[0071] 2. This application evaluates the installation data of the access equipment from two aspects: the tightness of the connection part and the tilt state of the equipment shell. For the evaluation of the tightness of the connection part, analysis is conducted from three angles: the wired interface part, the card interface part, and the installation tightness part. For the evaluation of the tilt state of the equipment shell, different weighting factors are assigned to different tilt methods. The differentiated calculation method makes the final equipment stability evaluation result more accurate and representative.

[0072] 3. This application evaluates the work of the corresponding purchasers and installers based on the results of the shell aging assessment and the equipment stability assessment, making the entire assessment system more comprehensive and adaptable, and making it easier for back-end staff to detect abnormalities in a timely manner. BRIEF DESCRIPTION OF THE DRAWINGS

[0073] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following briefly describes the drawings required for the specific embodiments or the description of the prior art. Similar elements or parts are generally identified by similar reference numerals throughout the drawings. Elements or parts in the drawings are not necessarily drawn to scale.

[0074] Figure 1 The structure block diagram of an access device evaluation system for industrial networks is shown in FIG. DETAILED DESCRIPTION

[0075] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0076] As mentioned in the background technology of this application, research has found that existing access equipment evaluation systems usually focus on whether the internal electrical parameters of the equipment are standard, but ignore the aging degree of the equipment's external shell, and are unable to accurately evaluate the aging status of the equipment's external shell, which has certain defects.

[0077] In order to solve the above-mentioned defects, the present application discloses an access device evaluation system for industrial networks, which can accurately evaluate the aging status of the device's external shell.

[0078] The following will describe in detail how the solution of this application solves the above technical problems with reference to the accompanying drawings.

[0079] See also Figure 1 In an embodiment of the present invention, an access device evaluation system for an industrial network includes a shell color change acquisition module, a device installation data acquisition module, a data analysis module, a preset data import module, an evaluation module, and a visual notification module; the shell color change acquisition module collects the shell color change data of each access device through a camera, and sends the collected data to the data analysis module; the device installation data acquisition module is used to collect the current installation data of each access device, and send the installation data to the data analysis module, wherein the installation data includes device connection part information and shell tilt angle information, the device connection part information is collected by an ultrasonic detector, and the shell tilt angle information is collected by a camera; the preset data import module is used to import preset data into the data analysis module and the evaluation module; the data analysis module is used to receive all data for analysis, and output the analysis results to the evaluation module; the evaluation module performs evaluation based on the received analysis results, and packages the analysis results and the evaluation results and sends them to the visual notification module.

[0080] In this embodiment, the specific process of the data analysis module analyzing the data sent by the shell color change acquisition module is as follows: the color change area of ​​the access device shell is marked as Ai through image recognition, i=1···n, where n is a positive integer, and image recognition is performed on Ai to determine whether it is a coating peeling area; if Ai is a coating peeling area, a first image analysis model is established, and image analysis is performed on Ai to determine whether the current coating peeling area is due to scratches; wherein, if the current coating peeling area is due to scratches, the corresponding Ai is planned to the first cluster; if the current coating peeling area is not due to scratches, the corresponding Ai is planned to the second cluster; if Ai is not a coating peeling area, a second image analysis model is established, and image analysis is performed on Ai to determine whether Ai is due to natural aging color change; wherein, if Ai is due to natural aging color change, Ai is planned to the third cluster; if Ai is not due to natural aging color change, Ai is planned to the fourth cluster. This application analyzes the color changes of the shell of the access device to quickly evaluate the aging status of the access device. In order to improve the accuracy of the evaluation results, an in-depth analysis is performed on the areas of each color change on the device shell. The type of each color change area is first analyzed, which makes the subsequent calculation of the comprehensive aging status of the shell more representative.

[0081] In this embodiment, the specific analysis process of the first image analysis model is as follows: perform image recognition analysis on the current coating peeling area Ai to determine whether Ai has scratches. If Ai has scratches, it means that Ai has the first significant feature; identify the shape of the current coating peeling area Ai to determine whether Ai is an irregular flake. If Ai is not an irregular flake, it means that Ai has the second significant feature; extract the edge contour of the current coating peeling area Ai, and divide the edge contour of Ai into several sub-contours; count the number of all sub-contours, mark it as M, and perform image recognition on each sub-contour; if the edge of the sub-contour is sharp and has a clear boundary with the non-peeling area, then plan the sub-contour to the first sequence; if the edge of the sub-contour is a straight line or a broken line, then plan the sub-contour to the second sequence; if If there are burrs or debris on the edge of the sub-contour, the sub-contour is planned to the third sequence; the number of sub-contours in the first sequence is counted, marked as m1, the number of sub-contours in the second sequence is counted, marked as m2, and the number of sub-contours in the third sequence is counted, marked as m3; the feature weight value W = (m1+m2+m3) / 3M of the current coating peeling area Ai is calculated; the feature weight value W is compared with the preset weight value w. If W≥w, it means that Ai has the third significant feature; if W<w, it means that Ai does not have the third significant feature; if the current coating peeling area Ai has any two of the first significant feature, the second significant feature, and the third significant feature, it means that the current coating peeling area Ai is peeling due to scratches; otherwise, it means that the current coating peeling area Ai is not peeling due to scratches. The first image analysis model can quickly distinguish whether the current coating peeling area is peeling due to scratches, which facilitates the subsequent accurate assessment of the aging status of the shell.

[0082] In this embodiment, the specific analysis process of the second image analysis model is as follows: extract the texture features of Ai, determine whether the texture continuity of Ai is destroyed, and if the texture continuity of Ai is not destroyed, it means that Ai has the fourth significant feature; extract the edge contour of Ai, and divide the edge contour of Ai into several sub-segments; calculate the color difference on both sides of the sub-segment through image recognition analysis, mark it as X, compare X with the preset color difference x, if X < x, then plan the sub-segment to the fourth sequence, if X ≥ x, then plan the sub-segment to the fifth sequence; count the number of sub-segments in the fourth sequence, mark it as Y1, and count the number of sub-segments in the fifth sequence, mark it as Y2; if Y1 > Y2, it means that Ai has the fifth significant feature; extract the regional image of Ai and divide it into several sub-images, count the number of all sub-images, mark it as Z, and perform image segmentation on each sub-image. Image recognition; if a crack is present in a sub-image, the sub-image is assigned to the sixth sequence; if deformation is present in a sub-image, the sub-image is assigned to the seventh sequence; if corrosion pits are present in a sub-image, the sub-image is assigned to the eighth sequence; the number of sub-images in the sixth sequence is counted, labeled z1; the number of sub-images in the second sequence is counted, labeled z2; and the number of sub-images in the third sequence is counted, labeled z3; the feature weight value Q of Ai is calculated as Q = (z1 + z2 + z3) / 3Z; the feature weight value Q is compared with the preset weight value q. If Q < q, Ai has the sixth significant feature; if Q ≥ q, Ai does not have the sixth significant feature; if Ai has any two of the fourth, fifth, or sixth significant features, the current color change of Ai is due to natural aging; otherwise, the current color change of Ai is not due to natural aging. The second image analysis model can quickly determine whether the current color change area is due to natural aging, facilitating subsequent accurate assessment of the aging status of the shell. It's important to note that image recognition and analysis technology is a well-known technology and a key branch of artificial intelligence (AI) and computer vision (CV). It uses computer algorithms to automatically analyze, classify, understand, and make decisions about image or video content. Its core goal is to extract semantic information (such as object category, location, attributes, and behavior) from image data, enabling machines to "understand" the visual world.

[0083] In this embodiment, the specific process of the data analysis module analyzing the data sent by the device installation data acquisition module is as follows: the ultrasonic detector detects the fastening status of each preset connection part of the access device through ultrasonic waves, and the ultrasonic waves will be reflected or scattered at the loose parts to determine whether there is looseness; the loose connection parts collected by the ultrasonic detector are marked as Bi, i=1···n, where n is a positive integer, and the connection parts are divided into three types according to type: wired interface parts, card insertion interface parts, and installation fastening parts; each loose connection part Bi is divided, and if the connection part is a wired interface part, the loose connection part Bi is divided into The fifth cluster, if the connection part is a card interface part, the loose connection part Bi is divided into the sixth cluster, if the connection part is an installation fastening part, the loose connection part Bi is divided into the seventh cluster; the shell tilt angle image captured by the camera is image recognized to determine whether the shell of the current access device is tilted, if it is tilted, the next step is entered, if it is not tilted, the shell installation angle is output as normal; the shell tilt mode in the shell tilt angle image is determined by image recognition analysis, wherein the shell tilt mode includes the shell and the installation base tilting at the same time, the shell tilting but the installation base not tilting, and the shell not tilting but the installation base tilting. This application evaluates the installation data of the access device from two aspects: the fastening state of the connection part and the tilt state of the device shell. Multi-faceted evaluation makes the final evaluation result more accurate.

[0084] In this embodiment, the specific evaluation process of the evaluation module is as follows: constructing a shell aging degree evaluation sub-model and outputting the shell aging degree evaluation result; obtaining the shell aging degree evaluation result of each access device, establishing a purchasing staff evaluation sub-model, and evaluating the work of the purchasing staff; constructing an equipment stability degree evaluation sub-model and outputting the equipment stability degree evaluation result; obtaining the stability degree evaluation result of each access device, establishing an installation staff evaluation sub-model, and evaluating the work of the installation staff. This application evaluates the corresponding purchaser work and installation staff work based on the shell aging degree evaluation result and the equipment stability evaluation result, making the entire evaluation system more comprehensive and adaptable, and making it easier for back-end staff to detect abnormalities in a timely manner.

[0085] In this embodiment, the specific evaluation process of the shell aging degree evaluation sub-model is as follows: count the number of Ai in the first cluster, marked as C1, and calculate the total area of ​​all Ai in the first cluster, marked as D1; ​​count the number of Ai in the second cluster, marked as C2, and calculate the total area of ​​all Ai in the second cluster, marked as D2; count the number of Ai in the third cluster, marked as C3, and calculate the total area of ​​all Ai in the third cluster, marked as D3; count the number of Ai in the fourth cluster, marked as C4, and calculate the total area of ​​all Ai in the fourth cluster , marked as D4; calculate the shell aging weight V1 = 60% * (C1 / c1 + C2 / c2 + C3 / c3 + C4 / c4) + 40% * (D1 / d1 + D2 / d2 + D3 / d3 + D4 / d4), where c1, c2, c3, c4, d1, d2, d3, and d4 are preset values; compare the shell aging weight V1 with the preset weight v1. If V1 > v1, the shell aging of the access device is abnormal; if V1 ≤ v1, the shell aging of the access device is normal. The shell aging assessment submodel can quickly assess whether the shell aging of the access device is abnormal.

[0086] In this embodiment, the specific evaluation process of the purchasing employee evaluation sub-model is as follows: obtain all access devices with abnormal shell aging and the corresponding purchasing personnel; count the total number of access devices with abnormal shell aging corresponding to the purchasing personnel, marked as E; count the total amount of the corresponding access devices purchased by the purchasing personnel, marked as F; calculate the weight value V2 of this purchase work = 45% * (E / e) + 55% * (F / f), where e and f are both preset values; compare the weight value V2 with the preset weight value v2. If V2>v2, it indicates that the purchaser's work is abnormal; if V2≤v2, it indicates that the purchaser's work is normal. The purchasing employee evaluation sub-model can quickly assess whether there are any abnormalities in the purchaser's purchasing work.

[0087] In this embodiment, the specific evaluation process of the stability evaluation sub-model is as follows: counting the number of Bi in the fifth cluster, marked as G1, counting the number of Bi in the sixth cluster, marked as G2, and counting the number of Bi in the seventh cluster, marked as G3; if the current access device housing is not tilted, outputting a weighting factor P=1; if the current access device housing and the installation base are tilted at the same time, outputting a weighting factor P=2; if the current access device housing is tilted but the installation base is not tilted, outputting a weighting factor P=1.5; if the current access device housing is not tilted but the installation base is tilted, outputting a weighting factor P=1.2; calculating a device stability weight value V3=P*(G1 / g1+G2 / g2+G3 / g3), where g1, g2, and g3 are all preset values; comparing the device stability weight value V3 with the preset weight value v3; if V3>v3, it indicates that the stability of the access device is abnormal; if V3≤v3, it indicates that the stability of the access device is normal. This application evaluates the installation data of access equipment from two aspects: the tightness of the connection part and the tilt state of the equipment shell. For the evaluation of the tightness of the connection part, analysis is conducted from three perspectives: the wired interface part, the card interface part, and the installation tightness part. For the evaluation of the tilt state of the equipment shell, different weighting factors are assigned to different tilt methods. The differentiated calculation method makes the final equipment stability evaluation result more accurate and representative.

[0088] In this embodiment, the specific evaluation process of the installer assessment sub-model is as follows: All access devices with abnormal stability and their corresponding installers are obtained; the total number of access devices with abnormal stability corresponding to the installers is counted, labeled K; K is compared with a preset value k. If K>k, it indicates that the installer is performing abnormally; if K≤k, it indicates that the installer is performing abnormally. The installer assessment sub-model can quickly assess whether an installer's installation work is abnormal.

[0089] The present invention analyzes the color change of the shell of the access device to quickly evaluate the aging status of the access device. In order to improve the accuracy of the evaluation results, an in-depth analysis is performed on the areas of each color change on the device shell. The type of each color change area is first analyzed, so that the subsequent calculation of the comprehensive aging status of the shell is more representative. The present application evaluates the installation data of the access device from two aspects: the tightness of the connection part and the tilt state of the device shell. For the evaluation of the tightness of the connection part, analysis is performed from three perspectives: the wired interface part, the card interface part, and the installation tightness part. For the evaluation of the tilt state of the device shell, different tilting methods are assigned different weighting factors. The differentiated calculation method makes the final equipment stability evaluation result more accurate and representative. Based on the shell aging evaluation results and the equipment stability evaluation results, the present application evaluates the corresponding purchaser's work and the installer's work, making the entire evaluation system more comprehensive and adaptable, and more convenient for backstage staff to detect abnormalities in a timely manner.

[0090] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the above embodiments, or make equivalent replacements for some or all of the technical features therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the scope of the technical solutions of the embodiments of the present invention, and they should all be included in the scope of the claims and description of the present invention.

Claims

1. An access device evaluation system for an industrial network, characterized in that: It includes a shell color change acquisition module, an equipment installation data acquisition module, a data analysis module, a preset data import module, an evaluation module, and a visual notification module; The shell color change acquisition module collects the shell color change data of each access device through a camera, and sends the collected data to the data analysis module; the device installation data acquisition module is used to collect the current installation data of each access device, and sends the installation data to the data analysis module, wherein the installation data includes the device connection part information and the shell inclination angle information, the device connection part information is collected by an ultrasonic detector, and the shell inclination angle information is collected by a camera; the preset data import module is used to import preset data into the data analysis module and the evaluation module; the data analysis module is used to receive all data for analysis, and output the analysis results to the evaluation module; the evaluation module performs evaluation based on the received analysis results, and packages the analysis results and the evaluation results and sends them to the visual notification module.

2. The access device evaluation system for industrial network according to claim 1, characterized in that: The specific process of the data analysis module analyzing the data sent by the shell color change acquisition module is as follows: By image recognition, the area where the color of the access device shell changes is marked as Ai, where i=1···n, where n is a positive integer, and image recognition is performed on Ai to determine whether it is a coating peeling area; If Ai is a coating peeling area, a first image analysis model is established to perform image analysis on Ai to determine whether the current coating peeling area is peeling due to scratches. If the current coating peeling area is peeling due to scratches, the corresponding Ai is planned to the first cluster; if the current coating peeling area is not peeling due to scratches, the corresponding Ai is planned to the second cluster. If Ai is not a coating peeling area, a second image analysis model is established to perform image analysis on Ai to determine whether Ai has changed color due to natural aging. If Ai has changed color due to natural aging, Ai is assigned to the third cluster; if Ai has not changed color due to natural aging, Ai is assigned to the fourth cluster.

3. The access device evaluation system for industrial network according to claim 2, characterized in that: The specific analysis process of the first image analysis model is: Perform image recognition analysis on the current coating peeling area Ai to determine whether Ai has scratches. If Ai has scratches, it means that Ai has the first significant feature; Identify the shape of the current coating peeling area Ai and determine whether Ai is an irregular flake. If Ai is not an irregular flake, it means that Ai has the second significant feature. Extract the edge contour of the current coating peeling area Ai and divide the edge contour of Ai into several sub-contours; Count the number of all sub-contours, mark them as M, and perform image recognition on each sub-contour; If the edge of the sub-contour is sharp and clearly demarcated from the unpeeled area, the sub-contour is planned to the first sequence; If the edge of the sub-contour is a straight line or a broken line, the sub-contour is planned to the second sequence; If there are burrs or debris left on the edge of the sub-contour, the sub-contour will be planned to the third sequence; Count the number of sub-contours in the first sequence, marked as m1, count the number of sub-contours in the second sequence, marked as m2, and count the number of sub-contours in the third sequence, marked as m3; Calculate the characteristic weight value W = (m1 + m2 + m3) / 3M of the current coating peeling area Ai; Compare the feature weight value W with the preset weight value w. If W ≥ w, it means that Ai has the third significant feature; If W<w, it means that Ai does not have the third significant feature; If the current coating peeling area Ai has any two of the first significant feature, the second significant feature, and the third significant feature, it means that the current coating peeling area Ai is peeling due to scratches. Otherwise, it means that the current coating peeling area Ai is not peeling due to scratches.

4. The access device evaluation system for industrial network according to claim 3, characterized in that: The specific analysis process of the second image analysis model is as follows: Extract the texture features of Ai and determine whether the texture continuity of Ai is destroyed. If the texture continuity of Ai is not destroyed, it means that Ai has the fourth significant feature; Extract the edge contour of Ai and divide the edge contour of Ai into several sub-segments; Calculate the color difference on both sides of the sub-segment through image recognition analysis, mark it as X, and compare X with the preset color difference x. If X < x, plan the sub-segment to the fourth sequence; if X ≥ x, plan the sub-segment to the fifth sequence; Count the number of sub-segments in the fourth sequence, marked as Y1, and count the number of sub-segments in the fifth sequence, marked as Y2. If Y1>Y2, it means that Ai has the fifth significant feature. Extract the regional image of Ai and divide it into several sub-images, count the number of all sub-images, mark them as Z, and perform image recognition on each sub-image; If there is a crack in the sub-image, the sub-image is planned to the sixth sequence; If there is deformation in the sub-image, the sub-image is planned to the seventh sequence; If there is a corrosion pit in the sub-image, the sub-image is planned to the eighth sequence; Count the number of sub-images in the sixth sequence, marked as z1, count the number of sub-images in the second sequence, marked as z2, and count the number of sub-images in the third sequence, marked as z3; Calculate the feature weight value of Ai Q = (z1 + z2 + z3) / 3Z; Compare the feature weight value Q with the preset weight value q. If Q < q, it means that Ai has the sixth significant feature. If Q≥q, it means that Ai does not have the sixth significant characteristic; If Ai has any two of the fourth, fifth, and sixth significant characteristics, it means that the current color change of Ai is due to natural aging; otherwise, it means that the current color change of Ai is not due to natural aging.

5. The access device evaluation system for industrial network according to claim 4, characterized in that: The specific process of the data analysis module analyzing the data sent by the device installation data acquisition module is as follows: The ultrasonic detector uses ultrasonic waves to detect the tightness of each preset connection part of the access device. The ultrasonic waves will be reflected or scattered at the loose parts to determine whether there is any looseness; The loose connection parts detected by the ultrasonic detector are marked as Bi, where i=1···n, where n is a positive integer. The connection parts are divided into three types according to their types: wired interface parts, card interface parts, and installation fastening parts; Each loose connection Bi is divided into the fifth cluster if the connection is a wired interface, the sixth cluster if the connection is a card interface, and the seventh cluster if the connection is a mounting fastening portion. Perform image recognition on the shell tilt angle image captured by the camera to determine whether the shell of the currently connected device is tilted. If so, proceed to the next step. If not, output that the shell installation angle is normal; The shell tilt mode in the shell tilt angle image is determined by image recognition analysis, wherein the shell tilt mode includes the shell and the installation base tilting at the same time, the shell tilting but the installation base not tilting, and the shell not tilting but the installation base tilting.

6. The access device evaluation system for industrial network according to claim 5, characterized in that: The specific evaluation process of the evaluation module is as follows: Construct a shell aging degree assessment sub-model and output the shell aging degree assessment results; Obtain the shell aging assessment results for each access device, establish a purchasing staff assessment sub-model, and evaluate the purchasing staff's work; Construct an equipment stability assessment sub-model and output the equipment stability assessment results; Obtain the stability assessment results of each access device, establish an installation staff assessment sub-model, and evaluate the work of the installation staff.

7. The access device evaluation system for industrial network according to claim 6, characterized in that: The specific evaluation process of the shell aging degree evaluation sub-model is as follows: Count the number of Ai in the first cluster, marked as C1, and calculate the total area of ​​all Ai in the first cluster, marked as D1; Count the number of Ai in the second cluster, marked as C2, and calculate the total area of ​​all Ai in the second cluster, marked as D2; Count the number of Ai in the third cluster, marked as C3, and calculate the total area of ​​all Ai in the third cluster, marked as D3; Count the number of Ai in the fourth cluster, marked as C4, and calculate the total area of ​​all Ai in the fourth cluster, marked as D4; Calculate the shell aging degree weight value V1 = 60% * (C1 / c1 + C2 / c2 + C3 / c3 + C4 / c4) + 40% * (D1 / d1 + D2 / d2 + D3 / d3 + D4 / d4), where c1, c2, c3, c4, d1, d2, d3, and d4 are all preset values; The shell aging degree weight value V1 is compared with the preset weight value v1. If V1>v1, it means that the shell aging degree of the access device is abnormal. If V1≤v1, it means that the shell aging degree of the access device is normal.

8. The access device evaluation system for industrial network according to claim 7, characterized in that: The specific evaluation process of the procurement employee evaluation sub-model is as follows: Obtain all access devices with abnormal shell aging and the corresponding purchasing personnel; Count the total number of access devices with abnormal shell aging corresponding to the purchasing personnel, marked as E; The total amount of the corresponding access equipment purchased by the purchasing personnel is counted and marked as F; Calculate the weight of this procurement task: V2 = 45% * (E / e) + 55% * (F / f), where e and f are both preset values. The weight value V2 is compared with the preset weight value v2. If V2>v2, it means that there is an abnormality in the work of the buyer this time. If V2≤v2, it means that the work of the buyer this time is normal.

9. The access device evaluation system for industrial network according to claim 8, characterized in that: The specific evaluation process of the stability evaluation sub-model is as follows: Count the number of Bi in the fifth cluster, marked as G1, count the number of Bi in the sixth cluster, marked as G2, count the number of Bi in the seventh cluster, marked as G3; If the housing of the currently connected device is not tilted, the output weighting factor P=1; if the housing of the currently connected device and the installation base are tilted at the same time, the output weighting factor P=2; if the housing of the currently connected device is tilted but the installation base is not tilted, the output weighting factor P=1.5; if the housing of the currently connected device is not tilted but the installation base is tilted, the output weighting factor P=1.2; Calculate the device stability weight V3 = P*(G1 / g1+G2 / g2+G3 / g3), where g1, g2, and g3 are all preset values; The device stability weight value V3 is compared with the preset weight value v3. If V3>v3, it means that the stability of the access device is abnormal. If V3≤v3, it means that the stability of the access device is normal.

10. The access device evaluation system for industrial network according to claim 9, characterized in that: The specific evaluation process of installing the employee evaluation sub-model is as follows: Obtain all access devices with abnormal stability and the corresponding installers; Count the total number of access devices with abnormal stability corresponding to the installer, marked as K; Compare K with the preset value k. If K>k, it means that the installer is working abnormally. If K≤k, it means that the installer is working abnormally.

Images