Intelligent street lamp intelligent supervision system and method based on cloud computing

Abstract

The invention discloses an intelligent street lamp intelligent supervision system and method based on cloud computing, and belongs to the technical field of intelligent street lamp supervision. The method comprises the following steps: acquiring position distribution of street lamps in a to-be-detected area and product specification information corresponding to each street lamp, detecting the street lamps in the to-be-detected area through a sensor, and generating street lamp detection feature information of each position in the to-be-detected area; analyzing the street lamp detection feature information after image recognition to obtain a corresponding street lamp quality evaluation report; according to the real-time street lamp quality evaluation report of the street lamp, generating a fault risk street lamp in combination with historical data; and calculating a fault risk reference value for the updated routing inspection route scheme, selecting the updated routing inspection route scheme with the minimum fault risk reference value as an optimal routing inspection scheme, and sending the optimal routing inspection scheme to a maintainer to which the optimal routing inspection scheme belongs. The influence on the original inspection route scheme is reduced, and the efficiency of inspection and maintenance of the street lamp is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of smart street lamp supervision, and specifically to a smart street lamp intelligent supervision system and method based on cloud computing. Background Art

[0002] As people's material and spiritual living standards continue to improve, the pursuit of life is developing towards a more comfortable, safe, efficient and energy-saving direction, and the requirements for architectural lighting technology are becoming higher and higher. The emerging "intelligent lighting" technology is an organic combination of modern computer technology, control technology, communication technology and architectural lighting technology, and is superior to traditional lighting technology in all aspects.

[0003] The corresponding smart street lamp equipment is prone to irregular failures, requiring maintenance personnel to conduct irregular inspections of the smart street lamps. However, the current management of smart street lamps often adopts the approach of repairing smart street lamps after a failure occurs, without quantitative analysis and management of smart street lamps with failure risks. When a smart street lamp with failure risks appears, the smart street lamp will be added to the existing inspection route, and the impact on the existing inspection route needs to be considered.

[0004] Therefore, the present invention discloses a cloud computing-based intelligent street lamp intelligent monitoring system and method to solve the above problems. Summary of the invention

[0005] The purpose of the present invention is to provide a cloud computing-based intelligent street lamp intelligent supervision system and method to solve the problems raised in the above background technology.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions: a smart street lamp intelligent supervision method based on cloud computing, the method comprising the following steps:

[0007] S1: Obtain the location distribution of street lamps in the area to be tested and the product specification information corresponding to each street lamp, detect the street lamps in the area to be tested through sensors, and generate street lamp detection feature information at each position in the area to be tested;

[0008] S2: Perform image recognition on the street lamp detection feature information at each location in the test area through image recognition technology, analyze the street lamp detection feature information after image recognition, and obtain a corresponding street lamp quality assessment report;

[0009] S3: Generate a street lamp with a risk of failure based on the real-time street lamp quality assessment report of the street lamp and the street lamp quality assessment report of the faulty street lamp when the maintenance situation occurs in the historical data;

[0010] S4: Obtain the inspection route plan of the maintenance personnel in the test area, add the newly generated fault risk street lights to the original inspection route plan, calculate the fault risk reference value for the updated inspection route plan, select the updated inspection route plan with the smallest fault risk reference value as the best inspection plan, and send the best inspection plan to the maintenance personnel.

[0011] According to the above scheme, when the street lamp detection feature data of each position in the test area is generated in S1, the detection feature information includes the detection image of the corresponding street lamp light beam and solar panel; the detection feature information also includes the three-dimensional space model of the corresponding street lamp shade and street lamp pole; the detection feature information corresponding to the same street lamp at different times is different; the light beam detection image is the image of the light beam emitted by the street lamp at maximum output power; the three-dimensional space model of the lampshade and street lamp pole is generated by the processor program after the sensor obtains the spatial data of the lampshade and the street lamp pole.

[0012] According to the above scheme, in S2, each street lamp detection feature information corresponds to a street lamp quality assessment report; the street lamp quality assessment report includes the image average grayscale difference and color feature deviation rate of the light beam detection image and the solar panel detection image, and the street lamp quality assessment report also includes the flatness difference value of the lampshade three-dimensional space model and the street lamp pole three-dimensional space model;

[0013] The beam detection images of street lamps at various positions and the solar panel detection images have corresponding initial comparison images; the lampshade three-dimensional space model of street lamps at various positions and the three-dimensional space model of street lamp poles have corresponding initial comparison models; the initial comparison images and initial comparison models are images and three-dimensional space models collected when the street lamps are installed;

[0014] The image average grayscale difference represents the ratio of the average grayscale values ​​corresponding to the pixel points of the detection image and the initial comparison image after the detection image of the corresponding street lamp and the initial comparison image are grayed;

[0015] The specific calculation method of the color feature deviation rate CFD is as follows:

[0016] CFD=(P max -P min )÷P 0 均 ;

[0017] Among them, P max represents the maximum gray value corresponding to the pixel after the detection image of the corresponding street lamp is grayed; P min represents the maximum gray value corresponding to the pixel after the detection image of the corresponding street lamp is grayed; P 0 均Represents the average value of the grayscale value corresponding to the pixel point after the initial contrast image of the corresponding street lamp is grayed;

[0018] The specific calculation method of the flatness difference value FDV is as follows:

[0019] FDV=(DA max -DA min )÷A 总 ;

[0020] Among them, DA max The DA represents the maximum deformation area of ​​the corresponding street lamp shade three-dimensional space model or street lamp pole three-dimensional space model compared with the corresponding initial comparison model; min A represents the minimum deformation area of ​​the corresponding lampshade three-dimensional space model of the street lamp or the three-dimensional space model of the street lamp pole compared with the corresponding initial comparison model; 总 represents the total surface area of ​​the corresponding lampshade three-dimensional space model or the lamp pole three-dimensional space model; the DA max DA min and A 总 A street lamp quality assessment report belonging to the same street lamp;

[0021] Different weights are set for the light beam detection image of the street lamp and the solar panel detection image, and the total image average grayscale difference and the total color feature deviation rate of the street lamp are calculated. Different weights are set for the three-dimensional spatial model of the lampshade and the three-dimensional spatial model of the street lamp pole, and the total flatness difference value of the street lamp is calculated.

[0022] The quantification of specific evaluation items in the street light quality evaluation report is achieved based on the three dimensions of total image average grayscale difference, total color feature deviation rate and total flatness difference value, which facilitates the subsequent analysis of the overall status of the street lights and provides data support for subsequent analysis and calculation.

[0023] According to the above scheme, in S3, the corresponding street lamp damage impact assessment value EV is calculated according to the street lamp quality assessment report; the specific calculation formula is as follows:

[0024] EV=F1×ZAGD+F2×ZCFD+F3×ZFDV;

[0025] Among them, F1, F2 and F3 are different damage impact assessment coefficients, and F1, F2 and F3 are constants preset in the database; ZAGD represents the total image average grayscale difference in the corresponding street light quality assessment report; ZCFD represents the total color feature deviation rate in the corresponding street light quality assessment report; ZFDV represents the total flatness difference value in the corresponding street light quality assessment report;

[0026] Obtain the average of the street light damage impact assessment values ​​corresponding to the corresponding street light quality assessment reports when maintenance situations occurred in the same street in the historical data, and record it as the median value of the street damage impact assessment; select the median value of the street damage impact assessment of the street with the most maintenance situations in the test area in the historical data and record it as the reference value of the street damage impact assessment;

[0027] Calculate an assessment impact coefficient for each street in the area to be tested, where the assessment impact coefficient is equal to the ratio of a street damage impact assessment reference value to a street damage impact assessment median value of the corresponding street;

[0028] In real life, the street lamps in the test area are not of uniform specifications, but the same specifications are generally used in the same street. There are certain differences in the service life and failure rate of street lamps of different specifications. The street lamps on the same street are selected to calculate the median value of the street damage impact assessment, and the street with the most maintenance situations in the test area is selected to calculate the reference value of the street damage impact assessment; calculating the assessment impact coefficient for each street in the test area can improve the accuracy of the risk characteristic value calculation and better find street lamps with failure risks.

[0029] Calculating a risk characteristic value of a street lamp, wherein the risk characteristic value is equal to the product of a street lamp damage impact assessment value corresponding to a corresponding street lamp quality assessment report and an assessment impact coefficient of a street to which the street lamp belongs corresponding to the corresponding street lamp quality assessment report;

[0030] If the risk characteristic value is less than the set risk characteristic value threshold, the street lamp to which the risk characteristic value belongs is determined to be a street lamp with no fault risk; otherwise, the street lamp to which the risk characteristic value belongs is determined to be a street lamp with fault risk.

[0031] According to the above scheme, in S4, for the fault risk street lamp, the inspection route plan of the maintenance personnel in the test area is obtained, the influence radius is set for the fault risk street lamp, and the influence circle of the fault risk street lamp is made with the position coordinates of the fault risk street lamp as the center of the circle, and the fault street lamps on the edge and inside the influence circle of the fault risk street lamp and on the inspection route plan are obtained, and the position coordinates of the fault street lamps on the same inspection route plan are formed into a set (x, y) = {(x1, y1), (x2, y2), ..., (x n ,y n )}; where n represents the total number of faulty street lamps in the faulty street lamp position coordinate set, and the position coordinates of the faulty risk street lamps are marked as (A, B);

[0032] Combine the coordinate set of the faulty street lamp position and the coordinates of the faulty risk street lamp position to calculate the inspection route impact value S; the specific calculation method is as follows:

[0033]

[0034] Where (x i ,y i ) and (x i+1 ,y i+1 ), are two consecutive faulty street lamp position coordinates in the faulty street lamp position coordinate set, i∈[1,n-1]; if there is only one inspection route plan in the faulty risk street lamp influence circle generated by the influence radius preset by the system, then the influence radius is expanded until there are at least two inspection route plans in the faulty risk street lamp influence circle; and each inspection route plan has at least two faulty street lamps in the faulty risk street lamp influence circle with the expanded influence radius;

[0035] Combined with the inspection route impact value, the fault risk reference value RFI is calculated for the updated inspection route plan; the specific calculation formula is as follows:

[0036] RFI=R1×(QD÷ZC+R2×HD÷ZC)×S;

[0037] Among them, R1 and R2 represent the preset fault risk reference coefficients; QD represents the inspection route length from the first fault street lamp position in the fault street lamp position coordinate set to the location of the maintenance personnel in the corresponding original inspection route plan; HD represents the inspection route length from the last fault street lamp position in the fault street lamp position coordinate set to the end point of the inspection route plan, the heating fault street lamp position; ZC represents the total inspection route length of the original inspection route plan;

[0038] By analyzing the fault risk reference values ​​corresponding to the updated inspection route plans, the best inspection plan can be accurately screened to reduce the impact on the original inspection route plan due to the need to add new fault risk street lights. While ensuring the inspection accuracy, the efficiency of street light inspection and maintenance can be improved, the fault risks of street lights can be discovered in a timely and effective manner, and corresponding maintenance measures can be taken in a timely manner to avoid street light damage.

[0039] The updated inspection route plan with the smallest fault risk reference value is selected as the optimal inspection plan, and the optimal inspection plan is sent to the maintenance personnel; the maintenance personnel are the maintenance personnel before the optimal inspection plan is updated; the optimal inspection plan includes the location coordinates of the fault risk street lamps and the product specification information corresponding to the fault risk street lamps.

[0040] Another aspect of the present application is a cloud computing-based intelligent street lamp intelligent supervision system, the system is applied to the above-mentioned cloud computing-based intelligent street lamp intelligent supervision method, the system includes a data management unit, a street lamp data acquisition module, a quality assessment and analysis module, a fault risk generation module and an inspection route update module;

[0041] The data management unit is used to store the location distribution of street lamps, product specification information corresponding to the street lamps, and data generated by system operation;

[0042] The street lamp data acquisition module is used to obtain the location distribution of street lamps in the test area and the product specification information corresponding to each street lamp, detect the street lamps in the test area through sensors, and generate street lamp detection feature information at each position in the test area;

[0043] The quality assessment and analysis module is used to perform image recognition on the street lamp detection feature information at each position in the test area through image recognition technology, analyze the street lamp detection feature information after image recognition, and obtain a corresponding street lamp quality assessment report;

[0044] The fault risk generation module is used to generate a fault risk street lamp based on the real-time street lamp quality assessment report of the street lamp, combined with the street lamp quality assessment report of the faulty street lamp when the maintenance situation occurs in the historical data;

[0045] The inspection route update module is used to obtain the inspection route plan of the maintenance personnel in the test area, add the newly generated fault risk street lights to the original inspection route plan, calculate the fault risk reference value for the updated inspection route plan, select the updated inspection route plan with the smallest fault risk reference value as the best inspection plan, and send the best inspection plan to the maintenance personnel.

[0046] According to the above solution, the street light data acquisition module includes a basic information acquisition unit and a detection feature acquisition unit;

[0047] The basic information acquisition unit is used to obtain the location distribution of street lamps in the area to be tested and the product specification information corresponding to each street lamp;

[0048] The detection feature acquisition unit is used to detect the street lights in the area to be detected by using sensors, and generate street light detection feature information at various positions in the area to be detected.

[0049] According to the above solution, the fault risk generation module includes a street lamp damage impact analysis unit and a risk feature analysis unit;

[0050] The street lamp damage impact analysis unit is used to calculate the corresponding street lamp damage impact assessment value according to the street lamp quality assessment report;

[0051] The risk characteristic analysis unit is used to calculate the risk characteristic value of the street lamp based on the street lamp damage impact assessment value corresponding to the real-time street lamp quality assessment report of the street lamp, combined with the street lamp damage impact assessment value corresponding to the corresponding street lamp quality assessment report when maintenance occurs, to determine the generation of a fault risk street lamp.

[0052] According to the above scheme, the inspection route update module includes an inspection route impact value analysis unit and a fault risk reference analysis unit;

[0053] The inspection route impact value analysis unit is used to analyze the impact degree of the inspection route on the pre-added inspection route scheme according to the position coordinates of the fault risk street lamp;

[0054] The fault risk reference analysis unit is used to analyze and calculate the fault risk reference value of the updated inspection route plan in combination with the inspection route impact value, select the updated inspection route plan with the smallest fault risk reference value as the optimal inspection plan, and send the optimal inspection plan to the maintenance personnel.

[0055] Compared with the prior art, the beneficial effects achieved by the present invention are as follows: the quantification of specific evaluation items in the street lamp quality evaluation report is realized according to the three dimensions of the total image average grayscale difference, the total color feature deviation rate and the total flatness difference value, which is convenient for the subsequent analysis of the overall status of the street lamps and provides data support for the subsequent analysis and calculation; the street lamps in the area to be tested are not of uniform specifications, but the same specifications of street lamps are generally used in the same street. There are certain differences in the service life and failure rate of street lamps of different specifications. The street lamps on the same street are selected to calculate the median value of the street damage impact assessment, and the maintenance situation in the area to be tested is selected. The reference value of street damage impact assessment is calculated for the street with the most visits. The impact coefficient is calculated for each street in the tested area, which can improve the accuracy of risk characteristic value calculation and better find street lamps with failure risks. By analyzing the failure risk reference value corresponding to the updated inspection route plan, the best inspection plan can be accurately screened to reduce the impact on the original inspection route plan due to the need to add new failure risk street lamps. While ensuring the inspection accuracy, the efficiency of street lamp inspection and maintenance is improved, the failure risk of street lamps is discovered in a timely and effective manner, and corresponding maintenance measures are taken in a timely manner, thereby avoiding the occurrence of street lamp damage. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0057] Figure 1 It is a flow chart of a smart street lamp intelligent supervision method based on cloud computing of the present invention;

[0058] Figure 2 It is a structural schematic diagram of a cloud computing-based intelligent street lamp intelligent supervision system of the present invention. DETAILED DESCRIPTION

[0059] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. 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.

[0060] See also Figure 1 The present invention provides a technical solution: a cloud computing-based intelligent street lamp intelligent supervision method, the method comprising the following steps:

[0061] S1: Obtain the location distribution of street lamps in the area to be tested and the product specification information corresponding to each street lamp, detect the street lamps in the area to be tested through sensors, and generate street lamp detection feature information at each position in the area to be tested;

[0062] When generating the street lamp detection feature data at various positions in the test area in S1, the detection feature information includes the detection image of the corresponding street lamp light beam and solar panel; the detection feature information also includes the three-dimensional space model of the corresponding street lamp shade and street lamp pole; the detection feature information corresponding to the same street lamp at different times is different; the light beam detection image is the image of the light beam emitted by the street lamp at maximum output power; the three-dimensional space model of the lamp shade and street lamp pole is generated by the processor program after the sensor obtains the spatial data of the lamp shade and the street lamp pole.

[0063] S2: Perform image recognition on the street lamp detection feature information at each location in the test area through image recognition technology, analyze the street lamp detection feature information after image recognition, and obtain a corresponding street lamp quality assessment report;

[0064] In S2, each street light detection feature information corresponds to a street light quality assessment report; the street light quality assessment report includes the image average grayscale difference and color feature deviation rate of the light beam detection image and the solar panel detection image, and the street light quality assessment report also includes the flatness difference value of the lampshade three-dimensional space model and the street light pole three-dimensional space model;

[0065] The beam detection images of street lamps at various locations and the solar panel detection images have corresponding initial comparison images; the three-dimensional space models of lampshades of street lamps at various locations and the three-dimensional space models of street lamp poles have corresponding initial comparison models; the initial comparison images and initial comparison models are images and three-dimensional space models collected when the street lamps are installed;

[0066] The image average grayscale difference represents the ratio of the average grayscale values ​​corresponding to the pixel points of the detection image and the initial comparison image after the detection image of the corresponding street lamp and the initial comparison image are grayed;

[0067] The specific calculation method of color feature deviation rate CFD is as follows:

[0068] CFD=(P max -P min )÷P 0 均 ;

[0069] Among them, P max represents the maximum gray value corresponding to the pixel after the detection image of the corresponding street lamp is grayed; P min represents the maximum gray value corresponding to the pixel after the detection image of the corresponding street lamp is grayed; P 0 均 Represents the average value of the grayscale value corresponding to the pixel point after the initial contrast image of the corresponding street lamp is grayed;

[0070] The specific calculation method of the flatness difference value FDV is as follows:

[0071] FDV=(DA max -DA min )÷A 总 ;

[0072] Among them, DA max The DA represents the maximum deformation area of ​​the corresponding street lamp shade three-dimensional space model or street lamp pole three-dimensional space model compared with the corresponding initial comparison model; min A represents the minimum deformation area of ​​the corresponding lampshade three-dimensional space model of the street lamp or the three-dimensional space model of the street lamp pole compared with the corresponding initial comparison model; 总 Represents the total surface area of ​​the corresponding lampshade three-dimensional space model or the lamp pole three-dimensional space model; DA max DA min and A 总 A street lamp quality assessment report belonging to the same street lamp;

[0073] Different weights are set for the light beam detection image of the street lamp and the solar panel detection image, and the total image average grayscale difference and the total color feature deviation rate of the street lamp are calculated. Different weights are set for the three-dimensional spatial model of the lampshade and the three-dimensional spatial model of the street lamp pole, and the total flatness difference value of the street lamp is calculated.

[0074] S3: Generate a street lamp with a risk of failure based on the real-time street lamp quality assessment report of the street lamp and the street lamp quality assessment report of the faulty street lamp when the maintenance situation occurs in the historical data;

[0075] In S3, according to the street light quality assessment report, the corresponding street light damage impact assessment value EV is calculated; the specific calculation formula is as follows:

[0076] EV=F1×ZAGD+F2×ZCFD+F3×ZFDV;

[0077] Among them, F1, F2 and F3 are different damage impact assessment coefficients, and F1, F2 and F3 are constants preset in the database; ZAGD represents the total image average grayscale difference in the corresponding street light quality assessment report; ZCFD represents the total color feature deviation rate in the corresponding street light quality assessment report; ZFDV represents the total flatness difference value in the corresponding street light quality assessment report;

[0078] Obtain the average of the street light damage impact assessment values ​​corresponding to the corresponding street light quality assessment reports when maintenance situations occurred in the same street in the historical data, and record it as the median value of the street damage impact assessment; select the median value of the street damage impact assessment of the street with the most maintenance situations in the test area in the historical data and record it as the reference value of the street damage impact assessment;

[0079] An assessment impact coefficient is calculated for each street in the area to be tested, and the assessment impact coefficient is equal to the ratio of the street damage impact assessment reference value to the street damage impact assessment median value of the corresponding street;

[0080] Calculate the risk characteristic value of the street lamp, which is equal to the product of the street lamp damage impact assessment value corresponding to the corresponding street lamp quality assessment report and the assessment impact coefficient of the street to which the street lamp belongs corresponding to the corresponding street lamp quality assessment report;

[0081] If the risk characteristic value is less than the set risk characteristic value threshold, the street lamp to which the risk characteristic value belongs is determined to be a street lamp with no fault risk; otherwise, the street lamp to which the risk characteristic value belongs is determined to be a street lamp with fault risk.

[0082] S4: Obtain the inspection route plan of the maintenance personnel in the test area, add the newly generated fault risk street lights to the original inspection route plan, calculate the fault risk reference value for the updated inspection route plan, select the updated inspection route plan with the smallest fault risk reference value as the best inspection plan, and send the best inspection plan to the maintenance personnel.

[0083] In S4, for the fault risk street lamp, the inspection route plan of the maintenance personnel in the test area is obtained, the influence radius is set for the fault risk street lamp, and the influence circle of the fault risk street lamp is made with the position coordinates of the fault risk street lamp as the center of the circle, and the fault street lamps on the edge and inside the influence circle of the fault risk street lamp and on the inspection route plan are obtained, and the position coordinates of the fault street lamps on the same inspection route plan are formed into a set (x, y) = {(x1, y1), (x2, y2), ..., (x n ,y n )}; where n represents the total number of faulty street lamps in the faulty street lamp position coordinate set, and the position coordinates of the faulty risk street lamps are marked as (A, B);

[0084] Combine the coordinate set of the faulty street lamp position and the coordinates of the faulty risk street lamp position to calculate the inspection route impact value S; the specific calculation method is as follows:

[0085]

[0086] Where (x i ,y i ) and (x i+1 ,y i+1 ), are two consecutive faulty street lamp position coordinates in the faulty street lamp position coordinate set, i∈[1,n-1]; if there is only one inspection route plan in the faulty risk street lamp influence circle generated by the influence radius preset by the system, then the influence radius is expanded until there are at least two inspection route plans in the faulty risk street lamp influence circle; and each inspection route plan has at least two faulty street lamps in the faulty risk street lamp influence circle with the expanded influence radius;

[0087] Embodiment 1: In this embodiment, the position coordinates of the fault risk street lamp are marked as (0, 0), and the system preset influence radius is equal to 1, then the function corresponding to the influence circle of the fault risk street lamp is y=(x-1) 2 ; The inspection route function corresponding to the inspection route plan 1 is y=x-1; there are two coordinates (1, 0) and (0, -1) of the faulty street lamps in the inspection route plan 1, both of which are on the function corresponding to the influence circle of the faulty risk street lamp;

[0088] The inspection route function corresponding to inspection route plan 2 is: There is only one coordinate of a faulty street light in inspection route plan 2 On the function corresponding to the influence circle of the fault risk street lamp, the coordinates of the fault street lamp that is second closest to the position coordinates of the fault risk street lamp in inspection route plan 2 are: The influence radius needs to be expanded to That is, after expanding the influence radius, the function corresponding to the influence circle of the fault risk street lamp is:

[0089] Combined with the inspection route impact value, the fault risk reference value RFI is calculated for the updated inspection route plan; the specific calculation formula is as follows:

[0090] RFI=R1×(QD÷ZC+R2×HD÷ZC)×S;

[0091] Among them, R1 and R2 represent the preset fault risk reference coefficients; QD represents the inspection route length from the first fault street lamp position in the fault street lamp position coordinate set to the location of the maintenance personnel in the corresponding original inspection route plan; HD represents the inspection route length from the last fault street lamp position in the fault street lamp position coordinate set to the end point of the inspection route plan, the heating fault street lamp position; ZC represents the total inspection route length of the original inspection route plan;

[0092] The updated inspection route plan with the smallest fault risk reference value is selected as the best inspection plan, and the best inspection plan is sent to the maintenance personnel; the maintenance personnel are the maintenance personnel before the best inspection plan is updated; the best inspection plan includes the location coordinates of the fault risk street lamps and the product specification information corresponding to the fault risk street lamps.

[0093] See also Figure 2 , the present invention provides a technical solution: a cloud computing-based intelligent street lamp intelligent supervision system, the system includes a data management unit, a street lamp data acquisition module, a quality assessment and analysis module, a fault risk generation module and an inspection route update module;

[0094] The data management unit is used to store the location distribution of street lamps, product specification information corresponding to the street lamps, and data generated by system operation;

[0095] The street lamp data acquisition module is used to obtain the location distribution of street lamps in the test area and the product specification information corresponding to each street lamp, detect the street lamps in the test area through sensors, and generate street lamp detection feature information at each position in the test area;

[0096] The quality assessment and analysis module is used to perform image recognition on the street lamp detection feature information at each location in the test area through image recognition technology, analyze the street lamp detection feature information after image recognition, and obtain a corresponding street lamp quality assessment report;

[0097] The fault risk generation module is used to generate fault risk street lamps based on the real-time street lamp quality assessment report of the street lamps and the street lamp quality assessment report of the faulty street lamps when maintenance occurs in the historical data;

[0098] The inspection route update module is used to obtain the inspection route plan of the maintenance personnel in the tested area, add the newly generated fault risk street lights to the original inspection route plan, calculate the fault risk reference value for the updated inspection route plan, select the updated inspection route plan with the smallest fault risk reference value as the best inspection plan, and send the best inspection plan to the maintenance personnel.

[0099] The street light data acquisition module includes a basic information acquisition unit and a detection feature acquisition unit;

[0100] The basic information acquisition unit is used to obtain the location distribution of street lamps in the area to be tested and the product specification information corresponding to each street lamp;

[0101] The detection feature acquisition unit is used to detect the street lights in the area to be detected by using sensors, and generate street light detection feature information at various positions in the area to be detected.

[0102] The fault risk generation module includes a street lamp damage impact analysis unit and a risk feature analysis unit;

[0103] The street lamp damage impact analysis unit is used to calculate the corresponding street lamp damage impact assessment value according to the street lamp quality assessment report;

[0104] The risk characteristic analysis unit is used to calculate the risk characteristic value of the street lamp based on the street lamp damage impact assessment value corresponding to the real-time street lamp quality assessment report of the street lamp, combined with the street lamp damage impact assessment value corresponding to the corresponding street lamp quality assessment report when maintenance occurs, to determine the generation of fault risk street lamps.

[0105] The inspection route update module includes an inspection route impact value analysis unit and a fault risk reference analysis unit;

[0106] The inspection route impact value analysis unit is used to analyze the impact degree of the inspection route on the pre-added inspection route plan according to the position coordinates of the fault risk street lamp;

[0107] The fault risk reference analysis unit is used to analyze and calculate the fault risk reference value of the updated inspection route plan in combination with the inspection route impact value, select the updated inspection route plan with the smallest fault risk reference value as the best inspection plan, and send the best inspection plan to the maintenance personnel.

[0108] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0109] Finally, it should be noted that the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art can still modify the technical solutions described in the aforementioned embodiments or replace some of the technical features therein by equivalents. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A cloud computing-based intelligent street lamp intelligent supervision method, characterized in that: The method comprises the following steps: S1: Obtain the location distribution of street lamps in the area to be tested and the product specification information corresponding to each street lamp, detect the street lamps in the area to be tested through sensors, and generate street lamp detection feature information at each position in the area to be tested; S2: Perform image recognition on the street lamp detection feature information at each location in the test area through image recognition technology, analyze the street lamp detection feature information after image recognition, and obtain a corresponding street lamp quality assessment report; S3: Generate a street lamp with a risk of failure based on the real-time street lamp quality assessment report of the street lamp and the street lamp quality assessment report of the faulty street lamp when the maintenance situation occurs in the historical data; S4: Obtain the inspection route plan of the maintenance personnel in the test area, add the newly generated fault risk street lights to the original inspection route plan, calculate the fault risk reference value for the updated inspection route plan, select the updated inspection route plan with the smallest fault risk reference value as the best inspection plan, and send the best inspection plan to the maintenance personnel.

2. According to the cloud computing-based intelligent street lamp intelligent supervision method of claim 1, it is characterized by: When generating the street lamp detection feature data of each position in the test area in S1, the detection feature information includes the detection image of the light beam and solar panel corresponding to the street lamp; the detection feature information also includes the three-dimensional space model of the lampshade and the lamp pole corresponding to the street lamp; the detection feature information corresponding to the same street lamp at different times is different; the light beam detection image is the image of the light beam emitted by the street lamp at maximum output power; the three-dimensional space model of the lampshade and the lamp pole is generated by the processor program after the sensor obtains the spatial data of the lampshade and the lamp pole.

3. According to the cloud computing-based intelligent street lamp intelligent supervision method of claim 2, it is characterized by: In S2, each street lamp detection feature information corresponds to a street lamp quality assessment report; the street lamp quality assessment report includes the image average grayscale difference and color feature deviation rate of the light beam detection image and the solar panel detection image, and the street lamp quality assessment report also includes the flatness difference value of the lampshade three-dimensional space model and the street lamp pole three-dimensional space model; The beam detection images of street lamps at various positions and the solar panel detection images have corresponding initial comparison images; the lampshade three-dimensional space model of street lamps at various positions and the three-dimensional space model of street lamp poles have corresponding initial comparison models; the initial comparison images and initial comparison models are images and three-dimensional space models collected when the street lamps are installed; The image average grayscale difference represents the ratio of the average grayscale values ​​corresponding to the pixel points of the detection image and the initial comparison image after the detection image of the corresponding street lamp and the initial comparison image are grayed; The specific calculation method of the color feature deviation rate CFD is as follows: CFD=(P max -P min )÷P 0 均 ; Among them, P max represents the maximum gray value corresponding to the pixel after the detection image of the corresponding street lamp is grayed; P min represents the maximum gray value corresponding to the pixel after the detection image of the corresponding street lamp is grayed; P 0 均 Represents the average value of the grayscale value corresponding to the pixel point after the initial contrast image of the corresponding street lamp is grayed; The specific calculation method of the flatness difference value FDV is as follows: FDV=(YES max -YES min )÷A 总 ; Among them, DA max The DA represents the maximum deformation area of ​​the corresponding street lamp shade three-dimensional space model or street lamp pole three-dimensional space model compared with the corresponding initial comparison model; min A represents the minimum deformation area of ​​the corresponding lampshade three-dimensional space model of the street lamp or the three-dimensional space model of the street lamp pole compared with the corresponding initial comparison model; 总 represents the total surface area of ​​the corresponding lampshade three-dimensional space model or the lamp pole three-dimensional space model; the DA max DA min and A 总 A street lamp quality assessment report belonging to the same street lamp; Different weights are set for the light beam detection image of the street lamp and the solar panel detection image, and the total image average grayscale difference and the total color feature deviation rate of the street lamp are calculated. Different weights are set for the three-dimensional spatial model of the lampshade and the three-dimensional spatial model of the street lamp pole, and the total flatness difference value of the street lamp is calculated.

4. According to the cloud computing-based intelligent street lamp intelligent supervision method of claim 3, it is characterized by: In S3, according to the street light quality assessment report, the corresponding street light damage impact assessment value EV is calculated; the specific calculation formula is as follows: EV=F1×ZAGD+F2×ZCFD+F3×ZFDV; Among them, F1, F2 and F3 are different damage impact assessment coefficients, and F1, F2 and F3 are constants preset in the database; ZAGD represents the total image average grayscale difference in the corresponding street light quality assessment report; ZCFD represents the total color feature deviation rate in the corresponding street light quality assessment report; ZFDV represents the total flatness difference value in the corresponding street light quality assessment report; Obtain the average of the street light damage impact assessment values ​​corresponding to the corresponding street light quality assessment reports when maintenance situations occurred in the same street in the historical data, and record it as the median value of the street damage impact assessment; select the median value of the street damage impact assessment of the street with the most maintenance situations in the test area in the historical data and record it as the reference value of the street damage impact assessment; Calculate an assessment impact coefficient for each street in the area to be tested, where the assessment impact coefficient is equal to the ratio of a street damage impact assessment reference value to a street damage impact assessment median value of the corresponding street; Calculating a risk characteristic value of a street lamp, wherein the risk characteristic value is equal to the product of a street lamp damage impact assessment value corresponding to a corresponding street lamp quality assessment report and an assessment impact coefficient of a street to which the street lamp belongs corresponding to the corresponding street lamp quality assessment report; If the risk characteristic value is less than the set risk characteristic value threshold, the street lamp to which the risk characteristic value belongs is determined to be a street lamp without fault risk; Otherwise, it is determined that the street lamp to which the risk characteristic value belongs is a fault risk street lamp.

5. According to claim 4, a cloud computing-based intelligent street lamp intelligent supervision method is characterized in that: In S4, for the fault risk street lamp, the inspection route plan of the maintenance personnel in the test area is obtained, the influence radius is set for the fault risk street lamp, and the influence circle of the fault risk street lamp is made with the position coordinates of the fault risk street lamp as the center of the circle, and the fault street lamps on the edge and inside the influence circle of the fault risk street lamp and on the inspection route plan are obtained, and the position coordinates of the fault street lamps on the same inspection route plan are formed into a set (x, y) = {(x1, y1), (x2, y2), ..., (x n ,y n )}; where n represents the total number of faulty street lamps in the faulty street lamp position coordinate set, and the position coordinates of the faulty risk street lamps are marked as (A, B); Combine the coordinate set of the faulty street lamp position and the coordinates of the faulty risk street lamp position to calculate the inspection route impact value S; The specific calculation method is as follows: Where (x i ,y i ) and (x i+1 ,y i+1 ), are two consecutive faulty street lamp position coordinates in the faulty street lamp position coordinate set, i∈[1,n-1]; If there is only one inspection route plan in the influence circle of the fault risk street lamp generated by the influence radius preset by the system, the influence radius is expanded until there are at least two inspection route plans in the influence circle of the fault risk street lamp; And each inspection route plan has at least two faulty street lamps in the fault risk street lamp influence circle with an expanded influence radius; Combined with the inspection route impact value, the fault risk reference value RFI is calculated for the updated inspection route plan; the specific calculation formula is as follows: RFI=R1×(QD÷ZC+R2×HD÷ZC)×S; Among them, R1 and R2 represent the preset fault risk reference coefficients; QD represents the inspection route length from the first fault street lamp position in the fault street lamp position coordinate set to the location of the maintenance personnel in the corresponding original inspection route plan; HD represents the inspection route length from the last fault street lamp position in the fault street lamp position coordinate set to the end point of the inspection route plan, the heating fault street lamp position; ZC represents the total inspection route length of the original inspection route plan; The updated inspection route plan with the smallest fault risk reference value is selected as the optimal inspection plan, and the optimal inspection plan is sent to the maintenance personnel; the maintenance personnel are the maintenance personnel before the optimal inspection plan is updated; the optimal inspection plan includes the location coordinates of the fault risk street lamps and the product specification information corresponding to the fault risk street lamps.

6. A cloud computing-based intelligent street lamp intelligent supervision system, the system is applied to the cloud computing-based intelligent street lamp intelligent supervision method according to any one of claims 1 to 5, characterized in that: The system includes a data management unit, a street light data acquisition module, a quality assessment and analysis module, a fault risk generation module and an inspection route update module; The data management unit is used to store the location distribution of street lamps, product specification information corresponding to the street lamps, and data generated by system operation; The street lamp data acquisition module is used to obtain the location distribution of street lamps in the test area and the product specification information corresponding to each street lamp, detect the street lamps in the test area through sensors, and generate street lamp detection feature information at each position in the test area; The quality assessment and analysis module is used to perform image recognition on the street lamp detection feature information at each position in the test area through image recognition technology, analyze the street lamp detection feature information after image recognition, and obtain a corresponding street lamp quality assessment report; The fault risk generation module is used to generate a fault risk street lamp based on the real-time street lamp quality assessment report of the street lamp, combined with the street lamp quality assessment report of the faulty street lamp when the maintenance situation occurs in the historical data; The inspection route update module is used to obtain the inspection route plan of the maintenance personnel in the test area, add the newly generated fault risk street lights to the original inspection route plan, calculate the fault risk reference value for the updated inspection route plan, select the updated inspection route plan with the smallest fault risk reference value as the best inspection plan, and send the best inspection plan to the maintenance personnel.

7. The cloud computing-based intelligent street lamp monitoring system according to claim 6 is characterized by: The street lamp data acquisition module includes a basic information acquisition unit and a detection feature acquisition unit; The basic information acquisition unit is used to obtain the location distribution of street lamps in the area to be tested and the product specification information corresponding to each street lamp; The detection feature acquisition unit is used to detect the street lights in the area to be detected by using sensors, and generate street light detection feature information at various positions in the area to be detected.

8. The cloud computing-based intelligent street lamp monitoring system according to claim 6 is characterized by: The fault risk generation module includes a street lamp damage impact analysis unit and a risk feature analysis unit; The street lamp damage impact analysis unit is used to calculate the corresponding street lamp damage impact assessment value according to the street lamp quality assessment report; The risk characteristic analysis unit is used to calculate the risk characteristic value of the street lamp based on the street lamp damage impact assessment value corresponding to the real-time street lamp quality assessment report of the street lamp, combined with the street lamp damage impact assessment value corresponding to the corresponding street lamp quality assessment report when maintenance occurs, to determine the generation of a fault risk street lamp.

9. The cloud computing-based intelligent street lamp monitoring system according to claim 6 is characterized by: The inspection route update module includes an inspection route impact value analysis unit and a fault risk reference analysis unit; The inspection route impact value analysis unit is used to analyze the impact degree of the inspection route on the pre-added inspection route scheme according to the position coordinates of the fault risk street lamp; The fault risk reference analysis unit is used to analyze and calculate the fault risk reference value of the updated inspection route plan in combination with the inspection route impact value, select the updated inspection route plan with the smallest fault risk reference value as the optimal inspection plan, and send the optimal inspection plan to the maintenance personnel.

Images