Photovoltaic power station fire hazard identification method based on AI

Through AI-based methods, using cable and environmental data to calculate the fire risk coefficient, the problem of insufficient prospective identification of fire hazards in photovoltaic power stations is solved, and faster identification and treatment of fire hazards is achieved.

CN119066296AActive Publication Date: 2024-12-03ANHUI STATE POWER INVESTMENT & NEW POWER TECH RES CO LTD
View PDF 3 Cites 0 Cited by

Patent Information

Application Number
CN202411119866.4
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-15
Publication Date
2024-12-03
Estimated Expiration
2044-08-15

AI Technical Summary

Technical Problem

The existing photovoltaic power station fire hazard identification method is not allowed to identify fire hazards and deal with fires in the absence of people or few people, resulting in poor prospective fires and difficult for operation and maintenance personnel to deal with them in a timely manner.

Method used

Using an AI-based method, by obtaining data on cable specification parameters, infrared images, ambient humidity, ambient temperature, failure times, current carrying capacity, laying method and usage time, the average temperature and total aging of the cable insulation layer are calculated, and the average temperature and total aging amount of the cable insulation layer are constructed. Influencing factor matrix, calculate the risk coefficient, and determine whether there are fire hazards.

Benefits of technology

A more forward-looking fire hazard identification has been achieved, and operation and maintenance personnel can have sufficient time to deal with fire hazards, reducing the fire risk during the operation of photovoltaic power stations.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119066296A_ABST
    Figure CN119066296A_ABST
Patent Text Reader

Abstract

The invention relates to the field of fire hazard identification, in particular to an AI-based photovoltaic power station fire hazard identification method. First data are formed by acquiring various parameters of the cable when the cable works in the photovoltaic power station, the average temperature of the insulating layer is calculated, the aging degree of the cable is estimated according to the first data and serves as one of the influence factors of fire disasters of the cable in the photovoltaic power station, and then the aging degree of the cable is estimated according to various influence factors of possible fire disasters when the cable works. And further forming an influence degree matrix, calculating a fire hazard according to the collected actual parameters of each influence factor, and judging whether the cable has the fire hazard according to a risk threshold so as to obtain information about whether the cable has the fire hazard in a more prospective manner. Operation and maintenance personnel can have more sufficient time to take measures on cables with fire hazards; the problems that an existing mode is relatively poor in perspectiveness when fire hazards are recognized, and operation and maintenance personnel are difficult to have sufficient time to deal with the fire hazards are solved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of fire hazard identification, and specifically to an AI-based method for identifying fire hazards in photovoltaic power stations. Background Art

[0002] At present, fire warning for photovoltaic power stations is usually carried out through multiple sensors combined with images for identification. For example, in the early stage of a fire, the gas produced by high temperature melting the internal materials of the cable can be detected to identify fire hazards by detecting the gas composition. Fire hazards can also be identified by image recognition of the smoke that appears before the cable fire. Cable temperature is monitored by infrared temperature measurement, and a notification of fire hazards is issued when the cable temperature is abnormal.

[0003] However, for the current unmanned or sparsely staffed photovoltaic power stations, when this type of method is used to identify fire hazards, it may take several hours from the identification of the fire hazard to the handling by operation and maintenance personnel. During this time, the cables may have burned, which will have a great impact on the normal operation of the photovoltaic power station. Therefore, the above-mentioned existing methods are relatively poor in foresight when identifying fire hazards, and it is difficult for operation and maintenance personnel to have sufficient time to deal with fire hazards. Summary of the invention

[0004] In view of the shortcomings of the prior art, the present invention provides an AI-based method for identifying fire hazards in photovoltaic power stations, which solves the problem that the prior method has relatively poor foresight in identifying fire hazards and operation and maintenance personnel have difficulty in having sufficient time to deal with fire hazards.

[0005] To achieve the above object, the present invention provides the following technical solutions:

[0006] A method for identifying fire hazards in photovoltaic power plants based on AI, the method comprising the following steps:

[0007] S1. Acquire first data including cable specification parameters, infrared images, ambient humidity, ambient temperature, number of failures, current carrying capacity, laying method and usage time;

[0008] S2. Calculate the average temperature of the cable insulation layer according to the first data;

[0009] S3, calculating the total aging amount of the cable according to the average temperature of the insulation layer of the cable at any time and the first data, setting a number of aging levels corresponding to different aging total amounts, and determining the aging level of the cable;

[0010] S4. Constructing an influence matrix of each influencing factor on the fire hazard of cables according to the first data and the aging level;

[0011] S5. Calculate the risk factor of the cable according to the influence matrix;

[0012] S6. Based on whether the risk factor is greater than the risk threshold, output prompt information on whether there is a fire hazard in the cable;

[0013] If so, a prompt message is output indicating that the cable has a fire hazard;

[0014] If not, then end.

[0015] Preferably, in step S21, the following steps are specifically included:

[0016] S21. Calculate the first heat generated by the cable core at any cross section; the calculation formula for the first heat is:

[0017]

[0018] In the above formula, Q 0 represents the first heat, I represents the current in the cable, R represents the resistance of the cable, and the cable length corresponding to the resistance is L;

[0019] S22, calculating the cross-sectional temperature at any position on any cross-sectional area in the cable according to the first heat;

[0020] S23. Calculate the average temperature of the insulation layer on any cross section in the cable according to the cross section temperature at any position on any cross section in the cable.

[0021] Preferably, in step S23, the following steps are specifically included:

[0022] S231. Calculate the coordinates of the center of any cross section in the cable according to the point set on the cross section. The expression of the coordinates of the center of the cross section is:

[0023]

[0024] In the above formula, (x 0 ,y 0 , z 0 ) are the x, y and z axis coordinates of the center of the circle, x i and i They represent the x-axis and y-axis coordinates of a point on any cross section in the cable, and the number of points obtained on the cross section is n;

[0025] S232, obtaining the radius range of the insulation layer of the cable;

[0026] S233, constructing a first circle for obtaining the average temperature of the insulation layer according to the radius range of the insulation layer of the cable and the coordinates of the center of the cross section; the expression of the first circle is:

[0027]

[0028] In the above formula, rmin and r max are the minimum and maximum values ​​of the radius range of the cable insulation layer, respectively, and α is the value coefficient;

[0029] S234. Obtain the temperature of any point on the first circle according to the cross-sectional temperature at any position on any cross-sectional area in the cable, as the average temperature of the insulation layer on any cross-sectional area in the cable.

[0030] Preferably, in step S3, the following steps are specifically included:

[0031] S31. Calculate the aging rate of the cable per unit time according to the average temperature of the insulation layer;

[0032] S32. Calculate the aging amount of the cable within a certain period of time according to the aging speed of the cable within a unit time. The calculation formula of the aging amount is:

[0033]

[0034] In the above formula, L represents the aging amount, t represents the usage time of the cable, and V(t) represents the relationship between the aging speed and time;

[0035] S33, obtaining several influencing factors affecting the aging amount of the cable, and calculating the total aging amount of the cable according to the aging amount;

[0036] S34, setting a plurality of aging total amount intervals and aging levels corresponding to the intervals, and determining the aging level of the cable according to the aging total amount interval corresponding to the aging total amount of the cable.

[0037] Preferably, in step S4, the following steps are specifically included:

[0038] S41, setting a number of influencing factors that affect cable fire to obtain an influencing factor set, and selecting any influencing factor from the influencing factor set to set an influence degree matrix, and setting a first weight of the influencing factor in the influence degree matrix, and marking the influencing factor in the influence degree matrix as a first influencing factor;

[0039] S42, selecting any influencing factor from the influencing factor set and marking it as a second influencing factor, setting a second weight corresponding to the second influencing factor, and then marking the second influencing factor as a first influencing factor and adding it to the influence matrix;

[0040] S43, comparing the influence degree of the second influencing factor and the first influencing factor in the influence degree matrix on the cable fire, making the second weight smaller than the first weight of the first influencing factor with a greater influence degree, and making the second weight larger than the first weight of the first influencing factor with a smaller influence degree;

[0041] S44, determining whether the influencing factor set is an empty set;

[0042] If yes, go to the next step;

[0043] If not, return to step S42;

[0044] S45, normalizing the first weight in the influence matrix to obtain the influence matrix; the calculation formula for normalizing the first weight and the second weight is:

[0045]

[0046] In the above formula, Z' i represents the first weight of the normalized first influencing factor of the i-th factor in the influence matrix, Z i It represents the first weight of the i-th first influencing factor before normalization in the influence matrix. The number of first weights in the influence matrix is ​​n.

[0047] Preferably, in step S43, the following steps are specifically included:

[0048] S431, setting a number of impact levels and corresponding impact ratios;

[0049] S432, determining whether there is a first influencing factor in the influence matrix whose first weight is the same as the second weight value of the second influencing factor;

[0050] If so, setting the second weight of the second influencing factor to the first weight of the first influencing factor;

[0051] If not, proceed to step S433;

[0052] S433, determining whether there is a first influencing factor with a smaller influence degree than the second influencing factor in the influence matrix;

[0053] If so, obtain the first influencing factor that is closest to the second influencing factor in terms of its influence and the corresponding first weight, and mark the first influencing factor as the third influencing factor;

[0054] If not, proceed to step S437;

[0055] S434. Calculate the second weight of the second influencing factor according to the third influencing factor and the influencing degree ratio; the calculation formula of the second weight is:

[0056] Z i =τ i,i-1 ·Z i-1

[0057] In the above formula, Z i Indicates the second weight of the second influencing factor, Z i-1is the first weight of the third influencing factor, τ i,i-1 is the influence ratio of the second influencing factor to the third influencing factor;

[0058] S435, determining whether there is a first influencing factor in the influence matrix that has a greater influence than the second influencing factor;

[0059] If so, obtaining the first influencing factor and the corresponding first weight, and marking the first influencing factor as the fourth influencing factor;

[0060] If not, proceed to step S44;

[0061] S436: scaling or expanding the first weight of the fourth influencing factor according to the influence degree ratio; the calculation formula of the scaled or expanded first weight of the fourth influencing factor is:

[0062]

[0063] In the above formula, Z' j represents the first weight of the fourth influencing factor after scaling or expansion, Z i Indicates the second weight of the second influencing factor, Z i represents the first weight of the fourth influencing factor before scaling or enlargement, Z i+1 Indicates the first influencing factor in the influence matrix that has a greater influence than the second influencing factor, and the influence ratio of the first influencing factor to the second influencing factor is the smallest, τ i,i-1 is the influence ratio of the second influencing factor to the third influencing factor;

[0064] S437, determining whether there is a first influencing factor in the influence matrix that has a greater influence than the second influencing factor;

[0065] If so, obtaining the first influencing factor that is closest to the second influencing factor in terms of its influence and the corresponding first weight, and marking the first influencing factor as the fifth influencing factor;

[0066] If not, proceed to step S44;

[0067] S438. Calculate the second weight of the second influencing factor according to the first weight of the fifth influencing factor and the influence ratio between the fifth influencing factor and the second influencing factor. The calculation formula of the first weight is:

[0068]

[0069] In the above formula, Z i Indicates the second weight of the second influencing factor, Z i+1 represents the first weight of the fifth influencing factor, τ i+1,iis the influence ratio of the fifth influencing factor to the second influencing factor.

[0070] Preferably, in step S5, the following steps are specifically included:

[0071] S51, obtaining parameters of influencing factors corresponding to the influence matrix;

[0072] S52. Calculate the risk factor of cable fire according to the parameters of the influencing factors and the influence matrix; the calculation formula of the risk factor is:

[0073]

[0074] In the above formula, F represents the risk factor of cable fire, Z' i represents the first weight of the normalized first influencing factor of the i-th factor in the influence matrix, δ i It represents the parameter corresponding to the i-th influencing factor. There are n influencing factors in total, and the influencing factors correspond one-to-one to the first influencing factor in the influence matrix.

[0075] Preferably, in step S22, the calculation formula of the cross-sectional temperature is:

[0076]

[0077] In the above formula, Q 0 represents the first heat, x and y represent the coordinates of any cross section in the cable, the temperature at that point is T, A is the thermal conductivity of the material in the cable, m 0 It represents the mass per unit area of ​​the material at any cross section in the cable, c represents the specific heat capacity of the material at that location, and t represents the service life of the cable.

[0078] Preferably, in step S31, the calculation formula of the aging speed is:

[0079]

[0080] In the above formula, V represents the aging rate of the cable per unit time, a and b are the first constant and the second constant, respectively, which are related to the activation energy of the insulation material, T 0 represents the average temperature of the insulation layer, T' represents the first temperature, and B represents the basic aging coefficient, which is 1.6089.

[0081] Preferably, in step S34, the calculation formula of the total aging amount is:

[0082] LZ=K 1 ·K 2 ·K 3 ·K 4 ·K 5 ·L·β

[0083] in,

[0084] K 1 =γ n , 1<γ<2

[0085]

[0086] In the above formula, K 1 represents the failure number influencing factor, γ represents the first coefficient, n represents the failure number, K 2 Indicates the influencing factor of the laying method. Its corresponding value varies according to the laying method. K 3 Represents the environmental humidity influence factor, and its different values ​​correspond to different environmental humidity ranges. 4 A represents the service life impact factor, 1 is the second coefficient, A 2 is the third coefficient, t 0 is the service life of the cable, K 5 is the load influencing factor, its value corresponds to the interval of cable load rate, and β is other influencing factors.

[0087] Compared with the prior art, the present invention provides an AI-based method for identifying fire hazards in photovoltaic power plants, which has the following beneficial effects:

[0088] 1. The present invention calculates fire hazards based on the actual parameters of the collected influencing factors, and thus determines whether the cable has fire hazards based on the risk threshold, thereby being able to obtain more forward-looking information on whether the cable has fire hazards, so that operation and maintenance personnel can have more sufficient time to take measures on cables with fire hazards.

[0089] 2. The present invention calculates the temperature at different positions on the internal cross section of the cable according to the material data inside the cable and the load of the fiber core, and thus according to the law of heat transfer, thereby calculating the temperature at various locations on the cross section of the cable, and further calculating the average temperature of the insulation layer, thereby estimating the total aging amount according to the subsequent aging rate and the average temperature of the insulation layer.

[0090] 3. The present invention calculates the average temperature of the cable and the temperature of the position on the cable insulation layer equal to each other during the experiment, thereby being able to directly obtain the temperature of the position on the cable as the average temperature of the insulation layer, thereby reducing the amount of calculation required for calculating the average temperature.

[0091] 4. The present invention obtains various influencing factors that affect the fire hazards of cables in photovoltaic power stations, and quantifies the degree of influence of each influencing factor on the fire hazard through experiments or experience to obtain an influence matrix, so as to calculate the risk coefficient based on the parameters of various influencing factors obtained in real time combined with the influence matrix, and then compare it with the risk threshold to determine whether the cable has a fire hazard. BRIEF DESCRIPTION OF THE DRAWINGS

[0092] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0093] Figure 1 The present invention is a flow chart of a method for identifying fire hazards in a photovoltaic power station. DETAILED DESCRIPTION

[0094] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the present invention is further described in detail below with reference to the accompanying drawings and specific implementation methods, so that the implementation process of how the present application uses technical means to solve technical problems and achieve technical effects can be fully understood and implemented accordingly.

[0095] Those skilled in the art can understand that all or part of the steps in the following embodiments can be completed by instructing the relevant hardware through a program, so the present application can be in the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present application can be in the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0096] In order to solve the problem that the existing methods have relatively poor foresight in identifying fire hazards and the operation and maintenance personnel have difficulty in having sufficient time to deal with fire hazards, the present invention provides an AI-based method for identifying fire hazards in photovoltaic power stations. By acquiring the cable's own parameters and environmental parameters during the working process, the probability of a cable fire is estimated, thereby estimating the size of the cable's fire hazard. The possibility of a cable fire can be understood more forward-lookingly. In a photovoltaic power station with no or few people, the operation and maintenance personnel can have more sufficient time to maintain the cables and eliminate major fire hazard points. The method comprises the following steps:

[0097] S1. Obtain first data including cable specification parameters, infrared images, ambient humidity, ambient temperature, number of faults, current carrying capacity, laying method and usage time. The cable specification parameters include the maximum current carrying capacity, wire diameter, insulation layer diameter range, insulation layer specific heat capacity and other parameters of the cable. The infrared image can be obtained by robot inspection using an infrared camera, or directly using an infrared camera fixed at a certain position to monitor a certain section of cable. The ambient humidity and ambient temperature can be obtained by a temperature and humidity sensor.

[0098] S2. Calculate the average temperature of the cable insulation layer according to the first data; the temperature of the cable insulation layer is mainly affected by the heat generated by the cable core during operation, and the temperature inside the cable gradually decreases from the core to the outside, so the heat generated by the core can be calculated by measuring the current and the cable resistance, and the temperature of the insulation layer can be inferred according to the specific heat capacity of the insulation layer and the material inside the cable. Specifically, in step S21, the following steps are specifically included:

[0099] S21. Calculate the first heat generated by the cable core at any cross section; the calculation formula for the first heat is:

[0100]

[0101] In the above formula, Q 0 represents the first heat, I represents the current in the cable, R represents the resistance of the cable, and the cable length corresponding to the resistance is L;

[0102] S22, calculating the cross-sectional temperature at any position on any cross-sectional area in the cable according to the first heat; the calculation formula of the cross-sectional temperature is:

[0103]

[0104] In the above formula, Q 0 represents the first heat, x and y represent the coordinates of any cross section in the cable, the temperature at that point is T, A is the thermal conductivity of the material in the cable, m 0 It represents the mass per unit area of ​​the material at any cross section in the cable, c represents the specific heat capacity of the material at that point, and t represents the service life of the cable;

[0105] S23, according to the cross-sectional temperature at any position on any cross-sectional area in the cable, calculate the average temperature of the insulation layer on any cross-sectional area in the cable. The insulation layer is a circular ring with the center of the cable as the center. Therefore, which part of the circular ring is used as the basis for calculating the average temperature needs further consideration. Here, in order to save the amount of calculation, the temperature at a certain position of the insulation layer is directly taken as the average temperature. It can be further clarified that in step S23, the following steps are specifically included:

[0106] S231. Calculate the coordinates of the center of any cross section in the cable according to the point set on the cross section. The expression of the coordinates of the center of the cross section is:

[0107]

[0108] In the above formula, (x 0 ,y 0 , z 0 ) are the x, y and z axis coordinates of the center of the circle, x i and i They represent the x-axis and y-axis coordinates of a point on any cross section in the cable, and the number of points obtained on the cross section is n;

[0109] S232, obtaining the radius range of the insulation layer of the cable;

[0110] S233, constructing a first circle for obtaining the average temperature of the insulation layer according to the radius range of the insulation layer of the cable and the coordinates of the center of the cross section; the expression of the first circle is:

[0111]

[0112] In the above formula, r min and r max are the minimum and maximum values ​​of the radius range of the cable insulation layer, respectively, and α is the value coefficient;

[0113] S234. The temperature of any point on the first circle is obtained according to the cross-sectional temperature at any position on any cross-section in the cable, as the average temperature of the insulation layer on any cross-section in the cable. The cross-sectional temperature at any position on any cross-section can be freely set. In actual operation, the temperature of each point on the cable cross-section can be obtained first, and the average temperature can be calculated. Then, it is determined by calculation which diameter of the insulation layer has a temperature equal to the average temperature, so that in subsequent calculations, the temperature at that point can be directly obtained, thereby saving a lot of calculations and being more convenient.

[0114] S3, calculating the total aging amount of the cable according to the average temperature of the insulation layer of the cable at any time and the first data, setting a number of aging levels corresponding to different aging total amounts, and determining the aging level of the cable; during the use of the cable, the cable is affected by the external environment and its current carrying capacity and cable material and other influencing factors, so the influence of different influencing factors on the aging speed of the cable is statistically analyzed through experiments, so as to simulate the aging speed of the cable, so as to facilitate the calculation and monitoring of the aging degree of the cable, and use this as a factor to determine whether the cable has a fire hazard. Specifically, in step S3, the following steps are specifically included:

[0115] S31. Calculate the aging rate of the cable per unit time based on the average temperature of the insulation layer; the calculation formula for the aging rate is:

[0116]

[0117] In the above formula, V represents the aging rate of the cable per unit time, a and b are the first constant and the second constant, respectively, which are related to the activation energy of the insulation material, T 0 It represents the average temperature of the insulation layer, T' represents the first temperature, and B represents the aging basic coefficient, which is generally 1.6089;

[0118] S32. Calculate the aging amount of the cable within a certain period of time according to the aging speed of the cable within a unit time. The calculation formula of the aging amount is:

[0119]

[0120] In the above formula, L represents the aging amount, t represents the usage time of the cable, and V(t) represents the relationship between the aging speed and time;

[0121] S33, obtaining several influencing factors affecting the aging amount of the cable, and calculating the total aging amount of the cable according to the aging amount; the calculation formula for the total aging amount is:

[0122] LZ=K 1 ·K 2 ·K 3 ·K 4 ·K 5 ·L·β

[0123] in,

[0124] K 1 =γ n , 1<γ<2

[0125]

[0126] In the above formula, K 1 represents the failure number influencing factor, γ represents the first coefficient, n represents the failure number, K 2 Indicates the influencing factor of the laying method. The corresponding value varies according to the laying method. For example, the direct burial laying is set to 1.2, the pipe laying is set to 1.3, etc. 3 Indicates the environmental humidity impact factor. Different values ​​correspond to different environmental humidity ranges. For example, the value is 1 when the humidity is 0-40%, 1.1 when it is 40%-60%, 1.2 when it is 60%-80%, and 1.3 when it is 80%-100%. 4 A represents the service life impact factor, 1 is the second coefficient, generally set to 0.9601, A 2 is the third coefficient, generally 0.01899, t0 is the service life of the cable, K 5 is the load influencing factor, and its value corresponds to the range of cable load rate. For example, when the load rate is less than 50%, its value is 1; when the load rate is between 50% and 70%, it is set to 1.2; when the load rate is greater than 70%, its value is set to 1.4. β is other influencing factors. At present, in the actual use of photovoltaic power stations, there are five main influencing factors affecting cable aging, namely, the number of cable failures, laying methods, ambient humidity, service life and cable load. Of course, there may be other influencing factors, so adjustments are made through other influencing factors.

[0127] S34. Set several aging total amount intervals and aging levels corresponding to the intervals, and determine the aging level of the cable according to the aging total amount intervals corresponding to the aging total amount of the cable; currently, the aging level of the cable is set to good, mild, moderate and severe levels, and the corresponding aging total amount intervals are LZ<30%, 30%≤LZ<50%, 50%≤LZ<70%, 70%≤LZ.

[0128] S4. Constructing an influence matrix of the influence degree of each influencing factor on the cable fire hazard according to the first data and the aging level; for the fire hazard of the photovoltaic power station cable, the influencing factors include dust, ambient temperature, ambient humidity, cable parameters and cable load in addition to the aging degree of the cable, so it is necessary to estimate the influence degree of the fire hazard through experiments, so as to facilitate the calculation of the risk coefficient reflecting the degree of fire hazard by statistically analyzing the parameters of each influencing factor in the subsequent actual use. Therefore, in step S4, the following steps are specifically included:

[0129] S41, setting a number of influencing factors that affect cable fire to obtain an influencing factor set, and selecting any influencing factor from the influencing factor set to set an influence degree matrix, and setting a first weight of the influencing factor in the influence degree matrix, and marking the influencing factor in the influence degree matrix as a first influencing factor;

[0130] S42, selecting any influencing factor from the influencing factor set and marking it as a second influencing factor, setting a second weight corresponding to the second influencing factor, and then marking the second influencing factor as a first influencing factor and adding it to the influence matrix;

[0131] S43, compare the influence degree of the second influencing factor and the first influencing factor in the influence matrix on the cable fire, make the second weight less than the first weight of the first influencing factor with a greater influence degree, and make the second weight greater than the first weight of the first influencing factor with a smaller influence degree. The size of the first weight of each first influencing factor in the influence matrix needs to be estimated based on experimental data. The following provides a specific estimation method for the size of the first weight of each first influencing factor. In step S43, it specifically includes the following steps:

[0132] S431. Set several influence levels and corresponding influence ratios; for example, when comparing the influence of the ith influence factor and the jth influence factor on the cable fire, if the ith influence factor is equally important than the jth influence factor, the difference in influence between the two is 1; if the ith influence factor is slightly more important than the jth influence factor, the influence ratio between the two is 3; if the ith influence factor is significantly more important than the jth influence factor, the influence ratio between the two is 5; if the ith influence factor is much more important than the jth influence factor, the influence ratio between the two is 7; if the ith influence factor is extremely important compared to the jth influence factor, the influence ratio between the two is 9;

[0133] S432, determining whether there is a first influencing factor in the influence matrix whose first weight is the same as the second weight value of the second influencing factor;

[0134] If so, setting the second weight of the second influencing factor to the first weight of the first influencing factor;

[0135] If not, proceed to step S433;

[0136] S433, determining whether there is a first influencing factor with a smaller influence degree than the second influencing factor in the influence matrix;

[0137] If so, obtain the first influencing factor that is closest to the second influencing factor in terms of its influence and the corresponding first weight, and mark the first influencing factor as the third influencing factor;

[0138] If not, proceed to step S437;

[0139] S434. Calculate the second weight of the second influencing factor according to the third influencing factor and the influencing degree ratio; the calculation formula of the second weight is:

[0140] Z i =τ i,i-1 ·Z i-1

[0141] In the above formula, Z i Indicates the second weight of the second influencing factor, Z i-1is the first weight of the third influencing factor, τ i,i-1 is the influence ratio of the second influencing factor to the third influencing factor;

[0142] S435, determining whether there is a first influencing factor in the influence matrix that has a greater influence than the second influencing factor;

[0143] If so, obtaining the first influencing factor and the corresponding first weight, and marking the first influencing factor as the fourth influencing factor;

[0144] If not, proceed to step S44;

[0145] S436: scaling or expanding the first weight of the fourth influencing factor according to the influence degree ratio; the calculation formula of the scaled or expanded first weight of the fourth influencing factor is:

[0146]

[0147] In the above formula, Z' j represents the first weight of the fourth influencing factor after scaling or expansion, Z i Indicates the second weight of the second influencing factor, Z i represents the first weight of the fourth influencing factor before scaling or enlargement, Z i+1 Indicates the first influencing factor in the influence matrix that has a greater influence than the second influencing factor, and the influence ratio of the first influencing factor to the second influencing factor is the smallest, τ i,i-1 is the influence ratio of the second influencing factor to the third influencing factor;

[0148] S437, determining whether there is a first influencing factor in the influence matrix that has a greater influence than the second influencing factor;

[0149] If so, obtaining the first influencing factor that is closest to the second influencing factor in terms of its influence and the corresponding first weight, and marking the first influencing factor as the fifth influencing factor;

[0150] If not, proceed to step S44;

[0151] S438. Calculate the second weight of the second influencing factor according to the first weight of the fifth influencing factor and the influence ratio between the fifth influencing factor and the second influencing factor. The calculation formula of the first weight is:

[0152]

[0153] In the above formula, Z i Indicates the second weight of the second influencing factor, Z i+1 represents the first weight of the fifth influencing factor, τ i+1,iis the influence ratio of the fifth influencing factor to the second influencing factor.

[0154] S44, determining whether the influencing factor set is an empty set;

[0155] If yes, go to the next step;

[0156] If not, return to step S42;

[0157] S45, normalizing the first weight in the influence matrix to obtain the influence matrix; the calculation formula for normalizing the first weight and the second weight is:

[0158]

[0159] In the above formula, Z' i represents the first weight of the normalized first influencing factor of the i-th factor in the influence matrix, Z i It represents the first weight of the i-th first influencing factor before normalization in the influence matrix. The number of first weights in the influence matrix is ​​n.

[0160] S5. Calculate the risk coefficient of the cable according to the influence matrix. After quantitatively obtaining the first weights of the first influence factors in the influence matrix, obtain the actual parameters corresponding to the first influence factors to facilitate the calculation of the risk coefficient. Specifically, in step S5, the following steps are specifically included:

[0161] S51, obtaining parameters of influencing factors corresponding to the influence matrix;

[0162] S52. Calculate the risk factor of cable fire according to the parameters of the influencing factors and the influence matrix; the calculation formula of the risk factor is:

[0163]

[0164] In the above formula, F represents the risk factor of cable fire, Z' i represents the first weight of the normalized first influencing factor of the i-th factor in the influence matrix, δ i It represents the parameter corresponding to the i-th influencing factor. There are n influencing factors in total, and the influencing factors correspond one-to-one to the first influencing factor in the influence matrix.

[0165] S6. Based on whether the risk factor is greater than the risk threshold, output prompt information on whether the cable has a fire hazard; the risk threshold is generally set between 40-50, which can not only ensure the service life of the cable and reduce cost waste, but also increase the degree of identification of fire hazards. When the risk factor is less than the risk threshold, there is no fire.

[0166] If so, a prompt message indicating that the cable has a fire hazard is output; the output prompt message of the cable includes information such as the cable number and position, so that the operation and maintenance personnel can know which cable has the fire hazard according to the prompt message.

[0167] If not, then end.

[0168] The present invention obtains various parameters of the cable when working in the photovoltaic power station to form first data, then calculates the average temperature of the insulation layer of the cable according to the first data, and then estimates the aging degree of the cable according to the first parameter and the average temperature of the insulation layer, as one of the influencing factors of the fire in the cable in the photovoltaic power station, and then further collects various influencing factors that may cause the fire according to the working environment of the cable in the photovoltaic power station, and obtains the degree of influence of various influencing factors on the fire according to the experiment, and further forms an influence matrix through the method mentioned in step S4, and calculates the fire hazard according to the actual parameters of each influencing factor collected and the influence matrix, that is, the risk coefficient of the occurrence of fire in the cable, so as to judge whether the cable has a fire hazard according to the risk threshold, so as to obtain the information of whether the cable has a fire hazard in a more forward-looking manner, so that the operation and maintenance personnel can obtain whether the cable has a fire hazard in advance, so that the operation and maintenance personnel can have more sufficient time to take measures on the cable with fire hazards.

[0169] The above implementation methods have been described in detail. Specific examples are used herein to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea. At the same time, for those skilled in the art, according to the idea of ​​the present invention, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as a limitation on the present invention.

Claims

1. A method for identifying fire hazards in photovoltaic power plants based on AI, characterized in that: The method comprises the following steps: S1. Acquire first data including cable specification parameters, infrared images, ambient humidity, ambient temperature, number of failures, current carrying capacity, laying method and usage time; S2. Calculate the average temperature of the cable insulation layer according to the first data; S3, calculating the total aging amount of the cable according to the average temperature of the insulation layer of the cable at any time and the first data, setting a number of aging levels corresponding to different aging total amounts, and determining the aging level of the cable; S4. Constructing an influence matrix of each influencing factor on the fire hazard of cables according to the first data and the aging level; S5. Calculate the risk factor of the cable according to the influence matrix; S6. Based on whether the risk factor is greater than the risk threshold, output prompt information on whether there is a fire hazard in the cable; If so, a prompt message is output indicating that the cable has a fire hazard; If not, then end.

2. The identification method according to claim 1, characterized in that: In step S21, the following steps are specifically included: S21. Calculate the first heat generated by the cable core at any cross section; the calculation formula for the first heat is: In the above formula, Q 0 represents the first heat, I represents the current in the cable, R represents the resistance of the cable, and the cable length corresponding to the resistance is L; S22, calculating the cross-sectional temperature at any position on any cross-sectional area in the cable according to the first heat; S23. Calculate the average temperature of the insulation layer on any cross section in the cable according to the cross section temperature at any position on any cross section in the cable.

3. The identification method according to claim 2, characterized in that: In step S23, the following steps are specifically included: S231. Calculate the coordinates of the center of any cross section in the cable according to the point set on the cross section. The expression of the coordinates of the center of the cross section is: In the above formula, (x0, y0, z0) are the coordinates of the x, y and z axes of the center of the circle, x i and i They represent the x-axis and y-axis coordinates of a point on any cross section in the cable, and the number of points obtained on the cross section is n; S232, obtaining the radius range of the insulation layer of the cable; S233, constructing a first circle for obtaining the average temperature of the insulation layer according to the radius range of the insulation layer of the cable and the coordinates of the center of the cross section; the expression of the first circle is: In the above formula, r min and r max are the minimum and maximum values ​​of the radius range of the cable insulation layer, respectively, and α is the value coefficient; S234. Obtain the temperature of any point on the first circle according to the cross-sectional temperature at any position on any cross-sectional area in the cable, as the average temperature of the insulation layer on any cross-sectional area in the cable.

4. The identification method according to claim 1, characterized in that: In step S3, the following steps are specifically included: S31. Calculate the aging rate of the cable per unit time according to the average temperature of the insulation layer; S32. Calculate the aging amount of the cable within a certain period of time according to the aging speed of the cable within a unit time. The calculation formula of the aging amount is: In the above formula, L represents the aging amount, t represents the usage time of the cable, and V(t) represents the relationship between the aging speed and time; S33, obtaining several influencing factors affecting the aging amount of the cable, and calculating the total aging amount of the cable according to the aging amount; S34, setting a plurality of aging total amount intervals and aging levels corresponding to the intervals, and determining the aging level of the cable according to the aging total amount interval corresponding to the aging total amount of the cable.

5. The identification method according to claim 1, characterized in that: In step S4, the following steps are specifically included: S41, setting a number of influencing factors that affect cable fire to obtain an influencing factor set, and selecting any influencing factor from the influencing factor set to set an influence degree matrix, and setting a first weight of the influencing factor in the influence degree matrix, and marking the influencing factor in the influence degree matrix as a first influencing factor; S42, selecting any influencing factor from the influencing factor set and marking it as a second influencing factor, setting a second weight corresponding to the second influencing factor, and then marking the second influencing factor as a first influencing factor and adding it to the influence matrix; S43, comparing the influence degree of the second influencing factor and the first influencing factor in the influence degree matrix on the cable fire, making the second weight smaller than the first weight of the first influencing factor with a greater influence degree, and making the second weight larger than the first weight of the first influencing factor with a smaller influence degree; S44, determining whether the influencing factor set is an empty set; If yes, go to the next step; If not, return to step S42; S45, normalizing the first weight in the influence matrix to obtain the influence matrix; the calculation formula for normalizing the first weight and the second weight is: In the above formula, Z' i represents the first weight of the normalized first influencing factor of the i-th factor in the influence matrix, Z i It represents the first weight of the i-th first influencing factor before normalization in the influence matrix. The number of first weights in the influence matrix is ​​n.

6. The identification method according to claim 5, characterized in that: In step S43, the following steps are specifically included: S431, setting a number of impact levels and corresponding impact ratios; S432, determining whether there is a first influencing factor in the influence matrix whose first weight is the same as the second weight value of the second influencing factor; If so, setting the second weight of the second influencing factor to the first weight of the first influencing factor; If not, proceed to step S433; S433, determining whether there is a first influencing factor with a smaller influence degree than the second influencing factor in the influence matrix; If so, obtain the first influencing factor that is closest to the second influencing factor in terms of its influence and the corresponding first weight, and mark the first influencing factor as the third influencing factor; If not, proceed to step S437; S434. Calculate the second weight of the second influencing factor according to the third influencing factor and the influencing degree ratio; the calculation formula of the second weight is: WITH i =τ i,i-1 ·WITH i-1 In the above formula, Z i Indicates the second weight of the second influencing factor, Z i-1 is the first weight of the third influencing factor, τ i,i-1 is the influence ratio of the second influencing factor to the third influencing factor; S435, determining whether there is a first influencing factor in the influence matrix that has a greater influence than the second influencing factor; If so, obtaining the first influencing factor and the corresponding first weight, and marking the first influencing factor as the fourth influencing factor; If not, proceed to step S44; S436: scaling or expanding the first weight of the fourth influencing factor according to the influence degree ratio; the calculation formula of the scaled or expanded first weight of the fourth influencing factor is: In the above formula, Z' j represents the first weight of the fourth influencing factor after scaling or expansion, Z i Indicates the second weight of the second influencing factor, Z j represents the first weight of the fourth influencing factor before scaling or enlargement, Z i+1 Indicates the first influencing factor in the influence matrix that has a greater influence than the second influencing factor, and the influence ratio of the first influencing factor to the second influencing factor is the smallest, τ i,i-1 is the influence ratio of the second influencing factor to the third influencing factor; S437, determining whether there is a first influencing factor in the influence matrix that has a greater influence than the second influencing factor; If so, obtaining the first influencing factor that is closest to the second influencing factor in terms of its influence and the corresponding first weight, and marking the first influencing factor as the fifth influencing factor; If not, proceed to step S44; S438. Calculate the second weight of the second influencing factor according to the first weight of the fifth influencing factor and the influence ratio between the fifth influencing factor and the second influencing factor. The calculation formula of the first weight is: In the above formula, Z i Indicates the second weight of the second influencing factor, Z i+1 represents the first weight of the fifth influencing factor, τ i+1,i is the influence ratio of the fifth influencing factor to the second influencing factor.

7. The identification method according to claim 1, characterized in that: In step S5, the following steps are specifically included: S51, obtaining parameters of influencing factors corresponding to the influence matrix; S52. Calculate the risk factor of cable fire according to the parameters of the influencing factors and the influence matrix; the calculation formula of the risk factor is: In the above formula, F represents the risk factor of cable fire, Z' i represents the first weight of the normalized first influencing factor of the i-th factor in the influence matrix, δ i It represents the parameter corresponding to the i-th influencing factor. There are n influencing factors in total, and the influencing factors correspond one-to-one to the first influencing factor in the influence matrix.

8. The identification method according to claim 2, characterized in that: In step S22, the calculation formula of the cross-sectional temperature is: In the above formula, Q 0 represents the first heat, x and y represent the coordinates of any cross section in the cable, the temperature at that point is T, A is the thermal conductivity of the material in the cable, m 0 It represents the mass per unit area of ​​the material at any cross section in the cable, c represents the specific heat capacity of the material at that location, and t represents the service life of the cable.

9. The identification method according to claim 4, characterized in that: In step S31, the calculation formula of the aging speed is: In the above formula, V represents the aging rate of the cable per unit time, a and b are the first constant and the second constant, respectively, which are related to the activation energy of the insulation material, T 0 represents the average temperature of the insulation layer, T' represents the first temperature, and B represents the basic aging coefficient, which is 1.6089.

10. The identification method according to claim 4, characterized in that: In step S34, the calculation formula of the total aging amount is: LZ=K1·K2·K3·K4·K5·L·β in, K1=γ n ,1<γ<2 In the above formula, K1 represents the influencing factor of the number of failures, γ represents the first coefficient, n represents the number of failures, K2 represents the influencing factor of the laying method, and its corresponding numerical value varies according to the different laying methods. K3 represents the influencing factor of the ambient humidity, and its different numerical values ​​correspond to different ambient humidity ranges. K4 represents the influencing factor of the service life, A1 is the second coefficient, A2 is the third coefficient, t0 is the service life of the cable, K5 is the load influencing factor, and its numerical value corresponds to the range of the cable load rate, and β is other influencing factors.

Citation Information

Patent Citations

  • Power distribution network cable line monitoring method, computer equipment and storage medium

    CN112016835A

  • Method and device for intelligent fire monitoring of photovoltaic modules in photovoltaic field area

    CN114792457A

  • Cable state evaluation and early warning method and device

    CN118393291A