A distributed photovoltaic power station fire alarm system and method based on big data

Abstract

The present invention discloses a distributed photovoltaic power station fire alarm system and method based on big data, which relates to the technical field of fire alarm. The alarm method comprises the following steps: constructing a patrol data management system to generate detection records of various photovoltaic power stations; conducting risk assessment on various photovoltaic power stations; analyzing the differences between the detection records and extracting the same features; transmitting the detection data of any photovoltaic power station about each same feature to the patrol equipment, and conducting a secondary assessment when patrolling the remaining photovoltaic power stations; whenever the patrol equipment conducts detection on any photovoltaic power station, obtaining the expected risk values ​​of the remaining photovoltaic power stations, and adjusting the patrol route in the patrol equipment; when the patrol equipment returns to conduct a secondary detection, obtaining the real-time assessment result of the photovoltaic power station, and comparing it with the revised assessment result; identifying abnormalities of the photovoltaic power station and providing feedback to the staff.

Description

Technical Field

[0001] The present invention relates to the field of fire alarm technology, and in particular to a distributed photovoltaic power station fire alarm system and method based on big data. Background Art

[0002] A distributed photovoltaic power station refers to a power generation system that uses decentralized resources, has a smaller installed capacity, and is arranged near users. It uses solar energy resources and is usually installed on the roofs of buildings, parking lots, and other places. Distributed photovoltaic power stations have developed rapidly in recent years due to their wide application and environmentally friendly characteristics.

[0003] With the increase in the number of photovoltaic power stations, fire safety issues have become increasingly prominent, so it is particularly important to establish an efficient fire alarm system; however, in the fire alarm system of distributed photovoltaic power stations, false detection is an important challenge. Since distributed photovoltaic power stations are established in a decentralized manner, there are differences in the environments in which each power station is located, and the external environment has a certain degree of influence on the detection of fire hazards. Therefore, each power station will have different abnormal thresholds. If only a simple threshold comparison is performed, false detection and missed detection are likely to occur, resulting in unnecessary alarms and waste of resources. Summary of the invention

[0004] The purpose of the present invention is to provide a distributed photovoltaic power station fire alarm system and method based on big data to solve the problems raised in the prior art.

[0005] To achieve the above object, the present invention provides the following technical solution: a distributed photovoltaic power station fire alarm method based on big data, the alarm method comprising the following steps:

[0006] Step S100: Preset inspection routes in the inspection equipment to inspect each photovoltaic power station, build an inspection data management system to record each inspection process of each photovoltaic power station, and generate inspection records of each photovoltaic power station; based on the inspection situation presented in any inspection record, perform risk assessment on the corresponding photovoltaic power station;

[0007] Step S200: Analyze the differences between the detection records and extract the same features between different photovoltaic power stations; transmit the detection data of each same feature of any photovoltaic power station to the inspection equipment, perform a secondary evaluation when inspecting other photovoltaic power stations, and make real-time corrections to the risk assessment of the corresponding detection records;

[0008] Step S300: Whenever the inspection device inspects any photovoltaic power station, the revised assessment results of the remaining photovoltaic power stations are extracted, and the latest maintenance records stored in the remaining photovoltaic power stations are obtained to obtain the expected risk values ​​of the remaining photovoltaic power stations; based on the expected risk values ​​of each photovoltaic power station, the inspection route in the inspection device is adjusted;

[0009] Step S400: For any photovoltaic power station, when the inspection equipment returns for secondary inspection, the real-time evaluation result of the photovoltaic power station is obtained, and the difference is compared with each real-time corrected evaluation result; based on the difference comparison result, the photovoltaic power station is identified as abnormal and feedback is given to the staff.

[0010] Furthermore, step S100 includes the following steps:

[0011] Step S101: Whenever the inspection equipment is dispatched to inspect each photovoltaic power station, the real-time location of the inspection equipment and the location of each photovoltaic power station are obtained, the connection status between each photovoltaic power station is obtained, and an inspection route that includes all photovoltaic power stations and has the smallest total route length is selected and input into the inspection equipment to start the inspection;

[0012] Step S102: when any photovoltaic power station is inspected during the inspection process, the inspection data generated during the inspection process of the photovoltaic power station is recorded and transmitted to the inspection data management system for storage, thereby generating a detection record of the photovoltaic power station; the detection data contains power generation data, component performance data, system efficiency data, and environmental data, etc.;

[0013] Step S103: Divide the test data recorded in any test record into data sets of several dimensions according to the data source, set a risk assessment rule for each dimension, obtain the risk value of each dimension, and accumulate the risk values ​​of all dimensions to obtain the risk value of the test record.

[0014] Further, step S200 includes the following steps:

[0015] Step S201: selecting one detection record of any two photovoltaic power stations from the inspection data management system, extracting detection data between the two selected detection records for any dimension, performing similarity comparison on the detection data of the dimension, setting a similarity threshold, and if the obtained similarity exceeds the similarity threshold, setting it as a feature comparison of the dimension;

[0016] Step S202: performing a similarity comparison on each detection record between the two photovoltaic power stations with respect to the dimension, and counting the number of feature comparisons n of the dimension. com , calculate the feature frequency ratio of the dimension α=n com / (a1×a2), where a1 is the number of detection records of one PV power station, and a2 is the number of detection records of another PV power station; a threshold α is set max , if α>α max , then the dimension is set as a common feature of the two photovoltaic power stations; the common feature set between any photovoltaic power station and the other photovoltaic power stations is extracted and stored in the inspection equipment; the common features reflect the similarities between different photovoltaic power stations, so that the detection conditions of each photovoltaic power station can reflect each other whether there is a false detection;

[0017] Step S203: Whenever the inspection device inspects any photovoltaic power station and generates a corresponding inspection record, the inspection record is stored in the inspection device, and when the inspection device inspects the remaining photovoltaic power stations according to the inspection route, the photovoltaic power station currently inspected by the inspection device is set as the real-time photovoltaic power station, and the same feature set between the photovoltaic power station and the real-time photovoltaic power station is extracted;

[0018] Step S204: extract the detection data corresponding to the same feature set of the photovoltaic power station from the inspection equipment, transmit all the extracted detection data to the real-time photovoltaic power station, and obtain the risk value of each same feature of the photovoltaic power station in the real-time photovoltaic power station; obtain the risk value of other dimensions of the photovoltaic power station except the same feature, according to the formula:

[0019] ;

[0020] Wherein, i and j are both positive integers and i∈(1,c), j∈(1,d), c is the number of identical features, d is the number of remaining dimensions in the photovoltaic power station excluding identical features, (F i ) ’ is the risk value of the i-th same characteristic, F j is the risk value of the jth dimension of the photovoltaic power station excluding the same features; and the risk value F presented by the detection data of the photovoltaic power station in the real-time photovoltaic power station is calculated. ’ The situation presented by the detection data of the same characteristics in other photovoltaic power stations can also reflect the risk value of the photovoltaic power station. At the same time, it can also reflect whether there are any abnormalities in the previous assessment of the photovoltaic power station, thereby reducing the probability of false detection.

[0021] Further, step S300 includes the following steps:

[0022] Step S301: Assume that the current inspection device is at the pth photovoltaic power station, and obtain the route distance between the pth photovoltaic power station and any qth photovoltaic power station as L pq, the travel speed of the inspection equipment is obtained as v, and the travel time between the p-th photovoltaic power station and the q-th photovoltaic power station is obtained as T pq ;

[0023] Step S302: Obtain each detection record stored in the inspection data management system of the p-th photovoltaic power station, extract the risk difference between any two adjacent detection records, obtain the record generation time of the two detection records respectively, obtain the generation time difference, calculate the unit loss value between the two detection records, and calculate the average value of the loss proportion of all two adjacent detection records to obtain the unit loss value η of the p-th photovoltaic power station p ; Because the detection data of a photovoltaic power station needs to be transmitted through the inspection equipment to transmit to other photovoltaic power stations, there is a time difference, and the operation of the photovoltaic power station is continuous, so it is necessary to obtain the unit loss of the photovoltaic power station to provide a more accurate basis for the subsequent expected risk value analysis;

[0024] Step S303: Obtain the risk value of the qth photovoltaic power station in the latest generated detection record as F q The risk value of the qth PV plant in the pth PV plant is (F qp ) ’ , according to the formula:

[0025] ;

[0026] Among them, (T wait ) q is the time interval between the generation time of the latest detection record of the qth photovoltaic power station and the current time; the expected risk value (F ex ) q ; Obtain the expected risk value of each photovoltaic power station, select the photovoltaic power station corresponding to the largest expected risk value as the next target power station for the inspection equipment, and adjust the inspection route of the inspection equipment; The analysis of the expected risk value can help the inspection equipment to judge the real-time risk value of each photovoltaic power station in real time, and help the inspection equipment to prioritize the inspection of high-risk power stations to avoid the occurrence of fire hazards;

[0027] Step S304: Whenever the inspection device inspects any photovoltaic power station, the expected risk values ​​of the remaining photovoltaic power stations are calculated, and the inspection route of the inspection device is corrected in real time.

[0028] Further, step S400 includes the following steps:

[0029] Step S401: arbitrarily select the pth photovoltaic power station, and when the inspection device returns to the pth photovoltaic power station, obtain each photovoltaic power station detected by the inspection device between two adjacent detection records of the pth photovoltaic power station, and generate a photovoltaic power station set;

[0030] Step S402: arbitrarily select the u-th photovoltaic power station from the photovoltaic power station set, and obtain the unit loss value η of the u-th photovoltaic power station p , and the risk value presented by the p-th photovoltaic power station in the u-th photovoltaic power station is (F pu ) ’ ; Count the number of identical features M in the identical feature set between the p-th photovoltaic power station and the u-th photovoltaic power station pu , the similarity between the p-th photovoltaic power station and the u-th photovoltaic power station is calculated to be τ pu =M pu / M, where M is the total number of dimensions of any photovoltaic power station; according to the formula:

[0031] ;

[0032] Wherein, u1 is a positive integer and u1∈(1,x), x is the number of photovoltaic power stations in the photovoltaic power station set, T pu is the travel time between the p-th photovoltaic power station and the u-th photovoltaic power station, τ p,u1 is the similarity between the p-th photovoltaic power station and the u1-th photovoltaic power station; the expected risk value (F p ) comp ;

[0033] Step S403: Obtain the detection data of the p-th photovoltaic power station in various dimensions, conduct real-time evaluation on the p-th photovoltaic power station, and calculate the real-time risk value of the p-th photovoltaic power station as (F p ) ac ; Set a risk difference ratio threshold δ, if |(F p ) comp -(F p ) ac | / (F p ) ac >δ, an abnormal reminder will be issued to the pth PV power station and feedback will be given to the staff.

[0034] In order to better implement the above method, a distributed photovoltaic power station fire alarm system is also proposed. The alarm system includes a power station inspection and evaluation module, a risk assessment and correction module, an inspection route adjustment module and an abnormal power station identification module;

[0035] The power station inspection and assessment module is used to preset inspection routes in the inspection equipment to inspect each photovoltaic power station, build an inspection data management system to record each inspection process of each photovoltaic power station, and generate inspection records for each photovoltaic power station; based on the inspection situation presented in any inspection record, the corresponding photovoltaic power station is risk assessed;

[0036] The risk assessment and correction module is used to analyze the differences between the various detection records and extract the same features between different photovoltaic power stations; transmit the detection data of each identical feature of any photovoltaic power station to the inspection equipment, conduct a secondary assessment when inspecting other photovoltaic power stations, and make real-time corrections to the risk assessment of the corresponding detection records;

[0037] The inspection route adjustment module is used to extract the revised evaluation results of the remaining photovoltaic power stations in the photovoltaic power station and obtain the latest maintenance records stored in the remaining photovoltaic power stations to obtain the expected risk values ​​of the remaining photovoltaic power stations whenever the inspection equipment inspects any photovoltaic power station; based on the expected risk values ​​of each photovoltaic power station, the inspection route in the inspection equipment is adjusted;

[0038] The abnormal power station identification module is used to obtain the real-time evaluation results of any photovoltaic power station when the inspection equipment returns for secondary inspection, and compare the differences with the various real-time corrected evaluation results; based on the difference comparison results, the abnormality of the photovoltaic power station is identified and feedback is given to the staff.

[0039] Further, the power plant inspection and assessment module includes an inspection data acquisition unit and a power plant risk assessment unit;

[0040] The inspection data acquisition unit is used to preset inspection routes in the inspection equipment to inspect each photovoltaic power station, build an inspection data management system to record each inspection process of each photovoltaic power station, and generate inspection records of each photovoltaic power station; the power station risk assessment unit is used to conduct risk assessment on the corresponding photovoltaic power station based on the inspection situation presented in any inspection record.

[0041] Further, the risk assessment correction module includes a same feature extraction unit and a risk assessment correction unit;

[0042] The same feature extraction unit is used to analyze the differences between each detection record and extract the same features between different photovoltaic power stations; the risk assessment correction unit is used to transmit the detection data of each same feature of any photovoltaic power station to the inspection equipment, and conduct a secondary assessment when inspecting other photovoltaic power stations, and make real-time corrections to the risk assessment of the corresponding detection records.

[0043] Further, the inspection route adjustment module includes an expected risk prediction unit and an inspection sequence setting unit;

[0044] The expected risk prediction unit is used to extract the revised assessment results of the remaining photovoltaic power stations in the photovoltaic power station and obtain the latest maintenance records stored in the remaining photovoltaic power stations to obtain the expected risk values ​​of the remaining photovoltaic power stations whenever the inspection equipment inspects any photovoltaic power station; the inspection sequence setting unit is used to adjust the inspection route in the inspection equipment based on the expected risk value of each photovoltaic power station.

[0045] Further, the abnormal power station identification module includes an inspection feedback comparison unit and a feedback abnormality judgment unit;

[0046] The inspection feedback comparison unit is used to obtain the real-time evaluation result of any photovoltaic power station when the inspection equipment returns for secondary inspection, and compare the difference with each real-time corrected evaluation result; the feedback abnormality judgment unit is used to identify the abnormality of the photovoltaic power station based on the difference comparison result and provide feedback to the staff.

[0047] Compared with the prior art, the present invention has the following beneficial effects:

[0048] 1. The present invention abandons the traditional method of judging abnormalities by simple threshold comparison, and adopts a new method of judging abnormalities by multiple evaluations of the detection data through other power stations, which can help staff reduce the frequency of false detection and effectively utilize fire protection resources;

[0049] 2. The present invention analyzes the same features between various photovoltaic power stations and evaluates the detection data against each other to obtain the similarity of the evaluation results of the same detection data under similar operating environments, and makes an accuracy judgment on each evaluation result, so as to more accurately identify anomalies and false detections;

[0050] 3. The present invention adjusts the inspection sequence of photovoltaic power stations in real time, helping inspection equipment to prioritize inspections of high-risk power stations, greatly reducing the probability of fire hazards. It can also help staff to detect abnormal situations in a timely manner, so as to take corresponding measures and use alarms and fire-fighting resources more effectively. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] Figure 1 A schematic diagram of the steps of a distributed photovoltaic power station fire alarm method based on big data;

[0052] Figure 2 This is a structural diagram of a distributed photovoltaic power station fire alarm system based on big data. DETAILED DESCRIPTION

[0053] 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.

[0054] Example: Figure 1 to Figure 2 As shown, the present invention provides a distributed photovoltaic power station fire alarm method based on big data, and the alarm method includes the following steps:

[0055] Step S100: Preset inspection routes in the inspection equipment to inspect each photovoltaic power station, build an inspection data management system to record each inspection process of each photovoltaic power station, and generate inspection records of each photovoltaic power station; based on the inspection situation presented in any inspection record, perform risk assessment on the corresponding photovoltaic power station;

[0056] Wherein, step S100 includes the following steps:

[0057] Step S101: Whenever the inspection equipment is dispatched to inspect each photovoltaic power station, the real-time location of the inspection equipment and the location of each photovoltaic power station are obtained, the connection status between each photovoltaic power station is obtained, and an inspection route that includes all photovoltaic power stations and has the smallest total route length is selected and input into the inspection equipment to start the inspection;

[0058] Step S102: when any photovoltaic power station is inspected during the inspection process, the inspection data generated by the photovoltaic power station during the inspection process is recorded and transmitted to the inspection data management system for storage, thereby generating an inspection record of the photovoltaic power station;

[0059] Step S103: Divide the test data recorded in any test record into data sets of several dimensions according to the data source, set a risk assessment rule for each dimension, obtain the risk value of each dimension, and accumulate the risk values ​​of all dimensions to obtain the risk value of the test record.

[0060] Step S200: Analyze the differences between the detection records and extract the same features between different photovoltaic power stations; transmit the detection data of each same feature of any photovoltaic power station to the inspection equipment, perform a secondary evaluation when inspecting other photovoltaic power stations, and make real-time corrections to the risk assessment of the corresponding detection records;

[0061] Wherein, step S200 includes the following steps:

[0062] Step S201: selecting one detection record of any two photovoltaic power stations from the inspection data management system, extracting detection data between the two selected detection records for any dimension, performing similarity comparison on the detection data of the dimension, setting a similarity threshold, and if the obtained similarity exceeds the similarity threshold, setting it as a feature comparison of the dimension;

[0063] Step S202: performing a similarity comparison on each detection record between the two photovoltaic power stations with respect to the dimension, and counting the number of feature comparisons n of the dimension. com , calculate the feature frequency ratio of the dimension α=n com / (a1×a2), where a1 is the number of detection records of one PV power station, and a2 is the number of detection records of another PV power station; a threshold α is set max , if α>α max , then the dimension is set as a common feature of the two photovoltaic power stations; the common feature set between any photovoltaic power station and the other photovoltaic power stations is extracted and stored in the inspection device;

[0064] Step S203: Whenever the inspection device inspects any photovoltaic power station and generates a corresponding inspection record, the inspection record is stored in the inspection device, and when the inspection device inspects the remaining photovoltaic power stations according to the inspection route, the photovoltaic power station currently inspected by the inspection device is set as the real-time photovoltaic power station, and the same feature set between the photovoltaic power station and the real-time photovoltaic power station is extracted;

[0065] Step S204: extract the detection data corresponding to the same feature set of the photovoltaic power station from the inspection equipment, transmit all the extracted detection data to the real-time photovoltaic power station, and obtain the risk value of each same feature of the photovoltaic power station in the real-time photovoltaic power station; obtain the risk value of other dimensions of the photovoltaic power station except the same feature, according to the formula:

[0066] ;

[0067] Wherein, i and j are both positive integers and i∈(1,c), j∈(1,d), c is the number of identical features, d is the number of remaining dimensions in the photovoltaic power station excluding identical features, (F i ) ’ is the risk value of the i-th same characteristic, F j is the risk value of the jth dimension of the photovoltaic power station excluding the same features; and the risk value F presented by the detection data of the photovoltaic power station in the real-time photovoltaic power station is calculated. ’ .

[0068] Step S300: Whenever the inspection device inspects any photovoltaic power station, the revised assessment results of the remaining photovoltaic power stations are extracted, and the latest maintenance records stored in the remaining photovoltaic power stations are obtained to obtain the expected risk values ​​of the remaining photovoltaic power stations; based on the expected risk values ​​of each photovoltaic power station, the inspection route in the inspection device is adjusted;

[0069] Wherein, step S300 includes the following steps:

[0070] Step S301: Assume that the current inspection device is at the pth photovoltaic power station, and obtain the route distance between the pth photovoltaic power station and any qth photovoltaic power station as L pq , the travel speed of the inspection equipment is obtained as v, and the travel time between the p-th photovoltaic power station and the q-th photovoltaic power station is obtained as T pq ;

[0071] Step S302: Obtain each detection record stored in the inspection data management system of the p-th photovoltaic power station, extract the risk difference between any two adjacent detection records, obtain the record generation time of the two detection records respectively, obtain the generation time difference, calculate the unit loss value between the two detection records, and calculate the average value of the loss proportion of all two adjacent detection records to obtain the unit loss value η of the p-th photovoltaic power station p ;

[0072] Step S303: Obtain the risk value of the qth photovoltaic power station in the latest generated detection record as F q The risk value of the qth PV plant in the pth PV plant is (F qp ) ’ , according to the formula:

[0073] ;

[0074] Among them, (T wait ) q is the time interval between the generation time of the latest detection record of the qth photovoltaic power station and the current time; the expected risk value (F ex ) q ; Obtain the expected risk value of each photovoltaic power station, select the photovoltaic power station corresponding to the largest expected risk value as the next target power station for the inspection equipment to go to, and adjust the inspection route of the inspection equipment;

[0075] Example 1: The risk value of a photovoltaic power station in the latest detection record is set to 10, and the risk value presented in another photovoltaic power station is set to 12. The unit loss value of the other photovoltaic power station is set to 0.1, and the travel time between the two photovoltaic power stations is 1h, and the time between the photovoltaic power station and the latest detection record is 9h. Therefore, the expected risk value of the photovoltaic power station is calculated to be (10+12) / 2+0.1×(1+9)=12;

[0076] Step S304: Whenever the inspection device inspects any photovoltaic power station, the expected risk values ​​of the remaining photovoltaic power stations are calculated, and the inspection route of the inspection device is corrected in real time.

[0077] Step S400: for any photovoltaic power station, when the inspection equipment returns to perform a second inspection, a real-time evaluation result of the photovoltaic power station is obtained, and a difference comparison is performed with each real-time revised evaluation result; based on the difference comparison result, an abnormality of the photovoltaic power station is identified and feedback is given to the staff;

[0078] Wherein, step S400 includes the following steps:

[0079] Step S401: arbitrarily select the pth photovoltaic power station, and when the inspection device returns to the pth photovoltaic power station, obtain each photovoltaic power station detected by the inspection device between two adjacent detection records of the pth photovoltaic power station, and generate a photovoltaic power station set;

[0080] Step S402: arbitrarily select the u-th photovoltaic power station from the photovoltaic power station set, and obtain the unit loss value η of the u-th photovoltaic power station p , and the risk value presented by the p-th photovoltaic power station in the u-th photovoltaic power station is (F pu ) ’ ; Count the number of identical features M in the identical feature set between the p-th photovoltaic power station and the u-th photovoltaic power station pu , the similarity between the p-th photovoltaic power station and the u-th photovoltaic power station is calculated to be τ pu =M pu / M, where M is the total number of dimensions of any photovoltaic power station; according to the formula:

[0081] ;

[0082] Wherein, u1 is a positive integer and u1∈(1,x), x is the number of photovoltaic power stations in the photovoltaic power station set, T pu is the travel time between the p-th photovoltaic power station and the u-th photovoltaic power station, τ p,u1is the similarity between the p-th photovoltaic power station and the u1-th photovoltaic power station; the expected risk value (F p ) comp ;

[0083] Example 2: It is assumed that there are two identical features between one photovoltaic power station and another photovoltaic power station, wherein the risk value presented by the photovoltaic power station in the other photovoltaic power station is 12, and the unit loss value of the other photovoltaic power station is 0.1, and the travel time between the two photovoltaic power stations is 1h; the number of identical features is set to account for 50%, and when the inspection equipment is in another photovoltaic power station, the expected risk value of the photovoltaic power station is calculated to be (12+0.1×1)×0.5=6.05;

[0084] Step S403: Obtain the detection data of the p-th photovoltaic power station in various dimensions, conduct real-time evaluation on the p-th photovoltaic power station, and calculate the real-time risk value of the p-th photovoltaic power station as (F p ) ac ; Set a risk difference ratio threshold δ, if |(F p ) comp -(F p ) ac | / (F p ) ac >δ, an abnormal reminder will be issued to the pth PV power station and feedback will be given to the staff.

[0085] A distributed photovoltaic power station fire alarm system, the alarm system includes a power station inspection and evaluation module, a risk assessment and correction module, an inspection route adjustment module and an abnormal power station identification module;

[0086] The power station inspection and assessment module is used to preset inspection routes in the inspection equipment to inspect each photovoltaic power station, build an inspection data management system to record each inspection process of each photovoltaic power station, and generate inspection records for each photovoltaic power station; based on the inspection situation presented in any inspection record, the corresponding photovoltaic power station is risk assessed;

[0087] The risk assessment and correction module is used to analyze the differences between the various detection records and extract the same features between different photovoltaic power stations; transmit the detection data of each identical feature of any photovoltaic power station to the inspection equipment, conduct a secondary assessment when inspecting other photovoltaic power stations, and make real-time corrections to the risk assessment of the corresponding detection records;

[0088] The inspection route adjustment module is used to extract the revised evaluation results of the remaining photovoltaic power stations in the photovoltaic power station and obtain the latest maintenance records stored in the remaining photovoltaic power stations to obtain the expected risk values ​​of the remaining photovoltaic power stations whenever the inspection equipment inspects any photovoltaic power station; based on the expected risk values ​​of each photovoltaic power station, the inspection route in the inspection equipment is adjusted;

[0089] The abnormal power station identification module is used to obtain the real-time evaluation results of any photovoltaic power station when the inspection equipment returns for secondary inspection, and compare the differences with the various real-time corrected evaluation results; based on the difference comparison results, the abnormality of the photovoltaic power station is identified and feedback is given to the staff.

[0090] Among them, the power station inspection and assessment module includes an inspection data acquisition unit and a power station risk assessment unit;

[0091] The inspection data acquisition unit is used to preset inspection routes in the inspection equipment to inspect each photovoltaic power station, build an inspection data management system to record each inspection process of each photovoltaic power station, and generate inspection records of each photovoltaic power station; the power station risk assessment unit is used to conduct risk assessment on the corresponding photovoltaic power station based on the inspection situation presented in any inspection record.

[0092] Wherein, the risk assessment correction module includes a same feature extraction unit and a risk assessment correction unit;

[0093] The same feature extraction unit is used to analyze the differences between each detection record and extract the same features between different photovoltaic power stations; the risk assessment correction unit is used to transmit the detection data of each same feature of any photovoltaic power station to the inspection equipment, and conduct a secondary assessment when inspecting other photovoltaic power stations, and make real-time corrections to the risk assessment of the corresponding detection records.

[0094] Among them, the inspection route adjustment module includes an expected risk prediction unit and an inspection sequence setting unit;

[0095] The expected risk prediction unit is used to extract the revised assessment results of the remaining photovoltaic power stations in the photovoltaic power station and obtain the latest maintenance records stored in the remaining photovoltaic power stations to obtain the expected risk values ​​of the remaining photovoltaic power stations whenever the inspection equipment inspects any photovoltaic power station; the inspection sequence setting unit is used to adjust the inspection route in the inspection equipment based on the expected risk value of each photovoltaic power station.

[0096] Among them, the abnormal power station identification module includes an inspection feedback comparison unit and a feedback abnormality judgment unit;

[0097] The inspection feedback comparison unit is used to obtain the real-time evaluation result of any photovoltaic power station when the inspection equipment returns for secondary inspection, and compare the difference with each real-time corrected evaluation result; the feedback abnormality judgment unit is used to identify the abnormality of the photovoltaic power station based on the difference comparison result and provide feedback to the staff.

[0098] It will be apparent to those skilled in the art that the invention is not limited to the details of the exemplary embodiments described above and that the invention can be implemented in other specific forms without departing from the spirit or essential features of the invention. Therefore, the embodiments should be considered exemplary and non-limiting in all respects, and the scope of the invention is defined by the appended claims rather than the foregoing description, and it is intended that all variations falling within the meaning and scope of the equivalent elements of the claims be included in the invention. Any reference numeral in a claim should not be considered as limiting the claim to which it relates.

Claims

1. A distributed photovoltaic power station fire alarm method based on big data, characterized in that: The alarm method comprises the following steps: Step S100: Preset inspection routes in the inspection equipment to inspect each photovoltaic power station, build an inspection data management system to record each inspection process of each photovoltaic power station, and generate inspection records of each photovoltaic power station; based on the inspection situation presented in any inspection record, perform risk assessment on the corresponding photovoltaic power station; Step S200: Analyze the differences between the detection records and extract the same features between different photovoltaic power stations; transmit the detection data of each same feature of any photovoltaic power station to the inspection equipment, perform a secondary evaluation when inspecting other photovoltaic power stations, and make real-time corrections to the risk assessment of the corresponding detection records; Step S300: Whenever the inspection device inspects any photovoltaic power station, the revised assessment results of the remaining photovoltaic power stations are extracted, and the latest maintenance records stored in the remaining photovoltaic power stations are obtained to obtain the expected risk values ​​of the remaining photovoltaic power stations; based on the expected risk values ​​of each photovoltaic power station, the inspection route in the inspection device is adjusted; The step S300 includes the following steps: Step S301: Assume that the current inspection device is at the pth photovoltaic power station, and obtain the route distance between the pth photovoltaic power station and any qth photovoltaic power station as L pq , the travel speed of the inspection equipment is obtained as v, and the travel time between the p-th photovoltaic power station and the q-th photovoltaic power station is obtained as T pq ; Step S302: Obtain each detection record stored in the inspection data management system of the p-th photovoltaic power station, extract the risk difference between any two adjacent detection records, obtain the record generation time of the two detection records respectively, obtain the generation time difference, calculate the unit loss value between the two detection records, and calculate the average value of the loss proportion of all two adjacent detection records to obtain the unit loss value η of the p-th photovoltaic power station p ; Step S303: Obtain the risk value of the qth photovoltaic power station in the latest generated detection record as F q The risk value of the qth PV plant in the pth PV plant is (F qp ) ’ , according to the formula: ； Among them, (T wait ) q is the time interval between the generation time of the latest detection record of the qth photovoltaic power station and the current time; the expected risk value (F ex ) q ; Obtain the expected risk value of each photovoltaic power station, select the photovoltaic power station corresponding to the largest expected risk value as the next target power station for the inspection equipment to go to, and adjust the inspection route of the inspection equipment; Step S304: Whenever the inspection device inspects any photovoltaic power station, the expected risk value of each of the remaining photovoltaic power stations is calculated, and the inspection route of the inspection device is corrected in real time; Step S400: For any photovoltaic power station, when the inspection equipment returns for secondary inspection, the real-time evaluation result of the photovoltaic power station is obtained, and the difference is compared with each real-time corrected evaluation result; based on the difference comparison result, the photovoltaic power station is identified as abnormal and feedback is given to the staff.

2. According to a big data-based distributed photovoltaic power station fire alarm method according to claim 1, it is characterized by: The step S100 includes the following steps: Step S101: Whenever the inspection equipment is dispatched to inspect each photovoltaic power station, the real-time location of the inspection equipment and the location of each photovoltaic power station are obtained, the connection status between each photovoltaic power station is obtained, and an inspection route that includes all photovoltaic power stations and has the smallest total route length is selected and input into the inspection equipment to start the inspection; Step S102: when any photovoltaic power station is inspected during the inspection process, the inspection data generated by the photovoltaic power station during the inspection process is recorded and transmitted to the inspection data management system for storage, thereby generating an inspection record of the photovoltaic power station; Step S103: Divide the test data recorded in any test record into data sets of several dimensions according to the data source, set a risk assessment rule for each dimension, obtain the risk value of each dimension, and accumulate the risk values ​​of all dimensions to obtain the risk value of the test record.

3. According to a distributed photovoltaic power station fire alarm method based on big data as described in claim 2, it is characterized by: The step S200 includes the following steps: Step S201: selecting one detection record of any two photovoltaic power stations from the inspection data management system, extracting detection data between the two selected detection records for any dimension, performing similarity comparison on the detection data of the dimension, setting a similarity threshold, and if the obtained similarity exceeds the similarity threshold, setting it as a feature comparison of the dimension; Step S202: performing a similarity comparison on each detection record between the two photovoltaic power stations with respect to the dimension, and counting the number of feature comparisons n of the dimension. com , calculate the feature frequency ratio of the dimension α=n com / (a1×a2), where a1 is the number of detection records of one PV power station, and a2 is the number of detection records of another PV power station; a threshold α is set max , if α>α max , then the dimension is set as a common feature of the two photovoltaic power stations; the common feature set between any photovoltaic power station and the other photovoltaic power stations is extracted and stored in the inspection device; Step S203: Whenever the inspection device inspects any photovoltaic power station and generates a corresponding inspection record, the inspection record is stored in the inspection device, and when the inspection device inspects the remaining photovoltaic power stations according to the inspection route, the photovoltaic power station currently inspected by the inspection device is set as the real-time photovoltaic power station, and the same feature set between the photovoltaic power station and the real-time photovoltaic power station is extracted; Step S204: extract the detection data corresponding to the same feature set of the photovoltaic power station from the inspection equipment, transmit all the extracted detection data to the real-time photovoltaic power station, and obtain the risk value of each same feature of the photovoltaic power station in the real-time photovoltaic power station; obtain the risk value of other dimensions of the photovoltaic power station except the same feature, according to the formula: ； Wherein, i and j are both positive integers and i∈(1,c), j∈(1,d), c is the number of identical features, d is the number of remaining dimensions in the photovoltaic power station excluding identical features, (F i ) ’ is the risk value of the i-th same characteristic, F j is the risk value of the jth dimension of the photovoltaic power station excluding the same features; and the risk value F presented by the detection data of the photovoltaic power station in the real-time photovoltaic power station is calculated. ’ .

4. According to a big data-based distributed photovoltaic power station fire alarm method according to claim 1, it is characterized by: The step S400 includes the following steps: Step S401: arbitrarily select the pth photovoltaic power station, and when the inspection device returns to the pth photovoltaic power station, obtain each photovoltaic power station detected by the inspection device between two adjacent detection records of the pth photovoltaic power station, and generate a photovoltaic power station set; Step S402: arbitrarily select the u-th photovoltaic power station from the photovoltaic power station set, and obtain the unit loss value η of the u-th photovoltaic power station p , and the risk value presented by the p-th photovoltaic power station in the u-th photovoltaic power station is (F pu ) ’ ; Count the number of identical features M in the identical feature set between the p-th photovoltaic power station and the u-th photovoltaic power station pu , the similarity between the p-th photovoltaic power station and the u-th photovoltaic power station is calculated to be τ pu =M pu / M, where M is the total number of dimensions of any photovoltaic power station; according to the formula: ； Wherein, u1 is a positive integer and u1∈(1,x), x is the number of photovoltaic power stations in the photovoltaic power station set, T pu is the travel time between the p-th photovoltaic power station and the u-th photovoltaic power station, τ p,u1 is the similarity between the p-th photovoltaic power station and the u1-th photovoltaic power station; the expected risk value (F p ) comp ; Step S403: Obtain the detection data of the p-th photovoltaic power station in various dimensions, conduct real-time evaluation on the p-th photovoltaic power station, and calculate the real-time risk value of the p-th photovoltaic power station as (F p ) ac ; Set a risk difference ratio threshold δ, if |(F p ) comp -(F p ) ac | / (F p ) ac >δ, an abnormal reminder will be issued to the pth PV power station and feedback will be given to the staff.

5. A distributed photovoltaic power station fire alarm system, used to execute a distributed photovoltaic power station fire alarm method based on big data as claimed in any one of claims 1 to 4, characterized in that: The alarm system includes a power station inspection assessment module, a risk assessment correction module, an inspection route adjustment module and an abnormal power station identification module; The power station inspection and assessment module is used to preset inspection routes in the inspection equipment to inspect each photovoltaic power station, build an inspection data management system to record each inspection process of each photovoltaic power station, and generate inspection records of each photovoltaic power station; based on the inspection situation presented in any inspection record, perform risk assessment on the corresponding photovoltaic power station; The risk assessment correction module is used to analyze the differences between the detection records and extract the same features between different photovoltaic power stations; transmit the detection data of each same feature of any photovoltaic power station to the inspection equipment, perform a secondary assessment when inspecting other photovoltaic power stations, and correct the risk assessment of the corresponding detection records in real time; The inspection route adjustment module is used to extract the revised assessment results of the remaining photovoltaic power stations in the photovoltaic power station and obtain the latest maintenance records stored in the remaining photovoltaic power stations to obtain the expected risk values ​​of the remaining photovoltaic power stations whenever the inspection equipment inspects any photovoltaic power station; Adjust the inspection routes in the inspection equipment based on the expected risk value of each PV power station; The abnormal power station identification module is used to obtain the real-time evaluation results of any photovoltaic power station when the inspection equipment returns for secondary inspection, and compare the differences with the various real-time corrected evaluation results; based on the difference comparison results, the abnormality of the photovoltaic power station is identified and feedback is provided to the staff.

6. A distributed photovoltaic power station fire alarm system according to claim 5, characterized in that: The power station inspection and assessment module includes an inspection data acquisition unit and a power station risk assessment unit; The inspection data acquisition unit is used to preset inspection routes in the inspection equipment to inspect each photovoltaic power station, build an inspection data management system to record each inspection process of each photovoltaic power station, and generate inspection records of each photovoltaic power station; the power station risk assessment unit is used to perform risk assessment on the corresponding photovoltaic power station based on the inspection situation presented in any inspection record.

7. A distributed photovoltaic power station fire alarm system according to claim 5, characterized in that: The risk assessment correction module includes a common feature extraction unit and a risk assessment correction unit; The same feature extraction unit is used to analyze the differences between the detection records and extract the same features between different photovoltaic power stations; The risk assessment correction unit is used to transmit the detection data of each identical feature of any photovoltaic power station to the inspection device, perform a secondary assessment when inspecting other photovoltaic power stations, and correct the risk assessment of the corresponding detection record in real time.

8. A distributed photovoltaic power station fire alarm system according to claim 5, characterized in that: The inspection route adjustment module includes an expected risk prediction unit and an inspection sequence setting unit; The expected risk prediction unit is used to extract the revised assessment results of the remaining photovoltaic power stations in the photovoltaic power station and obtain the latest maintenance records stored in the remaining photovoltaic power stations to obtain the expected risk values ​​of the remaining photovoltaic power stations whenever the inspection equipment inspects any photovoltaic power station; The inspection sequence setting unit is used to adjust the inspection route in the inspection device based on the expected risk value of each photovoltaic power station.

9. A distributed photovoltaic power station fire alarm system according to claim 5, characterized in that: The abnormal power station identification module includes an inspection feedback comparison unit and a feedback abnormality judgment unit; The inspection feedback comparison unit is used to obtain the real-time evaluation result of any photovoltaic power station when the inspection equipment returns for secondary inspection, and compare the difference with each real-time corrected evaluation result; The feedback abnormality judgment unit is used to identify abnormalities of the photovoltaic power station based on the difference comparison result and provide feedback to the staff.

Images