Photovoltaic power station intelligent fire-fighting early warning method based on Internet of Things

The intelligent fire warning method for photovoltaic power stations uses IoT-based monitoring and sub-warning models to improve fire risk prediction and ensure timely warnings, addressing the lack of effective fire safety in existing systems.

CN119091558AInactive Publication Date: 2024-12-06HUANENG GEERMU PHOTOVOLTAIC POWER GENERATION CO LTD
View PDF 0 Cites 2 Cited by

Patent Information

Application Number
CN202410974746.6
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-19
Publication Date
2024-12-06
Estimated Expiration
Not applicable · inactive patent

AI Technical Summary

Technical Problem

Existing fire safety systems in photovoltaic power stations fail to provide timely warnings for fire risks, leading to potential personal and property losses.

Method used

Implementing an intelligent fire warning method based on the Internet of Things, which establishes multiple equipment monitoring points, generates sub-warning models using historical fire parameters, and issues early warnings based on real-time data comparisons and trend analysis.

Benefits of technology

Enhances fire risk prediction accuracy and efficiency, ensuring timely warnings and safe operation of photovoltaic power stations by correcting fire warnings through real-time parameter comparisons and historical trend analysis.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119091558A_ABST
    Figure CN119091558A_ABST
Patent Text Reader

Abstract

The invention relates to the technical field of photovoltaic power station fire protection, in particular to a photovoltaic power station intelligent fire protection early warning method based on the Internet of Things. Comprising the following steps: generating a plurality of equipment monitoring points according to all equipment parameters of a photovoltaic power station, and establishing an electronic monitoring map according to all the equipment monitoring points; generating a sub-early warning model according to the historical fire parameters, and generating a fire risk value of each equipment monitoring point according to a preset feedback time node; judging whether an early warning instruction of each equipment monitoring point is generated or not according to the fire risk value; a plurality of equipment monitoring points in the photovoltaic power station are established based on the Internet of Things technology, equipment which is prone to fire disasters in the photovoltaic power station is comprehensively monitored, the real-time operation state of each equipment monitoring point is judged by periodically feeding back operation data, early warning is timely performed on possible or re-occurring risks, and safe operation of the photovoltaic power station is ensured.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of fire protection technology for photovoltaic power stations, and in particular to an intelligent fire protection early warning method for photovoltaic power stations based on the Internet of Things. Background Art

[0002] As a clean energy in the 21st century, solar energy has the advantages of being renewable, environmentally friendly and pollution-free and having huge development potential. Photovoltaic power stations are currently the most important form of solar energy resources in the world, among which distributed photovoltaic power stations are developing rapidly in my country's photovoltaic power generation field.

[0003] However, since distributed photovoltaic power stations are widely used in densely populated industrial areas and crowded areas, their fire safety needs to be paid more attention to. In recent years, various power station fire incidents have deeply warned the importance of fire safety in photovoltaic power stations, but existing technologies cannot achieve timely warning of fire risks in photovoltaic power stations, which may cause immeasurable personal and property losses. Summary of the invention

[0004] The purpose of this application is: to solve the above technical problems, this application provides a photovoltaic power station intelligent fire warning method based on the Internet of Things, aiming to improve the fire warning efficiency of photovoltaic power stations and reduce the fire risk of photovoltaic power stations.

[0005] In some embodiments of the present application, multiple equipment monitoring points are established within a photovoltaic power station based on the Internet of Things technology, and equipment that is prone to fire inside the photovoltaic power station is comprehensively monitored. By periodically feeding back operating data, the real-time operating status of each equipment monitoring point is determined, and early warnings are issued in a timely manner for possible or recurring risks, thereby ensuring the safe operation of the photovoltaic power station.

[0006] In some embodiments of the present application, by traversing the historical fire parameters of the photovoltaic power station, early warning sub-models for different categories of equipment are established, and for the equipment categories that have had fire problems, the corresponding fire characteristic parameters are extracted, and the corresponding first-level early warning sub-model is established. By comparing with the real-time parameters of the remaining equipment in the same category, fire warning correction is performed to improve the prediction accuracy of the fire risk of each equipment monitoring point.

[0007] In some embodiments of the present application, for equipment categories that have not experienced fire problems, a universal secondary warning sub-model is established by extracting features from historical fire parameters, and the influencing factors of the corresponding monitoring indicators are corrected according to different equipment categories. At the same time, based on the timing principle, the fluctuation trend of each monitoring indicator is extracted, and fire warning correction is performed, thereby improving the efficiency of fire warning and ensuring the safe operation of the photovoltaic power station.

[0008] In some embodiments of the present application, a photovoltaic power station intelligent fire warning method based on the Internet of Things is provided, including:

[0009] Generate multiple equipment monitoring points based on all equipment parameters of the photovoltaic power station, and establish an electronic monitoring map based on all equipment monitoring points;

[0010] Generate a sub-warning model based on historical fire parameters, and generate fire risk values ​​for each equipment monitoring point based on preset feedback time nodes;

[0011] Determine whether to generate early warning instructions for each equipment monitoring point based on the fire risk value;

[0012] Among them, when establishing an electronic monitoring map, it includes:

[0013] Generate a device monitoring point sequence A, A = (a1, a2...an), where ai is the i-th device monitoring point and n is the number of device monitoring points;

[0014] Obtain the location parameters of all equipment monitoring points;

[0015] Establish electronic monitoring maps.

[0016] In some embodiments of the present application, when generating a sub-warning model, it includes:

[0017] Generate a device category sequence B, B = (b1, b2...b n1 ), where b i is the i-th type of equipment, n1 is the number of equipment categories, and n1<n;

[0018] Traverse all equipment monitoring points and establish an equipment monitoring point-equipment category mapping table;

[0019] Select the target device category in sequence according to the device category sequence B;

[0020] Determine whether there is a fire record of the current target equipment category in the historical fire parameters;

[0021] If it exists, the first-level fire characteristic parameters of the target equipment category are generated according to the fire record, and the first-level sub-warning model of the target equipment category is established according to the first-level fire characteristic parameters;

[0022] If it does not exist, generate secondary fire characteristic parameters according to historical fire parameters, and establish a secondary sub-warning model of the target equipment category according to the secondary fire characteristic parameters;

[0023] Generate sub-warning models of equipment categories in sequence;

[0024] Establish the sub-warning model series C, C = (c1, c2...c n1 ), where c i is the sub-warning model of the i-th equipment category.

[0025] In some embodiments of the present application, when generating the fire risk value of each equipment monitoring point, it includes:

[0026] Select the target equipment monitoring points in sequence according to the equipment monitoring point number sequence A;

[0027] Generate a monitoring evaluation value g of the target equipment monitoring point;

[0028] Set the feedback time node of the target equipment monitoring point according to the monitoring evaluation value;

[0029] Call the corresponding target sub-warning model according to the equipment category of the target equipment monitoring point;

[0030] If the target sub-warning model is a first-level sub-warning model, a first-level processing instruction is generated;

[0031] If the target sub-warning model is a secondary sub-warning model, a secondary processing instruction is generated;

[0032] Generate the fire risk value f of the target monitoring point according to the preset feedback time node;

[0033] A fire risk value series F is established, where F = (f1, f2...fn), where fi is the fire risk value of the i-th equipment monitoring point.

[0034] In some embodiments of the present application, when generating a monitoring evaluation value of a monitoring point of a target device, the process includes:

[0035] Obtain equipment parameters and historical operating parameters of target equipment monitoring points;

[0036] Generate a monitoring evaluation value g according to a preset equipment evaluation model;

[0037]

[0038] Among them, e1 is the preset first fixed coefficient; e2 is the preset second fixed coefficient; hi is the reference value of the i-th equipment evaluation index; βi is the influencing factor of the i-th equipment evaluation index; n2 is the number of equipment evaluation indicators; ji is the reference value of the i-th historical evaluation index; μi is the influencing factor of the i-th historical evaluation index; n3 is the number of historical evaluation indicators.

[0039] In some embodiments of the present application, when determining whether to generate an early warning instruction for each device monitoring point, the process includes:

[0040] Presetting a first fire risk value interval (F1, F2) and a second fire risk assessment value interval (F2, F3);

[0041] If fi is in the preset first fire risk assessment value interval, the i-th equipment monitoring point generates a first-level warning instruction;

[0042] If fi is in the preset second fire risk assessment value interval, the i-th equipment monitoring point generates a second-level warning instruction.

[0043] In some embodiments of the present application, the primary processing instruction includes:

[0044] According to the target sub-warning model, the first-level monitoring indicator series Q of the target monitoring point is established, Q = (q1, q2…q m1 ), where qi is the i-th first-level monitoring indicator of the target equipment monitoring point; m1 is the number of first-level monitoring indicators;

[0045] Acquire the real-time monitoring parameters of the target equipment monitoring point according to the preset feedback time node, and generate the real-time reference value of each first-level monitoring indicator of the target monitoring point;

[0046] Obtain the real-time monitoring parameters of all equipment monitoring points of the same equipment category as the target equipment monitoring point, and generate the corrected average value of each first-level monitoring indicator.

[0047] In some embodiments of the present application, the primary processing instruction further includes:

[0048] Generate the fire risk value f of the target equipment monitoring point based on the deviation-corrected average value and real-time reference value of each primary monitoring indicator;

[0049]

[0050] Among them, e3 is the preset third fixed coefficient; e4 is the preset fourth fixed coefficient; ki is the influencing factor of the i-th first-level monitoring indicator of the target monitoring point; di is the real-time reference value of the i-th first-level monitoring indicator of the target monitoring point; d'i is the standard value of the i-th first-level monitoring indicator of the target monitoring point; △di is the corrected average value of the i-th first-level monitoring indicator.

[0051] In some embodiments of the present application, the secondary processing instruction includes:

[0052] Get the secondary monitoring indicator series P, P = (p1, p2...p m2 ), where pi is the i-th secondary monitoring indicator; m2 is the number of secondary monitoring indicators;

[0053] Obtain real-time monitoring parameters and historical monitoring parameters of the target equipment monitoring point according to the preset feedback time node;

[0054] Generate real-time reference values ​​of each secondary monitoring indicator of the target equipment monitoring point according to the real-time monitoring parameters;

[0055] Generate fluctuation evaluation values ​​of each secondary monitoring indicator of the target equipment monitoring point based on historical monitoring parameters.

[0056] In some embodiments of the present application, the secondary processing instruction further includes:

[0057] Generate a fire risk value f based on the real-time reference value and fluctuation evaluation value of each secondary monitoring indicator of the target equipment monitoring point;

[0058]

[0059] Among them, e5 is the preset fifth fixed coefficient, e6 is the preset sixth fixed coefficient; ri is the influencing factor of the i-th secondary monitoring indicator of the target equipment monitoring point; ti is the real-time reference value of the i-th secondary monitoring indicator of the target equipment monitoring point; t'i is the standard value of the i-th secondary monitoring indicator of the target equipment monitoring point; yi is the fluctuation evaluation value of the i-th secondary monitoring indicator of the target equipment monitoring point.

[0060] Compared with the prior art, the photovoltaic power station intelligent fire warning method based on the Internet of Things in the embodiment of the present application has the following beneficial effects:

[0061] Based on the Internet of Things technology, multiple equipment monitoring points are established within the photovoltaic power station to conduct comprehensive monitoring of the fire-prone equipment inside the photovoltaic power station. By periodically feeding back operating data, the real-time operating status of each equipment monitoring point is determined, and timely warnings are issued for possible or recurring risks to ensure the safe operation of the photovoltaic power station.

[0062] By traversing the historical fire parameters of the photovoltaic power station, early warning sub-models for different types of equipment are established. For the equipment categories that have had fire problems, the corresponding fire characteristic parameters are extracted, and the corresponding first-level early warning sub-model is established. By comparing the real-time parameters with the remaining equipment of the same category, fire early warning correction is carried out to improve the prediction accuracy of fire risks at each equipment monitoring point.

[0063] For equipment categories that have never experienced fire problems, a universal secondary warning sub-model is established by extracting features from historical fire parameters. The influencing factors of the corresponding monitoring indicators are corrected according to different equipment categories. At the same time, based on the time series principle, the fluctuation trend of each monitoring indicator is extracted to correct the fire warning, thereby improving the efficiency of fire warning and ensuring the safe operation of photovoltaic power stations. BRIEF DESCRIPTION OF THE DRAWINGS

[0064] Figure 1 It is a flow chart of a photovoltaic power station intelligent fire warning method based on the Internet of Things in the preferred embodiment of the present application. DETAILED DESCRIPTION

[0065] The specific implementation methods of the present application are further described in detail below in conjunction with the accompanying drawings and examples. The following examples are used to illustrate the present application but are not intended to limit the scope of the present application.

[0066] In the description of the present application, it should be understood that the terms "center", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", etc., indicating orientations or positional relationships, are based on the orientations or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as a limitation on the present application.

[0067] The terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of this application, unless otherwise specified, "plurality" means two or more.

[0068] In the description of this application, it should be noted that, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in this application can be understood according to specific circumstances.

[0069] like Figure 1 As shown, a photovoltaic power station intelligent fire warning method based on the Internet of Things in a preferred embodiment of the present application includes:

[0070] S101: Generate multiple equipment monitoring points according to all equipment parameters of the photovoltaic power station, and establish an electronic monitoring map according to all equipment monitoring points;

[0071] S102: Generate a sub-warning model based on historical fire parameters, and generate a fire risk value for each device monitoring point based on a preset feedback time node;

[0072] S103: judging whether to generate early warning instructions for each equipment monitoring point according to the fire risk value;

[0073] Among them, when establishing an electronic monitoring map, it includes:

[0074] Generate a device monitoring point sequence A, A = (a1, a2...an), where ai is the i-th device monitoring point and n is the number of device monitoring points;

[0075] Obtain the location parameters of all equipment monitoring points;

[0076] Establish electronic monitoring maps.

[0077] Specifically, when generating a sub-warning model, it includes:

[0078] Generate a device category sequence B, B = (b1, b2...b n1 ), where b i is the i-th type of equipment, n1 is the number of equipment categories, and n1<n;

[0079] Traverse all equipment monitoring points and establish an equipment monitoring point-equipment category mapping table;

[0080] Select the target device category in sequence according to the device category sequence B;

[0081] Determine whether there is a fire record of the current target equipment category in the historical fire parameters;

[0082] If it exists, the first-level fire characteristic parameters of the target equipment category are generated according to the fire record, and the first-level sub-warning model of the target equipment category is established according to the first-level fire characteristic parameters;

[0083] If it does not exist, generate secondary fire characteristic parameters according to historical fire parameters, and establish a secondary sub-warning model of the target equipment category according to the secondary fire characteristic parameters;

[0084] Generate sub-warning models of equipment categories in sequence;

[0085] Establish the sub-warning model series C, C = (c1, c2...c n1 ), where c i is the sub-warning model of the i-th equipment category.

[0086] Specifically, corresponding equipment monitoring points are established for equipment that is prone to fire in photovoltaic power stations, including but not limited to: photovoltaic modules, combiner boxes, inverters, step-up transformers, collection stations, power cables, etc.

[0087] Specifically, all equipment categories are generated according to the equipment types of different equipment monitoring points, and the equipment category of each equipment monitoring point is determined by establishing an equipment monitoring point-equipment category mapping table.

[0088] Specifically, by extracting characteristic parameters, a sub-warning model for each equipment category is established, and equipment monitoring points of the same category share the same sub-warning model.

[0089] In a preferred embodiment of the present application, when generating the fire risk value of each equipment monitoring point, it includes:

[0090] Select the target equipment monitoring points in sequence according to the equipment monitoring point number sequence A;

[0091] Generate a monitoring evaluation value g of the target equipment monitoring point;

[0092] Set the feedback time node of the target equipment monitoring point according to the monitoring evaluation value;

[0093] Call the corresponding target sub-warning model according to the equipment category of the target equipment monitoring point;

[0094] If the target sub-warning model is a first-level sub-warning model, a first-level processing instruction is generated;

[0095] If the target sub-warning model is a secondary sub-warning model, a secondary processing instruction is generated;

[0096] Generate the fire risk value f of the target monitoring point according to the preset feedback time node;

[0097] A fire risk value series F is established, where F = (f1, f2...fn), where fi is the fire risk value of the i-th equipment monitoring point.

[0098] Specifically, when generating the monitoring evaluation value of the target equipment monitoring point, it includes:

[0099] Obtain equipment parameters and historical operating parameters of target equipment monitoring points;

[0100] Generate a monitoring evaluation value g according to a preset equipment evaluation model;

[0101]

[0102] Among them, e1 is the preset first fixed coefficient; e2 is the preset second fixed coefficient; hi is the reference value of the i-th equipment evaluation index; βi is the influencing factor of the i-th equipment evaluation index; n2 is the number of equipment evaluation indicators; ji is the reference value of the i-th historical evaluation index; μi is the influencing factor of the i-th historical evaluation index; n3 is the number of historical evaluation indicators.

[0103] Specifically, equipment evaluation indicators include but are not limited to parameters such as equipment type, equipment importance, equipment impact range, location distance between equipment and fire-fighting points, types of fires caused by equipment, and difficulty of equipment fire extinguishing.

[0104] Specifically, historical operating parameters include, but are not limited to, the number of equipment fires, abnormal equipment fluctuations, and other parameters.

[0105] Specifically, by presetting the first fixed coefficient and the second fixed coefficient, all evaluation indicators are normalized so that different evaluation indicators are in the same value range.

[0106] Specifically, the larger the monitoring evaluation value, the more important the current equipment monitoring point is, and the smaller the time monitoring between the corresponding feedback time nodes is, ensuring that the fire risk of each equipment monitoring point can be warned in time to ensure the safe operation of the photovoltaic power station.

[0107] Specifically, when determining whether to generate an early warning instruction for each equipment monitoring point, it includes:

[0108] Presetting a first fire risk value interval (F1, F2) and a second fire risk assessment value interval (F2, F3);

[0109] If fi is in the preset first fire risk assessment value interval, the i-th equipment monitoring point generates a first-level warning instruction;

[0110] If fi is in the preset second fire risk assessment value interval, the i-th equipment monitoring point generates a second-level warning instruction.

[0111] Specifically, the first-level warning instruction means that the current equipment monitoring point has an operating abnormality and needs to be repaired in time. The second-level warning instruction means that the current equipment monitoring point has a potential failure risk and needs to be repaired and eliminated immediately.

[0112] In a preferred embodiment of the present application, the first-level processing instructions include:

[0113] According to the target sub-warning model, the first-level monitoring indicator series Q of the target monitoring point is established, Q = (q1, q2…q m1 ), where qi is the i-th first-level monitoring indicator of the target equipment monitoring point; m1 is the number of first-level monitoring indicators;

[0114] Acquire the real-time monitoring parameters of the target equipment monitoring point according to the preset feedback time node, and generate the real-time reference value of each first-level monitoring indicator of the target monitoring point;

[0115] Obtain the real-time monitoring parameters of all equipment monitoring points of the same equipment category as the target equipment monitoring point, and generate the corrected average value of each first-level monitoring indicator.

[0116] Specifically, the first-level processing instructions also include:

[0117] Generate the fire risk value f of the target equipment monitoring point based on the deviation-corrected average value and real-time reference value of each primary monitoring indicator;

[0118]

[0119] Among them, e3 is the preset third fixed coefficient; e4 is the preset fourth fixed coefficient; ki is the influencing factor of the i-th first-level monitoring indicator of the target monitoring point; di is the real-time reference value of the i-th first-level monitoring indicator of the target monitoring point; d'i is the standard value of the i-th first-level monitoring indicator of the target monitoring point; △di is the corrected average value of the i-th first-level monitoring indicator.

[0120] Specifically, the correction average value refers to the average value of the real-time reference values ​​of the first-level monitoring indicators of all equipment monitoring points of the same equipment category. By generating the correction average value, the accumulated errors of each first-level monitoring indicator are corrected.

[0121] Specifically, the sub-warning model is normalized by presetting the third fixed coefficient and the fourth fixed coefficient.

[0122] It can be understood that in the above embodiment, for the equipment category that has had fire problems, the corresponding fire characteristic parameters are extracted, and the corresponding first-level warning sub-model is established. By comparing the real-time parameters with the remaining equipment of the same category, fire warning correction is performed to improve the prediction accuracy of the fire risk of each equipment monitoring point.

[0123] In a preferred embodiment of the present application, the secondary processing instructions include:

[0124] Get the secondary monitoring indicator series P, P = (p1, p2...p m2 ), where pi is the i-th secondary monitoring indicator; m2 is the number of secondary monitoring indicators;

[0125] Obtain real-time monitoring parameters and historical monitoring parameters of the target equipment monitoring point according to the preset feedback time node;

[0126] Generate real-time reference values ​​of each secondary monitoring indicator of the target equipment monitoring point according to the real-time monitoring parameters;

[0127] Generate fluctuation evaluation values ​​of each secondary monitoring indicator of the target equipment monitoring point based on historical monitoring parameters.

[0128] Specifically, secondary processing instructions also include:

[0129] Generate a fire risk value f based on the real-time reference value and fluctuation evaluation value of each secondary monitoring indicator of the target equipment monitoring point;

[0130]

[0131] Among them, e5 is the preset fifth fixed coefficient, e6 is the preset sixth fixed coefficient; ri is the influencing factor of the i-th secondary monitoring indicator of the target equipment monitoring point; ti is the real-time reference value of the i-th secondary monitoring indicator of the target equipment monitoring point; t'i is the standard value of the i-th secondary monitoring indicator of the target equipment monitoring point; yi is the fluctuation evaluation value of the i-th secondary monitoring indicator of the target equipment monitoring point.

[0132] Specifically, the sub-warning module is normalized by presetting the fifth fixed coefficient and the sixth fixed coefficient.

[0133] Specifically, the larger the fluctuation evaluation value is, the greater the change trend of the corresponding secondary monitoring indicator in the current monitoring cycle is, that is, the worse the operating stability of the current equipment monitoring point is.

[0134] It can be understood that in the above embodiment, for equipment categories that have not experienced fire problems, feature extraction of historical fire parameters is performed to establish a universal secondary warning sub-model, and the influencing factors of the corresponding monitoring indicators are corrected according to different equipment categories. At the same time, based on the time series principle, the fluctuation trend of each monitoring indicator is extracted to perform fire warning correction, thereby improving the efficiency of fire warning and ensuring the safe operation of the photovoltaic power station.

[0135] According to the first concept of the present application, multiple equipment monitoring points are established within the photovoltaic power station based on the Internet of Things technology, and comprehensive monitoring is carried out on the equipment that is prone to fire inside the photovoltaic power station. By periodically feeding back operating data, the real-time operating status of each equipment monitoring point is determined, and timely warnings are issued for possible or recurring risks to ensure the safe operation of the photovoltaic power station.

[0136] According to the second concept of the present application, by traversing the historical fire parameters of the photovoltaic power station, early warning sub-models for different categories of equipment are established. For the equipment categories that have had fire problems, the corresponding fire characteristic parameters are extracted, and the corresponding first-level early warning sub-model is established. By comparing with the real-time parameters of the remaining equipment in the same category, fire warning correction is performed to improve the prediction accuracy of the fire risk of each equipment monitoring point.

[0137] According to the third concept of the present application, for equipment categories that have never had fire problems, a universal secondary warning sub-model is established by extracting features from historical fire parameters, and the influencing factors of the corresponding monitoring indicators are corrected according to different equipment categories. At the same time, based on the time series principle, the fluctuation trend of each monitoring indicator is extracted, and fire warning correction is performed, thereby improving the efficiency of fire warning and ensuring the safe operation of photovoltaic power stations.

[0138] The above is only a preferred implementation of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and substitutions can be made without departing from the technical principles of the present application. These improvements and substitutions should also be regarded as the scope of protection of the present application.

Claims

1. A photovoltaic power station intelligent fire warning method based on the Internet of Things, characterized in that: include: Generate multiple equipment monitoring points based on all equipment parameters of the photovoltaic power station, and establish an electronic monitoring map based on all equipment monitoring points; Generate a sub-warning model based on historical fire parameters, and generate fire risk values ​​for each equipment monitoring point based on preset feedback time nodes; Determine whether to generate early warning instructions for each equipment monitoring point based on the fire risk value; Among them, when establishing an electronic monitoring map, it includes: Generate a device monitoring point sequence A, A = (a1, a2...an), where ai is the i-th device monitoring point and n is the number of device monitoring points; Obtain the location parameters of all equipment monitoring points; Establish electronic monitoring maps.

2. The photovoltaic power station intelligent fire warning method based on the Internet of Things as claimed in claim 1 is characterized in that: When generating a sub-warning model, it includes: Generate a device category sequence B, B = (b1, b2...b n1 ), where b i is the i-th type of equipment, n1 is the number of equipment categories, and n1<n; Traverse all equipment monitoring points and establish an equipment monitoring point-equipment category mapping table; Select the target device category in sequence according to the device category sequence B; Determine whether there is a fire record of the current target equipment category in the historical fire parameters; If it exists, the first-level fire characteristic parameters of the target equipment category are generated according to the fire record, and the first-level sub-warning model of the target equipment category is established according to the first-level fire characteristic parameters; If it does not exist, generate secondary fire characteristic parameters according to historical fire parameters, and establish a secondary sub-warning model of the target equipment category according to the secondary fire characteristic parameters; Generate sub-warning models of equipment categories in sequence; Establish the sub-warning model series C, C = (c1, c2...c n1 ), where c i is the sub-warning model of the i-th equipment category.

3. The photovoltaic power station intelligent fire warning method based on the Internet of Things as claimed in claim 2 is characterized in that: When generating the fire risk value for each equipment monitoring point, it includes: Select the target equipment monitoring points in sequence according to the equipment monitoring point number sequence A; Generate a monitoring evaluation value g of the target equipment monitoring point; Set the feedback time node of the target equipment monitoring point according to the monitoring evaluation value; Call the corresponding target sub-warning model according to the equipment category of the target equipment monitoring point; If the target sub-warning model is a first-level sub-warning model, a first-level processing instruction is generated; If the target sub-warning model is a secondary sub-warning model, a secondary processing instruction is generated; Generate the fire risk value f of the target monitoring point according to the preset feedback time node; A fire risk value series F is established, where F = (f1, f2...fn), where fi is the fire risk value of the i-th equipment monitoring point.

4. The photovoltaic power station intelligent fire warning method based on the Internet of Things as claimed in claim 3 is characterized in that: When generating the monitoring evaluation value of the target equipment monitoring point, it includes: Obtain equipment parameters and historical operating parameters of target equipment monitoring points; Generate a monitoring evaluation value g according to a preset equipment evaluation model; Among them, e1 is the preset first fixed coefficient; e2 is the preset second fixed coefficient; hi is the reference value of the i-th equipment evaluation index; βi is the influencing factor of the i-th equipment evaluation index; n2 is the number of equipment evaluation indicators; ji is the reference value of the i-th historical evaluation index; μi is the influencing factor of the i-th historical evaluation index; n3 is the number of historical evaluation indicators.

5. The photovoltaic power station intelligent fire warning method based on the Internet of Things as claimed in claim 4, characterized in that: When judging whether to generate early warning instructions for each equipment monitoring point, it includes: Presetting a first fire risk value interval (F1, F2) and a second fire risk assessment value interval (F2, F3); If fi is in the preset first fire risk assessment value interval, the i-th equipment monitoring point generates a first-level warning instruction; If fi is in the preset second fire risk assessment value interval, the i-th equipment monitoring point generates a second-level warning instruction.

6. The photovoltaic power station intelligent fire warning method based on the Internet of Things as claimed in claim 5, characterized in that: The first-level processing instructions include: According to the target sub-warning model, the first-level monitoring indicator series Q of the target monitoring point is established, Q = (q1, q2…q m1 ), where qi is the i-th first-level monitoring indicator of the target equipment monitoring point; m1 is the number of first-level monitoring indicators; Acquire the real-time monitoring parameters of the target equipment monitoring point according to the preset feedback time node, and generate the real-time reference value of each first-level monitoring indicator of the target monitoring point; Obtain the real-time monitoring parameters of all equipment monitoring points of the same equipment category as the target equipment monitoring point, and generate the corrected average value of each first-level monitoring indicator.

7. The photovoltaic power station intelligent fire warning method based on the Internet of Things as claimed in claim 6, characterized in that: The first-level processing instruction also includes: Generate the fire risk value f of the target equipment monitoring point based on the deviation-corrected average value and real-time reference value of each primary monitoring indicator; Among them, e3 is the preset third fixed coefficient; e4 is the preset fourth fixed coefficient; ki is the influencing factor of the i-th first-level monitoring indicator of the target monitoring point; di is the real-time reference value of the i-th first-level monitoring indicator of the target monitoring point; d'i is the standard value of the i-th first-level monitoring indicator of the target monitoring point; △di is the corrected average value of the i-th first-level monitoring indicator.

8. The photovoltaic power station intelligent fire warning method based on the Internet of Things as claimed in claim 5, characterized in that: The secondary processing instructions include: Get the secondary monitoring indicator series P, P = (p1, p2...p m2 ), where pi is the i-th secondary monitoring indicator; m2 is the number of secondary monitoring indicators; Obtain real-time monitoring parameters and historical monitoring parameters of the target equipment monitoring point according to the preset feedback time node; Generate real-time reference values ​​of each secondary monitoring indicator of the target equipment monitoring point according to the real-time monitoring parameters; Generate fluctuation evaluation values ​​of each secondary monitoring indicator of the target equipment monitoring point based on historical monitoring parameters.

9. The photovoltaic power station intelligent fire warning method based on the Internet of Things as claimed in claim 8, characterized in that: The secondary processing instructions also include: Generate a fire risk value f based on the real-time reference value and fluctuation evaluation value of each secondary monitoring indicator of the target equipment monitoring point; Among them, e5 is the preset fifth fixed coefficient, e6 is the preset sixth fixed coefficient; ri is the influencing factor of the i-th secondary monitoring indicator of the target equipment monitoring point; ti is the real-time reference value of the i-th secondary monitoring indicator of the target equipment monitoring point; t'i is the standard value of the i-th secondary monitoring indicator of the target equipment monitoring point; yi is the fluctuation evaluation value of the i-th secondary monitoring indicator of the target equipment monitoring point.

Citation Information

Cited By

  • Infrared temperature measurement observation system and control method thereof

    CN119688075A

  • Photovoltaic power station fireproof early warning method and system based on inspection unmanned aerial vehicle

    CN120871964A