Intelligent fire-fighting hidden danger identification method

Abstract

The invention relates to the technical field of fire-fighting hidden danger identification, in particular to a fire-fighting hidden danger intelligent identification method. Comprising the following steps: setting a plurality of equipment points according to parameters of a to-be-inspected area, and establishing a monitoring sub-model of each equipment point; acquiring monitoring data of each equipment point, and generating a potential risk value of each equipment point; setting an inspection strategy according to all the potential risk values, obtaining feedback data according to the inspection strategy, and generating a fire-fighting hidden danger diagnosis result according to the feedback data; a plurality of monitoring points are set to carry out multi-dimensional monitoring on a to-be-inspected area, monitoring data of each monitoring point are periodically collected, the operation state of each monitoring point is accurately analyzed, a corresponding inspection strategy is set according to potential risk values of each equipment point, and manual inspection and unmanned aerial vehicle inspection technologies are combined, so that the inspection efficiency is improved. The overall inspection efficiency is improved, the inspection time and labor cost are reduced, potential fire hazards are diagnosed and early warned in time, and the diagnosis precision of the fire hazards is improved.

Description

Technical Field

[0001] The present application relates to the technical field of fire hazard identification, and in particular to a method for intelligently identifying fire hazards. Background Art

[0002] Traditional fire hazard detection methods mainly rely on equipment such as sensors, cameras and fire alarm systems to judge fire risks by monitoring temperature, smoke and image recognition.

[0003] However, these methods have problems such as low efficiency and high missed detection rate. First, they cannot achieve early prediction of fire hazards and can only issue an alarm after a fire actually occurs. Second, since they are usually based on a single sensing technology, false alarms or missed alarms may occur. Summary of the invention

[0004] The purpose of this application is: to solve the above-mentioned technical problems, this application provides a method for intelligent identification of fire hazards, aiming to improve the early warning efficiency of fire hazards and reduce the frequency of fires.

[0005] In some embodiments of the present application, multiple monitoring points are set to perform multi-dimensional monitoring of the inspection area, and the monitoring data of each monitoring point is periodically collected to accurately analyze the operating status of each monitoring point, and early warnings are issued in time for monitoring points with potential risks, thereby improving the efficiency of early warning of fire hazards and reducing the frequency of fires.

[0006] In some embodiments of the present application, corresponding inspection strategies are set according to the potential risk value of each equipment point, and manual inspection and drone inspection technology are combined to improve the overall inspection efficiency, eliminate invalid inspection work, reduce inspection time and labor costs, timely diagnose and warn of potential fire hazards, and improve the diagnostic accuracy of fire hazards.

[0007] In some embodiments of the present application, a method for intelligently identifying fire hazards is provided, comprising:

[0008] Set multiple equipment points according to the parameters of the area to be inspected, and establish a monitoring sub-model for each equipment point;

[0009] Obtain monitoring data of each equipment point and generate potential risk values ​​for each equipment point;

[0010] Set inspection strategies based on all potential risk values, obtain feedback data based on the inspection strategies, and generate fire hazard diagnosis results based on the feedback data;

[0011] When setting multiple equipment points, it includes:

[0012] Create a device point array A, A=(a 1,a 2 …a i …a n ), where a i is the i-th device point; n is the number of device points.

[0013] In some embodiments of the present application, a monitoring sub-model for each device point is established, including:

[0014] Set a in sequence according to the device point column A i is the target device point;

[0015] Generate the radiation area of ​​the target device point;

[0016] Set characteristic monitoring indicators of target equipment points according to equipment parameters in the radiation area;

[0017] Generate monitoring and evaluation values ​​based on historical parameters of the radiation area, and set the monitoring timeline of the target equipment point based on the monitoring and evaluation values;

[0018] Establish a monitoring sub-model for the target equipment point based on the monitoring timeline and all characteristic monitoring indicators;

[0019] Generate monitoring sub-models for each equipment point in turn;

[0020] Establish monitoring sub-model series B, B = (b 1 ,b 2 …b i …b n ), where b i is the monitoring sub-model of the i-th device point.

[0021] In some embodiments of the present application, generating a potential risk value for each device point includes:

[0022] Establish a potential risk value series F, F = (f 1 , f 2 …f i …f n ), where fi is the potential risk value of the i-th equipment point;

[0023] Set a in sequence according to the device point column A i is the target device point;

[0024] Set multiple monitoring time nodes according to the monitoring time axis of the target equipment point;

[0025] Obtain the monitoring data packet of the target device point at the current monitoring time node;

[0026] Generate the potential risk value f of the target device point at the current monitoring time node, and update the potential risk value series F;

[0027] Generate the potential risk values of each device point in sequence.

[0028] In some embodiments of the present application, generating the potential risk value f of the target device point at the current monitoring time node includes:

[0029]

[0030] Wherein, e1 is a preset first weight coefficient; e2 is a preset second weight coefficient; Q1 is a preset first fixed coefficient; Q2 is a preset second fixed coefficient; θ is the number of characteristic indicators of the target device point; μ i is the influence factor of the i-th characteristic indicator; j i is the reference value of the i-th characteristic indicator of the target device point at the current monitoring time node; j' i为目 is the standard reference value of the i-th characteristic indicator of the target device point; U1 is the historical reference value of the target device point at the current monitoring time node.

[0031] In some embodiments of the present application, setting the inspection strategy according to all the potential risk values includes:

[0032] Establish an inspection cycle;

[0033] Set the end time node of each inspection cycle as the inspection time node;

[0034] Set multiple time intervals within the current inspection cycle and establish a time interval sequence T;

[0035] T = (t 1 , t 2 …t i …t m ), where t i is the i-th time interval within the current inspection cycle; m is the number of time intervals within the current inspection cycle;

[0036] Generate the inspection evaluation value g of the current time interval;

[0037] Preset an inspection evaluation value threshold G1;

[0038] If g > G1, generate an inspection instruction for the current time interval and update the inspection cycle;

[0039] If g < G1, no first-level inspection instruction is generated for the current time interval;

[0040] If no first-level inspection instruction is generated within each time interval in the time interval sequence T, generate a first-level inspection instruction according to the inspection time node of the current inspection cycle;

[0041] Set the inspection strategy according to the first-level inspection instruction.

[0042] In some embodiments of the present application, generating the inspection evaluation value g of the current time interval includes:

[0043]

[0044] Among them, e3 is the preset third weight coefficient; e4 is the preset fourth weight coefficient; e5 is the preset fifth weight coefficient; Q3 is the preset third fixed coefficient; Q4 is the preset fourth fixed coefficient; Q5 is the preset fifth fixed coefficient; βi is the influencing factor of the i-th equipment point; f' is the preset first potential risk value threshold; Y(i) is the selection coefficient, if (f i -f')>0,Y(i)=1; if (f i -f')<0,Y(i)=0; U2 is a reference value generated based on the historical potential risk value in the current inspection cycle.

[0045] In some embodiments of the present application, setting an inspection strategy according to a first-level inspection instruction includes:

[0046] The potential risk value of each equipment point is obtained according to the generation time node of the first-level inspection instruction, and a real-time potential risk value series F1 is established;

[0047] F1=(f 11 , f 12 …f 1i …f 1n ), where f 1i is the potential risk value of the i-th equipment point at the generation time node of the first-level inspection instruction;

[0048] Preset a first potential risk value threshold f';

[0049] f 1i >f', set the i-th equipment point as the equipment point to be inspected;

[0050] Get all equipment points to be inspected;

[0051] Establish a list of equipment points to be inspected A1, A1 = (a 11 , a 12 …a 1i …a 1n1 ), where a 1i is the number of equipment points to be inspected; n1 is the number of equipment points to be inspected;

[0052] Establish an optimization model based on the location parameters of all equipment points to be inspected and the inspection equipment parameters;

[0053] Generate inspection strategies based on the optimization model.

[0054] In some embodiments of the present application, an inspection strategy is generated according to an optimization model, including:

[0055] Generate multiple first-level inspection plans based on the optimization model;

[0056] Establish the first-level inspection plan series D, D = (d 1 ,d 2 …d i …d n1 ), where d i is the i-th first-level inspection plan; n is the number of inspection plans;

[0057] Generate operational evaluation values ​​for each first-level inspection plan;

[0058] Establish the running evaluation value series H, H = (h 1 ,h 2 …h i …h n1 ), where h i is the operation evaluation value of the i-th first-level inspection plan;

[0059] Set the maximum value h in the running evaluation value series max The corresponding first-level inspection plan is the inspection strategy.

[0060] In some embodiments of the present application, establishing the operation evaluation value sequence H includes:

[0061] According to the first-level inspection plan sequence D, di is set as the target first-level inspection plan in sequence;

[0062] Generate the operation evaluation value h of the target first-level inspection plan;

[0063]

[0064] Among them, r is the number of evaluation indicators; η i is the influencing factor of the i-th evaluation index; k i is the reference value of the i-th evaluation index in the target first-level inspection plan;

[0065] Generate the operation evaluation value of each first-level inspection plan in sequence;

[0066] Establish a running evaluation value sequence H.

[0067] In some embodiments of the present application, generating fire hazard diagnosis results based on feedback data includes:

[0068] According to the equipment point number list A1 to be inspected, set a1 i as the target equipment point to be inspected;

[0069] Obtain feedback data from target equipment points to be inspected based on inspection strategies;

[0070] Generate sub-diagnosis results of the target equipment point to be inspected based on the processing results of the feedback data;

[0071] Generate sub-diagnosis results for each device point to be inspected in sequence;

[0072] Generate fire hazard diagnosis results based on all diagnosis results.

[0073] Compared with the prior art, the method for intelligently identifying fire hazards in the embodiment of the present application has the following beneficial effects:

[0074] By setting up multiple monitoring points to conduct multi-dimensional monitoring of the inspection area, and by periodically collecting monitoring data from each monitoring point, the operating status of each monitoring point can be accurately analyzed, and early warning can be issued in time for monitoring points with potential risks, thereby improving the efficiency of early warning of fire hazards and reducing the frequency of fires.

[0075] Set corresponding inspection strategies according to the potential risk value of each equipment point, and combine manual inspection and drone inspection technology to improve overall inspection efficiency, eliminate invalid inspection work, reduce inspection time and labor costs, and timely diagnose and warn potential fire hazards, thereby improving the diagnostic accuracy of fire hazards. BRIEF DESCRIPTION OF THE DRAWINGS

[0076] Figure 1 It is a flow chart of a method for intelligently identifying fire hazards in a preferred embodiment of the present application. DETAILED DESCRIPTION

[0077] 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.

[0078] 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.

[0079] 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.

[0080] 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.

[0081] like Figure 1 As shown, a fire hazard intelligent identification method according to a preferred embodiment of the present application includes:

[0082] S101: setting multiple equipment points according to the parameters of the area to be inspected, and establishing a monitoring sub-model for each equipment point;

[0083] S102: Acquire monitoring data of each equipment point and generate a potential risk value of each equipment point;

[0084] S103: setting an inspection strategy according to all potential risk values, obtaining feedback data according to the inspection strategy, and generating a fire hazard diagnosis result according to the feedback data;

[0085] When setting multiple equipment points, it includes:

[0086] Create a device point array A, A=(a 1 ,a 2 …a i …a n ), where a i is the i-th device point; n is the number of device points.

[0087] Specifically, multiple equipment points are set according to the fire equipment parameters and historical fire parameters in the area to be inspected, and corresponding monitoring equipment is set according to the fire hazard category of each equipment point.

[0088] Specifically, the equipment point can be a monitoring point for fire-fighting equipment or a monitoring point for areas prone to fire. Its fire hazards include, but are not limited to, missing fire-fighting equipment, high fire risk, abnormally high temperature, abnormal smoke and other categories.

[0089] Specifically, the monitoring equipment at the equipment point includes, but is not limited to, temperature sensors, smoke sensors, infrared cameras, etc., and its specific setting method can be set according to the type of fire hazard that the equipment point needs to monitor.

[0090] Specifically, a monitoring sub-model for each device point is established, including:

[0091] Set a in sequence according to the device point column A iis the target device point;

[0092] Generate the radiation area of ​​the target device point;

[0093] Set characteristic monitoring indicators of target equipment points according to equipment parameters in the radiation area;

[0094] Generate monitoring and evaluation values ​​based on historical parameters of the radiation area, and set the monitoring timeline of the target equipment point based on the monitoring and evaluation values;

[0095] Establish a monitoring sub-model for the target equipment point based on the monitoring timeline and all characteristic monitoring indicators;

[0096] Generate monitoring sub-models for each equipment point in turn;

[0097] Establish monitoring sub-model series B, B = (b 1 ,b 2 …b i …b n ), where b i is the monitoring sub-model of the i-th device point.

[0098] Specifically, the radiation area of ​​a device point refers to the area that can be monitored by the current device point. The corresponding monitoring sub-model is set according to the possible fire hazards in the radiation area, so as to achieve accurate monitoring of different areas and timely dynamic monitoring of the operating status of the radiation area of ​​each device point.

[0099] Specifically, characteristic monitoring indicators need to be set according to the types of fire hazards that may occur in the radiation area. For example, in areas where there are fire-fighting equipment, it is necessary to monitor the operating status of the fire-fighting equipment and whether it is missing and other indicator parameters. In areas where fires may occur, it is necessary to monitor temperature fluctuations and whether there is smoke and other indicator parameters.

[0100] It can be understood that in the above embodiment, different monitoring sub-models are established according to the fire hazard categories of different equipment points, so as to realize multi-dimensional monitoring of the area to be inspected, grasp the operating status of each equipment point in real time, and improve the early warning efficiency of fire hazards.

[0101] In a preferred embodiment of the present application, generating a potential risk value for each device point includes:

[0102] Establish a potential risk value series F, F = (f 1 , f 2 …f i …f n ), where fi is the potential risk value of the i-th equipment point;

[0103] Set a in sequence according to the device point column A i is the target device point;

[0104] Set multiple monitoring time nodes according to the monitoring time axis of the target equipment point;

[0105] Obtain the monitoring data packet of the target device point at the current monitoring time node;

[0106] Generate the potential risk value f of the target device point at the current monitoring time node, and update the potential risk value series F;

[0107] Generate the potential risk value of each equipment point in turn.

[0108] Specifically, the corresponding monitoring time nodes are set according to the historical parameters of each equipment point. The greater the probability of fire hazards occurring in the radiation area corresponding to the equipment point, the smaller the time interval between the corresponding monitoring time nodes.

[0109] Specifically, the monitoring time nodes of various equipment points are different. When the potential fault value of a single equipment point is updated, the real-time potential risk value series F1 needs to be updated.

[0110] Specifically, the potential risk value f of the target device point at the current monitoring time node is generated, including:

[0111]

[0112] Wherein, e1 is the preset first weight coefficient; e2 is the preset second weight coefficient; Q1 is the preset first fixed coefficient; Q2 is the preset second fixed coefficient; θ is the number of characteristic indicators of the target device point; μ i is the influencing factor of the i-th characteristic index; j i is the reference value of the i-th characteristic indicator of the target equipment point at the current monitoring time node; j' i为目 The standard reference value of the i-th characteristic indicator of the target equipment point; U1 is the historical reference value of the target equipment point at the current monitoring time node.

[0113] Specifically, all parameters in the model are normalized by presetting the first fixed coefficient and the second fixed coefficient, so that each parameter in the model is within the same value range.

[0114] Specifically, the larger the potential risk value, the greater the possibility that there are fire hazards in the radiation area corresponding to the current equipment point, and timely inspection and analysis are required to provide accurate early warning of potential fire hazards.

[0115] It is understandable that in the above embodiments, by setting multiple monitoring points to perform multi-dimensional monitoring on the area to be inspected, and by periodically collecting the monitoring data of each monitoring point, the operation status of each monitoring point is accurately analyzed, and early warnings are given to the monitoring points with potential risks in a timely manner, so as to improve the early warning efficiency for fire hazards and reduce the occurrence frequency of fires.

[0116] In the preferred embodiment of the present application, a patrol inspection strategy is set according to all potential risk values, including:

[0117] Establish a patrol inspection cycle;

[0118] Set the end time node of each patrol inspection cycle as the patrol inspection time node;

[0119] Set multiple time intervals within the current patrol inspection cycle and establish a time interval sequence T;

[0120] T=(t 1 , t 2 …t i …t m ), where t i is the i-th time interval within the current patrol inspection cycle; m is the number of time intervals within the current patrol inspection cycle;

[0121] Generate a patrol inspection evaluation value g for the current time interval;

[0122] Preset a patrol inspection evaluation value threshold G1;

[0123] If g>G1, a patrol inspection instruction is generated for the current time interval, and the patrol inspection cycle is updated;

[0124] If g<G1, no first-level patrol inspection instruction is generated for the current time interval;

[0125] If no first-level patrol inspection instruction is generated within each time interval in the time interval sequence T, a first-level patrol inspection instruction is generated according to the patrol inspection time node of the current patrol inspection cycle;

[0126] Set the patrol inspection strategy according to the first-level patrol inspection instruction.

[0127] Specifically, the duration of the patrol inspection cycle is set according to historical parameters, and by establishing multiple time intervals, the overall risk value within the area to be inspected is judged. When the patrol inspection evaluation value is greater than the preset patrol inspection evaluation value threshold, it indicates that there are more fire hazards in the current area to be inspected, greatly increasing the probability of fire occurrence, and it is necessary to process it in a timely manner.

[0128] Specifically, the patrol inspection evaluation value threshold can be set according to historical parameters.

[0129] Specifically, by combining periodic patrol inspections with threshold judgment, the processing efficiency for fire hazards is improved, and the fire risk is reduced.

[0130] Specifically, the inspection evaluation value g of the current time interval is generated, including:

[0131]

[0132] Among them, e3 is the preset third weight coefficient; e4 is the preset fourth weight coefficient; e5 is the preset fifth weight coefficient; Q3 is the preset third fixed coefficient; Q4 is the preset fourth fixed coefficient; Q5 is the preset fifth fixed coefficient; βi is the influencing factor of the i-th equipment point; f' is the preset first potential risk value threshold; Y(i) is the selection coefficient, if (f i -f')>0,Y(i)=1; if (f i -f')<0,Y(i)=0; U2 is a reference value generated based on the historical potential risk value in the current inspection cycle.

[0133] Specifically, all parameters in the model are normalized by presetting the third fixed coefficient, the fourth fixed coefficient and the fifth fixed coefficient, so that each parameter is within the same value range.

[0134] Specifically, the reference value of the historical potential risk value refers to the accumulated value of the inspection evaluation values ​​of all time intervals from the start time interval of the current inspection cycle to the current time interval.

[0135] Specifically, the larger the inspection evaluation value, the greater the possibility that there are fire hazards in the current inspection area.

[0136] It can be understood that in the above embodiment, by analyzing the operating status of all equipment points and generating inspection instructions in a timely manner, manual inspection and analysis can be performed on areas where fire hazards may exist, and existing fire hazards can be warned and dealt with in a timely manner to reduce fire risks.

[0137] In a preferred embodiment of the present application, the inspection strategy is set according to the first-level inspection instruction, including:

[0138] The potential risk value of each equipment point is obtained according to the generation time node of the first-level inspection instruction, and a real-time potential risk value series F1 is established;

[0139] F1=(f 11 , f 12 …f 1i …f 1n ), where f 1i is the potential risk value of the i-th equipment point at the generation time node of the first-level inspection instruction;

[0140] Preset a first potential risk value threshold f';

[0141] f1i >f', set the i-th equipment point as the equipment point to be inspected;

[0142] Get all equipment points to be inspected;

[0143] Establish a list of equipment points to be inspected A1, A1 = (a 11 , a 12 …a 1i …a 1n1 ), where a 1i is the number of equipment points to be inspected; n1 is the number of equipment points to be inspected;

[0144] Establish an optimization model based on the location parameters of all equipment points to be inspected and the inspection equipment parameters;

[0145] Generate inspection strategies based on the optimization model.

[0146] Specifically, the inspection equipment can be a drone equipment or a manual equipment, and its inspection route can be manual inspection and drone inspection.

[0147] Specifically, a constraint model is established according to the location parameters of all equipment points to be inspected and the inspection equipment parameters, and a corresponding plurality of inspection strategies are generated according to all feasible solutions.

[0148] Specifically, a single inspection strategy includes multiple inspection paths, all of which are distributed on each inspection path. The inspection paths in each inspection strategy are not completely the same.

[0149] Specifically, the inspection strategy is generated based on the optimization model, including:

[0150] Generate multiple first-level inspection plans based on the optimization model;

[0151] Establish the first-level inspection plan series D, D = (d 1 ,d 2 …d i …d n1 ), where d i is the i-th first-level inspection plan; n is the number of inspection plans;

[0152] Generate operational evaluation values ​​for each first-level inspection plan;

[0153] Establish the running evaluation value series H, H = (h 1 ,h 2 …h i …h n1 ), where h i is the operation evaluation value of the i-th first-level inspection plan;

[0154] Set the maximum value h in the running evaluation value series maxThe corresponding first-level inspection plan is the inspection strategy.

[0155] Specifically, the operation evaluation value series H is established, including:

[0156] According to the first-level inspection plan sequence D, di is set as the target first-level inspection plan in sequence;

[0157] Generate the operation evaluation value h of the target first-level inspection plan;

[0158]

[0159] Among them, r is the number of evaluation indicators; η i is the influencing factor of the i-th evaluation index; k i is the reference value of the i-th evaluation index in the target first-level inspection plan;

[0160] Generate the operation evaluation value of each first-level inspection plan in sequence;

[0161] Establish a running evaluation value sequence H.

[0162] Specifically, the evaluation indicators include, but are not limited to, total inspection time, inspection cost, inspection data collection accuracy and other parameters. The larger the operation evaluation value, the greater the comprehensive benefit of the corresponding inspection strategy and the higher the corresponding feasibility.

[0163] It can be understood that in the above embodiment, corresponding inspection strategies are set according to the potential risk value of each equipment point, and manual inspection and drone inspection technology are combined to improve the overall inspection efficiency, eliminate invalid inspection work, reduce inspection time and labor costs, and timely diagnose and warn of potential fire hazards, thereby improving the diagnostic accuracy of fire hazards.

[0164] In a preferred embodiment of the present application, generating fire hazard diagnosis results based on feedback data includes:

[0165] According to the equipment point number list A1 to be inspected, set a1 i as the target equipment point to be inspected;

[0166] Obtain feedback data from target equipment points to be inspected based on inspection strategies;

[0167] Generate sub-diagnosis results of the target equipment point to be inspected based on the processing results of the feedback data;

[0168] Generate sub-diagnosis results for each device point to be inspected in sequence;

[0169] Generate fire hazard diagnosis results based on all diagnosis results.

[0170] Specifically, the feedback data of each equipment point to be queried is obtained according to the inspection strategy, and the fire hazards in the radiation area corresponding to the equipment point to be inspected are diagnosed by comprehensively analyzing the monitoring data collected initially and the feedback data collected secondary, and the corresponding sub-diagnosis results are generated.

[0171] Specifically, corresponding rectification and maintenance strategies are generated according to the fire hazard diagnosis results, and potential fire hazards are dealt with in a timely manner, thereby reducing the probability of fire.

[0172] According to the first concept of the present application, multiple monitoring points are set to conduct multi-dimensional monitoring of the inspection area, and the monitoring data of each monitoring point is periodically collected to accurately analyze the operating status of each monitoring point, and early warning is issued in time for monitoring points with potential risks, thereby improving the efficiency of early warning of fire hazards and reducing the frequency of fires.

[0173] According to the second concept of the present application, corresponding inspection strategies are set according to the potential risk value of each equipment point, and combined with manual inspection and drone inspection technology to improve the overall inspection efficiency, eliminate invalid inspection work, reduce inspection time and labor costs, and timely diagnose and warn of potential fire hazards, thereby improving the diagnostic accuracy of fire hazards.

[0174] 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 method for intelligently identifying fire hazards, characterized in that: Including: Set multiple equipment points according to the parameters of the area to be inspected, and establish a monitoring sub-model for each equipment point; Obtain the monitoring data of each equipment point and generate the potential risk value of each equipment point; Set the inspection strategy according to all potential risk values, obtain the feedback data according to the inspection strategy, and generate the fire hazard diagnosis result according to the feedback data; Among them, when setting multiple equipment points, it includes: Create a device point sequence A, A=(a1,a2…a i …a n ), where a i is the i-th device point; n is the number of device points.

2. The method for intelligently identifying fire hazards according to claim 1, characterized in that: Establishing the monitoring sub-model of each equipment point includes: Set a in sequence according to the device point column A i is the target device point; Generate the radiation area of the target equipment point; Set the characteristic monitoring index of the target equipment point according to the equipment parameters in the radiation area; Generate the monitoring evaluation value according to the historical parameters in the radiation area, and set the monitoring time axis of the target equipment point according to the monitoring evaluation value; Establish the monitoring sub-model of the target equipment point according to the monitoring time axis and all characteristic monitoring indexes; Generate the monitoring sub-models of each equipment point in sequence; Establish monitoring sub-model series B, B = (b1, b2…b i …b n ), where b i is the monitoring sub-model of the i-th device point.

3. The method for intelligently identifying fire hazards according to claim 2, characterized in that: Generate the potential risk value of each equipment point, including: Establish a potential risk value series F, F = (f1, f2…f i …f n ), where fi is the potential risk value of the i-th equipment point; Set a in sequence according to the device point column A i is the target device point; Set multiple monitoring time nodes according to the monitoring time axis of the target equipment point; Obtain the monitoring data packet of the target equipment point at the current monitoring time node; Generate the potential risk value f of the target equipment point at the current monitoring time node, and update the potential risk value sequence F; Generate the potential risk values of each equipment point in sequence.

4. The method for intelligently identifying fire hazards according to claim 3, characterized in that: Generate the potential risk value f of the target equipment point at the current monitoring time node, including: Wherein, e1 is the preset first weight coefficient; e2 is the preset second weight coefficient; Q1 is the preset first fixed coefficient; Q2 is the preset second fixed coefficient; θ is the number of characteristic indicators of the target device point; μ i is the influencing factor of the i-th characteristic index; j i is the reference value of the i-th characteristic indicator of the target equipment point at the current monitoring time node; j' i为目 The standard reference value of the i-th characteristic indicator of the target equipment point; U1 is the historical reference value of the target equipment point at the current monitoring time node.

5. The method for intelligently identifying fire hazards according to claim 3, characterized in that: Set the inspection strategy according to all potential risk values, including: Establish the inspection cycle; Set the end time node of each inspection cycle as the inspection time node; Set multiple time intervals within the current inspection cycle and establish a time interval sequence T; T=(t1,t2…t i …t m ), where t i is the i-th time interval in the current inspection cycle; m is the number of time intervals in the current inspection cycle; Generate the inspection evaluation value g of the current time interval; Preset the inspection evaluation value threshold G1; If g > G1, generate an inspection instruction in the current time interval and update the inspection cycle; If g < G1, no first-level inspection instruction is generated in the current time interval; If no first-level inspection instruction is generated in each time interval in the time interval sequence T, generate a first-level inspection instruction according to the inspection time node of the current inspection cycle; Set the inspection strategy according to the first-level inspection instruction.

6. The method for intelligently identifying fire hazards according to claim 5, characterized in that: Generate the inspection evaluation value g of the current time interval, including: Among them, e3 is the preset third weight coefficient; e4 is the preset fourth weight coefficient; e5 is the preset fifth weight coefficient; Q3 is the preset third fixed coefficient; Q4 is the preset fourth fixed coefficient; Q5 is the preset fifth fixed coefficient; βi is the influencing factor of the i-th equipment point; f' is the preset first potential risk value threshold; Y(i) is the selection coefficient, if (f i -f')>0,Y(i)=1; if (f i -f')<0,Y(i)=0; U2 is a reference value generated based on the historical potential risk value in the current inspection cycle.

7. The method for intelligently identifying fire hazards according to claim 5, characterized in that: Set the inspection strategy according to the first-level inspection instruction, including: Obtain the potential risk value of each equipment point according to the generation time node of the first-level inspection instruction and establish a real-time potential risk value sequence F1; F1=(f 11 , f 12 …f 1i …f 1n ), where f 1i is the potential risk value of the i-th equipment point at the generation time node of the first-level inspection instruction; Preset the first potential risk value threshold f'; f 1i >f', set the i-th equipment point as the equipment point to be inspected; Obtain all the equipment points to be inspected; Establish a list of equipment points to be inspected A1, A1 = (a 11 , a 12 …a 1i …a 1n1 ), where a 1i is the number of equipment points to be inspected; n1 is the number of equipment points to be inspected; Establish an optimization model according to the position parameters of all the equipment points to be inspected and the inspection equipment parameters; Generate the inspection strategy according to the optimization model.

8. The method for intelligently identifying fire hazards according to claim 7, characterized in that: Generate the inspection strategy according to the optimization model, including: Generate multiple first-level inspection plans according to the optimization model; Establish a first-level inspection plan sequence D, D = (d1, d2…d i …d n1 ), where d i is the i-th first-level inspection plan; n is the number of inspection plans; Generate the operation evaluation value of each first-level inspection plan; Establish the running evaluation value sequence H, H = (h1, h2...h i …h n1 ), where h i is the operation evaluation value of the i-th first-level inspection plan; Set the maximum value h in the running evaluation value series max The corresponding first-level inspection plan is the inspection strategy.

9. The method for intelligently identifying fire hazards according to claim 8, characterized in that: Establish an operation evaluation value sequence H, including: Set di as the target first-level inspection plan in sequence according to the first-level inspection plan sequence D; Generate the operation evaluation value h of the target first-level inspection plan; Among them, r is the number of evaluation indicators; η i is the influencing factor of the i-th evaluation index; k i is the reference value of the i-th evaluation index in the target first-level inspection plan; Generate the operation evaluation values of each first-level inspection plan in sequence; Establish an operation evaluation value sequence H.

10. The method for intelligently identifying fire hazards according to claim 8, characterized in that: Generate the fire hazard diagnosis result according to the feedback data, including: Set a1i as the target equipment point to be inspected in sequence according to the equipment point sequence A1 to be inspected; Obtain the feedback data of the target equipment point to be inspected based on the inspection strategy; Generate sub-diagnosis results of the target equipment point to be inspected based on the processing results of the feedback data; Generate sub-diagnosis results for each device point to be inspected in sequence; Generate fire hazard diagnosis results based on all diagnosis results.

Images