Method and device for constructing fire extinguishing agent consumption prediction model in charging place

By collecting environmental and equipment data in charging places, building a deep learning network to predict the area of ​​fire impact, and combining historical data to generate a fire extinguishing agent dosage relationship curve, the problem of low fire prediction accuracy in the existing technology is solved, and the fire in charging places is realized The high-precision prediction and accurate assessment of fire extinguishing agent dosage improve fire extinguishing efficiency and adaptability.

CN119089796AInactive Publication Date: 2024-12-06MOLIFANG TECH (BEIJING) CO LTD

Patent Information

Application Number
CN202411271853.9
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-09-11
Publication Date
2024-12-06
Estimated Expiration
Not applicable · inactive patent

AI Technical Summary

Technical Problem

The existing fire protection systems have problems with insufficient real-time response capabilities and low prediction accuracy in fire prediction and fire extinguishing agent dosage prediction. Especially in charging places, traditional fire detection equipment is difficult to predict fires in a timely manner and take preventive measures, resulting in fire extinguishing. The dose evaluation is inaccurate.

Method used

By collecting environmental data of charging places and physical data of charging equipment, a deep learning network is built to predict the area affected by fire, and a relationship curve of fire extinguishing agent usage is generated based on historical data, and the current and temperature change rate is calculated in real time to determine the fire extinguishing agent usage is used. Deep learning networks handle nonlinear relationships to achieve high-precision prediction of fire risks and improve fire extinguishing efficiency.

Benefits of technology

Real-time capture of abnormal operating status of charging equipment and high-precision prediction of fire risk, improves fire extinguishing efficiency and estimation accuracy of fire extinguishing agent dosage, is highly adaptable, and can be continuously optimized based on new data.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119089796A_ABST
    Figure CN119089796A_ABST
Patent Text Reader

Abstract

The invention provides a charging place fire extinguishing agent consumption prediction model method and device, and relates to the technical field of fire safety protection. Environmental data of a charging place and physical data of charging equipment are collected, the current and temperature of the charging equipment are obtained, and a time sequence of the current and temperature is generated; calculating a current change rate and a temperature change rate at each moment to obtain a fire influence area at each moment; training a deep learning network by using the wind speed and the current change rate and the temperature change rate at each moment to obtain a fire prediction model capable of predicting the fire influence area, collecting fire historical data to generate a relation curve between the fire influence area and the fire extinguishing agent dosage, and obtaining the fire extinguishing agent dosage per unit area. And finally, inputting the wind speed, current change rate and temperature change rate data of the to-be-predicted charging place into the fire prediction model, calculating the fire influence area, and further predicting the required fire extinguishing agent dosage.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of fire safety protection technology, and in particular to a method and device for constructing a fire extinguishing agent usage prediction model for a charging site. Background Art

[0002] With the widespread popularity of electric vehicles and the increasing number of charging facilities, the safety of charging sites has received more and more attention. Especially in high temperature environments or when the equipment is running for a long time, the charging equipment may cause a fire due to overheating or abnormal current. It is particularly important to equip the appropriate amount of fire extinguishing agent for the scale of fire that may occur in the charging site. On the one hand, it can be extinguished in time when a fire occurs, and on the other hand, it can avoid waste of resources. To predict the amount of fire extinguishing agent, the premise is to accurately predict the affected area of ​​the fire. Most of the existing fire protection systems rely on traditional fire detection equipment, such as smoke detectors or temperature sensors. However, these devices can only respond after the fire occurs, making it difficult to predict the fire in time and take preventive measures, and it is impossible to achieve the purpose of evaluating the amount of fire extinguishing agent in advance. Therefore, it is urgent to build a solution based on the environmental data of the charging site and the physical data of the charging equipment to predict fires, and to evaluate the amount of fire extinguishing agent based on the fire prediction results to improve the efficiency of fire warning and fire fighting.

[0003] In the prior art, publication number CN114595530A discloses a method for constructing a prediction model for the amount of fire extinguishing agent used in a high-voltage switch cabinet fault and its application. By simulating various typical fault defect modes, the ignition time of the fault point and the fire extinguishing time after the gas fire extinguishing agent is applied are obtained. The fire extinguishing system determines the amount of fire extinguishing agent required to extinguish the fire source based on the fire extinguishing time, and establishes a univariate linear regression piecewise prediction model between the fault point ignition duration and the amount of fire extinguishing agent used.

[0004] The main problems with the above scheme are: when building the model, it mainly relies on various typical fault defect modes simulated in advance, lacks the ability to respond and adjust to the actual situation in real time. In the actual fire scene, it may not be able to respond to environmental changes or the dynamic evolution of the fault point in time; and the model is only built through a univariate linear regression equation, which cannot capture the nonlinear relationship between fire and fire extinguishing. The occurrence and extinguishing of fire are often affected by multiple factors. The univariate linear regression model is difficult to meet actual needs, and the prediction accuracy and adaptability are low.

[0005] The above information disclosed in this Background section is only for enhancement of understanding of the background of the present disclosure and therefore it may contain information that does not constitute the prior art that is already known to one of ordinary skill in the art. Summary of the invention

[0006] The purpose of the present invention is to provide a method and device for constructing a fire extinguishing agent usage prediction model for a charging site, so as to solve the problems raised in the above-mentioned background technology.

[0007] To achieve the above object, the present invention provides the following technical solutions:

[0008] A method for constructing a fire extinguishing agent usage prediction model for a charging site, the specific steps comprising:

[0009] Step 1: Collect environmental data of the charging site and physical data of the charging equipment at different times, and generate the charging equipment current based on the collected data, wherein the environmental data of the charging site includes: ambient temperature and wind speed, and the physical data of the charging equipment includes: charging equipment temperature, output voltage of the charging equipment, resistance of the charging equipment, and temperature coefficient of resistance material;

[0010] Step 2, calculating the current change rate and temperature change rate of the charging equipment at each moment, and determining the fire impact area at each moment based on the expert scoring method;

[0011] Step 3: Construct a deep learning network, use the wind speed of the charging site, the temperature change rate of the charging equipment, and the current change rate as the training set, and the fire impact area as the label, input them into the deep learning network for training, and obtain a fire prediction model with the input values ​​of wind speed, the temperature change rate of the charging equipment, and the current change rate, and the output value being the fire impact area of ​​the charging site;

[0012] Step 4: Determine the type of fire extinguishing agent to be used when a fire occurs, collect historical data on fires in charging locations, generate a relationship curve between the area affected by the fire and the amount of fire extinguishing agent required to extinguish the fire, and obtain the amount of fire extinguishing agent per unit area from the relationship curve;

[0013] Step 5: Input the wind speed of the charging place to be predicted, the temperature change rate of the charging equipment, and the current change rate into the fire prediction model to generate the fire impact area, and generate the predicted fire extinguishing agent usage based on the fire impact area and the fire extinguishing agent usage per unit area.

[0014] Furthermore, the formula for generating the charging device current is:

[0015] R=R0·(1+β·(T env -T0))

[0016]

[0017] Wherein, R represents the resistance of the charging device at ambient temperature, R0 represents the resistance of the charging device at standard temperature, β represents the temperature coefficient of the resistance material of the charging device, and 0.003≤β≤0.006, T envrepresents the ambient temperature, T0 represents the standard temperature, I represents the charging device current, and U represents the output voltage of the charging device.

[0018] Furthermore, the formula for generating the current change rate of the charging device is:

[0019]

[0020] Among them, ΔI i Indicates the current change rate of the charging device at time i, I i+1 Represents the charging device current at time i+1, I i represents the charging device current at time i, i is the index of the time, Δt i Represents the time interval between time i+1 and time i.

[0021] Furthermore, the formula for generating the temperature change rate of the charging device is:

[0022]

[0023] Where, ΔT i represents the temperature change rate of the charging device at time i, T i+1 represents the temperature of the charging device at time i+1, T i Indicates the temperature of the charging device at time i.

[0024] Furthermore, the principle for generating the relationship curve between the fire affected area and the amount of fire extinguishing agent required to extinguish the fire is:

[0025] A plane rectangular coordinate system is established with the fire affected area as the ordinate and the amount of fire extinguishing agent required to extinguish the fire as the abscissa. The fire affected area and the amount of fire extinguishing agent used in the fire history data are marked with coordinate points in the coordinate system. All coordinate points are connected to generate a fire affected area-fire extinguishing agent usage relationship curve. The slope of the curve is the amount of fire extinguishing agent used per unit area of ​​fire.

[0026] Furthermore, the formula for generating the predicted fire extinguishing agent usage is:

[0027] M=S·k

[0028] Among them, M represents the predicted amount of fire extinguishing agent, S represents the area affected by the fire, and k represents the amount of fire extinguishing agent per unit area of ​​fire.

[0029] The present invention also provides a device for constructing a prediction model for the amount of fire extinguishing agent used in a charging place, and the device is used to implement the above-mentioned method for constructing a prediction model for the amount of fire extinguishing agent used in a charging place, specifically comprising:

[0030] A data acquisition module, used to collect environmental data of the charging site and physical data of the charging equipment at different times, and generate the charging equipment current based on the collected data, wherein the environmental data of the charging site includes: ambient temperature and wind speed, and the physical data of the charging equipment includes: charging equipment temperature, output voltage of the charging equipment, resistance of the charging equipment, and temperature coefficient of resistance material;

[0031] The operation status calculation module is used to calculate the current change rate and temperature change rate of the charging equipment at each moment, and determine the fire impact area at each moment based on the expert scoring method;

[0032] The model building module is used to build a deep learning network. The wind speed of the charging site, the temperature change rate of the charging equipment, and the current change rate are used as training sets, and the fire impact area is used as a label. The training is input into the deep learning network to obtain a fire prediction model with the input value being the temperature change rate of the charging equipment and the current change rate, and the output value being the fire impact area of ​​the charging site.

[0033] The curve generation module is used to determine the type of fire extinguishing agent to be used when a fire occurs, collect historical data on fires in charging places, and generate a curve showing the relationship between the area affected by the fire and the amount of fire extinguishing agent required to extinguish the fire;

[0034] The output prediction module is used to input the wind speed of the charging place to be predicted, the temperature change rate of the charging equipment, and the current change rate into the fire prediction model to generate the fire affected area, and generate the predicted fire extinguishing agent usage based on the fire affected area and the fire extinguishing agent usage per unit area.

[0035] Compared with the prior art, the present invention has the following beneficial effects:

[0036] The present invention collects real-time environmental data and physical data of the charging equipment, calculates the rate of change of the current and temperature of the charging equipment, and provides comprehensive and dynamic data support for the fire prediction model. The current and temperature changes of the charging equipment are collected and calculated in real time, combined with environmental data, so that the input data is more accurate and rich, and the current change rate and temperature change rate at each moment are calculated to timely capture the abnormal operating state of the charging equipment and more accurately predict the fire risk. Based on the deep learning network, the fire prediction model is trained by collecting and calculating data. The deep learning network can effectively handle the complex nonlinear relationship between the charging equipment parameters and the fire affected area, so as to more accurately capture the relationship between the operating state of the charging equipment and the risk of fire, and can continuously optimize and self-adjust by continuously adding new data, so as to maintain high accuracy and high adaptability of fire prediction.

[0037] The present invention also determines the relationship curve between the fire impact area and the amount of fire extinguishing agent required to extinguish the fire through historical fire data, obtains the amount of fire extinguishing agent per unit area, and generates a predicted value of the amount of fire extinguishing agent based on the fire impact area and the amount of fire extinguishing agent per unit area generated by real-time prediction. By combining the analysis of historical data with the real-time prediction of the fire impact area, the fire extinguishing efficiency and the estimation accuracy of the amount of fire extinguishing agent are effectively improved, and by targeted selection of the type of fire extinguishing agent, the utilization rate of fire extinguishing resources is further optimized. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] Figure 1 This is a schematic diagram of a method flow of an embodiment of the present invention;

[0039] Figure 2 Schematic diagram of system modules according to an embodiment of the present invention. DETAILED DESCRIPTION

[0040] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with specific embodiments.

[0041] It should be noted that, unless otherwise defined, the technical terms or scientific terms used in the present invention should be understood by people with ordinary skills in the field to which the present invention belongs. The words "first", "second" and similar words used in the present invention do not indicate any order, quantity or importance, but are only used to distinguish different components. "Include" or "comprise" and similar words mean that the elements or objects appearing before the word include the elements or objects listed after the word and their equivalents, without excluding other elements or objects. "Connect" or "connected" and similar words are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "Up", "down", "left", "right" and the like are only used to indicate relative positional relationships. When the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0042] Example:

[0043] See also Figure 1 , the present invention provides a technical solution:

[0044] Step 1: Collect environmental data of the charging site and physical data of the charging equipment at different times, and generate the charging equipment current based on the collected data, wherein the environmental data of the charging site includes: ambient temperature and wind speed, and the physical data of the charging equipment includes: charging equipment temperature, output voltage of the charging equipment, resistance of the charging equipment, and temperature coefficient of resistance material;

[0045] In this embodiment, the formula for generating the charging device current is:

[0046] R=R0·(1+β·(T env -T0))

[0047]

[0048] Where R represents the resistance of the charging device at ambient temperature, R0 represents the resistance of the charging device at standard temperature, β represents the temperature coefficient of the resistance material of the charging device, and 0.003≤β≤0.006T env represents the ambient temperature, T0 represents the standard temperature, I represents the charging device current, and U represents the output voltage of the charging device;

[0049] As the temperature changes, the resistance of the charging device also changes. The temperature coefficient of resistance is a coefficient related to the material of the resistor, reflecting the magnitude of the change in resistance with temperature. The resistors in the charging device are mostly made of metal, so their temperature coefficient is positive, usually 0.003≤β≤0.006. The resistance R at the real-time temperature is the result of temperature correction of the resistance at the standard temperature. R is proportional to the resistance at the standard temperature, and is proportional to the temperature coefficient and the temperature difference.

[0050] The current size of the charging device reflects the charging speed on the one hand, and the safety of the charging device on the other hand. A higher current will cause the charging device to overheat and may cause a fire risk. The current size is proportional to the output voltage of the charging device and inversely proportional to the resistance of the charging device.

[0051] Step 2: Calculate the current change rate and temperature change rate of the charging equipment at each time, and determine the fire impact area at each time based on the expert scoring method;

[0052] In this embodiment, the formula for generating the current change rate of the charging device is:

[0053]

[0054] Among them, ΔI i Indicates the current change rate of the charging device at time i, I i+1 Represents the charging device current at time i+1, I i represents the charging device current at time i, i is the index of the time, Δt i Represents the time interval between time i+1 and time i.

[0055] The rate of change of the charging device current indicates the speed of change of the current per unit time, and reflects the fluctuation of the current. When the current suddenly increases or fluctuates frequently, it means that the equipment is bearing abnormal current, which may cause a fire. The rate of change of the charging device current is proportional to the current difference of adjacent collected data, and inversely proportional to the time interval of collected data.

[0056] The formula used to generate the rate of change of temperature of the charging equipment is:

[0057]

[0058] Where, ΔT i represents the temperature change rate of the charging device at time i, T i+1 represents the temperature of the charging device at time i+1, T i Indicates the temperature of the charging device at time i.

[0059] The rate of change of the charging device temperature indicates the speed of temperature change per unit time, and reflects the fluctuation of the device temperature. If the temperature of the charging device rises sharply, it means that the device is overheating, which may be caused by electrical failure, poor heat dissipation, equipment aging, etc. Overheating of the equipment may eventually lead to a fire. The rate of change of the charging device temperature is proportional to the temperature difference of adjacent collected data, and inversely proportional to the time interval between collected data.

[0060] Step 3: Construct a deep learning network, use the wind speed of the charging site, the temperature change rate of the charging equipment, and the current change rate as the training set, and the fire impact area as the label, input them into the deep learning network for training, and obtain a fire prediction model with the input values ​​of wind speed, the temperature change rate of the charging equipment, and the current change rate, and the output value being the fire impact area of ​​the charging site;

[0061] In this embodiment, the input features of the deep learning network are: the wind speed at the charging location, the rate of change of the charging device temperature, and the rate of change of the charging device current;

[0062] The structure of the deep learning network is:

[0063] Input layer: contains 3 neurons, which are used to receive the input of wind speed at the charging site, the rate of change of charging equipment temperature, and the rate of change of charging equipment current;

[0064] The first hidden layer: contains 64 neurons, activated by the ReLU activation function;

[0065] The second hidden layer: contains 32 neurons, activated using the ReLU activation function;

[0066] The third hidden layer: contains 16 neurons, activated by the ReLU activation function;

[0067] Output layer: Contains one neuron that outputs the affected area of ​​the fire and is activated using the Sigmoid function.

[0068] Step 4: Determine the type of fire extinguishing agent to be used when a fire occurs, collect historical data on fires in charging locations, generate a relationship curve between the area affected by the fire and the amount of fire extinguishing agent required to extinguish the fire, and obtain the amount of fire extinguishing agent per unit area from the relationship curve;

[0069] In this embodiment, the principle for generating the relationship curve between the fire affected area and the amount of fire extinguishing agent required to extinguish the fire is:

[0070] A plane rectangular coordinate system is established with the fire affected area as the ordinate and the amount of fire extinguishing agent required to extinguish the fire as the abscissa. The fire affected area and the amount of fire extinguishing agent used in the fire history data are marked with coordinate points in the coordinate system. All coordinate points are connected to generate a fire affected area-fire extinguishing agent usage relationship curve. The slope of the curve is the amount of fire extinguishing agent used per unit area of ​​fire.

[0071] Step 5: Input the wind speed of the charging place to be predicted, the temperature change rate of the charging equipment, and the current change rate into the fire prediction model to generate the fire impact area, and generate the predicted fire extinguishing agent usage based on the fire impact area and the fire extinguishing agent usage per unit area.

[0072] In this embodiment, the formula for generating the predicted amount of fire extinguishing agent is:

[0073] M=S·k

[0074] Among them, M represents the predicted amount of fire extinguishing agent, S represents the area affected by the fire, and k represents the amount of fire extinguishing agent per unit area of ​​fire.

[0075] The amount of fire extinguishing agent used is determined by the area of ​​the fire affected area and the amount of fire extinguishing agent used per unit area. The area of ​​the fire affected area depends on factors such as the type of combustible material in the fire and the wind speed at the fire scene. In fires occurring in charging places, dry powder fire extinguishing agents are usually used. The calculation formula for the amount of fire extinguishing agent used reflects the balance between the scale of the fire and the effectiveness of the fire extinguishing agent in the fire extinguishing operation, and reflects the need for timely control of the fire. The amount of fire extinguishing agent used per unit area of ​​fire k reflects the difficulty of fire extinguishing. The predicted amount of fire extinguishing agent used is proportional to the area of ​​the fire affected area and the amount of fire extinguishing agent used per unit area of ​​fire.

[0076] See also Figure 2 The present invention also provides a device for constructing a prediction model for the amount of fire extinguishing agent used in a charging place, and the device is used to implement the method for constructing a prediction model for the amount of fire extinguishing agent used in a charging place, specifically comprising:

[0077] A data acquisition module, used to collect environmental data of the charging site and physical data of the charging equipment at different times, and generate the charging equipment current based on the collected data, wherein the environmental data of the charging site includes: ambient temperature and wind speed, and the physical data of the charging equipment includes: charging equipment temperature, output voltage of the charging equipment, resistance of the charging equipment, and temperature coefficient of resistance material;

[0078] The operation status calculation module is used to calculate the current change rate and temperature change rate of the charging equipment at each moment, and determine the fire impact area at each moment based on the expert scoring method;

[0079] The model building module is used to build a deep learning network. The wind speed of the charging site, the temperature change rate of the charging equipment, and the current change rate are used as training sets, and the fire impact area is used as a label. The training is input into the deep learning network to obtain a fire prediction model with the input value being the temperature change rate of the charging equipment and the current change rate, and the output value being the fire impact area of ​​the charging site.

[0080] The curve generation module is used to determine the type of fire extinguishing agent to be used when a fire occurs, collect historical data on fires in charging places, and generate a curve showing the relationship between the area affected by the fire and the amount of fire extinguishing agent required to extinguish the fire;

[0081] The output prediction module is used to input the wind speed of the charging place to be predicted, the temperature change rate of the charging equipment, and the current change rate into the fire prediction model to generate the fire affected area, and generate the predicted fire extinguishing agent usage based on the fire affected area and the fire extinguishing agent usage per unit area.

[0082] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0083] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination thereof. When implemented by software, the above embodiments may be implemented in whole or in part in the form of a computer program product. Those skilled in the art may appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein may be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed by hardware or software methods depends on the specific application and design constraints of the technical solution.

[0084] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, and may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0085] The above description is only a specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application.

Claims

1. A method for constructing a fire extinguishing agent usage prediction model for a charging site, characterized in that: The specific steps include: Step 1: Collect environmental data of the charging site and physical data of the charging equipment at different times, and generate the charging equipment current based on the collected data, wherein the environmental data of the charging site includes: ambient temperature and wind speed, and the physical data of the charging equipment includes: charging equipment temperature, output voltage of the charging equipment, resistance of the charging equipment, and temperature coefficient of resistance material; Step 2, calculating the current change rate and temperature change rate of the charging equipment at each moment, and determining the fire impact area at each moment based on the expert scoring method; Step 3: Construct a deep learning network, use the wind speed of the charging site, the temperature change rate of the charging equipment, and the current change rate as the training set, and the fire impact area as the label, input them into the deep learning network for training, and obtain a fire prediction model with the input values ​​of wind speed, the temperature change rate of the charging equipment, and the current change rate, and the output value being the fire impact area of ​​the charging site; Step 4: Determine the type of fire extinguishing agent to be used when a fire occurs, collect historical data on fires in charging locations, generate a relationship curve between the area affected by the fire and the amount of fire extinguishing agent required to extinguish the fire, and obtain the amount of fire extinguishing agent per unit area from the relationship curve; Step 5: Input the wind speed of the charging place to be predicted, the temperature change rate of the charging equipment, and the current change rate into the fire prediction model to generate the fire impact area, and generate the predicted fire extinguishing agent usage based on the fire impact area and the fire extinguishing agent usage per unit area.

2. A method for constructing a prediction model for the amount of fire extinguishing agent used in a charging place according to claim 1, characterized in that: The formula for generating the charging device current in step 1 is: R=R0·(1+β·(T env -T0)) Wherein, R represents the resistance of the charging device at ambient temperature, R0 represents the resistance of the charging device at standard temperature, β represents the temperature coefficient of the resistance material of the charging device, and 0.003≤β≤0.006, T env represents the ambient temperature, T0 represents the standard temperature, I represents the charging device current, and U represents the output voltage of the charging device.

3. A method for constructing a prediction model for the amount of fire extinguishing agent used in a charging place according to claim 1, characterized in that: The formula for generating the current change rate of the charging device in step 2 is: Among them, △I i Indicates the current change rate of the charging device at time i, I i+1 Represents the charging device current at time i+1, I i represents the charging device current at time i, i is the index of the time, △t i Represents the time interval between time i+1 and time i.

4. A method for constructing a prediction model for the amount of fire extinguishing agent used in a charging place according to claim 3, characterized in that: The formula for generating the temperature change rate of the charging device in step 2 is: Among them, △T i represents the temperature change rate of the charging device at time i, T i+1 represents the temperature of the charging device at time i+1, T i Indicates the temperature of the charging device at time i.

5. The method for constructing a prediction model for the amount of fire extinguishing agent used in a charging place according to claim 1, characterized in that: The principle for generating the relationship curve between the fire affected area and the amount of fire extinguishing agent required to extinguish the fire in step 4 is: A plane rectangular coordinate system is established with the fire affected area as the ordinate and the amount of fire extinguishing agent required to extinguish the fire as the abscissa. The fire affected area and the amount of fire extinguishing agent used in the fire history data are marked with coordinate points in the coordinate system. All coordinate points are connected to generate a fire affected area-fire extinguishing agent usage relationship curve. The slope of the curve is the amount of fire extinguishing agent used per unit area of ​​fire.

6. A method for constructing a prediction model for the amount of fire extinguishing agent used in a charging place according to claim 1, characterized in that: The formula for generating the predicted amount of fire extinguishing agent in step 5 is: M=S·k Among them, M represents the predicted amount of fire extinguishing agent, S represents the area affected by the fire, and k represents the amount of fire extinguishing agent per unit area of ​​fire.

7. A device for constructing a prediction model for the amount of fire extinguishing agent used in a charging place, characterized in that: The device is used to implement the method for constructing a prediction model for the amount of fire extinguishing agent used in a charging place according to any one of claims 1 to 6, specifically comprising: A data acquisition module, used to collect environmental data of the charging site and physical data of the charging equipment at different times, and generate the charging equipment current based on the collected data, wherein the environmental data of the charging site includes: ambient temperature and wind speed, and the physical data of the charging equipment includes: charging equipment temperature, output voltage of the charging equipment, resistance of the charging equipment, and temperature coefficient of resistance material; The operation status calculation module is used to calculate the current change rate and temperature change rate of the charging equipment at each moment, and determine the fire impact area at each moment based on the expert scoring method; The model building module is used to build a deep learning network. The wind speed of the charging site, the temperature change rate of the charging equipment, and the current change rate are used as training sets, and the fire impact area is used as a label. The training is input into the deep learning network to obtain a fire prediction model with the input value being the temperature change rate of the charging equipment and the current change rate, and the output value being the fire impact area of ​​the charging site. The curve generation module is used to determine the type of fire extinguishing agent to be used when a fire occurs, collect historical data on fires in charging places, and generate a curve showing the relationship between the area affected by the fire and the amount of fire extinguishing agent required to extinguish the fire; The output prediction module is used to input the wind speed of the charging place to be predicted, the temperature change rate of the charging equipment, and the current change rate into the fire prediction model to generate the fire affected area, and generate the predicted fire extinguishing agent usage based on the fire affected area and the fire extinguishing agent usage per unit area.

Citation Information

Patent Citations

  • Construction method and application of high-voltage switch cabinet fault fire extinguishing agent consumption prediction model

    CN114595530A

  • Working method and device of autonomous fire extinguishment robot

    CN111346333A

  • Method for drawing fire risk level distribution diagram

    CN112308292A

  • Lithium ion battery energy storage station fire monitoring evaluation management method

    CN117523809A

  • Fire management method and system for enterprise internal places based on big data processing

    CN117592768A

Cited By

  • Fire hazard prediction system and method based on large machine model

    CN120974372A