Fire zoning and fire-fighting linkage control method and system for energy storage power station

Abstract

The invention relates to the technical field of energy storage power station fire fighting, in particular to an energy storage power station fire partition and fire fighting linkage control method and system, and the method comprises the steps: obtaining a multi-angle first image of a fire of an energy storage power station; acquiring a fire center and a fire area according to the first image; dividing the energy storage power station into a plurality of fire zones according to the fire center and the fire area; and performing corresponding fire zone control based on a preset fire-fighting linkage control strategy and the plurality of divided fire zones. According to the invention, the first image is acquired through the monitoring device of the energy storage power station, and the multi-angle image acquisition and the image recognition technology are combined, so that the fire center and the fire area can be quickly and accurately recognized; the energy storage power station is divided into a plurality of areas with different fire risks through fire partition division, so that fire protection resources can be distributed and utilized more reasonably, and more energy storage batteries are protected from being damaged by fire and fire protection.

Description

Technical Field

[0001] The present invention relates to the technical field of fire protection in energy storage power stations, and in particular to a fire zoning and fire protection linkage control method and system for energy storage power stations. Background Art

[0002] With the global energy transformation and vigorous development of renewable energy, energy storage power stations, as one of the key technologies supporting the large-scale application of renewable energy, are becoming increasingly important. Energy storage power stations can not only effectively adjust the balance of power supply and demand and improve the flexibility and stability of the power grid, but also play an important role in many fields such as new energy vehicles and smart grids. However, as the scale and complexity of energy storage power stations increase, their fire risks also increase, posing severe challenges to the safe operation of energy storage power stations.

[0003] One of the core equipment of an energy storage power station is the battery pack. The battery packs are arranged in a certain way to form an energy storage power station. The battery packs are expensive. In the event of a fire, how to protect as many battery packs as possible from damage by fire and fire is the current research direction. Summary of the invention

[0004] (I) Purpose of the invention

[0005] The purpose of the present invention is to provide a method and system for fire zoning and fire linkage control of an energy storage power station, which can protect as many battery packs as possible from fire and fire damage when a fire occurs.

[0006] (II) Technical solution

[0007] In order to solve the above problems, the present invention provides a fire zoning and fire linkage control method for an energy storage power station, comprising:

[0008] Acquire multi-angle first images of a fire in an energy storage power station;

[0009] Acquire the fire center and the fire area according to the first image;

[0010] Divide the energy storage power station into multiple fire zones according to the fire center and fire area;

[0011] Based on the preset fire linkage control strategy and the multiple fire zones that have been divided, corresponding fire zone control is carried out.

[0012] In another aspect of the present invention, preferably, acquiring the fire center and the fire area according to the first image includes:

[0013] Construct a coordinate system, wherein the coordinate system takes the center of the energy storage power station as the origin, the first direction of the energy storage power station as the X-axis, the second direction of the energy storage power station as the Y-axis, and the direction perpendicular to the plane of the energy storage power station as the Z-axis;

[0014] Respectively identifying flame coordinates of flames in the first images at multiple angles in the constructed coordinate system;

[0015] fusing a plurality of the flame coordinates to generate a flame characteristic graph;

[0016] The center point algorithm is used to obtain the fire center of the flame characteristic diagram according to the generated flame characteristic diagram.

[0017] In another aspect of the present invention, preferably, the respectively identifying the flame coordinates of the flame in the first image at multiple angles in the constructed coordinate system comprises obtaining the flame coordinates of the flame in the constructed coordinate system using the following formula:

[0018]

[0019] Among them, (u, v) represents the pixel coordinates of the flame obtained in the first image; K is the internal parameter matrix of the device that obtains the first image, R and t are the rotation matrix and translation vector from the constructed coordinate system to the coordinate system of the device that obtains the first image, and (x', y', z') are the coordinates of the flame in the constructed coordinate system.

[0020] In another aspect of the present invention, preferably, the fusing of the plurality of flame coordinates to generate a flame characteristic diagram comprises:

[0021] Marking the flame coordinates in the first image at multiple angles in the constructed coordinate system to obtain a plurality of marking points;

[0022] The plurality of marked points are connected to generate a flame characteristic diagram.

[0023] In another aspect of the present invention, preferably, the connecting the plurality of annotation points comprises connecting them using the following formula:

[0024]

[0025] Among them, u represents the independent variable parameter, u∈[0,1]; d i Represents the annotation point, n is the number of annotation points; N i,k (u) represents the k-order B-spline basis function; ω i Represents the weight factor.

[0026] In another aspect of the present invention, preferably, obtaining the fire center of the flame characteristic diagram by using a center point algorithm comprises:

[0027] The fire center of the flame signature is calculated using the following formula,

[0028]

[0029] Among them, (x i ,y i ) represents the coordinates of the outer contour of the flame characteristic diagram, i = 1, 2, ..., n; (x m ,y m ) represents the coordinates of the fire center.

[0030] In another aspect of the present invention, preferably, dividing the energy storage power station into a plurality of fire zones according to the fire center and the fire area includes:

[0031] According to the battery type and fire area of ​​the energy storage power station, the fire spread speed is predicted with the fire center as the starting point, and the energy storage power station is divided into high-risk fire zones, medium-risk fire zones and low-risk fire zones.

[0032] In another aspect of the present invention, preferably,

[0033] The high-risk fire zones include the fire center, the fire area, and the area where the fire spread speed is within the first threshold range;

[0034] The medium-risk fire zone is located outside the high-risk fire zone and is an area where the fire spread speed is within the second threshold range;

[0035] The low-risk fire zone is located outside the medium-risk fire zone and is an area where the fire spread speed is within a third threshold range.

[0036] In another aspect of the present invention, preferably, the fire spread speed is predicted by the following formula:

[0037]

[0038] Where R represents the fire spread speed, I R It represents the heat released per unit area per minute; ζ represents the windless flux ratio; φ w represents the wind influence coefficient, φ s is the slope influence coefficient, ρ b represents the density of combustibles in the energy storage power station; σ represents the surface area to volume ratio, Q represents the heat required for the combustibles in the energy storage power station to be ignited, e -bd It means that the fire spread speed decays exponentially with the increase of distance; c is a very small positive value.

[0039] In another aspect of the present invention, preferably, a fire zoning and fire linkage control system for an energy storage power station includes: a first acquisition module: acquiring multi-angle first images of a fire in the energy storage power station;

[0040] The second acquisition module is used to acquire the fire center and the fire area according to the first image;

[0041] Partition module: divides the energy storage power station into multiple fire zones according to the fire center and fire area;

[0042] Control module: Based on the preset fire linkage control strategy and multiple fire zones, perform corresponding fire zone control.

[0043] (III) Beneficial effects

[0044] The above technical solution of the present invention has the following beneficial technical effects:

[0045] The present invention acquires the first image through the monitoring equipment of the energy storage power station. Since the monitoring equipment is arranged at various positions, the first image at multiple angles is acquired. The combination of multi-angle image acquisition and image recognition technology can quickly and accurately identify the fire center and the fire area. By dividing the fire zones, the energy storage power station is divided into multiple areas with different fire risks, which not only enables fire-fighting resources to be more reasonably allocated and utilized, but also prevents excessive firefighting, and protects more energy storage batteries from fire and fire-fighting damage. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] Figure 1 It is an overall flow chart of an embodiment of the present invention. DETAILED DESCRIPTION

[0047] In order to make the purpose, technical scheme and advantages of the present invention clearer, the present invention is further described in detail below in conjunction with specific embodiments and with reference to the accompanying drawings. It should be understood that these descriptions are only exemplary and are not intended to limit the scope of the present invention. In addition, in the following description, the description of well-known structures and technologies is omitted to avoid unnecessary confusion of the concept of the present invention.

[0048] Obviously, the described embodiments are only some embodiments of the present invention, but not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0049] In the description of the present invention, it should be noted that the terms “first”, “second” and “third” are only used for descriptive purposes and cannot be understood as indicating or implying relative importance.

[0050] In addition, the technical features involved in the different embodiments of the present invention described below can be combined with each other as long as they do not conflict with each other.

[0051] Embodiment 1

[0052] A fire zoning and fire linkage control method for an energy storage power station, Figure 1 FIG. 1 shows an overall flow chart of an embodiment of the present invention, as shown in FIG. Figure 1 As shown, including:

[0053] Obtain multi-angle first images of the fire in the energy storage power station; obtain the first image through the monitoring equipment of the energy storage power station, because the monitoring equipment is set in various locations. When a fire occurs in the energy storage power station, obtain the multi-angle first images, which include the fire image.

[0054] According to the first image, a fire center and a fire area are obtained. The specific contents of obtaining the fire center and the fire area are not limited herein. Optionally, in this embodiment, according to the first image, obtaining the fire center and the fire area includes:

[0055] A coordinate system is constructed, wherein the center of the energy storage power station is the origin, the first direction of the energy storage power station is the X-axis, the second direction of the energy storage power station is the Y-axis, and the direction perpendicular to the plane of the energy storage power station is the Z-axis; the first direction here can be any direction parallel to the horizontal plane, and the second direction is a direction parallel to the horizontal plane and perpendicular to the first direction; the constructed coordinate system not only takes the center of the energy storage power station as the origin, but also needs to ensure that the image data acquired by all monitoring equipment can be accurately mapped to this coordinate system, which involves the calibration of the monitoring equipment, including the precise measurement and adjustment of parameters such as focal length, angle, and position.

[0056] Respectively identifying the flame coordinates of the flame in the first image at multiple angles in the constructed coordinate system; the first image includes the flame, and identifying the flame coordinate features in the first image at multiple angles includes obtaining the flame coordinate features using the following formula:

[0057]

[0058] Wherein, (u, v) represents the pixel coordinates of the flame in the first image; K is the intrinsic matrix of the device that obtains the first image, R and t are the rotation matrix and translation vector from the constructed coordinate system to the coordinate system of the device that obtains the first image, and (x', y', z') are the flame coordinate features in the constructed coordinate system. The rotation matrix R and the translation vector t describe the transformation relationship from the constructed coordinate system (world coordinate system) to the camera coordinate system (or device coordinate system). This is determined by the external parameters of the camera (i.e., the position and orientation of the camera). Detect the flame in the first image. This can be achieved by methods such as color thresholding, texture analysis, machine learning or deep learning. Once the flame is detected, the pixel coordinates (u, v) of its boundary or center point (such as the center of mass) can be determined; using the known camera intrinsic matrix K, the rotation matrix R and the translation vector t, the pixel coordinates (u, v) of the flame are converted into coordinates (x', y', z') in the three-dimensional world coordinate system. Since the flame is observed from multiple angles, the flame coordinates are identified from multiple first images and merged into a unified constructed coordinate system.

[0059] fusing a plurality of the flame coordinates to generate a flame characteristic graph;

[0060] This feature map can be a three-dimensional voxel grid containing the probability or intensity information of the flame; or it can be a two-dimensional projection map used to display the distribution and shape of the flame on a plane. In this embodiment, the flame coordinates in the first image of multiple angles are fused to generate a flame feature map; including:

[0061] The flame coordinates in the first images of multiple angles are marked in the constructed coordinate system to obtain several marked points; the flame coordinates are identified from the first image of each angle, and these coordinates are converted into the constructed coordinate system. Since multiple cameras may capture different parts of the same flame at the same time, there may be redundancy between the marked points. In addition, due to factors such as image noise, illumination changes, occlusion, etc., the marked points may also contain errors. In order to reduce redundancy and errors, the following method is optionally used: by comparing the spatial positions of the marked points, those duplicate points whose positions are very close, that is, the distance is less than a certain threshold are removed. Statistical filtering such as mean filtering, median filtering or model-based filtering such as Kalman filtering is applied to smooth the position of the marked points to reduce noise and errors. Anomaly detection algorithms such as statistical-based methods, density-based methods or distance-based methods are used to identify and remove outliers that are significantly deviated from other marked points.

[0062] The plurality of annotated points are connected to generate a flame signature graph. After obtaining a plurality of annotated points, they are connected to form a complete flame signature graph. This involves matching and fusion problems between curves; optionally, the connection method includes directly connecting adjacent points; using a graph theory algorithm to find the optimal connection path, or using a machine learning model to predict and fill in the gaps between points. In this embodiment,

[0063] The several labeled curves are connected using the following formula:

[0064]

[0065] Among them, u represents the independent variable parameter, u∈[0,1]; d i Represents the annotation point, n is the number of annotation points; N i,k (u) represents the k-order B-spline basis function; ω i Represents the weight factor.

[0066] Using the center point algorithm, according to the generated flame characteristic graph, obtaining the fire center of the flame characteristic graph includes:

[0067] The fire center of the flame signature is calculated using the following formula,

[0068]

[0069] Among them, (x i ,y i ) represents the coordinates of the outer contour of the flame characteristic diagram, i = 1, 2, ..., n; (x m ,y m ) represents the coordinates of the fire center.

[0070] According to the fire center and fire area, the energy storage power station is divided into multiple fire zones. The fire zone is the area formed by the fusion of multiple marked points, including:

[0071] According to the battery type and fire area of ​​the energy storage power station, the fire spread speed is predicted with the fire center as the starting point, and the energy storage power station is divided into high-risk fire zones, medium-risk fire zones and low-risk fire zones;

[0072] The fire spread rate is predicted by the following formula:

[0073]

[0074] Where R represents the fire spread speed, I R It represents the heat released per unit area per minute; ζ represents the windless flux ratio; φ w represents the wind influence coefficient, φ s is the slope influence coefficient, ρb represents the density of combustibles in the energy storage power station; σ represents the surface area to volume ratio, Q represents the heat required for the combustibles in the energy storage power station to be ignited, e -bd It means that the fire spread speed decays exponentially with the increase of distance; c is a very small positive value.

[0075] Based on the preset fire linkage control strategy and the multiple fire zones that have been divided, corresponding fire zone control is carried out.

[0076] In this embodiment, high-risk fire zones include fire centers, fire areas, and areas where the fire spread speed is within a first threshold range; high-risk fire zones are set as critical values ​​where the fire spreads extremely quickly, the fire is difficult to control, and poses a serious threat to personnel and equipment. In this area, emergency response procedures must be initiated immediately to evacuate personnel and select appropriate fire extinguishing methods and fire extinguishing agents based on the type and size of the fire.

[0077] The medium-risk fire zone is located outside the high-risk fire zone and is an area where the fire spread speed is within the second threshold range; it is between high risk and low risk, and the fire spreads faster but is still controllable; some measures will be taken to prevent the spread of fire, and measures to isolate the source of fire will be set up in this area to cut off the path of fire spread, control the development of the fire, and protect the surrounding area.

[0078] The low-risk fire zone is located outside the medium-risk fire zone. It is an area where the fire spread speed is within the third threshold range. The fire spread speed is slow and only needs to be monitored.

[0079] In this embodiment, the first image is acquired by the monitoring device of the energy storage power station. Since the monitoring device is set at various locations, the first image of multiple angles is acquired. The combination of multi-angle image acquisition and image recognition technology can quickly and accurately identify the fire center and fire area; through fire zoning, the energy storage power station is divided into multiple areas with different fire risks, which not only makes it possible to more reasonably allocate and utilize firefighting resources, but also prevents excessive firefighting and protects more energy storage batteries from fire and firefighting damage.

[0080] Embodiment 2

[0081] A fire zoning and fire linkage control system for an energy storage power station, characterized by comprising: a first acquisition module: acquiring multi-angle first images of a fire in the energy storage power station;

[0082] The second acquisition module is used to acquire the fire center and the fire area according to the first image;

[0083] Partition module: divides the energy storage power station into multiple fire zones according to the fire center and fire area;

[0084] Control module: Based on the preset fire linkage control strategy and multiple fire zones, perform corresponding fire zone control.

[0085] It should be understood that the above specific embodiments of the present invention are only used to illustrate or explain the principles of the present invention, and do not constitute a limitation of the present invention. Therefore, any modifications, equivalent substitutions, improvements, etc. made without departing from the spirit and scope of the present invention should be included in the protection scope of the present invention. In addition, the appended claims of the present invention are intended to cover all changes and modifications that fall within the scope and boundaries of the appended claims, or the equivalent forms of such scope and boundaries.

[0086] The present invention has been described above with reference to the embodiments of the present invention. However, these embodiments are for illustrative purposes only and are not intended to limit the scope of the present invention. The scope of the present invention is defined by the appended claims and their equivalents. Without departing from the scope of the present invention, a person skilled in the art may make various substitutions and modifications, which should all fall within the scope of the present invention.

[0087] Although the embodiments of the present invention have been described in detail, it should be understood that the various changes, substitutions, and alterations could be made hereto without departing from the spirit and scope of the invention.

[0088] Obviously, the above embodiments are merely examples for the purpose of clear explanation, and are not intended to limit the implementation methods. For those skilled in the art, other different forms of changes or modifications can be made based on the above description. It is not necessary and impossible to list all the implementation methods here. The obvious changes or modifications derived therefrom are still within the scope of protection of the invention.

Claims

1. A fire zoning and fire linkage control method for an energy storage power station, characterized in that: include: Acquire multi-angle first images of a fire in an energy storage power station; Acquire the fire center and the fire area according to the first image; Divide the energy storage power station into multiple fire zones according to the fire center and fire area; Based on the preset fire linkage control strategy and the multiple fire zones that have been divided, corresponding fire zone control is carried out.

2. The method according to claim 1, characterized in that The step of acquiring the fire center and the fire area according to the first image includes: Construct a coordinate system, wherein the coordinate system takes the center of the energy storage power station as the origin, the first direction of the energy storage power station as the X-axis, the second direction of the energy storage power station as the Y-axis, and the direction perpendicular to the plane of the energy storage power station as the Z-axis; Respectively identifying flame coordinates of flames in the first images at multiple angles in the constructed coordinate system; fusing a plurality of the flame coordinates to generate a flame characteristic graph; The center point algorithm is used to obtain the fire center of the flame characteristic diagram according to the generated flame characteristic diagram.

3. The method according to claim 2, characterized in that The respectively identifying the flame coordinates of the flame in the first image at multiple angles in the constructed coordinate system includes obtaining the flame coordinates of the flame in the constructed coordinate system using the following formula: Among them, (u, v) represents the pixel coordinates of the flame obtained in the first image; K is the internal parameter matrix of the device that obtains the first image, R and t are the rotation matrix and translation vector from the constructed coordinate system to the coordinate system of the device that obtains the first image, and (x', y', z') are the coordinates of the flame in the constructed coordinate system.

4. The method according to claim 3, characterized in that The step of fusing the plurality of flame coordinates to generate a flame characteristic graph includes: Marking the flame coordinates in the first image at multiple angles in the constructed coordinate system to obtain a plurality of marking points; The plurality of marked points are connected to generate a flame characteristic diagram.

5. The method according to claim 4, characterized in that The connecting the plurality of marked points comprises connecting them using the following formula: Among them, u represents the independent variable parameter, u∈[0,1]; d i Represents the annotation point, n is the number of annotation points; N i,k (u) represents the k-order B-spline basis function; ω i Represents the weight factor.

6. The method according to claim 5, characterized in that Using the center point algorithm, obtaining the fire center of the flame characteristic diagram includes: The fire center of the flame signature is calculated using the following formula, Among them, (x i ,y i ) represents the coordinates of the outer contour of the flame characteristic diagram, i = 1, 2, ..., n; (x m ,y m ) represents the coordinates of the fire center.

7. The method according to claim 6, characterized in that According to the fire center and fire area, the energy storage power station is divided into multiple fire zones including: According to the battery type and fire area of ​​the energy storage power station, the fire spread speed is predicted with the fire center as the starting point, and the energy storage power station is divided into high-risk fire zones, medium-risk fire zones and low-risk fire zones.

8. The method according to claim 7, characterized in that The high-risk fire zones include the fire center, the fire area, and the area where the fire spread speed is within the first threshold range; The medium-risk fire zone is located outside the high-risk fire zone and is an area where the fire spread speed is within the second threshold range; The low-risk fire zone is located outside the medium-risk fire zone and is an area where the fire spread speed is within a third threshold range.

9. The method according to claim 8, characterized in that The fire spread rate is predicted by the following formula: Where R represents the fire spread speed, I R It represents the heat released per unit area per minute; ζ represents the windless flux ratio; φ w represents the wind influence coefficient, φ s is the slope influence coefficient, ρ b represents the density of combustibles in the energy storage power station; σ represents the surface area to volume ratio, Q represents the heat required for the combustibles in the energy storage power station to be ignited, e -bd It means that the fire spread speed decays exponentially with the increase of distance; c is a very small positive value.

10. A fire zoning and fire linkage control system for an energy storage power station, characterized in that: include: A first acquisition module: acquiring a first image of a fire in an energy storage power station from multiple angles; The second acquisition module is used to acquire the fire center and the fire area according to the first image; Partition module: divides the energy storage power station into multiple fire zones according to the fire center and fire area; Control module: Based on the preset fire linkage control strategy and multiple fire zones, perform corresponding fire zone control.

Images