Wind driven generator cabin fire early warning system based on image recognition

Abstract

The invention relates to the technical field of wind driven generators, in particular to a wind driven generator cabin fire early warning system based on image recognition. Comprising a central control unit used for establishing a smoke image model; the monitoring unit is used for setting a plurality of monitoring sub-areas, and monitoring sub-modules are arranged in the monitoring sub-areas; the monitoring unit is used for collecting monitoring data in each monitoring sub-region, and the monitoring data comprises equipment image data and environment image data; the smoke unit is used for judging whether smoke exists in the cabin or not; a plurality of monitoring sub-areas are established according to equipment parameters in the cabin of the wind driven generator, whether smoke exists in the cabin or not is monitored in real time, and when smoke does not exist, potential fire risk sources are found in time according to equipment state models in the monitoring sub-areas, and early warning maintenance is carried out. When smoke exists in the cabin, the possible spreading area and speed of the smoke are predicted, so that data support is provided for fire-fighting decision making, and cost loss caused by a fire disaster is reduced.

Description

Technical Field

[0001] The present application relates to the technical field of wind turbines, and in particular to a wind turbine cabin fire warning system based on image recognition. Background Art

[0002] The main components of wind power, such as the inverter, transformer and controller, are all located in the wind turbine cabin. These components contain a large number of electrical components. Once high temperature, electrical short circuit and sparking occur, it is very easy to cause a fire. At the same time, the hydraulic oil and gear box of the hydraulic station of the wind turbine, as well as the lubricating oil, cabin cover, fairing and blades of the oil pump station are all flammable materials. Once the electrical components of the inverter, transformer and controller in the wind turbine cabin catch fire, it is very easy to cause a fire in the entire cabin and even the hub blades.

[0003] With the widespread application of wind power generation technology, fire safety in wind turbine cabins has become a crucial issue. The existing fire protection system in wind turbine cabins has many shortcomings: ordinary smoke and temperature detectors are prone to false alarms or failures in harsh environments such as large temperature differences at high altitudes, high humidity, and strong winds and sand, and have low reliability. The lack of effective visual monitoring means makes it difficult to accurately locate the fire source and the development of the fire in the early stages of a fire, which is not conducive to taking targeted firefighting measures in a timely manner. Summary of the invention

[0004] The purpose of this application is: to solve the above-mentioned technical problems, this application provides a wind turbine cabin fire warning system based on image recognition, aiming to improve the fire warning efficiency and processing speed in the wind turbine cabin, and ensure the safe operation of the wind turbine.

[0005] In some embodiments of the present application, multiple monitoring sub-areas are established based on the equipment parameters inside the wind turbine cabin, and by adding a smoke unit, real-time monitoring is performed on whether there is smoke inside the cabin. When there is no smoke, all equipment inside the cabin is monitored based on the equipment status models established in each monitoring sub-area to determine whether the equipment has abnormal heating, smoking, component displacement or damage, etc., so as to promptly discover potential fire risk sources, conduct early warning maintenance, and ensure safe operation of the cabin.

[0006] In some embodiments of the present application, when there is smoke in the cabin, the monitoring unit continuously collects environmental images in each monitoring sub-area, performs real-time analysis and processing on the collected image sequence, calculates the diffusion direction and speed of the smoke through comparative analysis of multiple consecutive frames of images, and generates a smoke movement trend map based on the spatial layout information of the cabin to predict the area and speed at which the smoke may spread, thereby providing data support for fire-fighting decisions, improving the efficiency of fire handling inside the cabin, and reducing the cost losses caused by the fire.

[0007] In some embodiments of the present application, a wind turbine nacelle fire warning system based on image recognition is provided, comprising: Central control unit, used to build smoke image model; A monitoring unit, used to set a plurality of monitoring sub-areas, wherein the monitoring sub-areas are provided with monitoring sub-modules; The monitoring unit is used to collect monitoring data in each monitoring sub-area, and the monitoring data includes equipment image data and environment image data; Smoke unit, used to determine whether there is smoke inside the cabin; The central control unit comprises: A first processing module, used to set working parameters of the monitoring unit; The equipment module is used to establish the equipment status model of each monitoring sub-area and generate the operation abnormal value of each monitoring sub-area according to the preset monitoring time node; The second processing module is used to generate fire fighting decisions based on the smoke image model and all environmental image data.

[0008] In some embodiments of the present application, the first processing module is further used to: Get the real-time smoke status inside the cabin; If there is no smoke, set the monitoring unit to the first-level working mode; The first-level working mode includes: Set multiple monitoring time nodes; Acquire equipment image data of each monitoring sub-area according to preset monitoring time nodes; If smoke is present, set the monitoring unit to secondary working mode; The secondary working mode includes: Set the image acquisition parameters of the monitoring unit; Collect environmental image data of each monitoring sub-area; Generate feedback data packets for each monitoring sub-area.

[0009] In some embodiments of the present application, the device module is also used for: Establish a monitoring sub-area sequence A, A=(a1, a2…a i …a n ), where a i is the ith monitoring sub-area; n is the number of monitoring sub-areas; Set a according to the monitoring sub-area sequence A i Monitor sub-areas for the target; Obtain the device parameters of the target monitoring sub-area and generate a training data packet based on the device parameters; Establishing a device status model for the target monitoring sub-area based on the training data packet; Establish the equipment status model of each monitoring sub-area in turn; Establish the equipment state model series B, B=(b1, b2…b i …b n ), where bi is the equipment status model of the i-th monitoring sub-area.

[0010] In some embodiments of the present application, the device module is also used for: Set the device state model of the target monitoring sub-area as the target device state model; Obtain the device image data of the target monitoring sub-area at the current monitoring time node; preprocessing device image data based on a target device state model; Generate the abnormal operation value f of the target monitoring sub-area at the current monitoring time node according to the processing result; f= µ i *j i ]; Among them, θ is the number of equipment indicators in the target monitoring sub-area; µ i is the influencing factor of the i-th equipment index; j i is the deviation evaluation value of the i-th equipment indicator in the target monitoring sub-area at the current monitoring time node; Generate the abnormal operation value of each monitoring sub-area at the current monitoring time node in sequence; Establish abnormal operation value series F, F=(f1,f2…f i …f n ), where f i is the abnormal operation value of the i-th monitoring sub-area at the current monitoring time node; According to the abnormal operation value series F, it is determined whether an early warning instruction is generated at the current monitoring time node.

[0011] In some embodiments of the present application, determining whether a warning instruction is generated at the current monitoring time node includes: Generate an operation risk value c according to the abnormal operation value series F; c=e1*Q1* f i ]+e2*Q2* Y(i)*(f i -f')]; Among them, 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; f' is the abnormal operation value threshold; Y(i) is the selection coefficient, if (f i -f')>0,Y(i)=1 / (f i -f'); if (fi -f') < 0, Y(i) = 0; Preset the first operating risk value threshold C1; If c > C1, generate a warning instruction at the current monitoring time node; If c < C1, do not generate a warning instruction at the current monitoring time node b.

[0012] In some embodiments of the present application, the second processing module is further configured to: When the monitoring unit is in the secondary working mode, obtain the feedback data packets of each monitoring sub-region; Set a according to the monitoring sub-region sequence A i As the sub-region to be diagnosed; Establish an environmental image sequence D based on the feedback data packet of the sub-region to be diagnosed, D = (d1, d2…d i …d m ), where d i Is the i-th frame environmental image of the sub-region to be diagnosed collected based on the time series; m is the environmental image acquisition quantity; Generate a smoke analysis result for the sub-region to be diagnosed according to the smoke image model and the environmental image sequence D; Generate smoke analysis results for each monitoring sub-region in sequence; Perform fusion processing on all the smoke analysis results, and generate a smoke movement trend chart according to the fusion result; Generate a fire fighting decision according to the smoke movement trend chart.

[0013] In some embodiments of the present application, when generating the smoke analysis result of the diagnostic sub-region, it includes: Set d in sequence according to the environmental image sequence D i As the target environmental image; Obtain the smoke contour map k1 in the target environmental image; Obtain the smoke contour map k2 of the previous frame environmental image based on the time series of the target environmental image; Generate the smoke movement parameters in the target environmental image according to the comparison result of the smoke contour map k1 and the smoke contour map k2; Generate the smoke movement parameters of each environmental image in sequence; Generate the smoke diffusion direction and the smoke diffusion speed sequence V of the sub-region to be diagnosed according to all the smoke movement parameters; Smoke diffusion speed sequence V, V = (v1, v2…v i …v m ), where v i Is the smoke diffusion speed in the i-th frame environmental image of the sub-region to be diagnosed; Generate the initial fire value g of the sub-region to be diagnosed according to the smoke diffusion speed sequence V The smoke analysis results of the sub-area to be diagnosed are generated according to the initial fire value g and the smoke diffusion direction.

[0014] In some embodiments of the present application, generating an initial fire value g of a sub-area to be diagnosed includes: g=e3*Q3* v i / m]+e4*Q4*U; Among them, e3 is the preset third weight coefficient; e4 is the preset fourth weight coefficient; Q3 is the preset third fixed coefficient; Q4 is the preset fourth fixed coefficient; U is the primary reference value generated based on the smoke diffusion speed series V.

[0015] In some embodiments of the present application, the second processing module is further used to: Establish a correlation model based on the location parameters of all monitoring sub-areas; Obtain the smoke diffusion direction of each monitoring sub-area; Generate a smoke movement trend graph based on the correlation model and the smoke diffusion direction of all monitored sub-areas; Generate compensation coefficients for each monitoring sub-area based on the smoke movement trend graph; Establish compensation coefficient series R, R=(r1, r2…r i …r n ), where r i is the compensation coefficient of the i-th monitoring sub-area; Generate the first-level fire value of each monitoring sub-area according to the compensation coefficient sequence R; Generate firefighting decisions based on all first-level fire values.

[0016] In some embodiments of the present application, when a firefighting decision is generated according to all primary fire values, it includes: Establish the first-level fire value series H=(h1,h2…h i …h n ), where h i is the first-level fire value of the i-th monitoring sub-area; h i =r i *g i， Among them, g i is the initial fire value of the ith monitoring sub-area; According to the first-level fire value series H, the working parameters of the fire-fighting equipment in each monitoring sub-area are set in turn.

[0017] Compared with the prior art, the wind turbine cabin fire warning system based on image recognition in the embodiment of the present application has the following beneficial effects: According to the equipment parameters inside the wind turbine cabin, multiple monitoring sub-areas are established, and by adding a smoke unit, the presence of smoke inside the cabin is monitored in real time. When there is no smoke, all the equipment inside the cabin is monitored according to the equipment status model established in each monitoring sub-area to determine whether the equipment has abnormal heating, smoking, component displacement or damage, etc., so as to promptly discover potential fire risk sources, conduct early warning maintenance, and ensure the safe operation of the cabin.

[0018] When there is smoke in the cabin, the monitoring unit continuously collects environmental images in each monitoring sub-area, performs real-time analysis and processing on the collected image sequence, calculates the diffusion direction and speed of the smoke through comparative analysis of multiple consecutive frames of images, and generates a smoke movement trend map based on the spatial layout information of the cabin to predict the area and speed at which the smoke may spread, thereby providing data support for fire-fighting decisions, improving the efficiency of fire handling inside the cabin, and reducing the cost losses caused by the fire. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 It is a structural schematic diagram of a wind turbine cabin fire warning system based on image recognition in the preferred embodiment of the present application. DETAILED DESCRIPTION

[0020] 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.

[0021] 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.

[0022] 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.

[0023] 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.

[0024] like Figure 1 As shown, a wind turbine cabin fire warning system based on image recognition in a preferred embodiment of the present application includes: Central control unit, used to build smoke image model; A monitoring unit, used to set a plurality of monitoring sub-areas, each of which is provided with a monitoring sub-module; The monitoring unit is used to collect monitoring data in each monitoring sub-area, and the monitoring data includes equipment image data and environment image data; Smoke unit, used to determine whether there is smoke inside the cabin; The central control unit includes: A first processing module, used to set working parameters of the monitoring unit; The equipment module is used to establish the equipment status model of each monitoring sub-area and generate the operation abnormal value of each monitoring sub-area according to the preset monitoring time node; The second processing module is used to generate fire fighting decisions based on the smoke image model and all environmental image data.

[0025] Specifically, the smoke unit is preferably a plurality of smoke sensors, wherein the smoke sensors are arranged in each monitoring sub-area for real-time monitoring of whether there is smoke inside the cabin.

[0026] Specifically, the monitoring submodule is preferably an infrared camera device, which can collect image data and temperature data in each monitoring sub-area.

[0027] Specifically, multiple monitoring sub-areas are established according to the spatial layout parameters inside the cabin and the location parameters of major components such as the wind turbine inverter, transformer and controller, and each monitoring sub-area is provided with a monitoring sub-module and fire-fighting equipment.

[0028] Specifically, the first processing module is also used for: Get the real-time smoke status inside the cabin; If there is no smoke, set the monitoring unit to the first-level working mode; The first-level working mode includes: Set multiple monitoring time nodes; Acquire equipment image data of each monitoring sub-area according to preset monitoring time nodes; If smoke is present, set the monitoring unit to secondary working mode; The secondary working modes include: Set the image acquisition parameters of the monitoring unit; Collect environmental image data of each monitoring sub-area; Generate feedback data packets for each monitoring sub-area.

[0029] Specifically, the first-level working mode means that there is no smoke inside the cabin. At this time, the operating status of each device is monitored to timely warn and repair potential fire hazards to avoid fire inside the cabin and ensure the safe operation of the cabin.

[0030] Specifically, the secondary working mode means that there is smoke inside the current cabin, and each monitoring sub-area needs to be analyzed to generate the diffusion direction and speed of the smoke and the area and speed at which the smoke may spread, so as to make accurate fire-fighting decisions and improve the efficiency of fire handling inside the cabin.

[0031] In a preferred embodiment of the present application, the device module is also used for: Establish a monitoring sub-area sequence A, A=(a1, a2…a i …a n ), where a i is the ith monitoring sub-area; n is the number of monitoring sub-areas; Set a according to the monitoring sub-area sequence A i Monitor sub-areas for the target; Obtain the device parameters of the target monitoring sub-area and generate a training data packet based on the device parameters; Establishing a device status model for the target monitoring sub-area based on the training data packet; Establish the equipment status model of each monitoring sub-area in turn; Establish the equipment state model series B, B=(b1, b2…b i …b n ), where bi is the equipment status model of the i-th monitoring sub-area.

[0032] Specifically, by analyzing the equipment in the target monitoring sub-area, an appearance model of the equipment in normal operating state is constructed, thereby generating a corresponding equipment state model.

[0033] Specifically, the equipment module is also used to: Set the device state model of the target monitoring sub-area as the target device state model; Obtain the device image data of the target monitoring sub-area at the current monitoring time node; preprocessing device image data based on a target device state model; Generate the abnormal operation value f of the target monitoring sub-area at the current monitoring time node according to the processing result; f= µ i *j i ]; Among them, θ is the number of equipment indicators in the target monitoring sub-area; µ i is the influencing factor of the i-th equipment index; j i is the deviation evaluation value of the i-th equipment indicator in the target monitoring sub-area at the current monitoring time node; Generate the abnormal operation value of each monitoring sub-area at the current monitoring time node in sequence; Establish abnormal operation value series F, F=(f1,f2…f i …f n ), where f i is the abnormal operation value of the i-th monitoring sub-area at the current monitoring time node; According to the abnormal operation value series F, it is determined whether an early warning instruction is generated at the current monitoring time node.

[0034] Specifically, the equipment indicators include, but are not limited to, equipment operating temperature and equipment operating appearance. The larger the deviation evaluation value is, the greater the deviation between the current equipment operating state and the normal operating state is.

[0035] Specifically, the collected device image data includes conventional images and infrared images. By analyzing the conventional images, deviation evaluation values ​​of various device indicators related to the device appearance are generated. By analyzing the infrared images, deviation evaluation values ​​of various device indicators related to the device operating temperature are generated.

[0036] Specifically, judging whether a warning instruction is generated at the current monitoring time node includes: Generate an operation risk value c according to the abnormal operation value series F; c=e1*Q1* f i ]+e2*Q2* Y(i)*(f i -f')]; Among them, 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; f' is the abnormal operation value threshold; Y(i) is the selection coefficient, if (f i -f')>0,Y(i)=1 / (f i -f'); if (f i -f')<0,Y(i)=0; Preset the first operating risk value threshold C1; If c > C1, generate a warning instruction at the current monitoring time node; If c < C1, do not generate a warning instruction at the current monitoring time node b.

[0037] Specifically, normalize all the parameters in the model by presetting the first fixed coefficient and the second fixed coefficient, so that each parameter in the model is within the same value range.

[0038] Specifically, the abnormal operation value threshold can be set according to historical parameters. The greater the operation risk value, the greater the possibility that there is a potential fire risk inside the nacelle at the current feedback time node (such as local overheating caused by electrical equipment short - circuit, high temperature generated by mechanical component friction, etc.).

[0039] Specifically, formulate a corresponding maintenance strategy according to the warning instruction, so as to timely eliminate the potential fire risk inside the nacelle.

[0040] It can be understood that in the above - mentioned embodiments, multiple monitoring sub - regions are established according to the equipment parameters inside the wind turbine nacelle, and by adding smoke units, it is monitored in real time whether there is smoke inside the nacelle. When there is no smoke, according to the equipment state models in each established monitoring sub - region, all the equipment inside the nacelle is monitored to judge whether there are abnormal situations such as abnormal heating, smoking, component displacement or damage of the equipment, timely discover potential fire risk sources, and give early warning for maintenance to ensure the safe operation of the nacelle.

[0041] In the preferred embodiment of the present application, the second processing module is further used for: When the monitoring unit is in the secondary working mode, obtain the feedback data packets of each monitoring sub - region; Set a i as the sub - region to be diagnosed according to the monitoring sub - region sequence A; Establish an environmental image sequence D according to the feedback data packet of the sub - region to be diagnosed, D=(d1, d2…d i …d m ), where d i is the i - th frame of environmental image of the sub - region to be diagnosed collected based on the time series; m is the environmental image acquisition amount; Generate a smoke analysis result of the sub - region to be diagnosed according to the smoke image model and the environmental image sequence D; Generate the smoke analysis results of each monitoring sub - region in turn; Perform fusion processing on all the smoke analysis results, and generate a smoke movement trend chart according to the fusion result; Generate a fire - fighting decision according to the smoke movement trend chart.

[0042] Specifically, when the smoke unit detects the presence of smoke inside the cabin, it collects multiple frames of environmental images of each monitoring sub-area and generates a corresponding image sequence based on the time series. By extracting the color of the smoke (the color of smoke produced by the combustion of different substances is different), the type of burning material is determined, and the diffusion direction and speed of the smoke are calculated through comparative analysis of multiple consecutive frames of images.

[0043] Specifically, when generating smoke analysis results for diagnostic sub-areas, these include: According to the environmental image sequence D, set d i is the target environment image; Obtain the smoke contour image k1 in the target environment image; Obtain a smoke contour image k2 of a previous frame of the target environment image based on the time series; Generate smoke motion parameters in the target environment image according to the comparison results of the smoke contour image k1 and the smoke contour image k2; Generate smoke motion parameters for each environment image in sequence; Generate a series V of smoke diffusion direction and smoke diffusion speed in the sub-region to be diagnosed according to all smoke motion parameters; Smoke diffusion speed series V, V = (v1, v2…v i …v m ), where v i is the smoke diffusion speed in the i-th frame of the environment image of the sub-area to be diagnosed; Generate the initial fire value g of the sub-area to be diagnosed according to the smoke diffusion speed series V; The smoke analysis results of the sub-area to be diagnosed are generated according to the initial fire value g and the smoke diffusion direction.

[0044] Specifically, if all data in the smoke diffusion speed series V are 0, it means that there is no smoke in the current sub-region to be diagnosed, that is, the fire point is not in the current sub-region to be diagnosed.

[0045] Specifically, generating the initial fire value g of the sub-area to be diagnosed includes: g=e3*Q3* v i / m]+e4*Q4*U; Among them, e3 is the preset third weight coefficient; e4 is the preset fourth weight coefficient; Q3 is the preset third fixed coefficient; Q4 is the preset fourth fixed coefficient; U is the primary reference value generated based on the smoke diffusion speed series V.

[0046] Specifically, a first-level reference value is set according to the changing state of the smoke diffusion speed. If the smoke diffusion speed is in an increasing state, the corresponding first-level reference value is larger; if it is in a stable or decreasing state, the corresponding first-level reference value is smaller. That is, the larger the first-level reference value, the faster the current smoke diffusion speed is.

[0047] Specifically, all parameters in the model are normalized by presetting the third fixed coefficient and the fourth fixed coefficient, so that each parameter in the model is in the same value range.

[0048] Specifically, the larger the initial fire value, the more serious the fire situation in the corresponding monitoring sub-area, and the need to increase the working efficiency of the corresponding fire-fighting equipment to control the spread of the fire in a timely manner and reduce the overall fire loss.

[0049] It can be understood that in the above embodiment, when there is smoke in the cabin, the monitoring unit continuously collects environmental images in each monitoring sub-area, performs real-time analysis and processing on the collected image sequence, calculates the diffusion direction and speed of the smoke through comparative analysis of multiple consecutive frames of images, and generates a smoke movement trend graph in combination with the spatial layout information of the cabin to predict the area and speed at which the smoke may spread, thereby providing data support for fire fighting decisions.

[0050] In a preferred embodiment of the present application, the second processing module is also used for: Establish a correlation model based on the location parameters of all monitoring sub-areas; Obtain the smoke diffusion direction of each monitoring sub-area; Generate a smoke movement trend graph based on the correlation model and the smoke diffusion direction of all monitored sub-areas; Generate compensation coefficients for each monitoring sub-area based on the smoke movement trend graph; Establish compensation coefficient series R, R=(r1, r2…r i …r n ), where r i is the compensation coefficient of the i-th monitoring sub-area; Generate the first-level fire value of each monitoring sub-area according to the compensation coefficient sequence R; Generate firefighting decisions based on all first-level fire values.

[0051] Specifically, according to whether there is an adjacent relationship between the monitoring sub-areas and the gas flow trend inside the cabin, the smoke diffusion model between the monitoring sub-areas is set to generate the corresponding association model.

[0052] Specifically, the monitoring sub-area where smoke may spread can be analyzed based on the smoke movement trend diagram, so as to set the corresponding compensation coefficient. The larger the compensation coefficient, the greater the possibility that smoke will diffuse in the corresponding monitoring sub-area.

[0053] Specifically, when generating firefighting decisions based on all first-level fire values, it includes: Establish the first-level fire value series H=(h1,h2…h i …h n ), where h i is the first-level fire value of the i-th monitoring sub-area; h i =r i *g i， Among them, g i is the initial fire value of the ith monitoring sub-area; According to the first-level fire value series H, the working parameters of the fire-fighting equipment in each monitoring sub-area are set in turn.

[0054] Specifically, the first-level fire value threshold is set, when h i When the fire value is greater than the first level threshold, the fire fighting equipment in the i-th monitoring sub-area is activated, and the fire fighting equipment in the i-th monitoring sub-area is activated according to h i Set the spray speed of the fire-fighting equipment; set the spray angle of the fire-fighting equipment in the i-th monitoring sub-area according to the smoke movement trend diagram.

[0055] It can be understood that in the above embodiment, when it is determined that a fire has occurred, the corresponding fire-fighting equipment (such as dry powder fire extinguishers, gas fire extinguishing devices, etc.) is activated according to the first-level fire value of each monitoring sub-area, and the optimal injection speed and injection angle are determined, thereby improving the efficiency of fire handling in the cabin and reducing fire losses.

[0056] According to the first concept of the present application, multiple monitoring sub-areas are established according to the equipment parameters inside the wind turbine cabin, and by adding a smoke unit, real-time monitoring is performed on whether there is smoke inside the cabin. When there is no smoke, all equipment inside the cabin is monitored according to the equipment status model established in each monitoring sub-area to determine whether the equipment has abnormal heating, smoking, component displacement or damage, etc., so as to promptly discover potential fire risk sources, conduct early warning maintenance, and ensure the safe operation of the cabin.

[0057] According to the second concept of the present application, when there is smoke in the cabin, the monitoring unit continuously collects environmental images in each monitoring sub-area, performs real-time analysis and processing on the collected image sequence, calculates the diffusion direction and speed of the smoke through comparative analysis of multiple consecutive frames of images, and generates a smoke movement trend map in combination with the spatial layout information of the cabin to predict the area and speed at which the smoke may spread, thereby providing data support for fire-fighting decisions, improving the efficiency of fire handling inside the cabin, and reducing the cost losses caused by the fire.

[0058] 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 wind turbine cabin fire warning system based on image recognition, characterized in that: Including: A central control unit for establishing a smoke image model; A monitoring unit for setting a plurality of monitoring sub - regions, and monitoring sub - modules are arranged in the monitoring sub - regions; The monitoring unit is used to collect monitoring data in each monitoring sub - region, and the monitoring data includes equipment image data and environmental image data; A smoke unit for judging whether there is smoke inside the engine room; The central control unit includes: A first processing module for setting the working parameters of the monitoring unit; An equipment module for establishing the equipment state model of each monitoring sub - region and generating the abnormal operation value of each monitoring sub - region according to the preset monitoring time node; A second processing module for generating a fire - fighting decision according to the smoke image model and all environmental image data.

2. The wind turbine cabin fire warning system based on image recognition according to claim 1, characterized in that: The first processing module is further used for: Obtaining the real - time smoke state inside the engine room; If there is no smoke, setting the monitoring unit to the first - level working mode; The first - level working mode includes: Setting a plurality of monitoring time nodes; Obtaining the equipment image data of each monitoring sub - region according to the preset monitoring time node; If there is smoke, setting the monitoring unit to the second - level working mode; The second - level working mode includes: Setting the image acquisition parameters of the monitoring unit; Collecting the environmental image data of each monitoring sub - region; Generating a feedback data packet for each monitoring sub - region.

3. The wind turbine cabin fire warning system based on image recognition according to claim 2, characterized in that: The equipment module is further used for: Establish a monitoring sub-area sequence A, A=(a1, a2…a i …a n ), where a i is the ith monitoring sub-area; n is the number of monitoring sub-areas; Set a according to the monitoring sub-area sequence A i Monitor sub-areas for the target; Obtaining the equipment parameters of the target monitoring sub - region and generating a training data packet according to the equipment parameters; Establishing the equipment state model of the target monitoring sub - region according to the training data packet; Sequentially establishing the equipment state models of each monitoring sub - region; Establish the equipment state model series B, B=(b1, b2…b i …b n ), where bi is the equipment status model of the i-th monitoring sub-area.

4. The wind turbine cabin fire warning system based on image recognition as claimed in claim 3, characterized in that: The equipment module is further used for: Setting the equipment state model of the target monitoring sub - region as the target equipment state model; Obtaining the equipment image data of the target monitoring sub - region at the current monitoring time node; Pre - processing the equipment image data based on the target equipment state model; Generating the abnormal operation value f of the target monitoring sub - region at the current monitoring time node according to the processing result; f= µ i *j i ]; Among them, θ is the number of equipment indicators in the target monitoring sub-area; µ i is the influencing factor of the i-th equipment index; j i is the deviation evaluation value of the i-th equipment indicator in the target monitoring sub-area at the current monitoring time node; Sequentially generating the abnormal operation values of each monitoring sub - region at the current monitoring time node; Establish abnormal operation value series F, F=(f1,f2…f i …f n ), where f i is the abnormal operation value of the i-th monitoring sub-area at the current monitoring time node; Judging whether to generate a warning instruction at the current monitoring time node according to the abnormal operation value sequence F.

5. The wind turbine cabin fire warning system based on image recognition according to claim 4, characterized in that: Judging whether to generate a warning instruction at the current monitoring time node includes: Generating an operation risk value c according to the abnormal operation value sequence F; c=e1*Q1* f i ]+e2*Q2* Y(i)*(f i -f')]; Among them, 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; f' is the abnormal operation value threshold; Y(i) is the selection coefficient, if (f i -f')>0,Y(i)=1 / (f i -f'); if (f i -f')<0,Y(i)=0; Presetting a first operation risk value threshold C1; If c > C1, generating a warning instruction at the current monitoring time node; If c < C1, not generating a warning instruction at the current monitoring time node b.

6. The wind turbine cabin fire warning system based on image recognition according to claim 5, characterized in that: The second processing module is further used for: When the monitoring unit is in the second - level working mode, obtaining the feedback data packets of each monitoring sub - region; Set a according to the monitoring sub-area sequence A i is the sub-region to be diagnosed; According to the feedback data packet of the sub-area to be diagnosed, the environmental image sequence D is established, D=(d1, d2…d i …d m ), where d i is the i-th frame of the environment image of the sub-region to be diagnosed acquired based on the time series; m is the amount of environment image acquisition; Generating the smoke analysis result of the sub - region to be diagnosed according to the smoke image model and the environmental image sequence D; Sequentially generating the smoke analysis results of each monitoring sub - region; Performing fusion processing on all smoke analysis results and generating a smoke movement trend chart according to the fusion result; Generating a fire - fighting decision according to the smoke movement trend chart.

7. The wind turbine cabin fire warning system based on image recognition according to claim 6, characterized in that: When generating the smoke analysis result of the diagnostic sub - region, it includes: According to the environmental image sequence D, set d i is the target environment image; Obtaining the smoke contour map k1 in the target environmental image; Obtaining the smoke contour map k2 of the previous frame of the environmental image based on the time series of the target environmental image; Generate smoke motion parameters in the target environment image according to the comparison results of the smoke contour image k1 and the smoke contour image k2; Generate smoke motion parameters for each environment image in sequence; Generate a series V of smoke diffusion direction and smoke diffusion speed in the sub-region to be diagnosed according to all smoke motion parameters; Smoke diffusion speed series V, V = (v1, v2…v i …v m ), where v i is the smoke diffusion speed in the i-th frame of the environment image of the sub-area to be diagnosed; Generate the initial fire value g of the sub-area to be diagnosed according to the smoke diffusion speed series V; The smoke analysis results of the sub-area to be diagnosed are generated according to the initial fire value g and the smoke diffusion direction.

8. The wind turbine cabin fire warning system based on image recognition according to claim 7, characterized in that: Generate the initial fire value g of the sub-area to be diagnosed, including: g=e3*Q3* v i / m]+e4*Q4*U; Among them, e3 is the preset third weight coefficient; e4 is the preset fourth weight coefficient; Q3 is the preset third fixed coefficient; Q4 is the preset fourth fixed coefficient; U is the primary reference value generated based on the smoke diffusion speed series V.

9. The wind turbine cabin fire warning system based on image recognition according to claim 8, characterized in that: The second processing module is also used for: Establish a correlation model based on the location parameters of all monitoring sub-areas; Obtain the smoke diffusion direction of each monitoring sub-area; Generate a smoke movement trend graph based on the correlation model and the smoke diffusion direction of all monitored sub-areas; Generate compensation coefficients for each monitoring sub-area based on the smoke movement trend graph; Establish compensation coefficient series R, R=(r1, r2…r i …r n ), where r i is the compensation coefficient of the i-th monitoring sub-area; Generate the first-level fire value of each monitoring sub-area according to the compensation coefficient sequence R; Generate firefighting decisions based on all first-level fire values.

10. The wind turbine cabin fire warning system based on image recognition according to claim 9, characterized in that: When generating firefighting decisions based on all primary fire values, including: Establish the first-level fire value series H=(h1,h2…h i …h n ), where h i is the first-level fire value of the i-th monitoring sub-area; h i =r i *g i， Among them, g i is the initial fire value of the ith monitoring sub-area; According to the first-level fire value series H, the working parameters of the fire-fighting equipment in each monitoring sub-area are set in turn.

Images