Fire extinguishing automatic homing method and system

Abstract

The invention discloses a fire extinguishing automatic homing method and system, and the method is characterized in that the method comprises the following steps: 1, collecting a target image through employing an infrared thermal imaging temperature measurement module and a visible light imaging module, and carrying out the preprocessing of the target image; 2, analyzing the preprocessed image by adopting a template matching method, and confirming a temperature anomaly region in the preprocessed image; 3, evaluating the temperature anomaly severity, the flame size, the detection distance and the geographic information of the temperature anomaly region by means of a DFMEA method, and obtaining a fire source sequence according to the temperature anomaly severity, the flame size, the detection distance and the geographic information; and 4, the fire extinguishing path of the automatic homing vehicle and the fire extinguishing mode of the automatic homing device are controlled according to the fire source sequence. According to the method, the combustion characteristics of the fire sources are obtained by analyzing the temperature abnormal area in the target image, and the sequence of the fire sources is judged by means of the DFMEA method and the fire is extinguished in sequence.

Description

Technical Field

[0001] The present invention relates to the field of power systems, and more specifically, to a method and system for automatic fire extinguishing. Background Art

[0002] Substations are an important foundation and support for strong smart grids. They are the source of grid operation data collection and command execution units. They are closely linked to other links and are an important guarantee for the safe, high-quality and economical operation of a unified strong smart grid. They are also the main embodiment of the realization of smart grid automation features. Therefore, strengthening the construction of substations is crucial to the construction of strong smart grids.

[0003] The modern electric power industry is developing towards high voltage levels. In order to ensure the safe and efficient operation of power production, higher requirements are placed on the status inspection and maintenance of power equipment and safety assurance measures.

[0004] The CAFS fire extinguishing system is an important equipment for fighting fires in substations / converter stations, and is widely used in the field of smart fire protection. In the substation environment, the homing system used for the CAFS fire extinguishing system should be a key device to assume the responsibility of locating the location information of the fire source and guiding the fire extinguishing action. Due to its non-contact and infrared radiation sensitive characteristics, the infrared thermal imaging homing system has shown excellent technical performance and application effects in the temperature measurement and fault warning of equipment and machinery, and has performed well in the detection of the operating status of power equipment. Regularly checking the joints / conductive parts of the disconnector equipment with infrared temperature measuring equipment, especially during heavy loads or high temperatures, strengthening the monitoring of the temperature rise of the operating equipment, and taking timely measures when problems are found are important ways to ensure the safety of the substation.

[0005] However, the existing fire cannon fire fighting fire trucks have insufficient fire-seeking capabilities. The CAFS fire-fighting system's seeking system may misjudge the fire situation under visible light interference, reduce sensitivity under station radiation interference, and be difficult to be received by the detector due to radiation information reflection in extreme weather and when heavy oil burns in the station to produce black smoke.

[0006] In view of the above problems, there is an urgent need for a method and system for automatic fire extinguishing. Summary of the invention

[0007] In order to solve the deficiencies in the prior art, the present invention provides a method and system for automatic fire extinguishing, which obtains the combustion characteristics of the fire source by analyzing the temperature abnormality area in the target image, and uses the DFMEA method to determine the order of the fire sources and extinguish the fires in sequence.

[0008] The present invention adopts the following technical solution.

[0009] The first aspect of the present invention relates to a method for automatic fire extinguishing search, characterized in that the method comprises the following steps: step 1, using an infrared thermal imaging temperature measurement module and a visible light imaging module to collect a target image, and preprocessing the target image; step 2, using a template matching method to analyze the preprocessed image, and confirming the temperature abnormality area in the preprocessed image; step 3, using the DFMEA method to evaluate the temperature abnormality severity, flame size, detection distance, and geographic information of the temperature abnormality area, and obtain the fire source ranking based on this; step 4, controlling the fire extinguishing path of the automatic search vehicle and the fire extinguishing method of the automatic search device according to the fire source ranking.

[0010] Preferably, an infrared thermal imaging temperature measurement module and a visible light imaging module are used to capture the target image, and the target image is preprocessed, including: setting a temperature anomaly threshold, extracting the fire source area in the target image, and obtaining the actual coordinates of the fire source area through image positioning; using one or more of spatial domain transformation, spatial-frequency domain transformation, and frequency domain transformation to enhance the target image; and using wavelet transform to perform multi-scale decomposition on the enhanced target image to extract the gradient image of the target image or the fire source area.

[0011] Preferably, a template matching method is used to analyze the preprocessed image and confirm the temperature abnormality area in the preprocessed image, including: pre-calibrating the points, lines, and surfaces of the background, and corresponding the points, lines, and surfaces in the pre-calibrated background to the gradient image by identifying the feature points in the target image; according to the temperature of the pixel points in the gradient image, reading the temperature, temperature range, and average temperature of the points, lines, and surfaces in the pre-calibrated background.

[0012] Preferably, a template matching method is used to analyze the preprocessed image and confirm the abnormal temperature area in the preprocessed image, including: presetting the normal temperature range of the points, lines and surfaces in the calibration background, and analyzing the temperature characteristics of the points, lines and surfaces read out by the gradient image based on this; if the temperature characteristics fall within the normal temperature range, the points, lines and surfaces do not belong to the automatically searched target; if the temperature characteristics do not fall within the normal temperature range, the points, lines and surfaces belong to the automatically searched target.

[0013] Preferably, the DFMEA method is used to evaluate the severity of temperature anomaly, flame size, detection distance, and geographic information in the temperature anomaly area, and the fire source ranking is obtained accordingly, including: for each automatically searched target, the DFMEA method is used to obtain the fire source ranking of the automatically searched target; the DFMEA method uses the temperature anomaly severity, flame size, detection distance, and geographic information to calculate the fire source ranking of the automatically searched target; the temperature anomaly severity, flame size, detection distance, and geographic information are obtained based on the temperature features in multiple gradient images corresponding to the automatically searched target.

[0014] Preferably, the fire extinguishing path of the automatic seeker vehicle and the fire extinguishing method of the automatic seeker are controlled according to the fire source ranking, including: the fire extinguishing path of the automatic seeker vehicle is obtained based on the fire source ranking of the automatic seeker target and the geographic information planning of the automatic seeker target; the fire extinguishing method of the automatic seeker includes the azimuth angle of the automatic seeker, the fire extinguishing medium, the fire extinguishing intensity, and the fire extinguishing time, and the fire extinguishing method is obtained based on the severity of the temperature anomaly, the flame size, and the geographic information of the automatic seeker target.

[0015] Preferably, controlling the fire extinguishing path of the automatic homing vehicle and the fire extinguishing method of the automatic homing device according to the fire source sequence includes: extinguishing the fire based on the fire extinguishing path of the automatic homing vehicle and the fire extinguishing method of the automatic homing device.

[0016] The second aspect of the present invention relates to a system for automatic fire extinguishing search using the method described in the first aspect of the present invention; characterized in that: the system includes an acquisition module, an analysis module, a sorting module and a fire extinguishing module; wherein the acquisition module is used to acquire target images using an infrared thermal imaging temperature measurement module and a visible light imaging module, and preprocess the target images; the analysis module is used to analyze the preprocessed images using a template matching method, and confirm the temperature abnormality area in the preprocessed images; the sorting module is used to evaluate the temperature abnormality severity, flame size, detection distance, and geographic information of the temperature abnormality area with the help of the DFMEA method, and obtain the fire source ranking accordingly; the fire extinguishing module is used to control the fire extinguishing path of the automatic search vehicle and the fire extinguishing method of the automatic search device according to the fire source ranking.

[0017] A third aspect of the present invention relates to a terminal, comprising a processor and a storage medium; the storage medium is used to store instructions; the processor is used to operate according to the instructions to execute the steps of the method described in the first aspect of the present invention.

[0018] A fourth aspect of the present invention relates to a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the method described in the first aspect of the present invention.

[0019] The beneficial effect of the present invention is that, compared with the prior art, the method and system for automatic fire extinguishing search in the present invention obtains the combustion characteristics of the fire source by analyzing the temperature abnormal area in the target image, and uses the DFMEA method to judge the order of the fire sources and extinguish the fires in sequence. The method of the present invention solves the problem of insufficient fire-finding ability of fire-fighting cannon fire-fighting fire trucks, and solves the problems of misjudgment of fire conditions by the CAFS fire-fighting system search system under visible light interference, decreased sensitivity under radiation interference in the station, and radiation information reflection under extreme weather and black smoke generated by heavy oil combustion in the station, which makes it difficult to be received by the detector. The purpose of improving the fire-finding ability of the substation fire-fighting system is achieved, and the technical problem of reducing the risk of damage to the fire truck itself can be solved.

[0020] The beneficial effects of the present invention also include:

[0021] 1. For multiple abnormal situations, risk assessment is performed based on abnormal area, distance and other information, and the input is serialized in the order of decreasing danger, so as to ensure the scientificity and effectiveness of the fire extinguishing sequence. At the same time, the extinguishing of the fire source is tracked during the fire extinguishing process, and the action path of the sprinkler is dynamically planned in real time.

[0022] 2. The main controller automatically finds and compares the temperature with the calibrated background system temperature, accurately reads the temperature range of points, lines, surfaces, and regions, the extreme high and low temperature values, the lowest temperature, the maximum temperature, and the average temperature. At the same time, it automatically detects, tracks, and marks the highest and lowest temperature points in the detection scene. Based on the fire test combustion data and the combustion temperature fitting curve, it analyzes the changing characteristics of the temperature field around the flame, and gives the longitude and latitude coordinates of the abnormal area. The coordinates of the temperature abnormality area are calibrated and prioritized according to the temperature abnormality, abnormal area, and distance, and the fire cannon spray system is linked. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 This is a schematic diagram of image preprocessing in a method for automatic fire extinguishing search according to the present invention. DETAILED DESCRIPTION

[0024] In order to make the purpose, technical solution and advantages of the present invention clearer and more accurate, the technical solution of the present invention is described in detail below through multiple specific implementation methods. The embodiments adopted by the present invention are only used to explain the present invention and are not used to limit the content of the present invention.

[0025] Figure 1 FIG. 1 is a schematic diagram of image preprocessing in a method for automatic fire extinguishing search according to the present invention. Figure 1 As shown, the first aspect of the present invention relates to a method for automatic fire extinguishing, which includes steps 1 to 4.

[0026] Step 1: Use infrared thermal imaging temperature measurement module and visible light imaging module to collect target images and perform preprocessing on the target images.

[0027] Preferably, an infrared thermal imaging temperature measurement module and a visible light imaging module are used to capture the target image, and the target image is preprocessed, including: setting a temperature anomaly threshold, extracting the fire source area in the target image, and obtaining the actual coordinates of the fire source area through image positioning; using one or more of spatial domain transformation, spatial-frequency domain transformation, and frequency domain transformation to enhance the target image; and using wavelet transform to perform multi-scale decomposition on the enhanced target image to extract the gradient image of the target image or the fire source area.

[0028] The method of the present invention includes an automatic seeker and an automatic seeker main controller, and the automatic seeker exchanges information with the automatic seeker main controller to complete the return of fire location information. The automatic seeker consists of an infrared thermal imaging recognition device and a color image recognition device, and simultaneously collects infrared radiation emitted by external objects and captures color images containing fire information. The automatic seeker main controller compares and measures the calibrated background system temperature, accurately reads the lowest temperature, highest temperature and average temperature of points, lines and areas, and automatically detects, tracks and marks the highest and lowest temperature points in the detection scene. Based on the fire test combustion data and the combustion temperature fitting curve, the temperature field change characteristics around the flame are analyzed, and the longitude and latitude coordinates of the abnormal area are given to link the fire cannon spray system.

[0029] In the main controller of the automatic search, the temperature anomaly threshold is first set to identify the suspected fire source area. The images collected by the infrared thermal imaging temperature measurement module and the visible light imaging module are subjected to image analysis and positioning processing to achieve accurate regional positioning of the target fire source area. The image positioning process can collect the position, angle, zoom multiple and other information of the infrared thermal imaging temperature measurement module and the visible light imaging module in real time, and analyze the actual position of the image based on this. In another method, a three-dimensional model within a limited interval such as a substation can be obtained by pre-scanning, and geometric features and color features can be extracted from it to construct feature points. When collecting the target image, the feature points in the target image are analyzed, and the actual collection position, angle, depth and other features of the target image are obtained based on this. The target information extracted at different angles and scales is converted into position information in a standard three-dimensional model by feature extraction, so that the flame information represented by each pixel on the target image corresponds to the actual space to be measured.

[0030] The spatial domain transformation, spatial domain-frequency domain transformation, and frequency domain transformation can adopt the commonly used methods in the existing technology. For example, the spatial domain transformation can include the common methods such as graying the pixel values ​​in the spatial domain dimension of the image, denoising, etc. The spatial domain-frequency domain transformation can be used to extract the enhanced information of the image in a certain frequency domain, and the frequency domain transformation can be filtered by high-pass filtering, low-pass filtering, medium-pass filtering, etc. In short, the above methods improve the image quality and achieve image enhancement.

[0031] On this basis, wavelet transform and other methods can be used to perform multi-scale decomposition, extract gradient images, and assist in identifying and locating temperature anomaly areas. Based on wavelet decomposition, wavelet transform decomposes the preprocessed and enhanced target image into multiple gradient images under different wavelets. On this basis, the fire source information in the target image is analyzed through the features in multiple gradient images.

[0032] Through the above-mentioned method, the present invention is based on the technical principle of passively receiving the target thermal infrared radiation. Even in extreme weather such as rain and fog, it is still very easy to penetrate obstacles and detect fire source information, so the image processing method has strong penetration. The image information intuitively displays the temperature field on the surface of the object, is not affected by strong light, and supports anti-strong light interference. Since infrared thermal imaging is not affected by strong light, harsh environment, etc., its stability is stronger than infrared detection, red ultraviolet detection and visible light detection. Through a comprehensive collection method, the stability of the collected information is ensured. The temperature resolution of the image acquisition and processing process of the present invention is as high as 50mk, the temperature measurement range is -50~550℃, and the temperature measurement accuracy is as high as ±2℃. The principle is heat detection, which is not affected by radiation and reflection in the station. It is very suitable for non-contact large-area telemetry and has a long detection distance.

[0033] Step 2: Analyze the preprocessed image using a template matching method and identify the temperature abnormality area in the preprocessed image.

[0034] Preferably, a template matching method is used to analyze the preprocessed image and confirm the temperature abnormality area in the preprocessed image, including: pre-calibrating the points, lines, and surfaces of the background, and corresponding the points, lines, and surfaces in the pre-calibrated background to the gradient image by identifying the feature points in the target image; according to the temperature of the pixel points in the gradient image, reading the temperature, temperature range, and average temperature of the points, lines, and surfaces in the pre-calibrated background.

[0035] Feature analysis methods such as SIFT can extract information from the calibration background. The calibration background can be collected in advance. These features may include the edges of buildings, etc. By collecting feature information in advance, geometric features at different spatial positions can be obtained. The method of the present invention pre-calibrates the points, lines, and surfaces of the background, and after identifying similar features in the target image, the target image is mapped to the calibration background. The position information of the gradient image is consistent with that of the target image. The gradient image includes various types of image feature information, such as the temperature of each pixel in the geometric features, the temperature range of all pixels, and the average temperature.

[0036] Through template matching, combined with alignment and gradient information, the gradient images of multiple layers of visible light and the gradient images of multiple layers of infrared thermal images are analyzed to achieve accurate positioning of temperature anomaly areas.

[0037] Preferably, a template matching method is used to analyze the preprocessed image and confirm the abnormal temperature area in the preprocessed image, including: presetting the normal temperature range of the points, lines and surfaces in the calibration background, and analyzing the temperature characteristics of the points, lines and surfaces read out by the gradient image based on this; if the temperature characteristics fall within the normal temperature range, the points, lines and surfaces do not belong to the automatically searched target; if the temperature characteristics do not fall within the normal temperature range, the points, lines and surfaces belong to the automatically searched target.

[0038] In the preset calibration background model, the temperature of points, lines, surfaces and other features can be analyzed according to the actual situation. For example, the temperature range of the edge of the building in the calibration background can be determined according to the climate conditions. If the real-time temperature of these geometric features exceeds the temperature range, it may cause potential fire risks.

[0039] The actual temperature of points, lines, and surfaces can be obtained by comprehensive analysis of multiple gradient images. For example, in multiple gradient images decomposed by wavelet. The corresponding pixel position can generate the temperature of each pixel on multiple gradient images according to the grayscale transformation of multiple images. One way is to solve the average dimension of each pixel as the temperature of the pixel. On this basis, the pixel is mapped to a spatial position in the calibration model.

[0040] Step 3: Use the DFMEA method to evaluate the severity of temperature anomaly, flame size, detection distance, and geographic information in the temperature anomaly area, and rank the fire sources accordingly.

[0041] Preferably, the DFMEA method is used to evaluate the severity of temperature anomaly, flame size, detection distance, and geographic information in the temperature anomaly area, and the fire source ranking is obtained accordingly, including: for each automatically searched target, the DFMEA method is used to obtain the fire source ranking of the automatically searched target; the DFMEA method uses the temperature anomaly severity, flame size, detection distance, and geographic information to calculate the fire source ranking of the automatically searched target; the temperature anomaly severity, flame size, detection distance, and geographic information are obtained based on the temperature features in multiple gradient images corresponding to the automatically searched target.

[0042] DFMEA is a design failure mode and effects analysis method. This method can preset a fire model, which includes the severity of temperature anomalies, flame size, detection distance, and geographical information at a certain location, resulting in a fire risk.

[0043] In one embodiment, the severity S of the temperature anomaly, the flame size F and the detection distance L are first evaluated, and then the risk priority coefficient RPN is calculated to evaluate the size of the fire source. The risk priority coefficient RPN and the location of the fire source are used to obtain the ranking of the fire sources, and the fire sources are arranged in order from large to small and from far to near, and the priorities are confirmed. The location of the fire source is based on GIS technology to perform spatial analysis and visualization of the temperature anomaly area, thereby indicating the geographical distribution and priority of the abnormal area.

[0044] The severity S of the temperature anomaly, the flame size F, and the detection distance L can all be obtained from the contents of multiple gradient images. For example, the temperature of the pixel is inferred from the grayscale in multiple gradient images. The average temperature or temperature distribution of all pixels near the feature pixel is calculated, and the temperature feature is obtained based on the distribution feature. The temperature feature is compared with the pre-obtained temperature range to obtain the severity of the temperature anomaly. The flame size can be calculated based on the number of pixels that exceed the abnormal temperature range, the scale of the collected image, the zoom level, and other information. The detection distance can be determined based on the depth information analysis in the image.

[0045] The risk priority coefficient RPN is positively correlated with the severity S, flame size F, and detection distance L. By reasonably designing the risk priority coefficient calculation formula, the order of flames from large to small can be obtained.

[0046] On the other hand, the location of the fire source is derived based on the GIS technology. During the fire fighting process, the fire fighting path from near to far can be dynamically planned and stored based on the actual location of the fire fighting vehicle, the number and location of the spare vehicles, etc.

[0047] In addition, the present invention also supports the application of machine learning algorithms to analyze large amounts of temperature data to identify temperature anomaly patterns, and to fit factors such as the temperature anomaly change peak value and change curve with the temperature change curve under different fire intensities, so as to predict the possible development trend of the fire and the current combustion situation, and optimize the priority classification.

[0048] Step 4, control the fire extinguishing path of the automatic search vehicle and the fire extinguishing method of the automatic search device according to the fire source sequence.

[0049] Preferably, the fire extinguishing path of the automatic seeker vehicle and the fire extinguishing method of the automatic seeker are controlled according to the fire source ranking, including: the fire extinguishing path of the automatic seeker vehicle is obtained based on the fire source ranking of the automatic seeker target and the geographic information planning of the automatic seeker target; the fire extinguishing method of the automatic seeker includes the azimuth angle of the automatic seeker, the fire extinguishing medium, the fire extinguishing intensity, and the fire extinguishing time, and the fire extinguishing method is obtained based on the severity of the temperature anomaly, the flame size, and the geographic information of the automatic seeker target.

[0050] At each fire source target location, the method of the present invention supports the prediction of the fire extinguishing path. At each fire source node on the path, the fire extinguishing angle and fire extinguishing duration can also be output based on the relationship between the fire extinguishing position of the automatically found vehicle and the actual fire source position. For example, the fire extinguishing angle is obtained by obtaining the azimuth of the gun head of the automatically found vehicle based on the relative position relationship between the actual parking position of the automatically found vehicle and the actual fire source position obtained in the aforementioned steps. In addition, the fire extinguishing duration can be obtained based on the flame size and flame temperature analyzed in the aforementioned steps. In some embodiments, the automatically found vehicle can deploy a variety of fire extinguishing media, and the appropriate media can be analyzed based on the shape, temperature and other characteristics of the flame. The fire extinguishing intensity can be appropriately adjusted based on the adjustable fire extinguishing intensity of the gun head and the distance between the vehicle and the fire source.

[0051] Preferably, controlling the fire extinguishing path of the automatic homing vehicle and the fire extinguishing method of the automatic homing device according to the fire source sequence includes: extinguishing the fire based on the fire extinguishing path of the automatic homing vehicle and the fire extinguishing method of the automatic homing device.

[0052] When the above analysis detects a flame signal, the control unit will analyze the data provided by the sensor to determine the location of the fire source. Then, the control unit will drive the motor to adjust the spray direction of the cannon head to aim at the fire source, and start the pump group and solenoid valve to spray the fire extinguishing medium to extinguish the fire. During the fire extinguishing process, the system will continue to repeat the above steps to determine and track the fire source to ensure that the fire is completely extinguished.

[0053] In the actual process, the fire extinguishing path, fire extinguishing angle and other aforementioned parameters can be adjusted in real time and dynamically according to the current fire extinguishing situation.

[0054] The control flow chart of the CAFS fire extinguishing system's automatic search can accurately monitor the fire source, analyze the characteristics of the temperature field changes around the flame, and give the longitude and latitude coordinates of the abnormal area. The system is also equipped with corresponding feedback adjustment functions. The corresponding data of the state of the gun head rotation angle can be monitored in real time. If it exceeds the set monitoring time of the system, it will respond immediately. For example, the system will determine it as an interference source and re-locate the fire source. When the fire extinguishing system controller exceeds the timing time, the seeker can also be reset. The system can monitor the movement state of the gun head and the target angle value in real time to maintain the consistency of the two. Through the consistency of the above values, it can accurately judge whether the positioning is successful, and cooperate with the target timing time to effectively determine whether it is an interference source, thereby further ensuring the accuracy of the data.

[0055] In the actual fire extinguishing process, the automatic homing system can be installed on the automatic homing main controller associated with multiple vehicles and multiple fire collection devices. The fire extinguishing system controls the movement of the vehicle, and the automatic homing controller in the vehicle can send a start signal and start timing processing. At the same time, the automatic homing vehicle controls the movement of the gun head according to the parameters sent by the main controller, and can also start positioning at the same time and find the fire source through the infrared thermal imaging recognition device and the color image recognition device. The main controller of the homing receives data, compares it with the background temperature, analyzes the temperature field change, calibrates the coordinate information and abnormal area and distance of the temperature abnormal area, forms the fire extinguishing point processing sequence, and records the fire extinguishing position for all temperature abnormal area coordinates. When the fire source is found, the fire extinguishing system controller stops the movement of the gun head and performs timing processing on the determined target value. When the target value exceeds 10s, the system will judge it as an interference source and let the homing system start positioning again. When the target value is within 10s, the homing system sends the target angle value of all abnormal position coordinates (X, Y, Z) to the automatic homing main controller in the processing order.

[0056] The automatic homing main controller controls the movement of the gun head through the fire extinguishing system controller and sends the gun head movement status and gun head movement results to the automatic homing system. At this time, the fire extinguishing system controller stops the gun head movement, and the automatic homing system will again judge the consistency between the fire source angle and the current gun head angle. When the above two angles are inconsistent, the homing system will again send the target angle value to the automatic homing main controller. When the above two angles are consistent, the fire extinguishing system controller timing and the automatic homing system timing are completed at the same time, and the homing system sends a fire source positioning indication success and turns on the fan, sends an in-position signal and starts to perform fire extinguishing operations in sequence according to the given coordinate angle value sequence. The fire extinguishing system controller sends a homing reset signal and resets the homing device.

[0057] When the timing of the fire extinguishing system controller exceeds 5 minutes, press the FM button, the fire extinguishing system controller sends a reset signal to reset the seeker. When the timing of the seeking system exceeds 5 minutes, it means that the seeking system has failed to locate the fire source. The fire extinguishing system controller sends a reset signal to reset the seeker, and the process ends here.

[0058] Through the system's timing processing, that is, the fire extinguishing system controller is timed out for five minutes, it indicates that the gun head positioning has failed, and the gun head will be reset. If the timing processing of the search system exceeds 5 minutes, it indicates that the fire source positioning has failed, and the fire extinguishing system controller gun head can also be reset, thereby ensuring that the fire source can be positioned effectively and quickly, and the gun head that failed to locate can also be reset.

[0059] The second aspect of the present invention relates to a system for automatic fire extinguishing search; the system is implemented by the method described in the first aspect of the present invention; the system includes an acquisition module, an analysis module, a sorting module and a fire extinguishing module; wherein the acquisition module is used to acquire a target image using an infrared thermal imaging temperature measurement module and a visible light imaging module, and preprocess the target image; the analysis module is used to analyze the preprocessed image using a template matching method, and confirm the temperature abnormality area in the preprocessed image; the sorting module is used to evaluate the temperature abnormality severity, flame size, detection distance, and geographic information of the temperature abnormality area with the help of the DFMEA method, and obtain the fire source ranking accordingly; the fire extinguishing module is used to control the fire extinguishing path of the automatic search vehicle and the fire extinguishing method of the automatic search device according to the fire source ranking.

[0060] In one embodiment, the automatic seeker is installed in the form of a camera on the top of the fire cannon of the CAFS fire extinguishing system and in the equipment box on the side of the turntable of the CAFS fire extinguishing system. The automatic seeker is communicated with the main controller of the automatic seeker through an RS485 interface, and the automatic seeker is used to read the infrared thermal imaging temperature data in real time as the fire cannon head moves. The main controller of the automatic seeker is installed in the equipment box on the side of the turntable of the CAFS fire extinguishing system.

[0061] The automatic seeker is composed of infrared thermal imaging recognition device, color image recognition device, recognition device bracket, automatic seeker stainless steel cavity, cavity mounting bracket accessories, wiring harness, aviation plug, hose and wires and other equipment components. The main controller of the automatic seeker is composed of fire identification and motion control drive hardware platform, thermal imaging fire identification processing hardware platform, thermal imaging identification hardware platform, switching power supply, installation fixed base, aviation plug, hose and wires and other equipment components. The control commands between the components are connected by hard wire, and the feedback commands are connected by communication.

[0062] The fire truck is also equipped with an on-board control system, which is installed in the equipment box on the side of the CAFS fire extinguishing system turntable. As the integration of the whole vehicle control, its main function is to receive the remote control transmission signal to make actions and control the start of various parts of the fire truck. The multi-bus architecture is adopted, and the upper and lower vehicles use 4-way bus parallel communication to reduce the channel load rate, reduce packet loss, and realize distributed communication. The automatic search system transmits the processed fire search information, including fire signal and location information, to the CAN network through CAN signals. The network supports a minimum baud rate of 250. The on-board main controller reads the fire search information from the CAN network.

[0063] The seeking system sends an indication of successful fire source location and turns on the fan, sends an in-position signal and starts fire extinguishing operations at the same time. The seeking system turns on the fan after successful positioning. The fan is installed in conjunction with the fire cannon installed on the fire truck. The purpose of this setting is to allow the water mist to spray farther, thereby improving the long-distance fire-fighting effect.

[0064] A third aspect of the present invention relates to a terminal, comprising a processor and a storage medium; the storage medium is used to store instructions; the processor is used to operate according to the instructions to execute the steps of the method described in the first aspect of the present invention.

[0065] A fourth aspect of the present invention relates to a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the method described in the first aspect of the present invention.

[0066] In summary, the infrared thermal imaging automatic search control system is based on infrared thermal imaging temperature detection technology, and can automatically search for temperature abnormal areas and fire source areas of the protected objects in real time. The automatic searcher collects the infrared thermal imaging video image data of the scene in real time through thermal imaging images, and transmits it to the main controller of the automatic search, analyzes the distribution characteristics of the temperature in the protected area, and uses the feature weighting mechanism to target the abnormal area to guide the CAFS fire extinguishing system to spray the fire extinguishing medium to cool down.

[0067] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit them. Although the present invention is described in detail with reference to the above embodiments, it should be understood by those skilled in the art that the technical solutions of the present invention still include contents that can modify or replace the specific embodiments of the present invention. Any modification or replacement that does not depart from the spirit and scope of the present invention shall be included in the protection scope of the claims of the present invention.

Claims

1. A method for automatic fire extinguishing, characterized in that: The method comprises the following steps: Step 1, using an infrared thermal imaging temperature measurement module and a visible light imaging module to collect a target image, and preprocessing the target image; Step 2, analyzing the preprocessed image using a template matching method, and confirming the temperature abnormality area in the preprocessed image; Step 3, using the DFMEA method to evaluate the severity of temperature anomaly, flame size, detection distance, and geographic information of the temperature anomaly area, and rank the fire sources accordingly; Step 4, control the fire extinguishing path of the automatic search vehicle and the fire extinguishing method of the automatic search device according to the fire source sequence.

2. A method for automatic fire extinguishing according to claim 1, characterized in that: The infrared thermal imaging temperature measurement module and the visible light imaging module are used to collect the target image, and the target image is preprocessed, including: Set the temperature anomaly threshold, extract the fire source area in the target image, and obtain the actual coordinates of the fire source area through image positioning; Implementing target image enhancement by using one or more of spatial domain transformation, spatial domain-frequency domain transformation, and frequency domain transformation; Wavelet transform is used to perform multi-scale decomposition on the enhanced target image to extract the gradient image of the target image or the fire source area.

3. A method for automatic fire extinguishing according to claim 2, characterized in that: The adopting of the template matching method to analyze the preprocessed image and confirming the temperature abnormality area in the preprocessed image includes: Pre-calibrate the background points, lines, and surfaces, and correspond the pre-calibrated background points, lines, and surfaces to the gradient image by identifying the feature points in the target image; According to the temperature of the pixel point in the gradient image, the temperature, temperature range and average temperature of the pre-calibrated background point, line and surface are read out.

4. A method for automatic fire extinguishing according to claim 3, characterized in that: The adopting of the template matching method to analyze the preprocessed image and confirming the temperature abnormality area in the preprocessed image includes: The normal temperature range of points, lines and surfaces in the calibration background is preset, and the temperature characteristics of points, lines and surfaces read out through the gradient image are analyzed accordingly; If the temperature characteristic falls within the normal temperature range, the point, line, or surface is not an automatically searched target; If the temperature feature does not fall within the normal temperature range, the point, line, or surface is an automatically searched target.

5. The method for automatic fire extinguishing according to claim 4, characterized in that: The DFMEA method is used to evaluate the severity of temperature anomaly, flame size, detection distance, and geographic information of the temperature anomaly area, and the fire source ranking is obtained accordingly, including: For each automatically searched target, the DFMEA method is used to obtain the fire source ranking of the automatically searched target; The DFMEA method uses the severity of temperature anomalies, flame size, detection distance, and geographic information to calculate the fire source ranking of the automatic search target; The temperature anomaly severity, flame size, detection distance, and geographic information are obtained based on temperature features in a plurality of gradient images corresponding to the automatically sought target.

6. A method for automatic fire extinguishing according to claim 5, characterized in that: The method of controlling the fire extinguishing path of the automatic seeker and the fire extinguishing method of the automatic seeker according to the fire source sequence includes: The fire extinguishing path of the automatically sought vehicle is obtained based on the fire source ranking of the automatically sought target and the geographic information planning of the automatically sought target; The fire extinguishing method of the automatic seeker includes the azimuth angle of the automatic seeker, the fire extinguishing medium, the fire extinguishing intensity, and the fire extinguishing time. The fire extinguishing method is obtained based on the temperature anomaly severity, flame size, and geographic information of the automatically found target.

7. A method for automatic fire extinguishing according to claim 6, characterized in that: The method of controlling the fire extinguishing path of the automatic seeker and the fire extinguishing method of the automatic seeker according to the fire source sequence includes: Fire is extinguished based on the fire extinguishing path of the automatic seeker and the fire extinguishing method of the automatic seeker.

8. A fire extinguishing automatic search system using the method described in any one of claims 1 to 7; characterized in that: The system includes a collection module, an analysis module, a sorting module and a fire extinguishing module; wherein, The acquisition module is used to acquire the target image using the infrared thermal imaging temperature measurement module and the visible light imaging module, and perform preprocessing on the target image; The analysis module is used to analyze the pre-processed image by using a template matching method, and to identify the temperature abnormality area in the pre-processed image; The ranking module is used to evaluate the severity of temperature anomaly, flame size, detection distance, and geographic information of the temperature anomaly area by using the DFMEA method, and obtain the fire source ranking accordingly; The fire extinguishing module is used to control the fire extinguishing path of the automatic seeker and the fire extinguishing mode of the automatic seeker according to the fire source sequence.

9. A terminal comprising a processor and a storage medium; characterized in that: The storage medium is used to store instructions; The processor is configured to operate according to the instructions to execute the steps of the method according to any one of claims 1-7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images