Light quantum radar fire source identifying and positioning method and system for fire extinguishing robot

Abstract

The invention relates to the technical field of radar fire source positioning, in particular to a light quantum radar fire source identifying and positioning method and system for a fire extinguishing robot. Acquiring radar point cloud data, temperature time sequence data and smoke concentration time sequence data of a fire scene; comparing the radar point cloud data with preset radar point cloud data, identifying smoke data points, analyzing motion characteristics of the smoke data points to determine a smoke diffusion path, and analyzing changes of temperature and smoke concentration time sequence data to determine a fire spreading path; comparing the two and combining temperature and smoke concentration change characteristics, identifying a real fire behavior evolution trend, and screening suspected fire source positions; and at each suspected fire source position, the initial power and the resolution of the light quantum radar are adaptively and intelligently adjusted according to indexes such as the area to be measured, the environmental complexity and the smoke concentration, fire source identification and positioning are carried out with the optimal performance, and the accuracy and the stability are improved. The range is dynamically reduced, radar parameters are adaptively adjusted, and accurate positioning of a fire source is facilitated.

Description

Technical Field

[0001] The present invention relates to the technical field of radar fire source location, and particularly to a method and system for identifying and locating a fire source by a quantum radar for a fire-fighting robot. Background Art

[0002] In the fire monitoring and fire-fighting operation sites, complex environments and smoke occlusion often occur. At this time, simple image acquisition is often difficult to effectively identify the fire source location. A quantum radar is an advanced high-precision detection device. By emitting specific quantum signals of light, when these signals interact with the target and then return, various information of the target can be obtained through the analysis of the quantum characteristics of the returned signals. Combining the quantum radar with a fire-fighting robot (such as an unmanned aerial vehicle, a fire truck, etc.) can realize the intelligent identification and location of the fire source point at the fire scene and extinguish the fire at the fire source point.

[0003] When the prior art uses a quantum radar to identify and locate a fire source at a fire scene, it usually collects and analyzes data globally at a fixed power and resolution for the fire scene, so as to identify and locate the fire source location. However, when a fire occurs, the environment at the scene is usually complex, the smoke will diffuse and data such as temperature will change in real time. Therefore, if the quantum radar still uses fixed parameters to conduct a blind comprehensive scan of the fire scene at this time, it will not only increase the difficulty of positioning, but also affect the accuracy of the quantum radar in identifying and locating the fire source. Summary of the Invention

[0004] In order to solve the technical problem that when a fire occurs, the environment at the scene is usually complex, the smoke will diffuse and data such as temperature will change in real time. Therefore, if fixed parameters are used to conduct a blind comprehensive scan of the fire scene, it will not only increase the difficulty of positioning, but also affect the accuracy of positioning. The purpose of the present invention is to provide a method and system for identifying and locating a fire source by a quantum radar for a fire-fighting robot. The specific technical solutions adopted are as follows: A method for identifying and locating a fire source by a quantum radar for a fire-fighting robot includes: Obtaining the radar point cloud data detected by the quantum radar for the fire scene, as well as the temperature time-series data and smoke concentration time-series data at each monitoring position; Comparing the radar point cloud data at each moment with the preset radar point cloud data to determine the smoke data points; among the radar point cloud data at different moments, based on the movement of the smoke data points, determining the smoke diffusion path of the fire scene; analyzing the change differences between the temperature time-series data and the change differences between the smoke concentration time-series data to determine the fire spread path; Compare the smoke diffusion path and the fire spread path, and screen for suspected fire source locations among all monitoring locations based on the temperature value change and smoke concentration value change at the current moment of the monitoring location; Take the monitoring range of each suspected fire source location as the range to be measured; within each range to be measured, select indicators from the area value, environmental complexity, and smoke concentration value at the current moment of the range to be measured to adjust the initial power and initial resolution of the quantum lidar respectively, so as to identify and locate the fire source in the range to be measured.

[0005] Further, the method for obtaining the smoke diffusion path includes: In the radar point cloud data at each moment, take the position of each smoke data point as the starting point, and take the position of the same smoke data point in the radar point cloud data at the adjacent next moment as the end point to obtain the motion vector of each smoke data point between the radar point cloud data at adjacent moments; In the radar point cloud data at each moment, for any xoz plane, synthesize the motion vectors of the radar point cloud data in the xoz plane to determine the motion direction of the xoz plane; Connect the motion directions of the same xoz plane in the radar point cloud data at all moments to obtain all smoke diffusion paths.

[0006] Further, the method for obtaining the fire spread path includes: Obtain the temperature curve of the temperature time series data at each monitoring location. On the temperature curve, obtain the slope value at each data point, and take the sum value of the slope values at all data points as the temperature change trend value at each monitoring location; Obtain the concentration curve of the smoke concentration time series data at each monitoring location. On the concentration curve, obtain the slope value at each data point, and take the sum value of the slope values at all data points as the smoke concentration change trend value at each monitoring location; Determine a preset neighborhood centered on each monitoring location. Within the preset neighborhood corresponding to each monitoring location, analyze the difference between the temperature change trend values and the difference between the smoke concentration change trend values between the central monitoring location and the neighborhood monitoring locations to obtain a direction determination factor; When the direction determination factor between the central monitoring location and each neighborhood monitoring location is greater than the preset direction determination threshold, the fire spread direction between the central monitoring location and each neighborhood monitoring location is from the neighborhood monitoring location to the central monitoring location, otherwise it is from the central monitoring location to the neighborhood monitoring location; Integrate the fire spread directions between all monitoring locations and neighborhood monitoring locations to obtain all fire spread paths.

[0007] Further, the method for obtaining the direction determination factor includes: Taking the normalized value of the difference between the temperature change trend values of the central monitoring position and each neighborhood monitoring position as the temperature change difference, and taking the normalized value of the difference between the smoke concentration change trend values of the central monitoring position and each neighborhood monitoring position as the smoke concentration change difference; Taking the normalized value of the product of the temperature change difference and the smoke concentration change difference as the direction determination factor.

[0008] Further, the method for obtaining the suspected fire source position includes: Comparing the fire spread path and the smoke diffusion path to screen out the positions to be analyzed among all monitoring positions; For any position to be analyzed, taking the sum value of the temperature change trend value and the smoke concentration change trend value at this position to be analyzed as the first fire source factor; Taking the sum value of the temperature value and the smoke concentration value at this position to be analyzed at the current moment as the second fire source factor; Taking the normalized value of the product of the first fire source factor and the second fire source factor at this position to be analyzed as the suspected fire source index at this position to be analyzed; Taking the positions to be analyzed with the suspected fire source index greater than the preset fire source threshold as the suspected fire source positions.

[0009] Further, the method for obtaining the positions to be analyzed includes: Mapping each fire spread path to the three-dimensional lidar point cloud data and comparing it with the smoke diffusion path. If the overlapping length of a certain fire spread path and a certain smoke diffusion path is greater than or equal to one-half of this smoke diffusion path, then taking this fire spread path as the path to be analyzed and taking the monitoring positions on the target path as the positions to be analyzed.

[0010] Further, in each range to be measured, among the area value of the range to be measured, the environmental complexity, and the smoke concentration value at the current moment, selecting indicators to adjust the initial power and initial resolution of the quantum lidar respectively, so as to identify and locate the fire source in the range to be measured, including: In each range to be measured, taking the sum value of the normalized value of the smoke concentration value at the suspected fire source position corresponding to the range to be measured at the current moment and the preset constant as the power adjustment coefficient; Taking the product of the power adjustment coefficient and the initial power as the adjusted power of the quantum lidar; Based on the quantity characteristics and gray scale characteristics of the data points in the lidar point cloud data in each range to be measured, determining the environmental complexity of each range to be measured; The sum of the normalized product of the environmental complexity and the area value of each range to be measured and a preset constant is used as the resolution adjustment coefficient; The product of the resolution adjustment coefficient and the initial distance resolution is used as the adjusted distance resolution of the quantum lidar, and the product of the resolution adjustment coefficient and the initial angular resolution is used as the adjusted angular resolution of the quantum lidar; Based on the adjusted power, adjusted distance resolution, and adjusted angular resolution corresponding to each range to be measured, the quantum lidar is used to detect and identify the fire source location in the range to be measured.

[0011] Further, the method for obtaining the environmental complexity includes: In each range to be measured, the variance of the gray values of all data points is used as the environmental complexity factor; The normalized value of the product of the environmental complexity factor and the number of smoke data points is used as the environmental complexity of each range to be measured.

[0012] Further, the method for obtaining the smoke data points includes: The radar point cloud data at each moment is compared with the preset radar point cloud data, and the newly appeared data points are used as the smoke data points; wherein, the preset radar point cloud data is the radar point cloud data at the scene when there is no fire.

[0013] A quantum lidar fire source identification and positioning system for a fire-fighting robot includes a processor and a memory. At least one instruction, at least one program, a code set, or an instruction set is stored in the memory. When at least one instruction, at least one program, the code set, or the instruction set is loaded and executed by the processor, the steps of the method for identifying and positioning a fire source using a quantum lidar for a fire-fighting robot are implemented.

[0014] The present invention has the following beneficial effects: Obtain the radar point cloud data of the fire scene where the fire-fighting robot is located. Since lidar is easily affected by smoke particles, resulting in interference with its signals, multiple monitoring positions are set in the fire scene, and the temperature time-series data and smoke concentration time-series data at each monitoring position are obtained. By realizing the collaborative analysis of the spatial structure of the fire scene environment and the monitoring data, the reliability of subsequent fire source localization can be improved. Comparing the radar point cloud data with the preset radar point cloud data can identify and extract smoke data points. Since smoke usually spreads with the spread of the fire, analyzing the motion characteristics of the smoke data points to determine the smoke diffusion path helps to narrow down the range and assist the fire-fighting robot in accurately locating and identifying the fire source. At the same time, the spread situation of the fire directly reflects the expansion trend of the fire, which is also helpful for fire source localization analysis. Therefore, the change differences between the temperature time-series data and the smoke concentration time-series data among the monitoring positions are analyzed to determine the fire spread path. Then, compare and analyze the smoke diffusion path and the fire spread path, and combine the change characteristics of the temperature value and the smoke concentration value to penetrate the thick smoke interference and identify the true fire evolution trend, and screen out the suspected fire source positions among all the monitoring positions, narrowing the monitoring range of the fire scene. Finally, within the range to be measured of each suspected fire source position, the present invention adaptively adjusts the initial power and initial resolution of the quantum lidar according to indicators such as the area to be measured, environmental complexity, and smoke concentration. This intelligent parameter adjustment method enables the quantum lidar carried by the fire-fighting robot to exert the best performance according to the actual needs in different scenarios, further improving the accuracy and stability of fire source identification and localization. In summary, the present invention combines the point cloud spatial information with the change rules of temperature and smoke concentration, quickly locks the suspected fire source area and dynamically narrows the scanning range, and adaptively adjusts the parameters of the quantum lidar carried by the fire-fighting robot, which helps to accurately locate the fire source and improve the timeliness of the fire-fighting robot's emergency rescue. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0016] Figure 1 It is a flowchart of a method for identifying and locating a fire source using a quantum lidar for a fire-fighting robot provided by an embodiment of the present invention; Figure 2 It is a flowchart of a method for obtaining a fire spread path provided by an embodiment of the present invention; Figure 3The method flow chart of a method for obtaining the suspected fire source location provided by an embodiment of the present invention; Figure 4 The system block diagram of a photon radar fire source identification and positioning system for a fire-fighting robot provided by an embodiment of the present invention; Figure 5 The system structure schematic diagram of a photon radar fire source identification and positioning system for a fire-fighting robot provided by an embodiment of the present invention. Specific embodiments

[0017] In order to further elaborate on the technical means and effects adopted by the present invention to achieve the intended invention purpose, the following combines the drawings and preferred embodiments to elaborate in detail on a photon radar fire source identification and positioning method and system for a fire-fighting robot according to the present invention, its specific embodiments, structures, features and effects. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. In addition, the specific features, structures or characteristics in one or more embodiments can be combined in any suitable form.

[0018] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the technical field to which the present invention belongs.

[0019] The following specifically describes the specific solution of a photon radar fire source identification and positioning method for a fire-fighting robot provided by the present invention in conjunction with the drawings.

[0020] Please refer to Figure 1 , which shows the method flow chart of a photon radar fire source identification and positioning method for a fire-fighting robot provided by an embodiment of the present invention. The method includes the following steps: Step S1: Obtain the radar point cloud data detected by the photon radar for the fire scene, as well as the temperature time series data and smoke concentration time series data at each monitoring position.

[0021] In a chemical industrial park, chemical fires are usually accompanied by the combustion of chemicals. During the combustion process, a large amount of smoke containing special chemical components will be generated, such as black smoke formed by the mixture of gases such as chlorine and hydrogen sulfide and soot. When the fire is large, these smokes will spread upward along the ventilation ducts, corridors and other channels inside the building and form a complex smoke field. In this environment, simple image acquisition is often difficult to accurately identify and locate the fire source.

[0022] Optical quantum radar is an advanced high-precision detection device. By emitting specific optical quantum signals, when these signals interact with the target and return, through the analysis of the quantum characteristics of the returned signals, various information about the target can be obtained. And it has a certain penetration ability for the smoke at the fire scene. Therefore, the optical quantum radar can be combined with the fire-fighting robot to be used for the identification and positioning of the fire source.

[0023] First of all, the spatial data of the fire scene can be obtained based on the optical quantum radar carried on the fire-fighting robot. Specifically, the fire-fighting robot needs to enter the fire scene and use the optical quantum radar to scan the fire scene. By emitting optical quantum signals and receiving the reflected signals, the radar point cloud data can be generated. The radar point cloud data helps to understand the spatial layout of the fire scene and is helpful for the subsequent identification and positioning of the fire source location.

[0024] At the same time, the temperature and smoke concentration at the fire scene are also important clues for judging the fire source location. Therefore, based on the multi-parameter sensors pre-set in the fire scene, the temperature time-series data and smoke concentration time-series data at the monitoring positions where each multi-parameter sensor is located are obtained, providing important information for the subsequent identification and positioning of the fire source location. In the embodiments of the present invention, the installation positions of the multi-parameter sensors can be set at key positions such as the ceiling, walls, columns, electrical equipment, and stairways. The specific quantity, position, and density can all be adjusted according to the implementation scenario and are not limited here. And each multi-parameter sensor has a certain monitoring range. The temperature time-series data and smoke concentration time-series data both represent the temperature situation and smoke concentration situation within this local area of the monitoring range.

[0025] It should be noted that the data acquisition frequency of the multi-parameter sensors should be consistent with the scanning frequency of the radar point cloud data. Thus, at each moment, there are simultaneously the radar point cloud data of the fire scene, the temperature values and smoke concentration values at each monitoring position. The specific data acquisition frequency and scanning frequency can be set to once per second. The specific frequency value can be adjusted according to the implementation scenario and is not limited here. The monitoring range of the multi-parameter sensor at each monitoring position can be set as a circular area with a radius of 3 meters centered on the multi-parameter sensor. The specific range can be adjusted according to the implementation scenario and is not limited here.

[0026] In the embodiments of the present invention, since there may be multiple fire-fighting robots working simultaneously in the space of the fire scene, when obtaining the radar point cloud data, taking one of the random fire-fighting robots as the center, the radar point cloud data of all fire-fighting robots can be integrated (fused according to the three-dimensional coordinates, and the point cloud particles with the same coordinates are fused), so as to obtain the radar point cloud data of the fire scene.

[0027] Step S2: Compare the radar point cloud data at each moment with the preset radar point cloud data to determine the smoke data points; based on the movement of the smoke data points in the radar point cloud data at different moments, determine the smoke diffusion path at the fire scene; analyze the variation differences between the temperature time series data and the smoke concentration time series data to determine the fire spread path.

[0028] When the fire at the fire scene is relatively large, although the optical quantum radar has good penetration, it may still be unable to quickly and accurately locate the position of the ignition source at the fire scene due to the influence of thick smoke and high temperature at the scene. And non-targeted scanning will only increase the time for identifying the ignition source, resulting in more damage. Smoke is one of the important characteristics of a fire, and its diffusion path is often closely related to factors such as the location of the ignition source, ventilation conditions, and building layout. By comparing the radar point cloud data at different moments, the smoke data points can be identified. Further analyzing the movement of these smoke data points can help determine the smoke diffusion path, thereby indirectly inferring the possible location of the ignition source and the spread direction of the fire. The temperature time series data and the smoke concentration time series data provide real-time change information on the temperature and smoke concentration at the fire scene. By analyzing the variation differences between these data, the spread speed and direction of the fire can also be understood. Therefore, by analyzing various data collected at the fire scene, it helps to reduce the time of blind search and ineffective actions in the subsequent process and improve the accuracy of identifying and locating the ignition source.

[0029] First, the radar point cloud data at each moment can be compared with the preset radar point cloud data to obtain the smoke data points.

[0030] Preferably, in an embodiment of the present invention, the method for obtaining the smoke data points includes: Smoke is one of the important characteristics of a fire. By comparing the radar point cloud data at each moment with the preset radar point cloud data, it can be identified which data points are new data points caused by smoke. Therefore, the newly emerged data points are used as the smoke data points, which are the basis for subsequent analysis of the smoke diffusion path; among them, the preset radar point cloud data is the radar point cloud data at the scene when there is no fire.

[0031] The diffusion path of smoke is often related to the location of the ignition source, the size of the fire, etc., and the diffusion path of smoke usually points to the ignition source or its nearby area. Therefore, by observing the movement trajectory of the smoke data points, the approximate location of the ignition source can be assisted in judgment.

[0032] Preferably, in an embodiment of the present invention, the method for obtaining the smoke diffusion path includes: The diffusion of smoke at the fire scene is a dynamic process, and the positions of smoke data points change over time. Therefore, in the radar point cloud data at each moment, taking the position of each smoke data point as the starting point and the position of the same smoke data point in the radar point cloud data at the adjacent next moment as the end point, the motion vector of each smoke data point between the radar point cloud data at adjacent moments can be obtained.

[0033] Then, in the radar point cloud data at each moment, for any xoz plane, the motion vectors of the radar point cloud data in that xoz plane are synthesized to determine the motion direction of that xoz plane. At this time, the motion direction of each xoz plane represents the overall motion direction of the plane, which helps to more intuitively understand the diffusion of smoke on different planes.

[0034] At this time, in the radar point cloud data at each moment, each xoz plane has a motion direction. Finally, the motion directions of the same xoz plane in the radar point cloud data at all moments are connected, and all the smoke diffusion paths during the smoke diffusion at the fire scene can be obtained, thus intuitively reflecting the diffusion of smoke over time up to the current moment.

[0035] During a fire, the temperature around the fire source will increase significantly and spread to the surrounding area, and the concentration of smoke also changes as the fire spreads. Therefore, by analyzing the change differences in the temperature time-series data and the change differences in the smoke concentration time-series data between different monitoring positions, the fire spread path can be determined based on the monitoring positions at the fire scene, and the approximate position of the fire source can also be assisted in judging in the subsequent process.

[0036] Preferably, in an embodiment of the present invention, the method for obtaining the fire spread path includes: Please refer to Figure 2 , which shows the method flow chart of the method for obtaining the fire spread path in an embodiment of the present invention. The method includes the following steps: Step S201: Analyze the change characteristics of the temperature values in the temperature time-series data at each monitoring position to determine the temperature change trend value at each monitoring position.

[0037] Obtain the temperature curve of the temperature time-series data at each monitoring location, and on the temperature curve, obtain the slope value at each data point. The slope value here can reflect the temperature change trend at each data point. The larger the positive value, the more obvious the upward trend of the temperature and the faster the rising rate; on the contrary, the smaller the negative value, the more obvious the downward trend of the temperature and the faster the falling rate. Finally, synthesize the slope values at all data points, and take the sum value of the slope values at all data points as the temperature change trend value at each monitoring location. Based on the above analysis, when the temperature change trend value at the monitoring location is positive and the larger it is, it indicates that the temperature at the monitoring location is generally in a rapidly rising trend.

[0038] Step S202: Analyze the change characteristics of the smoke concentration values in the smoke concentration time-series data at each monitoring location, and determine the smoke concentration change trend value at each monitoring location.

[0039] Obtain the concentration curve of the smoke concentration time-series data at each monitoring location, and on the concentration curve, obtain the slope value at each data point. The slope value here can reflect the smoke concentration change trend at each data point. The larger the positive value, the more obvious the upward trend of the smoke concentration and the faster the rising rate; on the contrary, the smaller the negative value, the more obvious the downward trend of the smoke concentration and the faster the falling rate. Finally, synthesize the slope values at all data points, and take the sum value of the slope values at all data points as the smoke concentration change trend value at each monitoring location. Based on the above analysis, when the smoke concentration change trend value at the monitoring location is positive and the larger it is, it indicates that the smoke concentration at the monitoring location is generally in a rapidly rising trend.

[0040] Step S203: Determine a preset neighborhood centered on each monitoring location. In the preset neighborhood corresponding to each monitoring location, analyze the difference between the temperature change trend values and the difference between the smoke concentration change trend values between the central monitoring location and the neighborhood monitoring locations to obtain a direction determination factor.

[0041] In view of the fact that when a fire occurs, as the fire source approaches, both the smoke concentration value and the temperature value at the monitoring location will have a rapidly rising trend. Therefore, by comparing the temperature change trend values and the smoke concentration change trend values between adjacent monitoring locations, a direction determination factor can be obtained, so as to determine the direction of fire spread in the subsequent process.

[0042] Within the preset neighborhood corresponding to each monitoring position, the value obtained by normalizing the difference between the temperature change trend value of the central monitoring position and that of each neighborhood monitoring position is used as the temperature change difference. The larger the temperature change difference, the more obvious the temperature rising trend at the central monitoring position is compared with that of the neighborhood monitoring positions. Similarly, the value obtained by normalizing the difference between the smoke concentration change trend value of the central monitoring position and that of each neighborhood monitoring position is used as the smoke concentration change difference. The larger the smoke concentration change difference, the more significant the smoke concentration rising trend at the central monitoring position is compared with that of the neighborhood monitoring positions. Given that the difference may be positive or negative, the normalization method used here is function.

[0043] [[ID=D5]]Finally, the value obtained by normalizing the product of the temperature change difference and the smoke concentration change difference is used as the direction determination factor. Based on the foregoing analysis, it can be seen that the larger the direction determination factor, the more obvious the rising trends of the temperature and smoke concentration at the central monitoring position are. Among them, normalization is a well-known technical means to those skilled in the art. The choice of the normalization function can be linear normalization or standard normalization, etc. The specific normalization method is not limited here.

[0044] It should be noted that in the embodiment of the present invention, the preset neighborhood corresponding to each monitoring position should include at least 3 monitoring positions, and the size of the preset neighborhood is larger than the monitoring range of the monitoring position. The specific size of the neighborhood can be adjusted according to the implementation scenario and is not limited here.

[0045] Step S204: Based on the direction determination factors between all monitoring positions and neighborhood monitoring positions, the fire spread path is obtained.

[0046] As the fire source approaches, for two adjacent monitoring positions a and b, if the rising trends of the smoke concentration value and temperature value at monitoring position a are greater than those at monitoring position b, then it can be considered that the fire spread direction between the two is from b to a. That is, when a is used as the central monitoring position and b is used as the neighborhood monitoring position of a, if the direction determination factor between a and b is larger, the more likely the fire spread direction between the two is from b to a.

[0047] Therefore, when the direction determination factor between the central monitoring position and each neighborhood monitoring position is greater than the preset direction determination threshold, the fire spread direction between the central monitoring position and each neighborhood monitoring position is from the neighborhood monitoring position to the central monitoring position; otherwise, it is from the central monitoring position to the neighborhood monitoring position.

[0048] Finally, by comprehensively considering the fire spread directions between all monitoring positions and neighborhood monitoring positions, all fire spread paths are obtained.

[0049] It should be noted that the preset direction determination threshold can be set to 0.5, and the specific value can be adjusted according to the implementation scenario and will not be limited here.

[0050] Step S3: Compare the smoke diffusion path and the fire spread path, and screen out the suspected fire source positions among all monitoring positions based on the change conditions of the temperature value and the smoke concentration value at the current moment at the monitoring positions.

[0051] Smoke and flames have different propagation methods in a fire, but they have the same source, that is, the area where the flame is burning or has burned out. Therefore, by comparing the paths of the two, the dynamic changes of the fire can be more comprehensively understood, which helps to identify the suspected fire source positions; at the same time, temperature and smoke concentration are two key indicators in fire monitoring. Near the fire source, there is often a sharp increase in temperature and a significant increase in smoke concentration. Therefore, by monitoring the change conditions of these parameters, potential fire source positions can be discovered, and a single data source may not provide enough information to judge the fire source position. By fusing multi-source data such as the smoke diffusion path, the fire spread path, the change of temperature value, and the change of smoke concentration value for analysis, the accuracy and reliability of judging the suspected fire source position can be greatly improved.

[0052] Preferably, in an embodiment of the present invention, the method for obtaining the suspected fire source position includes: Please refer to Figure 3 , which shows the method flow chart of the method for obtaining the suspected fire source position in an embodiment of the present invention. The method includes the following steps: Step S301: Compare the fire spread path and the smoke diffusion path to screen out the positions to be analyzed among all monitoring positions.

[0053] A fire source usually generates flames and smoke simultaneously. The flames spread along a certain path, and the smoke also diffuses with the air flow. Therefore, at the place where the coincidence degree of the fire spread path and the smoke diffusion path is relatively high, it is very likely to be the position where the fire source is located or close to the fire source.

[0054] Therefore, map each fire spread path into the three-dimensional radar point cloud data and compare it with the smoke diffusion path. Since the smoke often spreads before the flames, setting the coincidence length to be greater than or equal to half of the smoke diffusion path as the screening condition is to ensure that the selected fire spread path has sufficient relevance to the smoke diffusion path, thereby improving the accuracy of screening. If the coincidence length of a certain fire spread path and a certain smoke diffusion path is greater than or equal to half of the smoke diffusion path, then take this fire spread path as the path to be analyzed and the monitoring positions on the target path as the positions to be analyzed.

[0055] Step S302: Integrate the temperature change trend value and the smoke concentration change trend value at each position to be analyzed to obtain the first fire source factor at each position to be analyzed.

[0056] Near the fire source, the temperature and smoke concentration will show an upward trend over time. Therefore, for any position to be analyzed, the sum of the temperature change trend value and the smoke concentration change trend value at this position to be analyzed is used as the first fire source factor. The larger the first fire source factor, the more obvious the temperature increase trend and the smoke concentration increase trend at the position to be analyzed, and the more likely it is to be a suspected fire source position.

[0057] Step S303: Integrate the temperature value and the smoke concentration value at each position to be analyzed at the current moment to obtain the second fire source factor at each position to be analyzed.

[0058] The closer to the fire source, the more intuitive data shows higher temperature values and higher smoke concentration values. Therefore, the sum of the temperature value and the smoke concentration value at the current moment at this position to be analyzed is used as the second fire source factor. Similarly, the larger the second fire source factor, the larger the temperature value and the smoke concentration value at the position to be analyzed, and the more likely it is to be a suspected fire source position.

[0059] Step S304: Based on the first fire source factor and the second fire source factor at each position to be analyzed, screen out the suspected fire source positions among all positions to be analyzed.

[0060] Based on the foregoing analysis, it can be seen that both the first fire source factor and the second fire source factor are positively correlated with the possibility that the position to be analyzed is a suspected fire source position. Therefore, the value obtained by normalizing the product of the first fire source factor and the second fire source factor at this position to be analyzed is used as the suspected fire source index at the position to be analyzed. The larger the suspected fire source index, the greater the possibility that the position to be analyzed is a suspected fire source position. Among them, normalization is a well-known technical means in the art, and the choice of the normalization function can be linear normalization or standard normalization, etc. The specific normalization method is not limited here.

[0061] Finally, the positions to be analyzed with a suspected fire source index greater than the preset fire source threshold are used as suspected fire source positions.

[0062] It should be noted that the preset fire source threshold can be set to 0.6, and the specific value can be adjusted according to the implementation scenario and is not limited here.

[0063] Step S4: Use the monitoring range of each suspected fire source position as the range to be measured; within each range to be measured, among the area value of the range to be measured, the environmental complexity, and the smoke concentration value at the current moment, select indicators to adjust the initial power and initial resolution of the quantum lidar, so as to identify and locate the fire source in the range to be measured.

[0064] Based on the foregoing steps, the suspected fire source locations can be screened out among many monitoring locations at the fire scene. The screening of the suspected fire source locations reduces the working range for the fire-fighting robot, thus helping to improve the accuracy of fire source identification and location. After obtaining all the suspected fire source locations, the monitoring range of the suspected fire source locations can be scanned using a quantum lidar to identify the fire source points. However, considering the complex environment at the fire scene, the environmental conditions at the scene will affect the penetration power of the quantum lidar. Therefore, in order to make the working parameters of the quantum lidar match the environmental conditions within the monitoring range of the suspected fire source locations, ensure that the quantum lidar can maintain good performance in a complex environment, and improve the accuracy of fire source identification and location, in the embodiment of the present invention, the monitoring range of each suspected fire source location is used as a measurement range. Then, within each measurement range, among the area value of the measurement range, the complexity of the environment, and the smoke concentration value at the current moment, appropriate indicators are selected to adaptively adjust the initial power and initial resolution of the quantum lidar, so as to identify and locate the fire source within the measurement range.

[0065] Preferably, in an embodiment of the present invention, the process of adjusting the initial power and initial resolution of the quantum lidar to identify and locate the fire source within the measurement range includes: The power of the quantum lidar determines the number and energy of the photons it emits, and smoke will significantly attenuate the intensity of the photon signal, resulting in a decrease in the quantum state propagation efficiency, thus affecting the detection sensitivity. Therefore, by adjusting the power of the quantum lidar, the penetration probability of the photons can be increased, ensuring that the quantum lidar can still maintain sufficient detection ability in environments with different smoke concentrations.

[0066] Therefore, within each measurement range, the sum value of the normalized value of the smoke concentration value at the current moment at the suspected fire source location corresponding to the measurement range and a preset constant is used as the power adjustment coefficient. The greater the smoke concentration value, the greater the degree of smoke interference within the measurement range. Therefore, the quantum lidar requires higher penetration ability, and thus the power adjustment coefficient is larger. That is, within this measurement range, when the quantum lidar is scanning, it requires a higher working power.

[0067] Then, the product of the power adjustment coefficient and the initial power is used as the adjusted power of the quantum lidar. At this time, the adjusted power will match the environmental conditions within the measurement range better, so as to better identify and locate the fire source within the measurement range.

[0068] The resolution determines the minimum target size and distance interval that the optical quantum radar can distinguish. Improving the resolution helps to accurately identify targets in complex environments. The area value of the range to be measured determines the size of the range to be measured, and a larger range to be measured requires a higher resolution to ensure that every corner can be effectively covered. Moreover, multi-target reflections in complex environments can cause quantum state aliasing, and this situation also requires an increase in resolution to achieve signal separation. The number and gray-level characteristics of the data points in the radar point cloud data can reflect the complexity of the environment. Therefore, within each range to be measured, the variance of the gray-level values of all data points is used as the environmental complexity factor. The larger the environmental complexity factor, the more chaotic the gray-level distribution of the data points within the range to be measured, and the greater the change in gray-level values, usually indicating a more complex environment.

[0069] The number of smoke data points can also be used as an indicator to measure the environmental complexity. The more smoke data points, the denser the smoke distribution within the range to be measured, further increasing the environmental complexity. Therefore, the value obtained by normalizing the product of the environmental complexity factor and the number of smoke data points is used as the environmental complexity of each range to be measured. At this time, the larger the environmental complexity, the higher the environmental complexity within the range to be measured, and the more a higher resolution of the optical quantum radar is required.

[0070] Based on the foregoing analysis, it can be seen that there is also a positive correlation between the area value of the range to be measured and the resolution of the optical quantum radar. Therefore, the value obtained by normalizing the product of the environmental complexity of each range to be measured and the area value, plus a preset constant, is used as the resolution adjustment coefficient. The larger the resolution adjustment coefficient, the more a higher resolution of the optical quantum radar is required to perform scanning within the range to be measured. Normalization is a well-known technical means to those skilled in the art. The choice of the normalization function can be linear normalization or standard normalization, etc. The specific normalization method is not limited here.

[0071] Then, the product of the resolution adjustment coefficient and the initial range resolution is used as the adjusted range resolution of the optical quantum radar, and the product of the resolution adjustment coefficient and the initial angular resolution is used as the adjusted angular resolution of the optical quantum radar. At this time, the adjusted range resolution and the adjusted angular resolution will match the environmental conditions within the range to be measured better, so that the optical quantum radar can measure information such as the distance and direction of the target more accurately, which helps to identify and locate the fire source within the range to be measured.

[0072] Finally, based on the adjusted power and adjusted resolution corresponding to each range to be measured, the optical quantum radar is used to detect and identify the fire source location within the range to be measured, and the fire source location can be accurately identified.

[0073] It should be noted that in this embodiment of the present invention, in order to avoid overshoot of power and resolution, the preset constant is set to 1, and the specific value can also be adjusted according to the implementation scenario, which is not limited herein; the initial power of the optical quantum radar can be set to 1 watt, the initial distance resolution can be set to 3 meters, and the initial angular resolution can be set to 0.1°, and the specific values can all be adjusted according to the implementation scenario, which is not limited herein.

[0074] After identifying the fire source location based on the foregoing process, the fire-fighting robot can select different fire-extinguishing substances to extinguish the fire source point according to the type of combustibles at the fire scene. For example, for carbon-containing solids, water-type fire extinguishers, foam fire extinguishers, etc. can be used; for liquids or meltable solid substances, dry powder fire extinguishers, carbon dioxide fire extinguishers, etc. can be used.

[0075] In summary, obtaining the radar point cloud data of the fire scene, the temperature time series data and the smoke concentration time series data at each monitoring position, and realizing the collaborative analysis of the spatial structure of the fire scene environment and the monitoring data can improve the reliability of subsequent fire source positioning. By comparing the radar point cloud data with the preset radar point cloud data, the smoke data points can be identified and extracted. Since smoke usually spreads with the spread of the fire, analyzing the movement characteristics of the smoke data points to determine the smoke diffusion path helps to narrow down the scope for accurate fire source positioning and identification; at the same time, the spread of the fire directly reflects the expansion trend of the fire, which also helps in the positioning analysis of the fire source. Therefore, the change difference between the temperature time series data and the smoke concentration time series data between the monitoring positions is analyzed to determine the fire spread path. Then, by comparing and analyzing the smoke diffusion path and the fire spread path, and combining the change characteristics of the temperature value and the smoke concentration value, the true fire evolution trend can be penetrated through the thick smoke interference and identified, and the suspected fire source positions are screened out among all the monitoring positions, narrowing the monitoring scope of the fire scene. Finally, within the range to be measured at each suspected fire source position, in this embodiment of the present invention, the initial power and the initial resolution of the optical quantum radar are adaptively adjusted according to indicators such as the area to be measured, the environmental complexity, and the smoke concentration. This intelligent parameter adjustment method enables the optical quantum radar to exert the best performance according to the actual needs in different scenarios, further improving the accuracy and stability of fire source identification and positioning. By integrating the point cloud space information with the change rules of temperature and smoke concentration, this embodiment of the present invention quickly locks the suspected fire source area and dynamically reduces the scanning range, and adaptively adjusts the parameters of the optical quantum radar, which helps to accurately locate the fire source and improve the timeliness of emergency rescue.

[0076] This embodiment of the present invention also provides an optical quantum radar fire source identification and positioning system for a fire-fighting robot. Please refer to Figure 4, which shows a system block diagram, including a data acquisition module 401 for implementing step S1 in the above method embodiment; a path analysis module 402 for implementing step S2 in the above method embodiment; a suspected fire source location screening module 403 for implementing step S3 in the above method embodiment; and a fire source location and identification module 404 for implementing step S4 in the above method embodiment.

[0077] It should be noted that for the system provided in the above embodiment, only the division of the above functional modules is used for illustration. In practical applications, the above functions can be assigned to different functional modules according to needs, that is, the internal structure of the computer device can be divided into different functional modules to complete all or part of the functions described above. In addition, a quantum light radar fire source identification and location system for a fire-fighting robot and a method embodiment of a quantum light radar fire source identification and location method for a fire-fighting robot provided in the above embodiment belong to the same concept. The specific implementation process can be seen in the method embodiment and will not be elaborated here.

[0078] Please refer to Figure 5 , which shows a schematic diagram of the system structure of a quantum light radar fire source identification and location system for a fire-fighting robot provided by an embodiment of the present invention, including a processor 500, a memory 501, a bus 502, and a communication interface 503. The processor 500, the communication interface 503, and the memory 501 are connected through the bus 502. Among them, the memory 501 may include a high-speed random access memory. The bus 502 may be an ISA bus, a PCI bus, an EISA bus, etc. The processor 500 may be an integrated circuit chip with signal processing capabilities. At least one instruction, at least one program, a code set, or an instruction set is stored in the memory 501. When at least one instruction, at least one program, a code set, or an instruction set is loaded and executed by the processor, the steps in a quantum light radar fire source identification and location method for a fire-fighting robot are implemented.

[0079] It should be noted that the above sequence of the embodiments of the present invention is only for description and does not represent the superiority or inferiority of the embodiments. The processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0080] Each embodiment in this specification is described in a progressive manner. The same or similar parts among the embodiments can be referred to each other. Each embodiment focuses on the differences from other embodiments.

Claims

1. A method for identifying and locating fire sources using a quantum light radar for a fire-fighting robot, characterized in that, The method includes: Obtaining the radar point cloud data detected by the optical quantum radar for the fire scene, as well as the temperature time-series data and smoke concentration time-series data at each monitoring position; Comparing the radar point cloud data at each moment with the preset radar point cloud data to determine the smoke data points; in the radar point cloud data at different moments, based on the movement of the smoke data points, determining the smoke diffusion path of the fire scene; analyzing the change differences between the temperature time-series data and the change differences between the smoke concentration time-series data to determine the fire spread path; Comparing the smoke diffusion path and the fire spread path, and screening the suspected fire source positions among all the monitoring positions based on the change of the temperature value and the change of the smoke concentration value at the monitoring positions at the current moment; Taking the monitoring range of each suspected fire source position as the range to be measured; within each range to be measured, among the area value of the range to be measured, the environmental complexity, and the smoke concentration value at the current moment, select indicators to adjust the initial power and initial resolution of the optical quantum radar respectively, so as to identify and locate the fire source in the range to be measured.

2. The method for identifying and positioning a fire source using a quantum light radar for a fire extinguishing robot according to claim 1, wherein The method for obtaining the smoke diffusion path includes: In the radar point cloud data at each moment, taking the position of each smoke data point as the starting point and the position of the same smoke data point in the radar point cloud data at the adjacent next moment as the end point, to obtain the motion vector of each smoke data point between the radar point cloud data at adjacent moments; In the radar point cloud data at each moment, for any xoz plane, synthesizing the motion vectors of the radar point cloud data in the xoz plane to determine the motion direction of the xoz plane; Connecting the motion directions of the same xoz plane in the radar point cloud data at all moments to obtain all the smoke diffusion paths.

3. A method for identifying and locating a fire source using a quantum light radar for a fire extinguishing robot according to claim 1, characterized in that, The method for obtaining the fire spread path includes: Obtaining the temperature curve of the temperature time-series data at each monitoring position, on the temperature curve, obtaining the slope value at each data point, and taking the sum value of the slope values at all data points as the temperature change trend value at each monitoring position; Obtaining the concentration curve of the smoke concentration time-series data at each monitoring position, on the concentration curve, obtaining the slope value at each data point, and taking the sum value of the slope values at all data points as the smoke concentration change trend value at each monitoring position; Determining a preset neighborhood centered on each monitoring position, within the preset neighborhood corresponding to each monitoring position, analyzing the difference situation between the temperature change trend values of the central monitoring position and the neighborhood monitoring positions and the difference situation between the smoke concentration change trend values to obtain the direction determination factor; When the direction determination factor between the central monitoring position and each neighborhood monitoring position is greater than the preset direction determination threshold, the fire spread direction between the central monitoring position and each neighborhood monitoring position is from the neighborhood monitoring position to the central monitoring position, otherwise it is from the central monitoring position to the neighborhood monitoring position; Integrating the fire spread directions between all the monitoring positions and the neighborhood monitoring positions to obtain all the fire spread paths.

4. A method for identifying and locating a fire source using a quantum optical radar for a fire extinguishing robot according to claim 3, characterized in that, The method for obtaining the direction determination factor includes: The value obtained by normalizing the difference between the temperature change trend value at the central monitoring position and that at each neighborhood monitoring position is used as the temperature change difference, and the value obtained by normalizing the difference between the smoke concentration change trend value at the central monitoring position and that at each neighborhood monitoring position is used as the smoke concentration change difference; The value obtained by normalizing the product of the temperature change difference and the smoke concentration change difference is used as the direction determination factor.

5. The method for identifying and locating a fire source using a quantum light radar for a fire extinguishing robot according to claim 3, characterized in that, The method for obtaining the suspected fire source position includes: Comparing the fire spread path and the smoke diffusion path to screen out the positions to be analyzed among all monitoring positions; For any position to be analyzed, the sum of the temperature change trend value and the smoke concentration change trend value at this position to be analyzed is used as the first fire source factor; The sum of the temperature value and the smoke concentration value at this position to be analyzed at the current moment is used as the second fire source factor; The value obtained by normalizing the product of the first fire source factor and the second fire source factor at this position to be analyzed is used as the suspected fire source index at the position to be analyzed; The positions to be analyzed with the suspected fire source index greater than the preset fire source threshold are used as the suspected fire source positions.

6. The method for identifying and positioning a fire source by a quantum light radar for a fire extinguishing robot according to claim 5, characterized in that, The method for obtaining the positions to be analyzed includes: Mapping each fire spread path to the three-dimensional radar point cloud data and comparing it with the smoke diffusion path. If the overlapping length of a certain fire spread path and a certain smoke diffusion path is greater than or equal to one-half of the smoke diffusion path, then this fire spread path is used as the path to be analyzed, and the monitoring positions on the target path are used as the positions to be analyzed.

7. A method for identifying and locating a fire source using a quantum light radar for a fire extinguishing robot according to claim 1, characterized in that, In each range to be measured, among the area value, the environmental complexity, and the smoke concentration value at the current moment of the range to be measured, select indicators to adjust the initial power and initial resolution of the optical quantum radar respectively, so as to identify and locate the fire source in the range to be measured, including: In each range to be measured, the value obtained by normalizing the smoke concentration value at the suspected fire source position corresponding to the range to be measured at the current moment, and the sum value with a preset constant is used as the power adjustment coefficient; The product of the power adjustment coefficient and the initial power is used as the adjusted power of the optical quantum radar; Based on the quantity characteristics and gray-scale characteristics of the data points in the radar point cloud data of each range to be measured, determine the environmental complexity of each range to be measured; The value obtained by normalizing the product of the environmental complexity of each range to be measured and the area value, and the sum value with a preset constant is used as the resolution adjustment coefficient; The product of the resolution adjustment coefficient and the initial range resolution is used as the adjusted range resolution of the optical quantum radar, and the product of the resolution adjustment coefficient and the initial angular resolution is used as the adjusted angular resolution of the optical quantum radar; Based on the adjusted power, adjusted range resolution, and adjusted angular resolution corresponding to each range to be measured, use the optical quantum radar to detect the range to be measured and identify the fire source position.

8. A method for identifying and locating a fire source using a quantum light radar for a fire-fighting robot according to claim 7, characterized in that, The method for obtaining the environmental complexity includes: In each range to be measured, the variance of the gray-scale values of all data points is used as the environmental complexity factor; The value obtained by normalizing the product of the environmental complexity factor and the number of smoke data points is used as the environmental complexity of each range to be measured.

9. A method for identifying and locating a fire source using a quantum light radar for a fire extinguishing robot according to claim 1, characterized in that, The method for obtaining the smoke data points includes: Compare the radar point cloud data at each moment with the preset radar point cloud data, and regard the newly emerged data points as smoke data points; among them, the preset radar point cloud data is the radar point cloud data at the scene when there is no fire.

10. A photoquantum radar fire source identification and positioning system for a fire-fighting robot, characterized in that, It includes a processor and a memory. At least one instruction, at least one program, a code set or an instruction set is stored in the memory. When the at least one instruction, at least one program, the code set or the instruction set is loaded and executed by the processor, the steps of a method for identifying and positioning a light quantum radar fire source for a fire extinguishing robot as described in any one of claims 1-9 are implemented.

Images