Hot blast stove spark detection method and system based on optical-thermosensitive dual modes

Abstract

The invention relates to the technical field of hot blast stove spark detection, in particular to a hot blast stove spark detection method and system based on optical-thermosensitive bimodalities, and the method comprises the steps: setting a plurality of detection sections in a target detection area, and synchronously obtaining the temperature data, infrared data and airflow data of one or more sections; constructing a direction sensing temperature field of the detection section based on the temperature data and the airflow data; constructing an infrared radiation field of the detection section by using the infrared data; the direction sensing temperature field is converted into a radiation field through a temperature-radiation conversion algorithm, the radiation field is used for compensating an infrared radiation field of the detection section, and a net radiation field without background temperature interference is obtained; and performing spatial-temporal feature fusion detection on the net radiation field so as to realize Mars detection.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of hot blast stove star detection, and particularly relates to a hot blast stove star detection method and system based on optical-thermosensitive dual modal. BACKGROUND

[0002] In a high-temperature and high-background radiation environment such as a hot blast stove, the star cannot be accurately detected by relying on an infrared thermal imager alone. It is necessary to identify and locate the star by combining fixed-point temperature sensor (such as thermistor) and infrared thermal imager data to eliminate background thermal radiation interference and obtain infrared radiation data (such as radiation intensity image) containing only the star. That is, the temperature data measured by the temperature sensor is used to construct a background temperature field (temperature distribution), and after temperature-radiation conversion, the corresponding radiation field is obtained. The radiation field is separated from the infrared radiation intensity distribution output by the infrared thermal imager to exclude the influence of background radiation.

[0003] In the traditional background temperature field construction process (such as standard RBF difference), the influence of air flow direction on temperature distribution is blurred. For example, the temperature changes gently along the air flow direction, while the temperature may change abruptly perpendicular to the air flow direction. This blurring can cause inaccurate temperature estimation near the pipe wall and deviation in star trajectory prediction during star detection. SUMMARY

[0004] The present application fuses temperature data, infrared data and air flow data to construct a direction-aware temperature field. Based on the direction-aware temperature field and the infrared radiation field, a net radiation field is constructed to improve the accuracy of star detection.

[0005] The technical solution provided by the present application is: a hot blast stove star detection method based on optical-thermosensitive dual modal, the method comprising: setting multiple detection sections in a target detection area, and synchronously acquiring temperature data, infrared data and air flow data of one or more sections; constructing a direction-aware temperature field of the detection section based on the temperature data and the air flow data; and constructing an infrared radiation field of the detection section using the infrared data; converting the direction-aware temperature field into a radiation field through a temperature-radiation conversion algorithm, compensating the infrared radiation field of the detection section using the radiation field, and obtaining a net radiation field excluding background temperature interference; detecting the net radiation field in time and space to realize detection of the star.

[0006] Preferably, the synchronous acquisition of temperature data, infrared data and air flow data of one or more sections comprises: selecting a continuous section in the star moving path dividing the continuous section into sections: ; the distance between the cross sections is ; represents the interval adjustment coefficient; According to the preset acquisition frequency, the thermal sensor data is acquired to obtain temperature data of multiple positions of the detection cross section, and a temperature data set is constructed ; wherein, represents the temperature of the detection cross section at the moment ; , respectively represent the number of cross sections and the number of positions; represents the number of data acquisition times in the acquisition period; According to the preset acquisition frequency, the airflow sensor data is acquired to obtain airflow data of the detection cross section, and an airflow velocity vector is constructed ; represents the airflow velocity component of the detection cross section at the moment ; ; based on the airflow velocity vector, an airflow velocity vector set is constructed ; According to the preset acquisition frequency, the infrared thermal imaging device is acquired to obtain the infrared radiation intensity image of the detection cross section, and an infrared radiation intensity image set is constructed ; represents the infrared radiation intensity image data of the detection cross section at the moment ; The temperature data set, the airflow velocity vector set and the infrared radiation intensity image set are aligned on the time axis.

[0007] Preferably, the direction-aware temperature field of the detection cross section based on the temperature data and the airflow data comprises: Based on the temperature data, a current detection cross section temperature field is constructed, and a subsequent detection cross section temperature field is predicted; Based on the temperature field, the predicted later detection cross section temperature field, and combined with the airflow direction, a direction-aware temperature field is constructed.

[0008] Preferably, the direction-aware temperature field of the detection cross section based on the temperature data and the airflow data comprises: A background temperature field of the detection cross section at the moment is established, comprising: Suppose the detection cross section at the moment includes temperature measurement points; The temperature field of the detection surface is constructed by RBF interpolation method: Suppose the detection cross section at the moment​​​ The background temperature distribution, i.e., the background temperature field is ; ; in, Indicates the temperature measurement point Coordinate normalization; Indicates the coordinates of the reference point. ( , , This represents the average distance between temperature measurement points; Indicates the smoothing coefficient; Weight and smoothing coefficient Solving a system of linear equations using the least squares method: ; Indicates the first j The first detection cross section The measured temperature values ​​at each temperature measurement point; ; Predicting the temperature field of the subsequent probe cross section includes: Suppose that the temperature field of the probe section is predicted. ; Among them, the correction item ; Represents the thermal diffusivity, if ,but ; Corrected predicted temperature field at the probe interface, and corrected temperature field at the probe cross section. ;in, ;in, Indicates the first The first detection cross section The measured temperature at each temperature measurement point; This represents the correction factor.

[0009] Preferably, the temperature field based on the temperature field, the predicted temperature field of the subsequent detection section, and the direction-sensing temperature field constructed by combining the airflow direction include: Establish a model of the airflow direction at the detection cross section, i.e., the airflow direction field is: ; in, ; This represents the airflow velocity vector at any point in the detection cross section; Indicates the cross-sectional area of ​​the probe; Set boundary conditions, i.e., the direction of airflow at the cross-sectional boundary is 0; Quantifying heat exchange at the edge of a Mars impact probe cross-section includes: Constructing an energy model of the boundary of a Mars impact probe section: ;in, Indicates the kinetic energy component of Mars; Indicates the radiation component of Mars; These represent the temperature of Mars and the boundary temperature of the probe section, respectively. Indicates the contact area. , Indicates the duration of contact; Indicates the depth of boundary deformation; ;in, Indicates the density of Mars. Indicates the boundary elastic modulus; Indicates normal velocity; By combining airflow direction, the temperature field of the detection surface is improved, and the temperature field sensed in the direction of the detection surface is obtained: ; Among them, direction-weighted distance ; Anisotropic matrix ;in, Indicates direction sensitivity. Indicates the local airflow direction component. ; The weighting coefficients are obtained by solving the following system of linear equations. Specifically: ; Therefore, the temperature field of the subsequent detection section is: ; .

[0010] Preferably, the construction of a directional sensing temperature field based on the temperature field, the predicted temperature field of the subsequent detection section, and the airflow direction further includes: The fusion of the Martian impact probe's edge caused a temperature rise at the edge, necessitating edge correction, including: Constructing a layered temperature field: ; Among them, the edge attenuation coefficient ; ; ,in, This indicates the specific heat capacity and density of the pipe material that forms the edge of the detection section; Using a layered temperature field instead of the temperature field of the probe section, the temperature field of the subsequent probe section becomes: ; .

[0011] Preferably, the step of converting the direction-sensing temperature field into a radiation field using a temperature-radiation conversion algorithm, and then using the radiation field to compensate for the infrared radiation field of the detection cross-section to obtain a net radiation field that excludes background temperature interference, includes...

[0012] Obtain the layered temperature field and perform temperature-radiation conversion, specifically: radiation field ;in, Indicates emissivity; Point Background radiation intensity; Indicates the intensity of ambient radiation; Obtain the infrared radiation intensity distribution of the detection cross section, i.e., the infrared radiation field. ; Net radiation field .

[0013] Preferably, the spatiotemporal feature fusion detection of the net radiation field to achieve Mars exploration includes: Construct the net radiation field sequence of the detection cross section ; Spatiotemporal data cubes obtained from net radiation field sequences ,include: Add a time variable to the net radiation field to obtain ; but, ;,in, ; ; ;in, , , These represent the width, height, and acquisition time window length of the infrared radiation intensity image, respectively. Spatial feature enhancement is performed using a multi-scale high-speed Laplacian filtering algorithm, specifically enhancing small-sized high-temperature points in infrared radiation intensity images while suppressing large-sized background structures. Acquiring spatial features ; ;in, This represents a high-speed filter with a standard deviation of [value missing]. Used to smooth images; This represents the Laplacian operator, used to monitor image edges and high-temperature points; This represents the convolution operation; Represents the enhanced spatiotemporal data cube ; Temporal feature extraction is performed using a time-domain bandpass filtering algorithm, including: Obtaining temporal features ; ,in Indicates a bandpass filter. The passband frequency range is ;in, These represent the average velocity of Mars, the maximum diameter of Mars, and the minimum diameter of Mars, respectively. use and The motion trajectory characteristics of Mars were obtained by calculating using optical flow algorithms. ; By fusing temporal features, spatial features, and motion trajectories into a single probability map, the probability that each pixel belongs to Mars is quantified, including: The spatial features, temporal features, and motion trajectory are normalized to obtain the normalized result. , and ; Obtain fusion features ,in, , , Indicates the fusion weights; The probability distribution characteristics of Mars were obtained by three-dimensional Gaussian filtering. Mars probability distribution characteristics ,in, Represents a high-speed kernel function. , Indicates the radius of the spatial core. Indicates the time kernel radius; The location, size, temperature, and trajectory features of the target Mars are extracted from the obtained Mars probability distribution features, including: Quantify the position and trajectory of the target Mars, including: Calculate the weighted centroid of the probability distribution of Mars The trajectory of Mars was obtained by fitting the probability distribution weighted centroid using a quadratic polynomial, and the coefficients of the quadratic polynomial were obtained by the least squares method. The quadratic polynomial is ; Quantifying the size of the target Mars includes: Calculate the equivalent circular diameter of Mars, i.e.: Equivalent circle diameter ,in, Represents the area of ​​the target pixel; Calculate the average diameter of Mars within the cross-section ,in, This represents the total number of image frames containing the target Mars. Temperature inversion is performed to obtain the average net radiation field intensity of the target detection cross section. ; Then temperature ;in, This represents the Stefan-Boltzmann constant; After normalizing the obtained Martian temperature, equivalent circle diameter, and probability distribution of the target probe section using weighted centroid, the data is input into a pre-trained CNN model to output the Martian risk probability. ,if If the risk exceeds the preset risk threshold, an alarm signal will be output.

[0014] A Mars exploration system based on an optical-thermal dual-mode hot air furnace is used to execute the aforementioned Mars exploration method based on an optical-thermal dual-mode hot air furnace.

[0015] A computer-readable storage medium storing a computer program that is executed by a processor to implement the above-described optical-thermal dual-mode hot blast furnace Mars exploration method.

[0016] The beneficial effects of this invention are: 1. This invention divides the probe into multiple probe sections according to the Martian flow path and independently constructs the temperature field of each probe section (i.e., decoupling the space temperature field), which can avoid the accumulation of temperature field modeling errors caused by long-distance heat conduction. Considering the case of Martian impact on the tube wall, by constructing temperature fields in different regions (central region, wall boundary region, and wall boundary region), the influence of hot spots (Mars impact point) on the overall path temperature field can be avoided.

[0017] 2. This invention constructs a directional temperature field by utilizing the temperature fields and airflow directions of different regions. By integrating airflow dynamics and heat conduction characteristics, it solves the problem of the airflow affecting the temperature distribution pattern being blurred in the traditional temperature field construction process. Furthermore, by converting the directional temperature field into a radiation field and compensating for the infrared radiation field, a more accurate net radiation field can be obtained, thereby improving the accuracy of Mars exploration. Attached Figure Description

[0018] Figure 1 This is a flowchart of the Mars exploration method based on an optical-thermal dual-mode hot air furnace according to the present invention. Detailed Implementation

[0019] The following description is intended to disclose the present invention and enable those skilled in the art to implement it. The preferred embodiments described below are merely examples, and other obvious modifications will occur to those skilled in the art. The basic principles of the invention defined in the following description can be applied to other embodiments, modifications, improvements, equivalents, and other technical solutions that do not depart from the spirit and scope of the invention.

[0020] It is understood that the term "a" should be understood as "at least one" or "one or more," that is, in one embodiment, the number of an element can be one, while in another embodiment, the number of the element can be multiple, and the term "a" should not be understood as a limitation on the number.

[0021] Example 1: refer to Figure 1 The technical solution provided by this invention is: a Mars exploration method based on an optical-thermal dual-mode hot air furnace, comprising the following steps: Step 1: Set up multiple detection sections in the target detection area and simultaneously acquire temperature data, infrared data and airflow data of one or more sections.

[0022] The simultaneous acquisition of temperature data, infrared data, and airflow data from one or more cross-sections includes the following steps: Step 1.1: Select continuous segments in the Mars movement path. Divide the continuous segment into One cross section: The distance between the sections is ; Indicates the spacing adjustment factor; Data from the thermal sensor is collected at a preset acquisition frequency to obtain temperature data at multiple locations on the detection cross section, thus constructing a temperature dataset. ;in, express Constant detection cross section midpoint The temperature at that location , These represent the number of cross sections and the number of locations, respectively. Indicates the number of data collections within the collection period; Step 1.2: Collect airflow sensor data according to the preset acquisition frequency, obtain airflow data of the detection section, and construct the airflow velocity vector. ; express Constant detection cross section airflow Axis velocity components and Axial velocity components; constructing an airflow velocity vector set based on airflow velocity vectors. ; Step 1.3: Acquire infrared radiation intensity images of the detection cross section using an infrared thermal imaging device at a preset acquisition frequency, thus forming an infrared radiation intensity image set. ; express Time detection cross section Infrared radiation intensity image data; Step 1.4: Align the temperature dataset, airflow velocity vector set, and infrared radiation intensity image set on the time axis.

[0023] In this embodiment, multiple temperature measurement points are set within each probe section, and a thermistor (temperature sensor) is installed at each temperature measurement point to measure the temperature at that point. The shape and boundary of the probe section match the cross-sectional shape and edge of the pipe in which the Martian flow path is located.

[0024] Step 2: Construct the directional sensing temperature field of the detection cross section based on temperature and airflow data; construct the infrared radiation field of the detection cross section using infrared data. This includes the following steps: Step 2.1: Construct the temperature field of the current probe section based on the temperature data, and predict the temperature field of subsequent probe sections. This step can be achieved through the following steps: Step 2.1.1: Establish the detection cross section The background temperature field includes: Set the detection cross section Includes One temperature measurement point; The temperature field of the probe surface is constructed using the RBF interpolation method: Set the detection cross section The background temperature distribution, i.e., the background temperature field is ; ; in, Indicates the temperature measurement point Coordinate normalization; Indicates the coordinates of the reference point. ( , , This represents the average distance between temperature measurement points; Indicates the smoothing coefficient; Weight and smoothing coefficient Solving a system of linear equations using the least squares method: ; Indicates the first j The first detection cross section The measured temperature values ​​at each temperature measurement point; ; Step 2.1.2: Predict the temperature field of the subsequent probe section, including: Suppose that the temperature field of the probe section is predicted. ; Among them, the correction item ; Represents the thermal diffusivity, if ,but ; Corrected predicted temperature field at the probe interface, and corrected temperature field at the probe cross section. ;in, ;in, Indicates the first The first detection cross section The measured temperature at each temperature measurement point; This represents the correction factor.

[0025] In this embodiment, by predicting the temperature field (temperature distribution) of subsequent detection cross sections after the current detection cross section, the dependence on the number of thermistors can be reduced.

[0026] In some cases, when establishing the temperature field, it is necessary to consider the impact of Mars and the direction of airflow to address the issue of temperature anomalies at the edge of the probe section caused by Mars impacting the pipe wall. This is achieved through the following steps: Step 2.2: Based on the temperature field and the predicted temperature field of the later detection section, a directional sensing temperature field is constructed by combining the airflow direction. This includes the following steps: Step 2.2.1: Establish the airflow direction model of the detection section, that is, the airflow direction field is: ; in, ; This represents the airflow velocity vector at any point in the detection cross section; Indicates the cross-sectional area of ​​the probe; Step 2.2.2: Set boundary conditions, i.e., the direction of airflow at the cross-sectional boundary is 0; Step 2.2.3: Quantify the heat exchange at the edge of the Mars impact probe cross-section, including: Constructing an energy model of the boundary of a Mars impact probe section: ;in, Indicates the kinetic energy component of Mars; Indicates the radiation component of Mars; These represent the temperature of Mars and the boundary temperature of the probe section, respectively. Indicates the contact area. , Indicates the duration of contact; Indicates the depth of boundary deformation; ;in, Indicates the density of Mars. Indicates the boundary elastic modulus; Indicates normal velocity; Step 2.2.4: Combine the airflow direction to improve the temperature field of the detection surface and obtain the temperature field sensed in the direction of the detection surface: ; Among them, direction-weighted distance ; Anisotropic matrix ;in, Indicates direction sensitivity. Indicates the local airflow direction component. ; The weighting coefficients are obtained by solving the following system of linear equations. Specifically: ; Therefore, the temperature field of the subsequent detection section is: ; .

[0027] Step 3: Convert the direction-sensing temperature field into a radiation field using a temperature-to-radiation conversion algorithm. Use this radiation field to compensate for the infrared radiation field of the detection cross-section, obtaining a net radiation field that eliminates background temperature interference. This includes the following steps: The temperature field of the target detection section is obtained, and a temperature-radiation conversion is performed, specifically as follows: radiation field ;in, Indicates emissivity; Indicates the detection cross section Temperature field; Indicates the intensity of ambient radiation; Obtain the infrared radiation intensity distribution of the detection cross section, i.e., the infrared radiation field. ; Net radiation field .

[0028] Step 4: Perform spatiotemporal feature fusion detection on the net radiation field to achieve Mars exploration. This includes the following steps: Construct the net radiation field sequence of the detection cross section ; Spatiotemporal data cubes obtained from net radiation field sequences ,include: Add a time variable to the net radiation field to obtain ; but, ;,in, ; ; ;in, , , These represent the width, height, and acquisition time window length of the infrared radiation intensity image, respectively. Spatial feature enhancement is performed using a multi-scale high-speed Laplacian filtering algorithm, specifically enhancing small-sized high-temperature points in infrared radiation intensity images while suppressing large-sized background structures. Acquiring spatial features ; ;in, This represents a high-speed filter with a standard deviation of [value missing]. Used to smooth images; This represents the Laplacian operator, used to monitor image edges and high-temperature points; This represents the convolution operation; Represents the enhanced spatiotemporal data cube ; Temporal feature extraction is performed using a time-domain bandpass filtering algorithm, including: Obtaining temporal features ; ,in Indicates a bandpass filter. The passband frequency range is ;in, These represent the average velocity of Mars, the maximum diameter of Mars, and the minimum diameter of Mars, respectively. use and The motion trajectory characteristics of Mars were obtained by calculating using optical flow algorithms. ; By fusing temporal features, spatial features, and motion trajectories into a single probability map, the probability that each pixel belongs to Mars is quantified, including: The spatial features, temporal features, and motion trajectory are normalized to obtain the normalized result. , and ; Obtain fusion features ,in, , , Indicates the fusion weights; The probability distribution characteristics of Mars were obtained by three-dimensional Gaussian filtering. Mars probability distribution characteristics ,in, Represents a high-speed kernel function. , Indicates the radius of the spatial core. Indicates the time kernel radius; The location, size, temperature, and trajectory features of the target Mars are extracted from the obtained Mars probability distribution features, including: Quantify the position and trajectory of the target Mars, including: Calculate the weighted centroid of the probability distribution of Mars The trajectory of Mars was obtained by fitting the probability distribution weighted centroid using a quadratic polynomial, and the coefficients of the quadratic polynomial were obtained by the least squares method. The quadratic polynomial is ; Quantifying the size of the target Mars includes: Calculate the equivalent circular diameter of Mars, i.e.: Equivalent circle diameter ,in, Represents the area of ​​the target pixel; Calculate the average diameter of Mars within the cross-section ,in, This represents the total number of image frames containing the target Mars. Temperature inversion is performed to obtain the average net radiation field intensity of the target detection cross section. ; Then temperature ;in, This represents the Stefan-Boltzmann constant; After normalizing the obtained Martian temperature, equivalent circle diameter, and probability distribution of the target probe section using weighted centroid, the data is input into a pre-trained CNN model to output the Martian risk probability. ,if If the risk exceeds the preset risk threshold, an alarm signal will be output.

[0029] Example 2: In Example 1, the impact of the Martian impact on the avoidance temperature was taken into account, resulting in different temperature fields at different locations on the probe cross section. For example, the temperature field of the probe cross section was divided into the temperature field of the edge region, the temperature field of the center region, and the temperature field of the wall boundary region (impact region), and the temperature field of each region was calculated in a different way.

[0030] In Example 1, the temperature field of the central region is used for temperature compensation.

[0031] To improve the accuracy and adaptability of temperature compensation, we propose the following technical solution based on Example 1: The fusion of the Martian impact probe's edge caused a temperature rise at the edge, necessitating edge correction, including: Constructing a layered temperature field: ; In this embodiment, This represents the temperature field in the boundary region of the wall. Represents the temperature field in the edge region. Indicates the temperature field in the central region; Among them, the edge attenuation coefficient ; ; ,in, This indicates the specific heat capacity and density of the pipe material that forms the edge of the detection section; Using a layered temperature field instead of the temperature field of the probe section, the temperature field of the subsequent probe section becomes: ; .

[0032] Obtain the layered temperature field and perform temperature-radiation conversion, specifically: radiation field ;in, Indicates emissivity; Point Background radiation intensity; Indicates the intensity of ambient radiation; Obtain the infrared radiation intensity distribution of the detection cross section, i.e., the infrared radiation field. ; Net radiation field .

[0033] The present invention also provides a Mars exploration system based on an optical-thermal dual-mode hot blast furnace, the system being used to execute the aforementioned Mars exploration method based on an optical-thermal dual-mode hot blast furnace.

[0034] A computer-readable storage medium storing a computer program that is executed by a processor to implement the above-described optical-thermal dual-mode hot blast furnace Mars exploration method.

[0035] The processes described above with reference to the flowcharts in the embodiments disclosed in this invention can be implemented as computer software programs. The embodiments disclosed in this invention include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication component, and / or installed from a removable medium. When the computer program is executed by a central processing unit (CPU), it performs the functions defined in the methods of this application. It should be noted that the computer-readable medium described above in this application can be a computer-readable signal medium or a computer-readable storage medium, or any combination of the two. Computer-readable storage media can be, for example, but not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatuses, or devices, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections having one or more wire segments, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this application, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in connection with an instruction execution system, apparatus, or device. In this application, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium can also be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on a computer-readable medium may be transmitted using any suitable medium, including but not limited to: wireless segments, wire segments, optical fibers, RF, etc., or any suitable combination thereof.

[0036] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present invention. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, may be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0037] Those skilled in the art should understand that the embodiments of the present invention described above and shown in the accompanying drawings are merely examples and do not limit the present invention. The purpose of the present invention has been fully and effectively achieved. The functions and structural principles of the present invention have been shown and explained in the embodiments. Without departing from the principles described, the implementation of the present invention may have any changes or modifications.

Claims

1. A Mars exploration method based on an optical-thermal dual-mode hot blast furnace, characterized in that, The method includes: Multiple detection cross-sections are set up in the target detection area to simultaneously acquire temperature data, infrared data, and airflow data from one or more cross-sections. A directional temperature field for the detection cross section is constructed based on temperature and airflow data; an infrared radiation field for the detection cross section is constructed using infrared data. The temperature field of the direction sensing is converted into a radiation field by a temperature-radiation conversion algorithm. The radiation field is then used to compensate for the infrared radiation field of the detection section, so as to obtain a net radiation field that excludes background temperature interference. Spatiotemporal feature fusion detection of the net radiation field is used to achieve Mars exploration.

2. The Mars exploration method based on an optical-thermal dual-mode hot air furnace according to claim 1, characterized in that, The simultaneous acquisition of temperature data, infrared data, and airflow data from one or more cross-sections includes: Selecting continuous segments from the Mars movement path Divide the continuous segment into One cross section: The distance between the sections is ; Indicates the spacing adjustment factor; Data from the thermal sensor is collected at a preset acquisition frequency to obtain temperature data at multiple locations on the detection cross section, thus constructing a temperature dataset. ;in, express Constant detection cross section middle Temperature at point , These represent the number of cross sections and the number of locations, respectively. Indicates the number of data collections within the collection period; Data from the airflow sensor is collected at a preset sampling frequency to obtain airflow data at the detection cross section, and an airflow velocity vector is constructed. ; express Constant detection cross section airflow Axis velocity components and Axial velocity components; constructing an airflow velocity vector set based on airflow velocity vectors. ; Infrared thermal imaging equipment acquires infrared radiation intensity images of the detection cross section according to a preset acquisition frequency, forming an infrared radiation intensity image set. ; express Time detection cross section Infrared radiation intensity image data; Align the temperature dataset, airflow velocity vector set, and infrared radiation intensity image set on the time axis.

3. The Mars exploration method based on an optical-thermal dual-mode hot air furnace according to claim 2, characterized in that, The construction of the directional sensing temperature field of the detection cross section based on temperature data and airflow data includes: The temperature field of the current detection section is constructed based on the temperature data, and the temperature field of the subsequent detection sections is predicted. Based on the temperature field and the predicted temperature field of the later detection section, a directional sensing temperature field is constructed by combining the airflow direction.

4. The Mars exploration method based on an optical-thermal dual-mode hot air furnace according to claim 3, characterized in that, The process of constructing the temperature field of the current detection section based on temperature data and predicting the temperature field of subsequent detection sections includes: Establish detection cross section The background temperature field includes: Set the detection cross section Includes One temperature measurement point; The temperature field of the probe surface was constructed using the RBF interpolation method. Set the detection cross section The background temperature distribution, i.e., the background temperature field is ; ； in, Indicates the temperature measurement point Coordinate normalization; Indicates the coordinates of the reference point. ( , , This represents the average distance between temperature measurement points; Indicates the smoothing coefficient; Weight and smoothing coefficient Solving a system of linear equations using the least squares method: ; Indicates the first j The first detection cross section The measured temperature values ​​at each temperature measurement point; ; Predict the temperature field of the subsequent probe section, including: Suppose that the temperature field of the probe section is predicted. ; Among them, the correction item ; Represents the thermal diffusivity, if ,but ; Corrected predicted temperature field at the probe interface, and corrected temperature field at the probe cross section. ;in, ;in, Indicates the first The first detection cross section The measured temperature at each temperature measurement point; This represents the correction factor.

5. The Mars exploration method based on an optical-thermal dual-mode hot air furnace according to claim 4, characterized in that, The temperature field based on the temperature field and the predicted temperature field of the subsequent detection section, combined with the airflow direction to construct a direction-sensing temperature field, includes: Establish a model of the airflow direction at the detection cross section, i.e., the airflow direction field is: ； in, ; This represents the airflow velocity vector at any point in the detection cross section; Indicates the cross-sectional area of ​​the probe; Set boundary conditions, i.e., the direction of airflow at the cross-sectional boundary is 0; Quantifying heat exchange at the edge of a Mars impact probe cross-section includes: Constructing an energy model of the boundary of a Mars impact probe section: ;in, Indicates the kinetic energy component of Mars; Indicates the radiation component of Mars; These represent the temperature of Mars and the boundary temperature of the probe section, respectively. Indicates the contact area. , Indicates the duration of contact; Indicates the depth of boundary deformation; ;in, Indicates the density of Mars. Indicates the boundary elastic modulus; Indicates normal velocity; By combining airflow direction, the temperature field of the detection surface is improved, and the temperature field sensed in the direction of the detection surface is obtained: ； Among them, direction-weighted distance ; Anisotropic matrix ;in, Indicates direction sensitivity. Indicates the local airflow direction component. ; The weighting coefficients are obtained by solving the following system of linear equations. Specifically: ； Therefore, the temperature field of the subsequent detection section is: ； 。 6. The Mars exploration method based on an optical-thermal dual-mode hot air furnace according to claim 5, characterized in that, The temperature field based on the temperature field and the predicted temperature field of the subsequent detection section, combined with the airflow direction to construct a direction-sensing temperature field, also includes: The fusion of the Martian impact probe's edge caused a temperature rise at the edge, necessitating edge correction, including: Constructing a layered temperature field: ; Among them, the edge attenuation coefficient ; ; ,in, This indicates the specific heat capacity and density of the pipe material that forms the edge of the detection section; Using a layered temperature field instead of the temperature field of the probe section, the temperature field of the subsequent probe section becomes: ； 。 7. The Mars exploration method based on an optical-thermal dual-mode hot air furnace according to claim 6, characterized in that, The process involves converting the direction-sensing temperature field into a radiation field using a temperature-to-radiation conversion algorithm, then using this radiation field to compensate for the infrared radiation field of the detection cross-section, thereby obtaining a net radiation field that excludes background temperature interference. Obtain the layered temperature field and perform temperature-radiation conversion, specifically as follows: radiation field ;in, Indicates emissivity; Point Background radiation intensity; Indicates the intensity of ambient radiation; Obtain the infrared radiation intensity distribution of the detection cross section, i.e., the infrared radiation field. ; Net radiation field .

8. The Mars exploration method based on an optical-thermal dual-mode hot air furnace according to claim 7, characterized in that, The spatiotemporal feature fusion detection of the net radiation field to achieve Mars exploration includes: Construct the net radiation field sequence of the detection cross section ; Spatiotemporal data cubes obtained from net radiation field sequences ,include: Add a time variable to the net radiation field to obtain ; but, ;,in, ; ; ;in, , , These represent the width, height, and acquisition time window length of the infrared radiation intensity image, respectively. Spatial feature enhancement is performed using a multi-scale high-speed Laplacian filtering algorithm, specifically enhancing small-sized high-temperature points in infrared radiation intensity images while suppressing large-sized background structures. Acquiring spatial features ; ;in, This represents a high-speed filter with a standard deviation of [value missing]. Used to smooth images; This represents the Laplacian operator, used to monitor image edges and high-temperature points; This represents the convolution operation; Represents the enhanced spatiotemporal data cube ; Temporal feature extraction is performed using a time-domain bandpass filtering algorithm, including: Obtaining temporal features ; ,in Indicates a bandpass filter. The passband frequency range is ;in, These represent the average velocity of Mars, the maximum diameter of Mars, and the minimum diameter of Mars, respectively. use and The motion trajectory characteristics of Mars were obtained by calculating using optical flow algorithms. ; By fusing temporal features, spatial features, and motion trajectories into a single probability map, the probability that each pixel belongs to Mars is quantified, including: The spatial features, temporal features, and motion trajectory are normalized to obtain the normalized result. , and ; Obtain fusion features ,in, , , Indicates the fusion weights; The probability distribution characteristics of Mars were obtained by three-dimensional Gaussian filtering. Mars probability distribution characteristics ,in, Represents a high-speed kernel function. , Indicates the radius of the spatial core. Indicates the time kernel radius; The location, size, temperature, and trajectory features of the target Mars are extracted from the obtained Mars probability distribution features, including: Quantify the position and trajectory of the target Mars, including: Calculate the weighted centroid of the probability distribution of Mars The trajectory of Mars was obtained by fitting the probability distribution weighted centroid using a quadratic polynomial, and the coefficients of the quadratic polynomial were obtained by the least squares method. The quadratic polynomial is ; Quantifying the size of the target Mars includes: The equivalent circular diameter of Mars is calculated, i.e.: Equivalent circle diameter ,in, Represents the area of ​​the target pixel; Calculate the average diameter of Mars within the cross-section ,in, This represents the total number of image frames containing the target Mars. Temperature inversion is performed to obtain the average net radiation field intensity of the target detection cross section. ; Then temperature ;in, This represents the Stefan-Boltzmann constant; After normalizing the obtained Martian temperature, equivalent circle diameter, and probability distribution of the target probe section using weighted centroid, the data is input into a pre-trained CNN model to output the Martian risk probability. ,if If the risk exceeds the preset risk threshold, an alarm signal will be output.

9. A Mars exploration system based on an optical-thermal dual-mode hot air furnace, characterized in that, The system is used to perform the Mars exploration method based on an optical-thermal dual-mode hot air furnace as described in any one of claims 1-8.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that is executed by a processor to implement the Mars exploration method based on an optical-thermal dual-mode hot blast furnace as described in any one of claims 1-8.

Images