A dust explosion risk prediction method, system, device, and program

Abstract

The application discloses a kind of dust explosion risk prediction method, system, equipment and program, it is related to industrial safety and disaster prevention and control technical field, the method includes: obtaining the spectral data corresponding to space-time coordinates in the region to be measured;The spectral data includes wavelength and intensity;Based on element identification model and spectral data, the element contained in dust and the chemical concentration of element are obtained;Reconstruct three-dimensional concentration field, obtain the spatial concentration of each element in voxel;Based on the element contained in dust, the chemical concentration of element and three-dimensional concentration field, explosion risk dynamic coupling is carried out, and explosion probability index is obtained.The processing scheme of the present application can predict dust explosion risk in advance, suppress explosion accurately in a small range, improve safety, and reduce the cost of explosion suppression.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of industrial safety and disaster prevention and control, and particularly relates to a dust explosion risk prediction method, system, device and program. BACKGROUND

[0002] The existing explosion risk assessment method generally detects through a single-point sensor, and the monitoring range is small and the leakage source cannot be located.

[0003] Moreover, the existing dust explosion risk assessment method is only based on static parameters such as the minimum explosive concentration (MEC) and the minimum ignition energy (MIE), and cannot reflect the coupling effect of dynamic parameters such as dust concentration, particle size distribution and environmental temperature and humidity in actual production. The existing technology relies on periodic sampling detection, and cannot realize real-time updating of the risk level.

[0004] Therefore, the existing explosion risk assessment method has the above-mentioned defects, and needs to be further improved. How to create a new explosion risk assessment method has become the goal of the current industry. SUMMARY

[0005] Therefore, the present application provides a dust explosion risk prediction method, which at least partially solves the problems in the prior art.

[0006] In a first aspect, the present application provides a dust explosion risk prediction method, which comprises the following steps:

[0007] Obtaining spectral data corresponding to a space-time coordinate in a to-be-detected area; the spectral data comprises wavelength and intensity;

[0008] Obtaining elements contained in the dust and chemical concentrations of the elements based on an element identification model and the spectral data;

[0009] Reconstructing a three-dimensional concentration field to obtain a spatial concentration of each element in a voxel;

[0010] Performing dynamic coupling of explosion risk based on the elements contained in the dust, the chemical concentrations of the elements and the three-dimensional concentration field to obtain an explosion probability index.

[0011] According to a specific implementation manner of the present application, the obtaining of the elements contained in the dust and the chemical concentrations of the elements based on the element identification model and the spectral data comprises:

[0012] Preprocessing the spectral data;

[0013] Performing element identification based on a characteristic spectral segment of the preprocessed spectral data;

[0014] Respectively calculating characteristic peak areas of each element;

[0015] The chemical concentration of each element is calculated by a piecewise linear model.

[0016] According to an implementation manner of the embodiment of the present disclosure, the chemical concentration of each element is calculated by a piecewise linear model, including:

[0017] The piecewise linear model is established as follows:

[0018] ;

[0019] wherein, is the mass percentage of the element content; is the slope of the low-concentration section; is the slope of the high-concentration section; is the intercept of the low-concentration section; is the intercept of the high-concentration section; is the concentration threshold value; is the characteristic peak area of the element q.

[0020] According to an implementation manner of the embodiment of the present disclosure, the three-dimensional concentration field is reconstructed to obtain the spatial concentration of each element in the voxel, including:

[0021] The dust dispersion image is acquired;

[0022] The three-dimensional spatial coordinates of the dust particles in the dust dispersion image are calculated based on stereo matching and depth calculation;

[0023] The dust particles are aggregated into a spatially continuous density distribution based on the three-dimensional spatial coordinates of the dust particles, and a visual dust risk heat map is constructed;

[0024] The spatially continuous density distribution is discretized into monitoring units based on the dust risk heat map;

[0025] The mass concentration of the dust particles in the monitoring units is calculated respectively.

[0026] According to an implementation manner of the embodiment of the present disclosure, the spatially continuous density distribution is discretized into monitoring units based on the dust risk heat map, including:

[0027] The continuous three-dimensional space is discretized into monitoring units based on the following formula:

[0028] ;

[0029] wherein, , , is the three-dimensional index number of the voxel; , , Spatial coordinates of dust particles Minimum boundary of X-axis Minimum boundary of Y-axis Minimum boundary of Z-axis , , Dimension of voxel in three dimensions

[0030] The respective calculation of the mass concentration of dust particles in the monitoring unit comprises:

[0031] The number of dust particles in the monitoring unit is converted into mass concentration based on the following formula:

[0032] ;

[0033] Wherein, Mass concentration of dust particles in the monitoring unit Number of dust particles in the voxel Mass of single dust particle Volume of voxel × × ;

[0034] The multi-camera data is fused based on the following formula:

[0035] ;

[0036] Wherein, Current fusion concentration Number of cameras Camera index ; Local mass concentration calculated by the cth camera Allocation coefficient based on distance credibility ;

[0037] The allocation coefficient based on distance credibility is calculated based on the following method:

[0038] ;

[0039] Wherein, Allocation coefficient based on distance credibility of the cth camera Viewing angle distance factor Sum of viewing angle factors of all cameras to the current voxel

[0040] ​​According to a specific implementation of an embodiment of the present disclosure, the explosion risk dynamic coupling based on the elements contained in the dust, the chemical concentration of the elements, and the three-dimensional concentration field obtains an explosion probability index, including:

[0041] ;

[0042] wherein, is the explosion probability index; is a chemical activity factor; is a spatial enhancement factor; is an initiation condition switch;

[0043] The output range of the explosion probability index is [0, 1], and when > 0.7, a red alarm is triggered.

[0044] According to a specific implementation of an embodiment of the present disclosure, the chemical activity factor is calculated based on the following method :

[0045] ;

[0046] wherein, is the chemical activity factor; is a key element identifier; is an element weight factor; is the mass percentage of the element content; is an element safety reference content;

[0047] The spatial enhancement factor is calculated based on the following method :

[0048] ;

[0049] wherein, is a spatial distribution enhancement factor; is a risk sensitivity coefficient; is a current fusion concentration; is a minimum explosion concentration;

[0050] The initiation condition switch is calculated based on the following method :

[0051] ;

[0052] wherein, is the initiation condition switch; the current fusion concentration is judged; when the current fusion concentration is not less than the minimum explosion concentration, the initiation condition is reached; and when the current fusion concentration is less than the explosion concentration threshold, the risk is forced to be zero.

[0053] In a second aspect, the embodiments of the present disclosure provide a dust explosion risk prediction system, the system comprising:

[0054] a data acquisition module configured to acquire spectral data corresponding to a space-time coordinate in a to-be-measured region; the spectral data comprising wavelength and intensity;

[0055] a calculation module configured to obtain elements contained in dust and chemical concentrations of the elements based on an element identification model and the spectral data, and reconstruct a three-dimensional concentration field to obtain a spatial concentration of each element in a voxel;

[0056] a prediction module configured to perform explosion risk dynamic coupling based on the elements contained in the dust, the chemical concentrations of the elements, and the three-dimensional concentration field to obtain an explosion probability index.

[0057] In a third aspect, the embodiments of the present disclosure further provide an electronic device, the electronic device comprising:

[0058] at least one processor; and

[0059] a memory in communication with the at least one processor; wherein

[0060] the memory stores instructions executable by the at least one processor, and the instructions, when executed by the at least one processor, cause the at least one processor to perform the dust explosion risk prediction method in the first aspect or any implementation manner of the first aspect.

[0061] In a fourth aspect, the embodiments of the present disclosure further provide a non-transitory computer-readable storage medium storing computer instructions, the computer instructions, when executed by at least one processor, causing the at least one processor to perform the dust explosion risk prediction method in the first aspect or any implementation manner of the first aspect.

[0062] In a fifth aspect, the embodiments of the present disclosure further provide a computer program product, the computer program product comprising a computer program stored on a non-transitory computer-readable storage medium, the computer program comprising program instructions, the program instructions, when executed by a computer, causing the computer to perform the dust explosion risk prediction method in the first aspect or any implementation manner of the first aspect.

[0063] The dust explosion risk prediction method in the embodiments of the present disclosure performs explosion risk prediction based on spatial concentration and chemical concentration of dust particles, and performs different operations according to different prediction probabilities, thereby reducing the probability of explosion risk occurrence, and confirming a leakage point based on a three-dimensional concentration field, clustering a high-risk region, and accurately implementing explosion suppression operation, which not only improves safety, but also reduces explosion suppression cost. BRIEF DESCRIPTION OF DRAWINGS

[0064] Figure 1 A flow chart of a dust explosion risk prediction method provided by an embodiment of the present disclosure is shown in FIG. 1.

[0065] Figure 2 A data scatter plot provided by an embodiment of the present disclosure is shown in FIG. 2.

[0066] Figure 3 A structure diagram of a dust explosion risk prediction system provided by an embodiment of the present disclosure is shown in FIG. 3.

[0067] Figure 4 An electronic device provided by an embodiment of the present disclosure is shown in FIG. 4. DETAILED DESCRIPTION

[0068] The embodiments of the present disclosure will be described in detail below with reference to the drawings.

[0069] The above and other aspects of the present disclosure will become more apparent by describing in detail embodiments thereof with reference to the attached drawings in which:

[0070] It should be apparent to those skilled in the art that the aspects described herein can be implemented in a wide variety of forms and that the described aspects are merely exemplary. It should also be apparent that one aspect can be implemented independently of any other aspects without affecting the spirit and / or scope of the present disclosure. Accordingly, any specific reference to one aspect should not be construed as a limitation of any other aspect. The use of the terms "preferably," "preferably," "preferred," and "desirably" indicates that although the described features, methods, and / or materials can be useful and / or desired, they are not required and / or essential for the practice of the disclosure. Additionally, the use of terms such as "primarily," "secondarily," and the like can depend on the context in which they are used. Such terms are not necessarily intended to denote a particular order or importance, but for convenience and clarity, are used in connection with the more particular aspects disclosed herein. Therefore, the aspects described herein are meant to be only exemplary and that the scope of the aspects is to be determined by the following claims, which are to be given their full scope including equivalences to which they are entitled.

[0071] Further, in the following description, specific details are set forth in order to provide a thorough understanding of the examples. However, one skilled in the relevant art will recognize that the aspects can be practiced without one or more of the specific details, or with other methods, components, materials, and so forth.

[0072] The dust explosion risk prediction method in the embodiments of the present disclosure predicts the explosion risk through the spatial concentration and chemical concentration of dust particles, and performs different operations according to different prediction probabilities, thereby reducing the probability of explosion risk occurrence, and confirming the leakage point based on the three-dimensional concentration field, clustering the high-risk area, and accurately implementing the explosion suppression operation, thereby improving the safety and reducing the explosion suppression cost.

[0073] Figure 1 A schematic diagram of the dust explosion risk prediction method provided by the embodiments of the present disclosure is shown.

[0074] As shown in Figure 1 , at step S110, spectral data corresponding to a space-time coordinate in a to-be-measured region is acquired; the spectral data includes wavelength and intensity.

[0075] More specifically, the spectral data of the to-be-measured region is collected according to a preset path and a preset time interval.

[0076] For example, a robot carries a laser device to scan along a preset path, and emits a laser pulse at a three-dimensional space coordinate P(x, y, z) every 0.5 meters of movement or every 0.5 seconds of interval, and a spectrometer collects the spectral data of the point and records it as a vector , wherein, is the wavelength channel, is the spectral channel number.

[0077] More specifically, next go to step S120.

[0078] At step S120, the elements contained in the dust and the chemical concentration of the elements are obtained based on an element identification model and the spectral data.

[0079] In the embodiments of the present disclosure, the elements contained in the dust and the chemical concentration of the elements are obtained based on the element identification model and the spectral data, including: pre-processing the spectral data; performing element identification based on the characteristic spectral segments of the pre-processed spectral data; calculating the characteristic peak area of each element respectively; and calculating the chemical concentration of each element through a piecewise linear model.

[0080] In the embodiments of the present disclosure, the chemical concentration of each element is calculated through a piecewise linear model, including:

[0081] A piecewise linear model is established:

[0082] ;

[0083] , wherein, is the mass percentage of the element content; is the slope of the low concentration section; is the slope of the high concentration section; is the intercept for the low concentration segment; is the intercept for the high concentration segment; is the concentration threshold value.

[0084] More specifically, the spectral data vector is input into the element identification model, which is constructed based on the NIST spectral library, and element identification is achieved through feature peak matching and similarity calculation.

[0085] I. Preprocessing of spectral data vector.

[0086] 1. Noise reduction processing:

[0087]

[0088] wherein, is the smoothed spectrum; is the spectral channel number; is the spectral data vector; is the width of the filter window, which is set to 9 in the present application; is the channel index variable within the window.

[0089] 2. Baseline correction:

[0090]

[0091] wherein, is the intensity after baseline correction; is the smoothed spectrum; is the local sliding window index variable; is the spectral channel number; is the spectral data vector when the spectral channel number is .

[0092] II. Feature spectral region locking.

[0093] Define the characteristic wavelength range of the key elements, as shown in Table 1.

[0094] Table 1. Characteristic wavelength range of key elements

[0095]

[0096] III. Feature peak area calculation.

[0097] The feature peak area is calculated based on the following method:

[0098]

[0099] wherein, is the feature peak area of element q; is the starting channel number of the feature spectral segment; is the characteristic spectral segment termination channel number; is the baseline corrected intensity; is the spectral resolution, and the spectral resolution of the present application is 0.1 nm.

[0100] IV. Element identification

[0101] Calculate the matching degree between the pre-processed spectral data vector and the reference spectrum, and determine whether the element exists. Based on the NIST atomic spectrum database, the reference spectrum required by the present application can be obtained.

[0102] Calculate the matching degree with the reference spectral element based on the following formula :

[0103]

[0104] wherein, is the characteristic peak weight; is the summation index, which traverses the discrete variables of the specified set; is the baseline corrected spectral intensity; is the intensity of the reference spectrum.

[0105]

[0106] wherein, is the reference intensity of the wavelength in the standard spectrum library; is the sum of the theoretical intensities of all characteristic peaks of the element.

[0107] When the matching degree is not less than 0.90, it is determined that the element definitely exists; when the matching degree is between 0.80-0.89, and the matching degree of the second characteristic peak is greater than 0.75, it is determined that the element definitely exists; when the matching degree is less than 0.79, it is determined that the element does not exist.

[0108] V. Chemical concentration calibration conversion

[0109] Establish a piecewise linear model:

[0110]

[0111] wherein, is the mass percentage of the element content; is the slope of the low concentration segment; is the slope of the high concentration segment; is the intercept of the low concentration segment; is the intercept of the high concentration segment; is the concentration threshold value, i.e., the characteristic peak area value at which the spectral self-absorption effect begins to be significant.

[0112] (1) Divide the data into segments, into low concentration segment and high concentration segment.

[0113] The low concentration segment is ≤4000, such as S2 (600, 0.5) to S3 (4000, 1.0) as shown in the figure; the high concentration segment is Figure 2 ≥4000, such as S3 (4000, 1.0) to S6 (12000, 2.0) as shown in the figure. Figure 2 (2) Calculate the slope in each segment

[0114] The slope in the low concentration segment is :

[0115]

[0116]

[0117] wherein, is the change amount of the mass percentage of the element content in the low concentration segment; is the change amount of the area of the spectral characteristic peak in the low concentration segment.

[0118] The slope in the high concentration segment is :

[0119]

[0120] wherein, is the change amount of the mass percentage of the element content in the low concentration segment; is the change amount of the area of the spectral characteristic peak in the low concentration segment.

[0121] (3) Concentration turning threshold verification:

[0122] In ∈[2000,10000] range, select the slope change turning point S2-S6 (such as shown in the figure). Figure 2 Calculate the minimum residual sum of squares of each turning point

[0123] :

[0124]

[0125] wherein, is the mass percentage of the element content at the turning point; is the estimated value of the mass percentage of the element content at the turning point.

[0126]

[0127] wherein, is the slope of the concentration segment where the turning point is located; ​​​the area of the characteristic peak at the turning point; the intercept of the concentration section where the turning point is located.

[0128]

[0129] wherein, the average concentration of the concentration section where the turning point is located; the average area of the characteristic peak of the concentration section where the turning point is located.

[0130] As shown in Figure 2 , the data scatter plot is plotted with the area of the characteristic peak as the abscissa and the mass percentage of the element content as the ordinate, and the minimum residual sum of squares of the turning points S2-S6 is calculated respectively , the minimum residual sum of squares of the turning points S2-S6 is calculated respectively The minimum turning point is the concentration turning threshold.

[0131] Next, go to step S130.

[0132] At step S130, the three-dimensional concentration field is reconstructed to obtain the spatial concentration of each element in the voxel.

[0133] In the embodiment of the present application, the three-dimensional concentration field is reconstructed to obtain the spatial concentration of each element in the voxel, including: obtaining a dust dispersion image; obtaining the three-dimensional spatial coordinates of the dust particles in the dust dispersion image based on stereo matching and depth calculation; aggregating the dust particles into a spatially continuous density distribution based on the three-dimensional spatial coordinates of the dust particles, and constructing a visual dust risk heat map; discretizing the spatially continuous density distribution into monitoring units based on the dust risk heat map; and calculating the mass concentration of the dust particles in the monitoring units respectively.

[0134] In the embodiment of the present application, the spatially continuous density distribution is discretized into monitoring units based on the dust risk heat map, including:

[0135] The continuous three-dimensional space is discretized into monitoring units based on the following formula:

[0136] ;

[0137] wherein, , , is the three-dimensional index number of the voxel; , , is the spatial coordinates of the dust particles; is the minimum boundary of the X-axis; is the minimum boundary of the Y-axis; is the minimum boundary of the Z-axis; , , The dimensions of a voxel in three dimensions;

[0138] The calculation of the mass concentration of dust particles in the monitoring unit includes:

[0139] The quantity of dust particles within the monitoring unit is converted into mass concentration based on the following formula:

[0140] ;

[0141] in, To monitor the mass concentration of dust particles within the unit; The number of dust particles within a voxel; This refers to the mass of a single dust particle. voxel volume ( × × );

[0142] Multi-camera data is fused based on the following formula:

[0143] ;

[0144] in, This represents the current fusion concentration; Number of cameras; For camera indexing, ; The local mass concentration calculated for the c-th camera; For the assignment coefficients based on distance confidence, ;

[0145] The distribution coefficients for distance confidence are calculated using the following method:

[0146] ;

[0147] in, For the first The allocation coefficients for each camera based on distance reliability; The distance factor is the viewing angle. For the current voxel to all The sum of the perspective factors of the cameras.

[0148] More specifically, converting multi-camera images into a three-dimensional dust concentration distribution map includes the following steps:

[0149] 1. Arrange four industrial cameras (C1-C4) in a tetrahedral layout, with equal spacing between the cameras and facing the center of the monitoring area. Synchronously acquire images (dust dispersion images) with a period of 0.1 seconds, and align the camera coordinate system with the world coordinate system.

[0150] 2. Stereo matching and depth calculation.

[0151] In the dust explosion risk prediction system, stereo matching and depth calculation are the key to convert two-dimensional image information into three-dimensional spatial data. Through the calculation of dust image data collected by multiple cameras, the position coordinates of each dust particle in space are output.

[0152] a. Feature point extraction.

[0153] Through SIFT key point detection and dust particle morphology filtering, the feature points of the traceable dust particles are identified.

[0154] Based on the camera C1 image, the feature point set is obtained:

[0155]

[0156] wherein, is the feature point set of camera C1; is the feature point index number, ; is the total number of feature points; is the column coordinate (horizontal pixel position coordinate); is the row coordinate (vertical pixel position coordinate).

[0157] Feature point extraction can filter out non-dust particle noise (such as reflection, shadow), providing pure input for stereo matching.

[0158] b. Multi-view matching.

[0159] The positions of the same dust particle in different camera views are accurately associated.

[0160]

[0161] wherein, is the homography matrix (or 3x3 conversion matrix) from C1 to C2, which is calculated in advance by a calibration board; is the homogeneous coordinates of the feature points in C1 camera; is the predicted coordinates of the matching points in C2 camera; is the matching error vector, <0.5 pixel.

[0162] c. Depth calculation

[0163] Using the principle of triangulation, the parallax is converted into real distance.

[0164]

[0165] wherein, is the depth (vertical distance / vertical coordinate) of the dust particle to the camera plane; is the camera baseline distance; is the camera focal length; is the parallax; is the horizontal position of the dust particle at ; is the horizontal position of the dust particle at ;

[0166] 3. Spatial coordinate conversion

[0167]

[0168] wherein, , is the horizontal position of the dust particle in the spatial coordinate system; , is the horizontal and vertical coordinate of the image center pixel; is the depth of the dust particle to the camera plane; is the camera focal length; is the original column pixel coordinate of the feature point in the image; is the original row pixel coordinate of the feature point in the image.

[0169] 4. Voxel concentration calculation.

[0170] Receiving the spatial coordinates of discrete dust particles from stereo matching, aggregating the point cloud data into a spatially continuous density distribution, constructing a visual dust risk heat map, and providing a physical basis for explosion probability calculation.

[0171] The specific calculation method is as follows:

[0172] a. Spatial grid division

[0173] Discretize the continuous three-dimensional space into micro monitoring units, and establish an industrial coordinate system:

[0174]

[0175] wherein, , , is the three-dimensional index number of the voxel (i.e., the spatial grid coordinate); , , is the spatial coordinate of the dust particle; is the minimum boundary of the X-axis; is the minimum boundary of the Y-axis; is the minimum boundary of the Z-axis; , , is the size of the voxel in three dimensions, in the present application, the size of the voxel =0.1m.

[0176] b. Concentration Calculation Formula

[0177] The dust particle count is converted into an engineering-usable mass concentration based on the following formula:

[0178]

[0179] in, To monitor the mass concentration of dust particles within the unit; The number of dust particles within a voxel; This refers to the mass of a single dust particle. voxel volume ( × × ).

[0180] Multi-camera data fusion is performed based on the following formula:

[0181]

[0182] in, This represents the current fusion concentration; Number of cameras; For camera indexing, ; The local concentration calculated for the c-th camera; For the assignment coefficients based on distance confidence, .

[0183] By integrating multi-view data, we can solve the problems of blind spots, occlusion, and errors caused by single cameras, and eliminate spatial bias.

[0184] Weighting:

[0185]

[0186] in, For the first The camera's assignment coefficients are based on distance confidence; the closer the camera is to the center of the field of view, the higher its weight. ; , where is the viewing distance factor, representing the degree to which a voxel deviates from the camera's main field of view axis; For the current voxel to all The sum of the perspective factors of the cameras.

[0187] The weights are forced to zero under the following circumstances:

[0188]

[0189] in, This represents the normalized relative deviation distance between the current voxel and the camera's viewpoint center.

[0190] The dynamic background elimination is realized based on the following formula:

[0191]

[0192] wherein, is the effective dust particle number after eliminating the background; is the original identified all dust particle number; is the reference dust particle number when there is no dust; is the environmental interference factor, and the present application takes 0.2.

[0193] Next, go to step S140.

[0194] At step S140, based on the elements contained in the dust, the chemical concentration of the elements, and the three-dimensional concentration field, the explosion risk dynamic coupling is carried out to obtain an explosion probability index.

[0195] In the embodiment of the present application, the explosion risk dynamic coupling based on the elements contained in the dust, the chemical concentration of the elements, and the three-dimensional concentration field to obtain the explosion probability index comprises:

[0196] ;

[0197] wherein, is the explosion probability index; is the chemical activity factor; is the spatial enhancement factor; is the initiation condition switch;

[0198] The output range of the explosion probability index is [0, 1], and when > 0.7, a red alarm is triggered.

[0199] In the embodiment of the present application, the chemical activity factor is calculated based on the following method :

[0200] ;

[0201] wherein, is the chemical activity factor; is the key element identifier; is the element weight factor; is the mass percentage of the element content; is the element safety reference content;

[0202] The spatial enhancement factor is calculated based on the following method :

[0203] ;

[0204] Wherein, is a spatial distribution enhancement factor; is a risk sensitivity coefficient, and the application takes 0.15; is a current fusion concentration; is a minimum explosion concentration;

[0205] The initiation condition switch is calculated based on the following method :

[0206] ;

[0207] Wherein, is an initiation condition switch; the current fusion concentration is judged; when the current fusion concentration is not less than the minimum explosion concentration, the initiation condition is reached; and when the current fusion concentration is less than the explosion concentration threshold, the risk is forced to be zero.

[0208] More specifically, by fusing the chemical activity and spatial distribution characteristics of dust, the explosion probability of each position in a three-dimensional space is calculated in real time.

[0209] The explosion probability index is calculated based on the following method:

[0210] 1. Chemical activity factor calculation

[0211]

[0212] Wherein, is a chemical activity factor; is a key element identifier; is an element weight factor; is the mass percentage of element content; is an element safety reference content.

[0213] 2. Spatial distribution enhancement factor

[0214]

[0215] Wherein, is a spatial distribution enhancement factor; is a risk sensitivity coefficient, and the application takes 0.15; is a current fusion concentration; is a minimum explosion concentration.

[0216] 3. Explosion basic condition judgment

[0217]

[0218] Wherein, is the ignition condition switch; is the current fusion concentration; is the ignition condition when the current fusion concentration is not less than the minimum explosion concentration; is the forced zero risk when the current fusion concentration is less than the explosion concentration threshold.

[0219] 4. Probability synthesis and amplitude limiting

[0220]

[0221] wherein, is the explosion probability index; is the chemical activity factor, indicating the flammability of the dust; is the space enhancement factor; is the ignition condition switch, indicating whether the concentration reaches the ignition threshold.

[0222] The output range of the explosion probability index is [0, 1], when > 0.7 triggers a red alarm.

[0223] In the embodiment of the present application, the method further comprises a dynamic correction mechanism, which automatically increases the space enhancement factor when the concentration gradient is enhanced and the concentration rises rapidly:

[0224]

[0225] wherein, is the corrected space enhancement factor; is the space enhancement factor; is the concentration change amount; is the time interval; is the concentration change rate (g / m 3 / s); is the sudden increase response coefficient;

[0226] When is greater than , the space enhancement factor correction is triggered.

[0227] Table 2: Dust type self-adaptation

[0228]

[0229] In the embodiment of the present application, the method further comprises: hierarchical response control according to the explosion probability index, specifically including the following methods:

[0230] When the explosion probability index , the monitoring interface is displayed in green, and continuous monitoring is performed;

[0231] When the explosion probability index , the monitoring interface is displayed in yellow, and enhanced ventilation operation is performed;

[0232] When the explosion probability index is greater than 0, the monitoring interface displays red, and positioning and explosion suppression operations are performed. When the explosion probability index is greater than 0, the monitoring interface displays red, and the grid is locked Nitrogen is sprayed, the nitrogen spraying rate is greater than or equal to 20 L / s, and the concentration is reduced to a safe value within 8 seconds.

[0233] In the embodiment of the present application, the method further comprises constructing a spatiotemporal risk field, specifically comprising the following methods:

[0234] The independent explosion probability index of each voxel is calculated respectively, and a three-dimensional risk cloud chart is generated;

[0235] The adjacent voxels of are connected, the risk region volume is calculated, and a high-risk region cluster is performed:

[0236]

[0237] Wherein, is the risk region volume; is the number of high-risk voxels; is the volume of a single voxel.

[0238] When the explosion probability index is greater than 0, the regional explosion suppression is started.

[0239] Figure 3 The dust explosion risk prediction system 300 provided by the present application is shown, which comprises a data acquisition module 310, a calculation module 320 and a prediction module 330.

[0240] The data acquisition module 310 is used for acquiring spectral data corresponding to a space-time coordinate in a to-be-measured region; the spectral data comprises wavelength and intensity;

[0241] The calculation module 320 is used for obtaining elements contained in dust and chemical concentrations of the elements based on an element identification model and the spectral data; and reconstructing a three-dimensional concentration field to obtain a spatial concentration of each element in a voxel;

[0242] The prediction module 330 is used for performing explosion risk dynamic coupling based on the elements contained in the dust, the chemical concentrations of the elements and the three-dimensional concentration field to obtain an explosion probability index.

[0243] Referring to Figure 4 , the present disclosure further provides an electronic device 40, which comprises:

[0244] at least one processor; and

[0245] a memory in communication connection with the at least one processor; wherein

[0246] The memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform the dust explosion risk prediction method in the foregoing method embodiments.

[0247] The embodiments of the present disclosure also provide a non-transitory computer readable storage medium storing computer instructions for causing a computer to perform the dust explosion risk prediction method in the foregoing method embodiments.

[0248] The embodiments of the present disclosure also provide a computer program product including a computer program stored on a non-transitory computer readable storage medium, the computer program including program instructions that, when executed by a computer, cause the computer to perform the dust explosion risk prediction method in the foregoing method embodiments.

[0249] Reference will be made to the following description Figure 4 , which shows a structural diagram of an electronic device 40 suitable for use to implement the embodiments of the present disclosure. The electronic device in the embodiments of the present disclosure can include, but is not limited to, a mobile terminal such as a mobile phone, a notebook computer, a digital broadcast receiver, a PDA (Personal Digital Assistant), a PAD (Tablet Personal Computer), a PMP (Portable Multimedia Player), a vehicle terminal (e.g., a car navigation terminal), and the like, and a fixed terminal such as a digital TV, a desktop computer, and the like. Figure 4 The electronic device shown is merely an example and should not bring any limitation to the functions and use range of the embodiments of the present disclosure.

[0250] As shown in Figure 4 , the electronic device 40 can include a processing device (e.g., a central processor, a graphics processor, etc.) 401, which can perform various appropriate actions and processes according to programs stored in a read-only memory (ROM) 402 or loaded into a random access memory (RAM) 403 from a storage device 408. In the RAM 403, various programs and data required for the operation of the electronic device 40 are also stored. The processing device 401, the ROM 402, and the RAM 403 are connected to each other through a bus 404. An input / output (I / O) interface 405 is also connected to the bus 404.

[0251] In general, the following devices can be connected to the I / O interface 405: input devices 406 including, for example, a touch screen, a touch pad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; output devices 407 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; storage devices 408 including, for example, a magnetic tape, a hard disk, etc.; and communication devices 409. The communication devices 409 can allow the electronic device 40 to communicate wirelessly or wired with other devices to exchange data. While the electronic device 40 is shown with various devices, it is understood that all of the shown devices are not required to be implemented or present. More or less devices can alternatively be implemented or present.

[0252] In particular, according to embodiments of the present disclosure, the processes described above with reference to the flowcharts can be implemented as a computer software program. For example, embodiments of the present disclosure include a computer program product comprising a computer program carried on a computer readable medium, the computer program containing program code for executing the methods illustrated by the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network through the communication devices 409, or installed from the storage devices 408, or installed from the ROM 402. When the computer program is executed by the processing devices 401, the above-mentioned functions defined in the methods of the embodiments of the present disclosure are performed.

[0253] It should be noted that the computer-readable medium in the present disclosure can be a computer-readable signal medium or a computer-readable storage medium or any combination of the two. The computer-readable storage medium may, for example, but is not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or apparatus, or any combination of the above. More specific examples of the computer-readable storage medium can include, but are not limited to, an electrical connection having one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present disclosure, the computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, device or apparatus. In the present disclosure, the computer-readable signal medium can include a data signal carried in a baseband or as a part of a carrier wave, which carries computer-readable program code. Such a propagated data signal can take many forms, including but not limited to an electromagnetic signal, an optical signal, or any suitable combination of the above. The computer-readable signal medium can also be any computer-readable medium other than the computer-readable storage medium, which can send, propagate or transmit a program for use by or in conjunction with an instruction execution system, device or apparatus. The program code contained in the computer-readable medium can be transmitted by any suitable medium, including but not limited to a wire, a cable, a RF (radio frequency) or the like, or any suitable combination of the above.

[0254] The computer-readable medium described above can be contained in the electronic device described above; or can exist separately and not be assembled into the electronic device.

[0255] The computer-readable medium described above carries one or more programs, when the one or more programs are executed by the electronic device, the electronic device is caused to: obtain at least two Internet protocol addresses; send a node evaluation request including the at least two Internet protocol addresses to a node evaluation device, wherein the node evaluation device selects an Internet protocol address from the at least two Internet protocol addresses and returns; receive the Internet protocol address returned by the node evaluation device; wherein the obtained Internet protocol address indicates an edge node in a content distribution network.

[0256] Alternatively, the computer readable medium described above carries one or more programs, when the one or more programs are executed by the electronic device, the electronic device is caused to: receive a node evaluation request comprising at least two internet protocol addresses; select an internet protocol address from the at least two internet protocol addresses; and return the selected internet protocol address; wherein the received internet protocol address indicates an edge node in a content distribution network.

[0257] Computer program code for carrying out operations of the present disclosure can be written in any one or more of a variety of programming languages or combinations of languages including an object oriented programming language such as Java, Smalltalk, C++ or the like and conventional procedural programming languages such as the "C" programming language or similar programming languages. The program code may

[0258] The flow diagrams and the block diagrams in the drawings are illustrations of architectures, functionalities, and operations of possible implementations of systems, methods, and computer program products according to various embodiments of present disclosure. In this regard, each block in the flow diagrams and the block diagrams can represent a module, a procedure, or a part of code, which comprises one or more executable instructions for performing the specified functions. It should also be noted that, in some alternative implementations, the functions noted in the blocks can occur out of the order noted in the figures. For example, two blocks shown in succession may, in some cases, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and / or flow diagrams, and combinations of blocks in the block diagrams and / or flow diagrams, can be implemented by special purpose hardware-based systems that perform the specified functions or operations, or combinations of special purpose hardware and computer instructions.

[0259] The units described in the embodiments of the present disclosure can be implemented by means of software, or by means of hardware. In some cases, the name of the unit does not constitute a limitation on the unit itself, for example, the first obtaining unit can also be described as a unit for obtaining at least two internet protocol addresses.

[0260] It should be understood that various parts of the present disclosure can be implemented in hardware, software, firmware, or a combination thereof.

[0261] The above description is merely that of a specific implementation of the present disclosure, but the protection scope of the present disclosure is not limited thereto. Any person skilled in the art can easily think of changes or replacements within the technical range disclosed by the present disclosure, and such changes or replacements should be covered within the protection scope of the present disclosure.

Claims

1. A method of dust explosion risk prediction, characterized in that, The method comprises the following steps: Obtaining spectral data corresponding to space-time coordinates in a to-be-measured region; the spectral data comprises wavelength and intensity; Obtaining elements contained in dust and chemical concentrations of the elements based on an element identification model and the spectral data; Reconstructing a three-dimensional concentration field to obtain spatial concentrations of each element in a voxel; Performing dynamic coupling of explosion risk based on the elements contained in the dust, the chemical concentrations of the elements and the three-dimensional concentration field to obtain an explosion probability index; The reconstruction of the three-dimensional concentration field to obtain the spatial concentrations of each element in the voxel comprises: Obtaining a dust dispersion image; Obtaining three-dimensional spatial coordinates of dust particles in the dust dispersion image based on stereo matching and depth calculation; Aggregating the dust particles into a spatially continuous density distribution based on the three-dimensional spatial coordinates of the dust particles to construct a visual dust risk thermodynamic map; Discretizing the spatially continuous density distribution into monitoring units based on the dust risk thermodynamic map; Respectively calculating mass concentrations of the dust particles in the monitoring units.

2. The dust explosion risk prediction method according to claim 1, characterized in that, The obtaining of the elements contained in the dust and the chemical concentrations of the elements based on the element identification model and the spectral data comprises: Pretreating the spectral data; Performing element identification based on characteristic spectral bands of the pretreated spectral data; Respectively calculating characteristic peak areas of each element; Calculating chemical concentrations of each element by a piecewise linear model.

3. The dust explosion risk prediction method according to claim 2, characterized in that, The calculation of the chemical concentrations of each element by the piecewise linear model comprises: Establishing a piecewise linear model: wherein C q is the mass percentage of the element content; s1 is the slope of the low concentration section; s2 is the slope of the high concentration section; o1 is the intercept of the low concentration section; o2 is the intercept of the high concentration section; T q is the concentration threshold value; A q is the characteristic peak area of the element q.

4. The dust explosion risk prediction method according to claim 1, characterized in that, The discretization of the spatially continuous density distribution into the monitoring units based on the dust risk thermodynamic map comprises: Discretizing the continuous three-dimensional space into the monitoring units based on the following formula: wherein i, j, k are three-dimensional index numbers of voxels; x, y, z are spatial coordinates of the dust particle; x min is the minimum boundary of X-axis; y min is the minimum boundary of Y-axis; z min is the minimum boundary of Z-axis; Δx, Δy, Δz are the sizes of voxels in three dimensions; The respective calculation of the mass concentrations of the dust particles in the monitoring units comprises: Converting the number of the dust particles in the monitoring units into the mass concentration based on the following formula: wherein p(i,j,k) is the mass concentration of dust particles within the monitoring unit; N(i,j,k) is the number of dust particles within the voxel; m p is the mass of a single dust particle; V v is the volume of the voxel; Fusing multi-camera data based on the following formula: wherein p final is the current fused concentration; n is the number of cameras; c is the camera index, c e [1, n]; p c is the local quality concentration calculated by the cth camera; w c is the assignment factor based on distance credibility, w c e (0, 1); Calculating an allocation coefficient of distance reliability based on the following method: where w c is the assignment coefficient based on the distance reliability for the cth camera; d c is the viewing angle distance factor; is the sum of the viewing angle factors for all n cameras.

5. The dust explosion risk prediction method according to claim 4, characterized in that, The dynamic coupling of the explosion risk based on the elements contained in the dust, the chemical concentrations of the elements and the three-dimensional concentration field to obtain the explosion probability index comprises: P ex = min(a * b * g, 1.0); where P = the probability of explosion; α = the chemical reactivity factor; β = the spatial enhancement factor; γ = the initiation condition switch; and ex where P = the probability of explosion; α = the chemical reactivity factor; β = the spatial enhancement factor; γ = the initiation condition switch; and The output of the explosion probability index ranges [0, 1], when P ex > 0.7 triggers a red alert; Calculating a chemical activity factor a based on the following method: wherein a is a chemical activity factor; q is a key element identifier; w q is an element weight factor; C q is the mass percentage of element content; C q,ref is an element safety benchmark content; Calculating a spatial enhancement factor β based on the following method: where β is a spatial distribution enhancement factor; K1 is a risk sensitivity coefficient; p final is the current fusion concentration; p min is the minimum explosive concentration; Calculating an initiation condition switch γ based on the following method: Wherein, γ is the initiation condition switch; judging a current fused concentration; when the current fused concentration is not less than a minimum explosion concentration, the initiation condition is reached; when the current fused concentration is less than an explosion concentration threshold, forcibly setting the risk to zero.

6. A dust explosion risk prediction system, characterized in that The system comprises: A data acquisition module configured to obtain spectral data corresponding to space-time coordinates in a to-be-measured region; the spectral data comprises wavelength and intensity; The computing module is configured to obtain elements contained in the dust and chemical concentrations of the elements based on the element identification model and the spectral data, and reconstruct a three-dimensional concentration field to obtain spatial concentrations of each element in the voxels; the reconstructing a three-dimensional concentration field to obtain spatial concentrations of each element in the voxels comprises: obtaining a dust dispersion image; obtaining three-dimensional spatial coordinates of the dust particles in the dust dispersion image based on stereo matching and depth calculation; aggregating the dust particles into a spatially continuous density distribution based on the three-dimensional spatial coordinates of the dust particles, and constructing a visual dust risk heat map; discretizing the spatially continuous density distribution into monitoring units based on the dust risk heat map; and calculating mass concentrations of the dust particles in the monitoring units respectively. The prediction module is configured to perform dynamic coupling of an explosion risk based on the elements contained in the dust, the chemical concentrations of the elements, and the three-dimensional concentration field, to obtain an explosion probability index.

7. An electronic device, comprising: The electronic device includes: at least one processor; and a memory connected to the at least one processor in communication; wherein the memory stores instructions executable by the at least one processor, and when the instructions are executed by the at least one processor, the at least one processor performs the dust explosion risk prediction method according to any one of claims 1 to 5.

8. A computer program product, characterised in that, The computer program product includes a computer program stored on a non-transitory computer readable storage medium, and the computer program includes program instructions that, when executed by a computer, cause the computer to perform the dust explosion risk prediction method according to any one of claims 1 to 5.

Images