A method and device for grouping structural surface occurrence based on sparrow algorithm

Abstract

The invention provides a method and device for grouping the occurrence of structural surfaces based on a sparrow algorithm, and relates to the technical field of rock mass structural surface grouping. The method and device include converting a plurality of structural surface samples into normal vector samples of a plurality of spatial units in sequence; initializing a sparrow population based on the current number of clusters, updating the spatial position of the initial sparrow population, calculating the fitness value of the updated sparrow population, and obtaining the optimal sparrow population corresponding to the minimum fitness value; clustering the normal vector samples using the optimal sparrow population, and calculating the validity index of all clustered structural surface samples; and taking the number of clusters corresponding to the maximum value of the validity index and the clustering result as the final grouping. The invention is used to solve the technical problem that the existing occurrence grouping method is highly subjective and cannot accurately and quantitatively give objective grouping results.

Description

Technical Field

[0001] The invention relates to the technical field of rock mass structural surface grouping, and in particular to a structural surface occurrence grouping method and device based on a sparrow algorithm. Background Art

[0002] Rock mass is a complex block composed of structural planes and rocks. As a non-homogeneous material, it often breaks along the structural plane when it is destroyed. Therefore, the structural plane determines the strength and stability of the rock mass. However, due to the complexity of the field environment, many characteristic parameters of the structural plane are difficult to obtain. When the structural planes are grouped by mathematical means, the increase in grouping parameters greatly increases the dimension of calculation. The differences between the data make it difficult to measure their similarities. Therefore, the most commonly used method is still to group according to the occurrence data (i.e., dip and inclination) of the structural plane. Traditional occurrence grouping methods are mostly artificial and intuitively judged by rose diagrams and pole diagrams. They are highly subjective and cannot accurately and quantitatively give objective grouping results. Summary of the invention

[0003] The purpose of the present invention is to provide a method and device for grouping structural plane occurrences based on the sparrow algorithm to improve the above problems. In order to achieve the above purpose, the technical solution adopted by the present invention is as follows:

[0004] In a first aspect, the present application provides a method for grouping structural plane occurrences based on the sparrow algorithm, comprising:

[0005] Acquire a number of structural surface samples of the rock, and convert the several structural surface samples into normal vector samples of a number of space units in sequence;

[0006] Obtaining a cluster number range, selecting a current cluster number from the cluster number range, initializing a sparrow population based on the current cluster number, and obtaining a plurality of groups of initial sparrow populations randomly distributed in a multidimensional space;

[0007] Update the spatial position of the initial sparrow population, calculate the fitness values ​​of the normal vector samples of all structural surfaces and the updated sparrow population, and obtain the optimal sparrow population corresponding to the minimum fitness value;

[0008] The optimal sparrow population is used to cluster the normal vector samples of all structural surfaces, and the silhouette coefficients of all structural surface samples after clustering are calculated to obtain the clustering effectiveness index.

[0009] Update the number of clusters, and repeatedly calculate the effectiveness index of the optimal sparrow population and clusters corresponding to the updated number of clusters;

[0010] The number of clusters and clustering results corresponding to the maximum value of the effectiveness index are taken as the final grouping.

[0011] In a second aspect, the present application further provides a structural surface occurrence grouping device based on the sparrow algorithm, characterized in that it includes:

[0012] Acquisition module: acquires several structural surface samples of the rock, and converts the several structural surface samples into normal vector samples of several space units in sequence;

[0013] Initialization module: obtaining a cluster number range, selecting a current cluster number from the cluster number range, initializing a sparrow population based on the current cluster number, and obtaining a number of groups of initial sparrow populations randomly distributed in a multidimensional space;

[0014] Calculation module: Update the spatial position of the initial sparrow population, calculate the normal vector samples of all structural surfaces and the fitness values ​​of the updated sparrow population, and obtain the optimal sparrow population corresponding to the minimum fitness value;

[0015] Clustering module: cluster the normal vector samples of all structural surfaces using the optimal sparrow population, and calculate the silhouette coefficient of all structural surface samples after clustering to obtain the clustering effectiveness index;

[0016] Update module: Update the number of clusters, and repeatedly calculate the effectiveness index of the optimal sparrow population and clusters corresponding to the updated number of clusters;

[0017] Selection module: The number of clusters and clustering results corresponding to the maximum value of the effectiveness index are taken as the final grouping.

[0018] In a third aspect, the present application further provides a structural surface occurrence grouping device based on the sparrow algorithm, comprising:

[0019] Memory for storing computer programs;

[0020] A processor is used to implement the steps of the structural surface occurrence grouping method based on the sparrow algorithm when executing the computer program.

[0021] In a fourth aspect, the present application further provides a readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps of the above-mentioned method for grouping structural surface occurrences based on the sparrow algorithm are implemented.

[0022] The beneficial effects of the present invention are:

[0023] The present invention adopts a step correction factor to improve and optimize the sparrow clustering algorithm, thereby overcoming the defect that the sparrow algorithm is sensitive to initial values, thus affecting the clustering results. The algorithm is simple and easy to implement, and can ultimately search for the global optimal structural surface grouping result. In addition, the silhouette coefficient is used as an effectiveness indicator, which can realize automatic classification of the number of clustering groups and obtain the optimal number of classification groups, thereby reducing labor costs and greatly improving the accuracy and efficiency of classification.

[0024] Other features and advantages of the present invention will be described in the following description, and partly become apparent from the description, or be understood by implementing the embodiments of the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures particularly pointed out in the written description, claims, and drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments are briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without creative work.

[0026] Figure 1 It is a schematic diagram of the flow chart of the structural surface occurrence grouping method based on the sparrow algorithm described in an embodiment of the present invention;

[0027] Figure 2 It is a spatial schematic diagram of the rock mass structural surface in an embodiment of the present invention;

[0028] Figure 3 A schematic diagram of generating an initial sparrow population in an embodiment of the present invention;

[0029] Figure 4 This is a clustering effect diagram of the structural surface poles in an embodiment of the present invention;

[0030] Figure 5 It is a schematic diagram of the structure of a device for grouping structural surface occurrence based on the sparrow algorithm described in an embodiment of the present invention;

[0031] Figure 6 It is a schematic diagram of the structure of the structural surface occurrence grouping device based on the sparrow algorithm described in an embodiment of the present invention.

[0032] Markings in the figure:

[0033] 800. Structural surface occurrence grouping device based on sparrow algorithm; 801. Processor; 802. Memory; 803. Multimedia component; 804. I / O interface; 805. Communication component. DETAILED DESCRIPTION

[0034] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all of the embodiments. The components of the embodiments of the present invention generally described and shown in the drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present invention provided in the drawings is not intended to limit the scope of the claimed invention, but merely represents selected embodiments of the present invention. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0035] It should be noted that similar reference numerals and letters represent similar items in the following drawings, so once an item is defined in one drawing, it does not need to be further defined and explained in the subsequent drawings. At the same time, in the description of the present invention, the terms "first", "second", etc. are only used to distinguish the description and cannot be understood as indicating or implying relative importance.

[0036] Embodiment 1:

[0037] This embodiment provides a method for grouping structural plane occurrences based on the sparrow algorithm.

[0038] See also Figure 1 , the figure shows that the method includes:

[0039] S1. Obtain N structural surface samples of the rock, and convert the N structural surface samples into several normal vector samples in sequence. Figure 2 ;

[0040] Specifically, the rock structure surface to be measured is collected by using a drone or a high-definition camera to obtain the inclination α (0°-360°) and the dip angle θ (0°-90°) of each structure surface;

[0041] According to the inclination angle α and the inclination angle θ of the structural surface, the normal vector sample s=(x, y, z) of the structural surface space unit is obtained by using the conversion formula, and the conversion formula is:

[0042]

[0043] Wherein, x represents the component of the structural surface in the x-axis direction in the rectangular coordinate system; y represents the component of the structural surface in the y-axis direction in the rectangular coordinate system; z represents the component of the structural surface in the z-axis direction in the rectangular coordinate system.

[0044] Based on the above embodiments, the method further includes:

[0045] S2. Obtaining a cluster number range, selecting a current cluster number from the cluster number range, initializing a sparrow population based on the current cluster number, and obtaining several groups of initial sparrow populations randomly distributed in a multidimensional space;

[0046] The range of the number of clusters is set according to actual conditions. In this embodiment, the range of the number of clusters is set to [2,8], and [2,8] is traversed in sequence to select the optimal number of clusters from [2,8], and the current number of clusters selected is set to k;

[0047] Specifically, step S2 includes:

[0048] S21. Generate several groups of initial sparrow populations using the SPM chaotic mapping algorithm. Figure 3 , the initial sparrow population includes discoverers, followers and early warnings, and each group of sparrow populations contains the same number of sparrows as the number of clusters;

[0049] Specifically, the parameters of the sparrow population are initialized, including: the number of sparrow population n, the number of iterations M, the number of discoverers, followers and alarms, the alarm value R2, and the safety value ST. In this embodiment, the number of sparrow population n=200;

[0050] The discoverers, followers and warning persons are randomly distributed in each sparrow population;

[0051] Use the chaotic mapping algorithm to generate several groups of initial sparrow populations:

[0052] x ij =l+(ul)rand[x(t+1)]; (2)

[0053]

[0054] Where: x ij is the position of the i-th sparrow in the j-th dimension; rand is a random number in the range [0,1]; u is the upper boundary of the problem to be solved, and l is the lower boundary of the problem to be solved; x(t) is the random number generated for the t-th iteration, x(t+1) is the random number generated for the t+1-th iteration, η and μ are parameters with a value range of [0,1], and r is a random number between 0 and 1.

[0055] S22. Evenly distribute several groups of initial sparrow populations in the multidimensional space to generate the initial positions of the discoverer, the followers, and the early warning:

[0056]

[0057] In the formula, x(n) represents the nth sparrow population, x nm Represents the position of the nth sparrow in the m-dimensional space.

[0058] In this embodiment, since the current number of clusters is k, each sparrow population includes k sparrows, that is, each sparrow is regarded as a classification cluster C. b , where b = 1, 2,…, k.

[0059] Based on the above embodiments, the method further includes:

[0060] S3. Constructing a fitness function, using the spatial position of the updated initial sparrow population, calculating the fitness values ​​of the normal vector samples of all structural surfaces and the updated sparrow population, and obtaining the optimal sparrow population corresponding to the minimum fitness value;

[0061] Specifically, step S3 includes:

[0062] S31. Update the spatial positions of the discoverer, the follower and the warning device in turn to obtain several groups of updated sparrow populations;

[0063] Specifically, the spatial position of the discoverer is updated to obtain several updated groups of sparrow populations, including:

[0064] S311. Calculate the first fitness value between the normal vector sample of the structural surface and each group of initial sparrow populations using the fitness function;

[0065] The fitness function is:

[0066]

[0067] In the formula, c b is the b-th classification cluster C b The cluster center, s a is the classification cluster C b The b-th normal vector sample in , d(s a ,c b ) is s a to c b distance;

[0068] Preferably, in order to ensure that the structural surfaces with a 180° difference in inclination are the same group of structural surfaces, the square of the cosine distance is used for similarity measurement in this embodiment:

[0069]

[0070] In the formula, The transpose of the representation;

[0071] The fitness function is used to sequentially calculate the first fitness value between all structural surfaces and each initial population.

[0072] S312. Calculate the first candidate position based on the initial position of the discoverer, and calculate the second fitness value of the sparrow population when located at the first candidate position;

[0073] Specifically, the calculation method of the first candidate position is as follows:

[0074]

[0075] In the formula, x′ i,j represents the first candidate position, x i,j represents the initial position, Q is a random number obeying the normal distribution, L is a unit vector, R2 represents the warning value of the sparrow population position, and ST represents the safety threshold of the sparrow population position. Among them, when R2 < ST, it means that the warning value is less than the safety value. At this time, there is no predator in the foraging environment, and the discoverer can perform extensive search operations; when R2 ≥ ST, it means that some sparrows in the population have discovered the predator and issued a warning to other sparrows in the population, and all sparrows need to fly to the safe area for foraging.

[0076] w is a calculation parameter, and its calculation formula is:

[0077]

[0078] In the formula, itermax is the maximum number of iterations, T represents the current number of iterations, and exp() represents the exponential function.

[0079] Use the fitness function to calculate the second fitness value between the normal vector sample of the structural plane and each group of sparrow populations when located at the first candidate position;

[0080] S313. If the second fitness value is less than the first fitness value, move the discoverer to the first candidate position;

[0081] Otherwise, the discoverer remains at the initial position.

[0082] Specifically, update the spatial positions of the followers to obtain several updated groups of sparrow populations, including:

[0083] S314. Calculate the second candidate position based on the initial position of the follower, and calculate the third fitness value of the sparrow population when located at the second candidate position;

[0084] Specifically, the calculation method of the second candidate position is as follows:

[0085]

[0086] In the formula, x″ i,j represents the second candidate position, represents the optimal position currently discovered by the discoverer, X worstrepresents the current global worst position, A represents a matrix whose elements are randomly assigned to 1 or -1, and the pseudo-inverse A of A + =A T (AA T ) -1 ,When i>n / 2, it means that the i-th joiner has not obtained food and is in a hungry state. At this time, it needs to fly to other places to forage for more energy.

[0087] S315. If the third fitness value is less than the first fitness value, move the follower to the second candidate position;

[0088] Otherwise, the follower remains at the initial position.

[0089] Specifically, the spatial position of the alarm is updated to obtain several updated groups of sparrow populations, including:

[0090] S316. Calculate a third candidate position according to the initial position of the follower, and calculate a fourth fitness value of the sparrow population when located at the second candidate position;

[0091] Specifically, the calculation method of the third candidate position is:

[0092]

[0093] In the formula, x″′ i,j represents the third candidate position, represents the current global optimal position, represents the global optimal position of the T+1th iteration, β represents the step size factor, which is a random number that obeys the standard normal distribution, KK is the step size factor, which is a random number in [0,1], and f i represents the fitness value of the current sparrow individual, f g represents the global optimal fitness value, f w Represents the global worst fitness. When f i >f g When f i =f g When , it means that the sparrows in the middle of the population are also in danger and need to get closer to other sparrows to reduce the risk of being preyed upon;

[0094] Preferably, in order to improve the convergence speed and accuracy of SSA, the step size factors β and KK are modified using the following formula:

[0095]

[0096] Where M is the total number of iterations;

[0097] In this embodiment, the sparrow algorithm is improved by introducing SPM chaotic mapping and dynamic step size factor, so as to improve the global search and local optimum jumping capabilities of the sparrow algorithm, enhance its optimization performance, and improve the running speed.

[0098] S317. If the fourth fitness value is less than the first fitness value, move the follower to a third candidate position;

[0099] Otherwise, the follower remains at the initial position.

[0100] S32. Calculate the fitness value between the normal vector sample of the structural surface and each group of sparrow populations after the update using the fitness function;

[0101] When the discoverer, follower and warning device complete a position update, the fitness value between the normal vector sample and the sparrow population is calculated;

[0102] S33. Repeatedly update the spatial positions of the discoverer, follower and warning device. When the number of position updates reaches the maximum number of iterations M, obtain the sparrow population with the smallest fitness value as the optimal sparrow population.

[0103] Based on the above embodiments, the method further includes:

[0104] S4. clustering the normal vector samples of all structural surfaces using the optimal sparrow population, and calculating the silhouette coefficients of all structural surface samples after clustering to obtain the clustering effectiveness index;

[0105] Specifically, step S4 includes:

[0106] S41. Taking each sparrow in the optimal sparrow population as a cluster center, clustering the normal vector samples of the structural surface using formula (6) to obtain k classification clusters;

[0107] S42. Obtain all structural surface samples in each classification cluster, and calculate the first average distance a(i) between each structural surface sample and the structural surface samples in the same cluster in turn:

[0108] S43. Calculate the second average distance between each structural surface sample and the structural surface samples of the adjacent cluster, where the adjacent cluster is the classification cluster b(i) closest to the classification cluster to which the currently calculated structural surface sample belongs;

[0109] S44. Calculate the silhouette coefficient s(n) of the current structural surface according to the first average distance and the second average distance:

[0110]

[0111] S45. Perform weighted summation of the silhouette coefficients of all structural surfaces to obtain the clustering effectiveness index:

[0112]

[0113] In the formula, the value range of SC is [-1,1]. The larger the value, the closer the samples in the same cluster are, the farther the samples in different clusters are, and the better the clustering effect.

[0114] Based on the above embodiments, the method further includes:

[0115] S5. Update the number of clusters k * , repeatedly calculate the effectiveness index of the optimal sparrow population and clusters corresponding to the updated number of clusters;

[0116] Based on the above embodiments, the method further includes:

[0117] S6. The number of clusters and the clustering result corresponding to the maximum value of the effectiveness index are used as the final grouping;

[0118] In this embodiment, the effectiveness indexes corresponding to the number of clusters 2 to 6 are calculated in turn, and the optimal number of clusters corresponding to the maximum value of the effectiveness index is selected as the global optimal number, and the clustering effect diagram of the extreme points of the structural surface is drawn according to the optimal number, such as Figure 4 As shown in the figure, set1, set2, set3 and set4 represent different structural poles.

[0119] Embodiment 2:

[0120] like Figure 5 As shown, this embodiment provides a structural surface occurrence grouping device based on the sparrow algorithm, and the device includes:

[0121] Acquisition module: acquires several structural surface samples of the rock, and converts the several structural surface samples into normal vector samples of several space units in sequence;

[0122] Initialization module: obtaining a cluster number range, selecting a current cluster number from the cluster number range, initializing a sparrow population based on the current cluster number, and obtaining a number of groups of initial sparrow populations randomly distributed in a multidimensional space;

[0123] Calculation module: Update the spatial position of the initial sparrow population, calculate the normal vector samples of all structural surfaces and the fitness values ​​of the updated sparrow population, and obtain the optimal sparrow population corresponding to the minimum fitness value;

[0124] Clustering module: cluster the normal vector samples of all structural surfaces using the optimal sparrow population, and calculate the silhouette coefficient of all structural surface samples after clustering to obtain the clustering effectiveness index;

[0125] Update module: Update the number of clusters, and repeatedly calculate the optimal sparrow population and cluster effectiveness index corresponding to the updated number of clusters;

[0126] Selection module: The number of clusters and clustering results corresponding to the maximum value of the effectiveness index are taken as the final grouping.

[0127] Based on the above embodiment, the initialization module includes:

[0128] Initialization unit: using a chaotic mapping algorithm to generate several groups of initial sparrow populations, the initial sparrow populations include discoverers, followers and early warning, and each group of sparrow populations contains the same number of sparrows as the number of clusters;

[0129] Distribution unit: evenly distribute several groups of initial sparrow populations in the multidimensional space to generate the initial positions of the discoverers, followers and warners.

[0130] Based on the above embodiment, the update module includes:

[0131] Function construction unit: construct a fitness function, and use the fitness function to update the spatial positions of the discoverer, the follower and the alarm in sequence to obtain a number of updated groups of sparrow populations;

[0132] A first calculation unit: using the fitness function to calculate the fitness value between the normal vector sample of the structure surface and each group of sparrow populations after update;

[0133] The first updating unit: repeatedly updating the spatial positions of the discoverer, follower and warning device. When the number of position updates reaches the maximum number of iterations, the sparrow population with the smallest fitness value is obtained as the optimal sparrow population.

[0134] Based on the above embodiment, the first updating unit includes:

[0135] A second calculation unit: using the fitness function to calculate a first fitness value between the normal vector sample of the structural surface and each group of initial sparrow populations;

[0136] The third calculation unit is used to calculate the first candidate position according to the initial position of the discoverer, and calculate the second fitness value of the sparrow population when it is located at the first candidate position;

[0137] A first judgment unit: if the second fitness value is less than the first fitness value, moving the finder to the first candidate position;

[0138] Otherwise, the finder remains in the initial position.

[0139] Based on the above embodiment, the first updating unit includes:

[0140] The fourth calculation unit calculates a second candidate position according to the initial position of the follower, and calculates a third fitness value of the sparrow population when the sparrow population is located at the second candidate position;

[0141] The second judgment unit: if the third fitness value is less than the first fitness value, moving the follower to a second candidate position;

[0142] Otherwise, the follower remains at the initial position.

[0143] Based on the above embodiment, the clustering module includes:

[0144] Clustering unit: cluster the normal vector samples of the structural surface using each sparrow in the optimal sparrow population as a cluster center to obtain multiple classification clusters;

[0145] Acquisition unit: Acquisition of all structural surface samples in each classification cluster, and sequential calculation of the first average distance between each structural surface sample and the structural surface samples in the same cluster;

[0146] A fifth calculation unit: calculating a second average distance between each structural surface sample and structural surface samples of an adjacent cluster, wherein the adjacent cluster is a classification cluster closest to the classification cluster to which the currently calculated structural surface sample belongs;

[0147] The sixth calculation unit: calculates the contour coefficient of the current structural surface according to the first average distance and the second average distance;

[0148] Weighted summation unit: The silhouette coefficients of all structural surfaces are weighted summed to obtain the clustering effectiveness index.

[0149] It should be noted that, regarding the device in the above embodiment, the specific manner in which each module performs the operation has been described in detail in the embodiment of the method, and will not be elaborated here.

[0150] Embodiment 3:

[0151] Corresponding to the above method embodiment, this embodiment also provides a structural surface occurrence grouping device based on the Sparrow algorithm. The structural surface occurrence grouping device based on the Sparrow algorithm described below and the structural surface occurrence grouping method based on the Sparrow algorithm described above can refer to each other.

[0152] Figure 6 FIG. 8 is a block diagram of a device 800 for grouping structure planes based on a sparrow algorithm according to an exemplary embodiment. Figure 6 As shown, the structure plane generation status grouping device 800 based on the sparrow algorithm may include: a processor 801 and a memory 802. The structure plane generation status grouping device 800 based on the sparrow algorithm may also include one or more of a multimedia component 803, an I / O interface 804, and a communication component 805.

[0153] The processor 801 is used to control the overall operation of the structure plane occurrence grouping device 800 based on the sparrow algorithm to complete all or part of the steps in the structure plane occurrence grouping method based on the sparrow algorithm. The memory 802 is used to store various types of data to support the operation of the structure plane occurrence grouping device 800 based on the sparrow algorithm. These data may include, for example, instructions for any application or method operating on the structure plane occurrence grouping device 800 based on the sparrow algorithm, and application-related data, such as contact data, sent and received messages, pictures, audio, video, etc. The memory 802 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, disk or optical disk. The multimedia component 803 may include a screen and an audio component. The screen may be, for example, a touch screen, and the audio component is used to output and / or input audio signals. For example, the audio component may include a microphone for receiving external audio signals. The received audio signal may be further stored in the memory 802 or sent via the communication component 805. The audio component also includes at least one speaker for outputting audio signals. The I / O interface 804 provides an interface between the processor 801 and other interface modules, and the above-mentioned other interface modules can be keyboards, mice, buttons, etc. These buttons can be virtual buttons or physical buttons. The communication component 805 is used for wired or wireless communication between the structural surface occurrence grouping device 800 based on the sparrow algorithm and other devices. Wireless communication, such as Wi-Fi, Bluetooth, Near Field Communication (NFC), 2G, 3G or 4G, or a combination of one or more of them, so the corresponding communication component 805 can include: Wi-Fi module, Bluetooth module, NFC module.

[0154] In an exemplary embodiment, the structural surface occurrence grouping device 800 based on the sparrow algorithm can be implemented by one or more application specific integrated circuits (Application Specific Integrated Circuit, referred to as ASIC), digital signal processors (Digital Signal Processing Device, referred to as DSP), digital signal processing devices (Digital Signal Processing Device, referred to as DSPD), programmable logic devices (Programmable Logic Device, referred to as PLD), field programmable gate arrays (Field Programmable Gate Array, referred to as FPGA), controllers, microcontrollers, microprocessors or other electronic components, and is used to execute the above-mentioned structural surface occurrence grouping method based on the sparrow algorithm.

[0155] In another exemplary embodiment, a computer-readable storage medium including program instructions is also provided, and when the program instructions are executed by a processor, the steps of the above-mentioned method for grouping the occurrence of structural planes based on the sparrow algorithm are implemented. For example, the computer-readable storage medium may be the above-mentioned memory 802 including program instructions, and the above-mentioned program instructions may be executed by the processor 801 of the device 800 for grouping the occurrence of structural planes based on the sparrow algorithm to complete the above-mentioned method for grouping the occurrence of structural planes based on the sparrow algorithm.

[0156] Embodiment 4:

[0157] Corresponding to the above method embodiment, a readable storage medium is also provided in this embodiment. The readable storage medium described below and the structural surface occurrence grouping method based on the sparrow algorithm described above can refer to each other.

[0158] A readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the structural surface occurrence grouping method based on the sparrow algorithm in the above method embodiment are implemented.

[0159] The readable storage medium may specifically be a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, or other readable storage medium that can store program codes.

[0160] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

[0161] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. A structural surface occurrence grouping method based on the sparrow algorithm, characterized in that: include: Acquire a number of structural surface samples of the rock, and convert the several structural surface samples into normal vector samples of a number of space units in sequence; Obtaining a cluster number range, selecting a current cluster number from the cluster number range, initializing a sparrow population based on the current cluster number, and obtaining a plurality of groups of initial sparrow populations randomly distributed in a multidimensional space; Update the spatial position of the initial sparrow population, calculate the fitness values ​​of the normal vector samples of all structural surfaces and the updated sparrow population, and obtain the optimal sparrow population corresponding to the minimum fitness value; The optimal sparrow population is used to cluster the normal vector samples of all structural surfaces, and the silhouette coefficients of all structural surface samples after clustering are calculated to obtain the clustering effectiveness indicators, including: Each sparrow in the optimal sparrow population is taken as a cluster center, and the normal vector samples of the structural surface are clustered using the following formula to obtain k classification clusters: In the formula, Indicates c b The transpose of b Represents the b-th classification cluster C b The cluster center, s a Represents the classification cluster C b The bth normal vector sample in , θ represents the inclination angle; Get all the structural surface samples in each classification cluster, and calculate the first average distance a(i) between each structural surface sample and the structural surface samples in the same cluster in turn: Calculate the second average distance between each structural surface sample and the structural surface samples of the adjacent cluster, wherein the adjacent cluster is the classification cluster b(i) closest to the classification cluster to which the currently calculated structural surface sample belongs; The silhouette coefficient s(i) of the current structural surface is calculated based on the first average distance and the second average distance: The weighted sum of the silhouette coefficients of all structural surfaces is used to obtain the clustering effectiveness index: In the formula, the value range of SC is [-1,1]; Update the number of clusters, and repeatedly calculate the effectiveness index of the optimal sparrow population and clusters corresponding to the updated number of clusters; The number of clusters and clustering results corresponding to the maximum value of the effectiveness index are taken as the final grouping.

2. The structural surface occurrence grouping method based on the sparrow algorithm according to claim 1 is characterized in that ,Select the current number of clusters from the range of cluster numbers, initialize the sparrow population based on the current number of clusters, and obtain several groups of initial sparrow populations randomly distributed in the multidimensional space, including: A chaotic mapping algorithm is used to generate several groups of initial sparrow populations, wherein the initial sparrow populations include discoverers, followers and early warnings, and each group of sparrow populations contains sparrows with the same number as the clusters; Several groups of initial sparrow populations are evenly distributed in the multidimensional space to generate the initial positions of the discoverers, the followers and the warning persons.

3. The structural surface occurrence grouping method based on the sparrow algorithm according to claim 2 is characterized in that , Update the spatial position of the initial sparrow population, calculate the fitness values ​​of the normal vector samples of all structural surfaces and the updated sparrow population, and obtain the optimal sparrow population corresponding to the minimum fitness value, including: Constructing a fitness function, and using the fitness function to sequentially update the spatial positions of the discoverer, the follower, and the alarm, to obtain a number of updated groups of sparrow populations; The fitness function is used to calculate the fitness value between the normal vector sample of the structural surface and each group of sparrow populations after update; The spatial positions of the discoverer, follower and warning device are updated repeatedly. When the number of position updates reaches the maximum number of iterations, the sparrow population with the smallest fitness value is obtained as the optimal sparrow population.

4. The structural surface occurrence grouping method based on the sparrow algorithm according to claim 3 is characterized in that , update the spatial position of the discoverer, and obtain several updated groups of sparrow populations, including: Calculating the first fitness value between the normal vector sample of the structural surface and each group of initial sparrow populations by using the fitness function; Calculate a first candidate position according to the initial position of the discoverer, and calculate a second fitness value of the sparrow population when located at the first candidate position; If the second fitness value is less than the first fitness value, moving the finder to the first candidate position; Otherwise, the finder remains in the initial position.

5. The structural surface occurrence grouping method based on the sparrow algorithm according to claim 3 is characterized in that , Update the spatial position of the followers and obtain several updated groups of sparrow populations, including: Calculate a second candidate position according to the initial position of the follower, and calculate a third fitness value of the sparrow population when the sparrow population is located at the second candidate position; If the third fitness value is less than the first fitness value, moving the follower to a second candidate position; Otherwise, the follower remains at the initial position.

6. A structural surface occurrence grouping device based on the sparrow algorithm, characterized in that: include: Acquisition module: acquires several structural surface samples of the rock, and converts the several structural surface samples into normal vector samples of several space units in sequence; Initialization module: obtaining a cluster number range, selecting a current cluster number from the cluster number range, initializing a sparrow population based on the current cluster number, and obtaining a number of groups of initial sparrow populations randomly distributed in a multidimensional space; Calculation module: Update the spatial position of the initial sparrow population, calculate the normal vector samples of all structural surfaces and the fitness values ​​of the updated sparrow population, and obtain the optimal sparrow population corresponding to the minimum fitness value; Clustering module: cluster the normal vector samples of all structural surfaces using the optimal sparrow population, and calculate the silhouette coefficient of all structural surface samples after clustering to obtain the clustering effectiveness index; Update module: Update the number of clusters, and repeatedly calculate the optimal sparrow population and cluster effectiveness indicators corresponding to the updated number of clusters, including: Each sparrow in the optimal sparrow population is taken as a cluster center, and the normal vector samples of the structural surface are clustered using the following formula to obtain k classification clusters: In the formula, Indicates c b The transpose of b Represents the b-th classification cluster C b The cluster center, s a Represents the classification cluster C b The bth normal vector sample in , θ represents the inclination angle; Get all the structural surface samples in each classification cluster, and calculate the first average distance a(i) between each structural surface sample and the structural surface samples in the same cluster in turn: Calculate the second average distance between each structural surface sample and the structural surface samples of the adjacent cluster, wherein the adjacent cluster is the classification cluster b(i) closest to the classification cluster to which the currently calculated structural surface sample belongs; The silhouette coefficient s(i) of the current structural surface is calculated based on the first average distance and the second average distance: The weighted sum of the silhouette coefficients of all structural surfaces is used to obtain the clustering effectiveness index: In the formula, the value range of SC is [-1,1]; Selection module: The number of clusters and clustering results corresponding to the maximum value of the effectiveness index are taken as the final grouping.

7. The structural surface occurrence grouping device based on the sparrow algorithm according to claim 6 is characterized in that: The initialization module includes: Initialization unit: using a chaotic mapping algorithm to generate several groups of initial sparrow populations, the initial sparrow populations include discoverers, followers and early warning, and each group of sparrow populations contains the same number of sparrows as the number of clusters; Distribution unit: evenly distribute several groups of initial sparrow populations in the multidimensional space to generate the initial positions of the discoverers, followers and warners.

8. The structural surface occurrence grouping device based on the sparrow algorithm according to claim 7 is characterized in that: The update module includes: Function construction unit: construct a fitness function, and use the fitness function to update the spatial positions of the discoverer, the follower and the alarm in sequence to obtain a number of updated groups of sparrow populations; A first calculation unit: using the fitness function to calculate the fitness value between the normal vector sample of the structure surface and each group of sparrow populations after update; The first updating unit: repeatedly updating the spatial positions of the discoverer, follower and warning device. When the number of position updates reaches the maximum number of iterations, the sparrow population with the smallest fitness value is obtained as the optimal sparrow population.

9. The structural surface occurrence grouping device based on the sparrow algorithm according to claim 8 is characterized in that: The first updating unit comprises: A second calculation unit: using the fitness function to calculate a first fitness value between the normal vector sample of the structural surface and each group of initial sparrow populations; The third calculation unit is used to calculate the first candidate position according to the initial position of the finder, and calculate the second fitness value of the sparrow population when it is located at the first candidate position; A first judgment unit: if the second fitness value is less than the first fitness value, moving the finder to the first candidate position; Otherwise, the finder remains in the initial position.

10. The structural surface occurrence grouping device based on the sparrow algorithm according to claim 8, characterized in that: The first updating unit further includes: The fourth calculation unit: calculates a second candidate position according to the initial position of the follower, and calculates a third fitness value of the sparrow population when the sparrow population is located at the second candidate position; The second judgment unit: if the third fitness value is less than the first fitness value, moving the follower to a second candidate position; Otherwise, the follower remains at the initial position.

Images