Intelligent analysis and identification method for three-dimensional seismic wave point cloud data

Abstract

The invention relates to the field of seismic wave data processing, provides an intelligent analysis and identification method for three-dimensional seismic wave point cloud data in order to realize automatic forecasting, and performs machine intelligent geological object identification and automatic forecasting conclusion generation by directly performing standardization processing on point cloud data generated by a seismic wave method and through a corresponding relation in engineering experience. According to the method, the process from original data to images and then to manual interpretation is avoided, many problems in manual image analysis are avoided, meanwhile, a large amount of test original data is subjected to simplification and structured processing, the storage space and the data processing amount of subsequent work are saved, and the efficiency is improved. And a foundation is laid for machine intelligent fusion analysis among data under different forecasting methods.

Description

Technical Field

[0001] The present invention relates to the field of seismic wave data processing, and in particular to a method for intelligent analysis and recognition of three-dimensional seismic wave point cloud data. Background Art

[0002] Currently, seismic wave reflection imaging technologies such as TRT and TSP are widely used in tunneling and underground engineering. By receiving data through seismic wave reflection, software generates images based on these images and uses them to analyze and predict the geological conditions of the unexcavated section ahead of the tunnel, making them a key tool for advanced geological forecasting of underground projects. Currently, the entire process from receiving raw data to generating data maps is primarily developed and implemented by domestic and international equipment manufacturers. The process from image to prediction results relies on manual image recognition and analysis to further determine the spatial distribution patterns of prediction targets, such as unfavorable geological bodies.

[0003] The existing technology has the following deficiencies: 1. In the traditional forecasting model, field testing is first conducted. The test data is then calculated by the device's built-in algorithm and mapped. The image is the final result of the machine calculation. The image is then manually analyzed and the forecast conclusion is derived based on experience. This forecasting process is highly subjective, the analysis of results is subject to numerous interference factors, the accuracy is low, and the analysis efficiency is low.

[0004] 2. Images are difficult to analyze quantitatively, so it is difficult to convert them into a general data structure and enter the advanced forecast analysis system, which also makes it difficult to conduct data fusion analysis with other data-based advanced forecasting methods.

[0005] 3. There is no standardized forecasting system and machine recognition rules.

[0006] 4. The amount of raw test data is large and difficult to analyze directly. Summary of the Invention

[0007] In order to achieve automated forecasting, the present application provides a method for intelligent analysis and identification of three-dimensional seismic point cloud data.

[0008] The technical solution adopted by the present invention to solve the above problems is: The intelligent analysis and recognition method of 3D seismic point cloud data includes: Step 1: Collecting 3D seismic point cloud data of the tunnel; Step 2: Classify the seismic point cloud data according to the reflection morphology classification rules; Step 3: Obtain the positions of various types of reflection interfaces, and obtain the probability of existence of unfavorable geological bodies corresponding to each reflection morphology classification based on the relationship between the preset reflection morphology classification and the probability of existence of unfavorable geological bodies; Step 4: Accumulate the existence probabilities of the bad geological bodies corresponding to different reflection morphology classifications at the same location to obtain the existence probability of the bad geological body at the location.

[0009] Furthermore, after obtaining the positions of various types of morphological reflection interfaces, step 3 further includes: performing linear analysis between various types of reflection interfaces, and obtaining the probability of existence of unfavorable geological bodies corresponding to the linear relationship based on the relationship between the preset linear interface and the probability of existence of unfavorable geological bodies.

[0010] Furthermore, after obtaining the positions of various types of morphological reflection interfaces, step 3 further includes: obtaining the wave velocity change trend at the position, and obtaining the probability of existence of the adverse geological body corresponding to the wave velocity change trend based on the preset relationship between the wave velocity change trend and the probability of existence of the adverse geological body.

[0011] Furthermore, the reflection morphology classification includes: According to the morphology, it can be divided into planar continuous reflection, planar discontinuous reflection, staggered reflection, dense point reflection and sporadic point reflection; According to the morphological characteristics of positive and negative reflections, they are divided into positive and negative interval distribution, negative reflection as the main feature, positive reflection as the main feature, only negative reflection and only positive reflection; The two classification results are combined to obtain the final classification.

[0012] Furthermore, the classification rules are as follows: Planar continuous reflection: Detect and extract the smallest F% data from all seismic point cloud data, test the filtered data, and eliminate sporadic data with spatial discontinuous distribution based on the coordinate distribution of each data. Finally, compare the maximum value range of the Y coordinate in the filtered data with the spatial coordinate range of the tunnel diameter. If it is greater than or equal to the tunnel diameter, it is a planar continuous reflection with only negative reflections. Detect and extract the largest F% of data from all seismic point cloud data, test the filtered data, and eliminate sporadic data with discontinuous distribution in space based on the coordinate distribution of each data. Finally, compare the maximum value range of the Y coordinate in the filtered data with the spatial coordinate range of the tunnel diameter. If it is greater than or equal to the tunnel diameter, it is a continuous planar reflection with only positive reflection. Search among the detected continuous surface reflections. First, determine the distance A. If both positive and negative reflections exist within this distance range, determine whether the distribution is positive and negative, or whether negative reflections are dominant, or whether positive reflections are dominant, based on the quantitative relationship between the positive and negative reflections. Planar discontinuous reflection: Detect and extract the smallest F% of data from all seismic point cloud data, test the filtered data, and eliminate data with discontinuous distribution in space based on coordinate distribution. Finally, compare the maximum value range of the Y coordinate in the filtered data with the spatial coordinate range of the tunnel diameter. If the maximum length is less than the tunnel diameter or the preset value B, it is a planar discontinuous reflection with only negative reflections. Detect and extract the largest F% of data from all seismic point cloud data, test the filtered data, and eliminate data with discontinuous distribution in space based on coordinate distribution. Finally, compare the maximum value range of the Y coordinate in the filtered data with the spatial coordinate range of the tunnel diameter. If the maximum length is less than the tunnel diameter or the preset value B, it is a planar discontinuous reflection and only positive reflection; Search among the detected planar discontinuous reflections. First, determine the distance C. If both positive and negative reflections exist within this range, determine whether the distribution is positive and negative, or whether negative reflections are dominant, or whether positive reflections are dominant, based on the quantitative relationship between the positive and negative reflections. Dislocated reflex: On the basis of all planar discontinuous reflections, the staggered distance and distribution elevation of each positive reflection and negative reflection surface are detected respectively. Specifically, a planar discontinuous reflection of a positive reflection is searched within the range of ±Dm. If another planar discontinuous reflection of a positive reflection is found, and its vertical distribution range is complementary to that of the detected object, then these two planar discontinuous reflections and only positive reflections are merged into a staggered reflection and only positive reflection. Similarly, staggered reflections and only negative reflections can be obtained. Determine the distance E, search among the detected staggered reflections, and if both positive and negative reflections exist within the distance E, determine whether the distribution is positive and negative with alternating intervals, whether negative reflections are dominant, or whether positive reflections are dominant based on the quantitative relationship between the positive and negative reflections; Dense point reflections and scattered point reflections: After the above tests are completed, the remaining seismic point cloud data are screened, and the maximum and minimum G% data are retained. According to the distribution density of the coordinates of the sporadic numerical points, they are divided into dense point reflections and sporadic point reflections. According to the number of positive and negative value distributions, they are divided into positive and negative interval distribution, mainly negative reflections, mainly positive reflections, only positive reflections, or only negative reflections. A, B, C, D, E, F, and G are preset values.

[0013] Furthermore, the step 2 also includes encoding processing of reflection forms of different categories.

[0014] Furthermore, after obtaining the position of each reflection form classification, step 3 also includes encoding the position.

[0015] Furthermore, the step 4 further includes performing structured processing on the data based on coding before calculating the probability of the existence of the adverse geological body.

[0016] Furthermore, the method further includes step 5 of adjusting the classification rules and the probability of existence of the bad geological body corresponding to the reflection morphology classification according to the actual situation of the bad geological body after excavation.

[0017] Compared to existing technologies, this invention offers the following advantages: It directly standardizes the raw point cloud data generated by the seismic wave method and, using corresponding relationships drawn from engineering experience, enables machine-intelligent identification of geological objects and automatic generation of forecast conclusions. This method bypasses the process of converting raw data to images and then to manual interpretation, avoiding many of the problems inherent in manual image analysis. It also streamlines and structures large amounts of raw test point cloud data, saving storage space and subsequent data processing, laying the foundation for machine-intelligent fusion analysis of data from different forecasting methods. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 This is a flow chart of the intelligent analysis and recognition method for three-dimensional seismic point cloud data. DETAILED DESCRIPTION

[0019] In order to make the purpose, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0020] like Figure 1 As shown, the intelligent analysis and recognition method of three-dimensional seismic point cloud data includes: Step 1: Collect 3D seismic point cloud data for the tunnel. This example is based on the TRT results. The point cloud data from a single test is a set of normally distributed positive and negative values, where the median represents the normal state, and positive and negative values ​​correspond to positive and negative reflections and reflection intensities, respectively. Each value also corresponds to a set of spatial coordinates.

[0021] Step 2: Classify the seismic point cloud data according to the reflection morphology classification rules.

[0022] To improve classification accuracy and reduce data interference, seismic wave data must be filtered before classification. This embodiment categorizes seismic wave data into four types based on morphology: continuous surface reflections, discontinuous surface reflections, staggered reflections, and point reflections. Point reflections can be further subdivided into dense point reflections and sporadic point reflections. Based on the positive or negative value, seismic wave data can be categorized into negative reflections and positive reflections. The relationship between positive and negative reflections can be further subdivided into five types: positive-negative interval distribution, predominantly negative reflections, predominantly positive reflections, exclusively negative reflections, and exclusively positive reflections. Combining the two types of categorization yields the final classification result type.

[0023] The specific classification rules are: (1) Surface continuous reflection Detect and extract the smallest F% of all seismic point cloud data. In this embodiment, F is set to 20. Then, further detect the filtered data and eliminate non-adjacent data in space based on the coordinate distribution. Finally, compare the maximum value range of the Y coordinate in the filtered data with the spatial coordinate range of the tunnel diameter. If it is greater than or equal to the tunnel diameter, it is determined to be a planar continuous reflection, and the conclusion is that there are only negative reflections.

[0024] To facilitate subsequent data processing, reduce data processing volume, and save data storage space, each type is coded separately. In subsequent processing, the code can be used instead of the classification of each reflection form. For example, the above-mentioned continuous surface reflection with only negative reflection is coded as 14.

[0025] The largest 20% of all values ​​are extracted and tested. Non-adjacent data in space are eliminated based on the coordinate distribution. Finally, the maximum Y coordinate value range of the filtered data is compared with the spatial coordinate range of the tunnel diameter. If it is greater than or equal to the tunnel diameter, it can be concluded that the surface is continuously reflected and only positive reflection is obtained, and it is coded as 15. Further search is performed among the detected planar continuous reflections. First, the distance A is determined. If there are only multiple groups of positive reflections or multiple groups of negative reflections within the distance range, the code is retained unchanged. If there are both positive and negative reflections within the distance range, the distribution of positive and negative intervals, the distribution of mainly negative reflections or mainly positive reflections is determined based on the quantitative relationship between the positive and negative reflections. The corresponding codes are 11, 12, and 13, and the original codes 14 or 15 within the distance are deleted. If there are only positive reflections or only negative reflections, the original code is retained.

[0026] (2) Planar discontinuous reflection Detect and extract the smallest 20% of all values, test the filtered data, eliminate non-adjacent data in space based on the coordinate distribution, and finally compare the maximum value range of the Y coordinate in the filtered data with the spatial coordinate range of the tunnel diameter. If the maximum length is less than the tunnel diameter or the preset value B, it is determined to be a planar discontinuous reflection with only negative reflection, and the conclusion is coded as 24.

[0027] The largest 20% of all values ​​are extracted and tested. Non-adjacent data in space are eliminated based on the coordinate distribution. Finally, the maximum Y coordinate value range of the filtered data is compared with the spatial coordinate range of the tunnel diameter. If the maximum length is less than the tunnel diameter or the preset value B, it can be concluded that the surface is discontinuous and only has regular reflection, and it is coded as 25. Further search is performed among the detected planar discontinuous reflections. First, the distance C is determined. If there are only multiple groups of positive reflections or multiple groups of negative reflections within the distance range, the original code is retained unchanged. If there are both positive and negative reflections within the distance range, the distribution of positive and negative intervals, the distribution of mainly negative reflections or mainly positive reflections is determined based on the quantitative relationship between the positive and negative reflections. The corresponding codes are 21, 22, and 23, and the original codes 24 or 25 within the distance are deleted. If there are only positive reflections or only negative reflections, the original code is retained.

[0028] (3) Discontinuous reflection Based on all planar discontinuous reflections, each reflecting surface is tested for staggered distance and distributed elevation. Positive and negative reflecting surfaces need to be tested separately. For example, if a positive reflecting planar discontinuity is searched within the range of ±Dm, D can be 10. If another positive reflecting planar discontinuity is found, and its vertical distribution range is complementary to that of the detected object, the two surfaces previously coded 25 are merged into 35. Similarly, the code 34 can be obtained. After the above detection is completed, further detect the assigned staggered reflections. Within the distance E, determine whether it is a positive and negative interval distribution, negative reflections are dominant, or positive reflections are dominant based on the quantitative relationship between positive and negative reflections. The corresponding codes are 31, 32, and 33, and the original codes within this distance (codes 34~35) are deleted.

[0029] (4) Dense point reflections and sporadic point reflections After the above detection is completed, the remaining numerical points are screened and the maximum and minimum G% are retained. G is taken as 20. At this time, according to the distribution density of the coordinates of the sporadic numerical points, they are divided into dense point reflections and sporadic point reflections (for example, it is defined that the hit points in the space of 1m×1m×1m are ≥50, and the search is performed in units of 0.2m in the direction of the tunnel axis). Further, according to the distribution ratio of positive and negative values, they are defined and coded 41~55 respectively (for example, if 55 points meet the requirements in a single search and the positive reflection points are greater than 70%, the value is assigned 43; if the proportion of positive reflection points is between 50% and 70%, the value is assigned 41; if the proportion is greater than 90%, the value is assigned 45).

[0030] A, C, D, and E are preset distances that can be set based on actual needs. For example, a range of 20m to 50m is recommended. A value too large will reduce accuracy, while a value too small will be meaningless. B, F, and G can also be selected based on actual needs and are not limited here.

[0031] Step 3: Obtain the positions of various types of reflection interfaces, and obtain the probability of existence of unfavorable geological bodies corresponding to each reflection morphology classification based on the relationship between the preset reflection morphology classification and the probability of existence of unfavorable geological bodies.

[0032] The above steps complete the classification and assignment of point clouds to various reflective spatial forms. Furthermore, the spatial distribution of the reflective forms corresponding to each code must be described and encoded. By default, the starting point for a single test (a section perpendicular to the tunnel axis) is defined as the starting point. The position of the test object can then be defined based on the X-coordinate distribution range of each object. Due to the nature of the test, the effective value of a single test is generally within 100 meters. Therefore, a four-digit code is used, such as 4055, indicating that the distribution range of the object is 40 to 55 meters from the test starting section. When searching for the distribution range, some data on either side is generally excluded, such as 10% of the coordinate data on either side, to prevent the retrieved distribution range from being excessively affected by discrete points. Furthermore, the system should record the actual stake number information for each test. When outputting the conclusion, the system simply adds the distribution range to the actual stake number to obtain the actual spatial position of each object.

[0033] The probability of existence of bad geological bodies corresponding to each reflection form classification can be obtained by looking up a table. The probability table of this embodiment is as follows: Table 1 Probability of existence of unfavorable geological bodies corresponding to each reflection morphology classification

[0034] After completing the above tests, a linear analysis between all continuous and discontinuous planar reflections is performed. First, under top-down conditions (generally extracting two of the three coordinate values ​​at a time, such as the XY values, i.e., the planar distribution), each reflection surface is simplified to the coordinates of two points (the starting point and the end point) and replaced with a straight line. Under this condition, the starting and end points of adjacent reflection surfaces are connected. If the connecting line is approximately a straight line (determined by the approximate goodness of fit), it is considered that a linear image exists between the reflection surfaces. Based on the type of original reflection surface forming the line, it is classified as a linear structure formed between positive reflection surfaces, a linear structure formed between negative reflection surfaces, or a linear structure formed between positive and negative reflection surfaces, and is assigned a value of 61 to 63, respectively. This process is repeated under side-view conditions (i.e., in the XZ direction, where X is the tunnel axis), and the values ​​are assigned accordingly.

[0035] The probability of existence of unfavorable geological bodies corresponding to special structural surface types is shown in the following table: Table 2 Probability of existence of unfavorable geological bodies corresponding to special structural surface types

[0036] In addition to the above information, raw data collection generally includes other relevant information, such as a velocity map. The absolute value of the velocity map is significantly affected by the acquisition process, but the waveform trend can serve as an auxiliary judgment factor. Therefore, the velocity variation trend at each reflecting surface location can be statistically analyzed and coded with reference to the excitation surface velocity, as shown in Table 3. The velocity variation trend can be preset and defined. For example, if the average velocity value at the judgment location is greater than 30% compared to the average velocity value within 20 meters from the location to the excitation direction, it is considered a rapid increase; 10% to 30% is considered a slight increase; and less than 10% is considered basically consistent.

[0037] Table 3 Probability of existence of unfavorable geological bodies corresponding to wave velocity change trends

[0038] Step 4: Accumulate the existence probabilities of bad geological bodies corresponding to different reflection morphology classifications at the same location to obtain the existence probability of bad geological bodies at that location. If it exceeds 100%, it will be calculated as 100%.

[0039] If code 11 and code 24 exist simultaneously in the range of 4055, then the probability of occurrence of the geological interface in this range is output as 85% based on the probability of occurrence of their geological interfaces (+30% and +55%) respectively.

[0040] In order to improve the prediction accuracy, the classification rules and output probabilities can be modified according to the actual characteristics of the unfavorable geological body after excavation.

[0041] For example, if 10 sections are counted and the surface detection result is 11, the corresponding probability preset value is +30%. However, excavation confirms that there are geological interfaces in only 2 sections, so the actual probability is 20%. Therefore, the initial value corresponding to 11 is modified to +20%.

[0042] When using multiple geophysical methods to predict adverse geological bodies, data fusion analysis is involved. Similarly, data from geophysical methods with the same data structure are structured according to this method. At this time, the prediction weights of each method need to be defined, and the probability of occurrence of each geological interface is finally obtained after comprehensive analysis.

[0043] After a single point cloud data scan is completed, all reflective surfaces and special structure surfaces are converted into corresponding codes according to the rules. At this time, the structure of the coded data is specified and standardized. The purpose is to normalize the various data streams under different detection methods. Later, the machine can perform mutual operations on the data obtained by different methods according to the preset algorithm to achieve the purpose of comprehensive analysis. The overall data after recognition is arranged in a matrix. Each row contains the relevant information of a single reflective surface. The columns express different meanings according to different positions. When a position has no data or no meaning, it is replaced by a letter. The following are examples: XX YY 4 0 5 5 1 2 2 XX 6 1 3 5 4 2 BB 1 For example, if a project uses 11-bit coding, bits 1 and 2 represent the project location. Currently, no information is input and they are replaced by the letter X. Bits 3 and 4 indicate whether it is a linear image between objects. The first line indicates no and is replaced by the letter Y, and the second line is 61. Bits 5 to 8 are location distribution information, indicating the range of distribution location pile numbers. Bits 9 and 10 are reflection surface feature information. Since the second line is a linear image between objects, no data is input for the feature information position and they are replaced by letters. The last bit is other information, such as the wave velocity change trend.

[0044] By arranging the reflective surfaces according to this rule, we can quickly screen and identify reflective surfaces with certain characteristics, and also quickly perform calculations. For example, in the above example, the reflective surfaces in the first row are distributed between 40 and 55 meters, and the reflective surfaces in the second row are distributed between 35 and 42 meters. After cross-calculation, it is found that both reflective surfaces exist in the range of 40 to 42 meters.

Claims

1. A method for intelligent analysis and identification of three-dimensional seismic point cloud data, characterized in that: include: Step 1, collecting tunnel 3D seismic point cloud data; Step 2: classify the seismic point cloud data according to the reflection morphology classification rules; Step 3, obtaining the positions of various types of reflection interfaces, and obtaining the probability of existence of bad geological bodies corresponding to each reflection morphology classification according to the relationship between the preset reflection morphology classification and the probability of existence of bad geological bodies; Step 4: Accumulate the existence probabilities of bad geological bodies corresponding to different reflection morphology classifications at the same location to obtain the existence probability of the bad geological body at the location.

2. The intelligent analysis and identification method of three-dimensional seismic point cloud data according to claim 1 is characterized in that: After obtaining the positions of various types of reflection interfaces, step 3 further includes: performing linear analysis between various types of reflection interfaces, and obtaining the probability of existence of bad geological bodies corresponding to the linear relationship based on the relationship between the preset linear interface and the probability of existence of bad geological bodies.

3. The intelligent analysis and identification method of three-dimensional seismic point cloud data according to claim 1 is characterized in that: After obtaining the positions of various types of morphological reflection interfaces, step 3 further includes: obtaining the wave velocity change trend at the position, and obtaining the probability of existence of the bad geological body corresponding to the wave velocity change trend according to the preset relationship between the wave velocity change trend and the probability of existence of the bad geological body.

4. The intelligent analysis and identification method of three-dimensional seismic point cloud data according to claim 1 is characterized in that: Reflection morphology classification includes: According to the morphology, it can be divided into planar continuous reflection, planar discontinuous reflection, staggered reflection, dense point reflection and sporadic point reflection; According to the morphological characteristics of positive and negative reflections, they are divided into positive and negative interval distribution, negative reflection as the main feature, positive reflection as the main feature, negative reflection only, and positive reflection only; The two classification results are combined to obtain the final classification.

5. The intelligent analysis and identification method of three-dimensional seismic point cloud data according to claim 4 is characterized in that: The specific classification rules are: Surface continuous reflection: Detect and extract the smallest F% data from all seismic point cloud data, detect the filtered data, and remove the sporadic data with non-continuous distribution in space according to the coordinate distribution corresponding to each data. Finally, compare the maximum value range of the Y coordinate in the filtered data with the spatial coordinate range of the tunnel diameter. If it is greater than or equal to the tunnel diameter, it is a planar continuous reflection with only negative reflection. Detect and extract the largest F% of data from all seismic point cloud data, detect the filtered data, and remove the sporadic data with non-continuous distribution in space according to the coordinate distribution corresponding to each data. Finally, compare the maximum value range of the Y coordinate in the filtered data with the spatial coordinate range of the tunnel diameter. If it is greater than or equal to the tunnel diameter, it is a planar continuous reflection and only positive reflection; Search among the detected continuous reflections of each surface, first determine the distance A, if there are both positive reflections and negative reflections within the distance range, then determine whether it is positive and negative interval distribution, negative reflection is dominant or positive reflection is dominant according to the quantitative relationship between the positive reflections and the negative reflections; Planar discontinuity reflection: Detect and extract the smallest F% data from all seismic wave point cloud data, detect the filtered data, eliminate the data with non-continuous distribution in space according to the coordinate distribution, and finally compare the maximum value range of the Y coordinate in the filtered data with the spatial coordinate range of the tunnel diameter. If the maximum length is less than the tunnel diameter or the preset value B, it is a planar discontinuous reflection and only negative reflection; Detect and extract the largest F% of data from all seismic wave point cloud data, detect the filtered data, eliminate the data with non-continuous distribution in space according to the coordinate distribution, and finally compare the maximum value range of the Y coordinate in the filtered data with the spatial coordinate range of the tunnel diameter. If the maximum length is less than the tunnel diameter or the preset value B, it is a planar discontinuous reflection and only positive reflection; Search among the detected planar discontinuous reflections, first determine the distance C, if there are both positive and negative reflections within the range, then determine whether it is positive and negative interval distribution, negative reflection is dominant or positive reflection is dominant according to the quantitative relationship between the positive and negative reflections; Disconnected reflection: On the basis of all planar discontinuous reflections, the staggered distance and distribution elevation of each positive reflection and negative reflection surface are detected respectively, specifically: a planar discontinuous reflection of a positive reflection is searched within the range of ±Dm, if another planar discontinuous reflection of a positive reflection is found, and the vertical distribution range is complementary to the detected object, then these two planar discontinuous reflections and only positive reflections are merged into staggered reflections and only positive reflections; similarly, staggered reflections and only negative reflections can be obtained; Determine the distance E, search among the detected staggered reflections, if there are both positive and negative reflections within the distance E, determine whether it is positive and negative interval distribution, negative reflection is dominant or positive reflection is dominant according to the quantitative relationship between the positive and negative reflections; Dense point reflection and scattered point reflection: After the above tests are completed, the remaining seismic wave point cloud data are screened, and the maximum and minimum G% data are retained. According to the distribution density of the coordinates of the sporadic numerical points, they are divided into dense point reflections and sporadic point reflections. According to the number of positive and negative value distributions, they are divided into positive and negative interval distribution, mainly negative reflections, mainly positive reflections, only positive reflections, or only negative reflections; A, B, C, D, E, F, G are preset values.

6. The intelligent analysis and identification method of three-dimensional seismic point cloud data according to claim 1, characterized in that: The step 2 also includes encoding the reflection forms of different categories.

7. The intelligent analysis and identification method of three-dimensional seismic point cloud data according to claim 6, characterized in that: Step 3 also includes encoding the position after obtaining the position of each reflection form classification.

8. The intelligent analysis and identification method of three-dimensional seismic point cloud data according to claim 7, characterized in that: The step 4 also includes structural processing of the data based on coding before calculating the probability of the existence of the bad geological body.

9. The intelligent analysis and identification method of three-dimensional seismic point cloud data according to any one of claims 1 to 8, characterized in that: The method further includes step 5, adjusting the probability of existence of the bad geological body corresponding to the classification rules and the reflection morphology classification according to the actual situation of the bad geological body after excavation.

Images