Automatic generation method and system for sea breeze geological modeling horizon based on image recognition

Abstract

The present invention discloses a method and system for automatically generating sea breeze geological modeling horizons based on image recognition. The method first analyzes seismic images obtained from engineering geophysical surveys to obtain seismic horizon data. Then, based on the seismic horizon data, the coring depth of the station is determined, and coring is performed to obtain geotechnical data. The seismic horizon data is updated based on the geotechnical data, and then coring is guided by the updated seismic horizon data. This process is repeated until the comprehensive stratigraphic similarity between the geotechnical data and the seismic horizon data exceeds a set threshold. Through the interaction between coring and seismic horizon data, iterative updates of the seismic horizon data are achieved, ultimately obtaining accurate stratigraphic horizon data.

Description

Technical Field

[0001] The present invention relates to the technical field of geological survey data processing for offshore wind farms, and in particular to a method and system for automatically generating offshore wind geological modeling layers based on image recognition. Background Art

[0002] With the development of renewable energy sources such as offshore wind power, seismic facies research, as a key method for interpreting geophysical data, is becoming increasingly important in marine engineering construction. In conventional geophysical surveys, stratigraphic characterization primarily involves seismic analysis combined with geological, well logging, and geotechnical information to determine the sedimentary facies of the strata. Sedimentary facies, also known as seismic phases in seismic data, are analyzed. By studying seismic phases, including changes in seismic wave velocity, amplitude, phase, frequency, and waveform, we can determine geological structural characteristics, lithologic distribution, and stratigraphic features, thereby providing accurate and comprehensive geological information for engineering design and construction.

[0003] Currently, automatic image tracking technology is primarily used to determine stratigraphic positions. This involves identifying characteristic waveforms, determining seed points and stratigraphic azimuths, and then tracing the most similar pixels along the azimuths to complete stratigraphic picking. However, in practice, offshore wind turbines are often built in shallow, sedimentary environments dominated by sand and mud, resulting in ambiguous stratigraphic positions, unclear azimuths, and discontinuous stratigraphic positions. Consequently, the resulting stratigraphic data is inaccurate.

[0004] Therefore, the existing technology needs to be improved and enhanced. Summary of the Invention

[0005] The main purpose of the present invention is to provide a method, system, intelligent terminal and storage medium for automatically generating sea breeze geological modeling layers based on image recognition, aiming to solve the problem of inaccurate stratigraphic layer data obtained in the prior art.

[0006] In order to achieve the above-mentioned object, the first aspect of the present invention provides a method for automatically generating sea breeze geological modeling horizons based on image recognition, wherein the method comprises:

[0007] Conduct engineering geophysical surveys along the wind turbine locations to obtain seismic images;

[0008] Based on the seismic image, obtaining seismic horizon data;

[0009] Determine the coring depth based on the seismic horizon data and perform core drilling to obtain geotechnical data;

[0010] Comparing the seismic horizon data and the stratigraphic depth of each stratigraphic layer in the geotechnical data to obtain the similarity of each stratigraphic layer, and obtaining a comprehensive similarity based on the similarities of all stratigraphic layers;

[0011] Based on the consistency of the seismic phase axis, the seismic layer data is updated according to the geotechnical data;

[0012] When the comprehensive similarity is less than a set threshold, the coring depth of the next station is determined according to the seismic horizon data, and the coring is carried out and the seismic horizon data is iteratively updated;

[0013] The seismic layer data is output.

[0014] Optionally, obtaining seismic horizon data based on the seismic image includes:

[0015] obtaining a plurality of stratigraphic boundary points according to the seismic image;

[0016] Based on the seismic phase similarity and continuity, seismic horizon data are obtained according to the stratigraphic boundary points.

[0017] Optionally, obtaining seismic horizon data according to the stratigraphic boundary points based on seismic phase similarity and continuity includes:

[0018] Generate a number of automatic tracking line segments corresponding to the stratum depth according to all stratum boundary points tracked at each stratum depth;

[0019] The automatically traced line segments of all stratum depths constitute the seismic horizon data.

[0020] Optionally, obtaining a plurality of stratigraphic boundary points according to the seismic image includes:

[0021] Based on a preset sub-image size, dividing the seismic image into a plurality of sub-images;

[0022] Screening all sub-images at each depth to obtain a number of sub-images containing stratum boundary points, and setting the stratum boundary points as seed points;

[0023] Taking the sub-image where the seed point is located as the center, searching for stratum boundary points in a first preset number of sub-images in adjacent channels;

[0024] When a stratum boundary point is found in an adjacent trace, the stratum boundary point is set as a seed point and a cyclic search is performed;

[0025] When no stratum boundary point is found in the adjacent trace, the next adjacent trace is searched until the second preset number of adjacent traces are searched.

[0026] Optionally, the method of screening all sub-images at each depth to obtain a number of sub-images containing stratum boundary points includes:

[0027] The grayscale value of each pixel in the sub-image is compared with the preset pixel value, and the number of pixels whose grayscale value exceeds the preset pixel value is counted. When the number of pixels exceeds the preset threshold, the pixel with the lowest grayscale value in the sub-image is set as the stratum dividing point.

[0028] Optionally, updating the seismic horizon data according to the geotechnical data based on the consistency of seismic events includes:

[0029] Obtaining seismic events near each stratum in the seismic horizon data and the geotechnical data;

[0030] The seismic events of the geotechnical data of each stratum are compared with the seismic events of the seismic layer data. If the seismic events are inconsistent, the seismic layer data are updated according to the geotechnical data.

[0031] Optionally, the number of strata in the geotechnical data is different from the number of strata in the seismic horizon data, further comprising:

[0032] The strata of the geotechnical data and the strata of the seismic horizon data are compared to obtain the missing strata in the seismic horizon data, and then the missing strata are added to the seismic horizon data.

[0033] A second aspect of the present invention provides a system for automatically generating sea breeze geological modeling horizons based on image recognition, wherein the system comprises:

[0034] Seismic imaging module, used to conduct engineering geophysical surveys along the wind turbine locations and obtain seismic images;

[0035] A seismic horizon module, configured to obtain seismic horizon data based on the seismic image;

[0036] A geotechnical data module is used to determine the coring depth according to the seismic horizon data and to perform core drilling to obtain geotechnical data;

[0037] a comprehensive similarity module, for comparing the seismic horizon data and the stratigraphic depth of each stratigraphic layer in the geotechnical data, obtaining the similarity of each stratigraphic layer, and obtaining a comprehensive similarity based on the similarities of all stratigraphic layers;

[0038] An updating module, configured to update the seismic horizon data according to the geotechnical data based on the consistency of the seismic events;

[0039] A comparison module, configured to determine a coring depth for a next station based on the seismic horizon data, perform coring drilling, and iteratively update the seismic horizon data when the comprehensive similarity is less than a set threshold;

[0040] The result module is used to output the seismic layer data.

[0041] The third aspect of the present invention provides an intelligent terminal, which includes a memory, a processor, and an image-recognition-based automatic generation program for sea breeze geological modeling layers, which is stored in the memory and can be run on the processor. When the image-recognition-based automatic generation program for sea breeze geological modeling layers is executed by the processor, any one of the steps of the image-recognition-based automatic generation method for sea breeze geological modeling layers is implemented.

[0042] The fourth aspect of the present invention provides a computer-readable storage medium, which stores a program for automatically generating sea breeze geological modeling layers based on image recognition. When the program for automatically generating sea breeze geological modeling layers based on image recognition is executed by a processor, it implements any step of the method for automatically generating sea breeze geological modeling layers based on image recognition.

[0043] As can be seen from the above, the present invention first analyzes the seismic images obtained from the engineering geophysical survey to obtain seismic horizon data. The coring depth of the station is then determined based on the seismic horizon data, and coring is performed to obtain geotechnical data. The seismic horizon data is updated based on the geotechnical data, and then the updated seismic horizon data is used to guide coring. This process is repeated until the combined stratigraphic similarity between the geotechnical and seismic horizon data exceeds a set threshold. Compared to existing technologies, this method achieves iterative updates of seismic horizon data through interaction between coring and seismic horizon data, ultimately obtaining accurate stratigraphic data. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0045] Figure 1 1 is a flow chart of a method for automatically generating sea breeze geological modeling horizons based on image recognition provided by an embodiment of the present invention;

[0046] Figure 2 yes Figure 1 A schematic diagram of a seismic image of an embodiment;

[0047] Figure 3 yes Figure 1 Schematic diagram of automatic line tracing of an embodiment;

[0048] Figure 4 yes Figure 1 Four stratigraphic diagrams obtained from seismic images in the embodiment;

[0049] Figure 5 yes Figure 1 Specific flow diagram of step S200 in the embodiment;

[0050] Figure 6 yes Figure 1 Schematic diagram of image segmentation in the embodiment;

[0051] Figure 7 yes Figure 1 Schematic diagram of determining stratum boundary points in a sub-image in an embodiment;

[0052] Figure 8 yes Figure 1 Schematic diagram of searching for adjacent sub-images in the embodiment;

[0053] Figure 9 yes Figure 1 Schematic diagram of the comparison results of the F16 placeholder similarity in the embodiment;

[0054] Figure 10 yes Figure 1 Schematic diagram of the comparison results of the F21 placeholder similarity in the embodiment;

[0055] Figure 11 yes Figure 1 Schematic diagram of the comparison results of the F19 placeholder similarity in the embodiment;

[0056] Figure 12 Schematic diagram of a system for automatically generating sea breeze geological modeling horizons based on image recognition provided by an embodiment of the present invention;

[0057] Figure 13 This is the implementation architecture diagram of the automatic generation system of sea breeze geological modeling layers based on image recognition;

[0058] Figure 14 This is a block diagram of the internal structure principle of a smart terminal provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0059] In the following description, specific details such as particular system structures and techniques are provided for purposes of illustration, not limitation, to facilitate a thorough understanding of the embodiments of the present invention. However, it will be apparent to those skilled in the art that the present invention may be practiced in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted so as not to obscure the description of the present invention with unnecessary detail.

[0060] It will be understood that when used in this specification and the appended claims, the term "comprising" indicates the presence of described features, integers, steps, operations, elements and / or components, but does not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or groups thereof.

[0061] It should also be understood that the terms used in the present specification are only for the purpose of describing particular embodiments and are not intended to limit the present invention. As used in the present specification and the appended claims, the singular forms "a", "an", and "the" are intended to include the plural forms unless the context clearly indicates otherwise.

[0062] It should be further understood that the term "and / or" used in the present description and the appended claims refers to and includes any and all possible combinations of one or more of the associated listed items.

[0063] As used in this specification and the appended claims, the term "if" can be interpreted as "when" or "upon" or "in response to determining" or "in response to detecting," depending on the context. Similarly, the phrase "if it is determined" or "if [described condition or event] is detected" can be interpreted as meaning "upon determination" or "in response to determining" or "upon detection of [described condition or event]" or "in response to detecting [described condition or event]," depending on the context.

[0064] The following is a clear and complete description of the technical solutions in the embodiments of the present invention, in conjunction with the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0065] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0066] In response to the problem of inaccurate stratigraphic data obtained by the current automatic image tracking technology for determining stratigraphic levels, the present invention provides a method for automatically generating sea breeze geological modeling levels based on image recognition. First, the seismic images obtained by engineering geophysical surveys are analyzed to obtain seismic stratigraphic data, and drilling and coring are guided according to the seismic stratigraphic data. The seismic stratigraphic data are adjusted and upgraded according to the geotechnical data obtained by drilling and coring. Through the interaction between drilling and coring and seismic stratigraphic data, iterative updating of seismic stratigraphic data is achieved, and ultimately accurate stratigraphic stratigraphic data is obtained.

[0067] Exemplary Methods

[0068] like Figure 1As shown, an embodiment of the present invention provides a method for automatically generating sea breeze geological modeling layers based on image recognition, which is deployed on various electronic terminals, such as mobile terminals, computers, or servers. Specifically, the method includes the following steps:

[0069] Step S100: Conducting an engineering geophysical survey along the wind turbine location to obtain a seismic image;

[0070] Specifically, in offshore wind farm site survey projects, the survey work in the feasibility study phase is the focus of the entire offshore wind power engineering survey. It is necessary to find out the composition and distribution of the strata in the site, the physical and mechanical parameters and burial depth of the wind turbine unit foundation bearing layer, and the main engineering geological problems. If the engineering geophysical survey is not completed in the pre-feasibility study phase, it should be carried out in conjunction with the preliminary layout of the wind turbine before geotechnical drilling; if the engineering geophysical survey has been completed in the pre-feasibility study phase, but the seismic data obtained by the geophysical method used is too coarse, or is far away from the location where the wind turbine is laid, the seismic survey line should be re-run or the survey line should be increased before drilling to obtain the following information: Figure 2 The seismic image shown, where the seismic survey line is a survey line arranged along the designed wind turbine location.

[0071] Step S200: obtaining seismic layer data based on the seismic image;

[0072] Specifically, seismic horizon data consists of a series of seismic waveform sequences, with adjacent seismic waveform sequences often manifesting as seismic events in the horizontal direction. In seismic facies interpretation, since seismic events on a seismic section represent the seismic response of a particular stratum or the combined seismic response of several strata, and have a certain correspondence with the strata, continuous tracking of seismic events on actual seismic sections is a prerequisite for horizon interpretation.

[0073] Various image processing methods can be used to analyze seismic images and obtain seismic horizon data. In one example, a mean filter is used to smooth the seismic image. The value of each byte of the original pixel is subtracted from the value of each byte of the smoothed pixel to obtain a new pixel (i.e., the value of this pixel is the difference between the two values). After grayscale processing of the image, pixel values ​​below a threshold are assigned a value of 0, and all other values ​​are assigned a value of 255. This completes the black-and-white conversion process, and basic seismic horizon data can be obtained after the black-and-white conversion.

[0074] In this embodiment, the seismic image is first grayscaled, and then based on the principle of seismic phase similarity and continuity, several stratigraphic boundary points are obtained from the seismic image. The stratigraphic boundary points are the tracking points on the seismic profile, and the lines connecting the stratigraphic boundary points form automatic tracking segments. Specifically, all stratigraphic boundary points tracked at each depth are connected to generate several automatic tracking segments corresponding to each depth. All automatic tracking segments constitute seismic layer data. This method is referred to as the full layer tracking method below. After full layer tracking, the following can be obtained: Figure 3 The automatic tracking segments shown are also called seismic phase axes, which can provide a detailed interpretation of the strata. In order to improve the accuracy of the automatic tracking segment interpretation of the strata, it is preferred that the number of automatic tracking segments is more than three times the number of generated strata. Taking the preset wind turbine F16 position as an example, Figure 3 and Figure 4 As shown, four strata are generated, with a total of 14 automatically traced line segments passing through the F16 wind turbine location.

[0075] The stratigraphic boundary points are obtained based on the seismic images, such as Figure 5 As shown, the specific steps include:

[0076] Step S210: dividing the seismic image into a plurality of sub-images based on a preset sub-image size;

[0077] Specifically, a seismic profile is equivalent to unfolding a map of underground strata layer by layer from shallow to deep along the survey line direction (also called the gather direction). Figure 6 As shown in the figure, the seismic data of a certain survey line that has been processed into a grayscale image can be segmented according to the following method: find the upper left corner of the seismic image and set it as the origin, expand the seismic image with the gather direction as the horizontal axis and the time direction (also called the depth direction) as the vertical axis, and according to the preset sub-image size, such as 5x5 or 10x10 pixels, first along the gather direction and then along the time direction from the upper left vertex to the lower right bottom point. For example Figure 6 The seismogram has 1580x990 pixels. 5x5 pixels are set as a sub-image. The left vertex fixed gather starting point is set to 0. In a certain fixed time direction, there are m=316 sub-images in the gather direction of the horizontal axis. Similarly, the left vertex time starting point (T0) is set to 0. In a certain fixed gather direction, there are n=198 sub-images in the time direction of the vertical axis. Therefore, Figure 6 The seismogram is divided into m*n=62568 sub-images.

[0078] Step S220: Screening all sub-images at each depth to obtain a number of sub-images containing stratum boundary points, and setting the stratum boundary points as seed points;

[0079] Specifically, each sub-image at each depth is searched from the time starting point T0 from shallow to deep, Figure 6 Taking the seismic image of as an example, first determine whether each sub-image has a stratigraphic boundary point along the gather direction. The judgment method is: compare the gray value of each pixel in the sub-image with the preset pixel value, count the number of pixels whose gray value exceeds the preset pixel value, and when the number of the above-mentioned pixels exceeds the preset threshold, it is determined that the sub-image contains a stratigraphic boundary point, and the pixel with the lowest gray value in the sub-image is set as the stratigraphic boundary point (also called a valid pixel point). Figure 7 For example, assuming the preset pixel value is 150 and the preset threshold is 9, Figure 7 The pixel values ​​of all pixels in sub-image A are higher than the preset pixel values, so there is no stratum boundary point in sub-image A; Figure 7 In sub-image B, there are 6 pixels whose pixel values ​​are lower than the preset pixel value, but the number is less than the preset threshold value of 9, so there is no stratigraphic boundary point in sub-image B; Figure 7 In sub-image C, 14 pixels have pixel values ​​below the preset pixel value, and this number is greater than the preset threshold of 9. Therefore, sub-image C contains the stratigraphic boundary point. The pixel corresponding to the lowest pixel value in sub-image C is the stratigraphic boundary point. After obtaining the stratigraphic boundary point at each depth, these stratigraphic boundary points are used as seed points in subsequent steps to track and search adjacent traces.

[0080] Step S230: taking the sub-image where the seed point is located as the center, searching for stratum boundary points in a first preset number of sub-images in adjacent channels;

[0081] Specifically, starting from the seed point, track the valid pixel points of the adjacent track at a certain angle. Figure 8 As shown, with the sub-image where the seed point is located as the center, a first preset number of sub-images in the adjacent channel are obtained. For example, assuming that the first preset number is five, the sub-image in the adjacent channel with the same vertical coordinate as the sub-image where the seed point is located, as well as two sub-images above and two sub-images below are obtained, resulting in five sub-images. The same judgment method as in step S220 is then applied to each of the five sub-images to determine whether there are stratigraphic boundary points in these sub-images. It should be noted that although this embodiment tracks the sub-images of the adjacent channel with the sub-image where the seed point is located as the center, the angle is not specifically limited, and sub-images in the adjacent channel that are flush with or below the sub-image where the seed point is located can also be tracked.

[0082] Step S240: When a stratum boundary point is found in an adjacent trace, the stratum boundary point is set as a seed point and a cyclic search is performed;

[0083] Specifically, when a stratum boundary point is found in an adjacent channel, the found stratum boundary point is used as a seed point, and the method of step S230 is adopted to search for sub-images of adjacent channels of the seed point, and a cyclic search is performed.

[0084] When more than one sub-image in adjacent channels contains stratum boundary points, the pixel values ​​of these stratum boundary points are compared, and the pixel point with the lowest pixel value is selected as the final stratum boundary point, and the remaining stratum boundary points are discarded.

[0085] Step S250: When no stratum boundary point is found in the adjacent trace, the next adjacent trace is searched until a second preset number of adjacent traces are searched.

[0086] Specifically, if no stratigraphic boundary point is found within an adjacent trace, a search is performed on the sub-image at the same vertical coordinate position in the next adjacent trace of the current seed point (also known as a translation search). If no stratigraphic boundary point is found, the search continues with the next adjacent trace until a second preset number of adjacent traces have been searched. If no stratigraphic boundary point is found, the search process ends. For example, assuming that the trace set containing the seed point is A, the second preset number is 3, and the order of A's adjacent traces is B, C, and D. If no stratigraphic boundary point is found in adjacent trace B, adjacent trace C is searched. If no stratigraphic boundary point is found, adjacent trace D is searched. If no stratigraphic boundary point is found, the search process ends for that segment.

[0087] After the search is completed, the searched stratum boundary points are connected to obtain automatic tracking line segments.

[0088] The above-mentioned full-layer tracking method can also be applied to seismic images with fuzzy layers, unclear azimuths and discontinuousness, and achieve a higher recognition accuracy.

[0089] In this embodiment, the complete implementation process of full-layer tracking is: global search of all sub-images in two directions, first from near to far along the gather direction, and then from shallow to deep along the time direction. In order to avoid layer overlap and repeated search, the searched sub-images are marked. Figure 6 For example, at time T0, all (0,m) sub-images in the gather direction are traversed and searched. Then, the steps at time T0 are repeated in the time direction to traverse all (n,m) sub-images in the grayscale image. The results are then evaluated through human-computer interaction. If the automatically picked results are rough or over-picked, seismic interpretation experts can make local corrections and refine the depiction by adjusting parameters such as sub-image size, preset pixel value, preset threshold, first preset number, and second preset number, ensuring the accuracy, rationality, and reliability of the horizon details and overall trends.

[0090] Step S300: Determine the coring depth based on the seismic horizon data and perform core drilling to obtain geotechnical data;

[0091] Specifically, marine geological surveys typically integrate point-based geotechnical surveys with regional engineering geophysical exploration to establish a regional engineering geological model, thereby achieving a detailed understanding of the regional sedimentary environment from point to surface. Seismic facies analysis can only accurately determine stratigraphic horizons and seismic facies markers of target layers through observation and testing of subsurface rock and soil samples after geotechnical survey drilling and coring. Unlike offshore oil and gas field exploration, offshore wind farms are characterized by large land areas and numerous turbine sites. Therefore, the number and location of cores taken are particularly critical. Coring is generally conducted discontinuously. In complex geological conditions, insufficient cores or incorrect location selection can significantly hinder seismic facies analysis and horizon determination. Conversely, in areas with relatively simple regional geology, drilling and coring at every planned turbine site would significantly increase survey costs. The preferred solution is for geotechnical engineers to make on-site adjustments to the coring plan and station layout based on the coring results. However, seismic facies interpretation is multifaceted, and geotechnical engineers are generally not seismic interpretation experts, making it difficult to accurately interpret seismic data on-site in a short period of time. In this embodiment, coring is performed based on seismic horizon data to determine the coring depth and obtain geotechnical data.

[0092] Before there is geotechnical data, full-layer tracking is used to obtain the formation Figure 4 As shown, seismic interpretation based on seismic horizon data yielded four horizons (Hor. 10, Hor. 20, Hor. 30, and Hor. 40). Taking the pre-set F16 wind turbine location as an example, without measured geotechnical data, the seismic prediction for the first horizon (Hor. 10) was 7.3 meters deep. When designing the coring depth for the first station, the seismic horizon data should be fully considered, with increased coring near the boundary surface of the stratigraphic transition. It should also be understood that seismic interpretation of stratigraphic interfaces is based on wave impedance, which does not fully reflect the stratigraphic medium.

[0093] Step S400: comparing the stratum depth of each stratum in the seismic horizon data and the geotechnical data to obtain the similarity of each stratum, and obtaining the comprehensive similarity based on the similarities of all strata;

[0094] Specifically, after obtaining the geotechnical data of the first station (F16), the geotechnical data are converted into time-acoustic data, and then the similarity of each stratum is compared with the seismic layer data, and then the comprehensive similarity is calculated.

[0095] In this embodiment, the similarity is calculated by directly dividing the stratum depth obtained by geotechnical analysis with the stratum depth of the seismic horizon data. Figure 9As shown in the figure, the first layer (Hor. 10) of seismic horizon data (i.e., earthquake prediction) is 7.3 meters below the mud surface, and the measured geotechnical data (i.e., geotechnical measurements) is 6.1 meters below the mud surface. The first layer has a similarity of 84%. Similarly, the second layer has a similarity of 99%, the third layer has a similarity of 100%, and the fourth layer has a similarity of 97%. Averaging the similarity values ​​for these four layers yields an overall similarity (accuracy) of 94.0%.

[0096] Step S500: Based on the consistency of the seismic events, the seismic layer data is updated according to the geotechnical data;

[0097] Specifically, after the comparison is completed, the nearest seismic event near the measured depth of each stratum is automatically searched. If it is different from the seismic horizon data, the system automatically modifies and updates the seismic horizon data. That is, the above-mentioned step S200 is taken to perform a tracking search at the measured depth of each stratum, and the seismic events obtained by the search are compared with the seismic events in the seismic horizon data. If they are different, the seismic events in the seismic horizon data are updated with the seismic events obtained by the search. That is, not only the stratum depth in the seismic horizon data is updated according to the geotechnical data, but also a tracking search is performed according to the updated stratum depth to obtain stratum data to update the seismic events in the seismic horizon data.

[0098] Furthermore, when the number of strata in the geotechnical data is different from that in the seismic layer data, it is generally because strata are missing in the seismic layer data. By comparing the strata in the geotechnical data and the strata in the seismic layer data, the missing strata in the seismic layer data are determined and added to the seismic layer data.

[0099] Step S600: When the comprehensive similarity is less than the set threshold, the coring depth of the next station is determined based on the seismic layer data, and the drilling coring is performed and the seismic layer data is iteratively updated;

[0100] Step S700: Output seismic layer data.

[0101] Specifically, the comprehensive similarity measures the correlation between seismic horizon data and geotechnical data obtained from coring. When the comprehensive similarity exceeds a set threshold, it means that the seismic horizon data is close to the data obtained from coring, and sampling of the stations along this survey line can be terminated. When the comprehensive similarity is less than the set threshold, it is necessary to determine the coring depth of the next station based on the seismic horizon data and continue coring. The seismic horizon data is continuously iteratively updated based on the geotechnical data obtained from coring to improve the accuracy of the seismic horizon data.

[0102] In this embodiment, after the first station (F16) has been drilled and cored, the updated seismic layer data (i.e., the updated stratigraphic interpretation) after the previous coring should be fully considered when designing the coring depth of the second station (F21). Based on the coring results of the second station (F21), the seismic layer data is updated again in the same manner as in step S500. Figure 10 As shown, at a new station (F21), taking the first layer (Hor. 10) as an example, the seismic prediction is 6.2 meters, and the measured geotechnical depth is 5.7 meters, with a similarity of 91%. Because the initial stratigraphic interpretation was revised at the first station, the accuracy of the seismic prediction has been significantly improved. The combined similarity of the five layers is 96.8%. This continues until the Nth station is cored. When the combined similarity exceeds the preset threshold, sampling at that station on this survey line ends.

[0103] like Figure 11 As shown in the figure, at the third station (F19), the seismic prediction for the first layer (Hor. 10) is 6.2 meters, while the actual rock and soil measurement is 6.1 meters, resulting in a similarity of 98% and an overall similarity (accuracy) of 97.3%. This exceeds the preset threshold of 97.0%, and sampling for this station on the survey line is complete. The obtained seismic horizon data is accurate stratigraphic data.

[0104] In principle, drilling sampling stations are located at wind turbine locations. In this embodiment, while traditional methods require drilling sampling at six pre-set wind turbine locations for geotechnical investigation, this embodiment only requires drilling sampling at three wind turbine locations to meet the investigation requirements. This effectively reduces field investigation costs.

[0105] As described above, by employing full-layer phase tracking and updating effective seismic interpretation, deviations from automated seismic image interpretation can be minimized. Comparing field seismic geotechnical data with real-time stratigraphic interpretation not only improves the accuracy of existing automated seismic horizon tracking but also enhances its practicality. Compared to traditional methods, this method enhances the reliability and accuracy of geological survey data and can be applied to a wider range of scenarios. It can accurately interpret seismic phases, providing accurate, reasonable, and reliable seismic phase layer details and overall trends. Furthermore, it helps transform existing geotechnical operations: from pre-designed site locations to on-site site location decisions, reducing drilling locations and ultimately reducing costs and increasing efficiency in offshore wind exploration.

[0106] Exemplary Systems

[0107] like Figure 12 As shown, corresponding to the above-mentioned method for automatically generating sea breeze geological modeling layers based on image recognition, an embodiment of the present invention further provides a system for automatically generating sea breeze geological modeling layers based on image recognition, and the above-mentioned system for automatically generating sea breeze geological modeling layers based on image recognition includes:

[0108] Seismic image module 600, used to conduct engineering geophysical surveys along the wind turbine location to obtain seismic images;

[0109] A seismic horizon module 610 is configured to obtain seismic horizon data based on the seismic image;

[0110] A geotechnical data module 620 is configured to determine a coring depth based on the seismic horizon data and perform coring drilling to obtain geotechnical data;

[0111] A comprehensive similarity module 630 is used to compare the depth of each stratum in the seismic horizon data and the geotechnical data to obtain the similarity of each stratum and obtain a comprehensive similarity based on the similarities of all strata;

[0112] An updating module 640 is configured to update the seismic horizon data according to the geotechnical data based on the consistency of the seismic events;

[0113] Comparison module 650, configured to determine the coring depth of the next station according to the seismic horizon data, perform coring and iteratively update the seismic horizon data when the comprehensive similarity is less than a set threshold;

[0114] The result module 660 is used to output the seismic layer data.

[0115] Specifically, the implementation architecture of the automatic generation system of sea breeze geological modeling layers in this embodiment is as follows: Figure 13 As shown in the figure, it mainly includes: data layer, function layer and display layer. The data layer is used to store seismic data and geotechnical data, including raw database, processing database and relational database. The raw database stores shallow profile, single-channel and multi-channel high-resolution BOOMER, electric spark and seismic data (hereinafter referred to as seismic data) from engineering geophysical surveys, and coring, field testing and CPT data (hereinafter referred to as geotechnical data) from geotechnical engineering surveys; the processing database is used to store processed seismic data (such as updated seismic horizon data); and the relational database is used to store correlation data (such as similarity and comprehensive similarity) established based on seismic data and geotechnical data.

[0116] The functional layer primarily includes functions such as image processing, image recognition, phase tracking, stratigraphic interpretation, and seismic and geotechnical data comparison. The seismic image module 600 implements image processing, the seismic horizon module 610 implements image recognition, phase tracking, and stratigraphic interpretation, the comprehensive similarity module 630 and the update module 640 implement seismic and geotechnical data comparison, and the geotechnical data module 620 processes measured geotechnical engineering data. The functional layer also includes data interaction functions for interacting with the data and display layers, such as real-time data refresh, real-time data access, and relational data access.

[0117] The display layer is used to display the image processing process, seismic layers, rock and soil layers, the joint display of seismic and rock and soil, and the stratigraphic interpretation display.

[0118] It should be noted that stratigraphic interpretation is required both before and during geotechnical investigations. Before geotechnical data is available, stratigraphic division is primarily based on seismic characteristics, including tracking segment length, angle, continuity, and repeatability. Correlation analysis of seismic and geotechnical data of the functional layer is reflected in the implementation of geotechnical operations. After obtaining geotechnical data, the functional layer will modify and update the previous seismic prediction layer in real time based on the geotechnical data and establish iterations. After field acquisition at each station is completed, the on-site geotechnical engineer will input the measured results into the data layer, establish or modify the relational database in a human-computer interactive manner, and set the layer that needs to be modified. Based on the principle of proximity, the automatic tracking segment closest to the measured geotechnical layer is set as the new stratigraphic layer marker, and the stratigraphic layer interpretation and prediction accuracy are updated in real time. When the newly established correlation accuracy of the relational database is greater than the preset threshold, no new geotechnical sampling will be performed within this survey line.

[0119] Specifically, in this embodiment, the specific functions of each module of the above-mentioned sea breeze geological modeling layer automatic generation system based on image recognition can refer to the corresponding description in the above-mentioned sea breeze geological modeling layer automatic generation method based on image recognition, and will not be repeated here.

[0120] Based on the above embodiment, the present invention also provides an intelligent terminal, whose principle block diagram can be shown as follows: Figure 14 As shown. The above-mentioned intelligent terminal includes a processor, a memory, a network interface and a display screen connected via a system bus. The processor of the intelligent terminal is used to provide computing and control capabilities. The memory of the intelligent terminal includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a program for automatically generating sea breeze geological modeling layers based on image recognition. The internal memory provides an environment for the operation of the operating system and the program for automatically generating sea breeze geological modeling layers based on image recognition in the non-volatile storage medium. The network interface of the intelligent terminal is used to communicate with an external terminal via a network connection. When the program for automatically generating sea breeze geological modeling layers based on image recognition is executed by the processor, the steps of any one of the above-mentioned methods for automatically generating sea breeze geological modeling layers based on image recognition are implemented. The display screen of the intelligent terminal can be a liquid crystal display screen or an electronic ink display screen.

[0121] Those skilled in the art will understand that Figure 14 The principle block diagram shown in the figure is only a block diagram of a partial structure related to the solution of the present invention and does not constitute a limitation on the smart terminal to which the solution of the present invention is applied. The specific smart terminal may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0122] In one embodiment, a smart terminal is provided. The smart terminal includes a memory, a processor, and an image recognition-based automatic generation program for sea breeze geological modeling layers, which is stored in the memory and can be run on the processor. When the image recognition-based automatic generation program for sea breeze geological modeling layers is executed by the processor, the following operating instructions are performed:

[0123] Conduct engineering geophysical surveys along the wind turbine locations to obtain seismic images;

[0124] Based on the seismic image, obtaining seismic horizon data;

[0125] Determine the coring depth based on the seismic horizon data and perform core drilling to obtain geotechnical data;

[0126] Comparing the seismic horizon data and the stratigraphic depth of each stratigraphic layer in the geotechnical data to obtain the similarity of each stratigraphic layer, and obtaining a comprehensive similarity based on the similarities of all stratigraphic layers;

[0127] Based on the consistency of the seismic phase axis, the seismic layer data is updated according to the geotechnical data;

[0128] When the comprehensive similarity is less than a set threshold, the coring depth of the next station is determined according to the seismic horizon data, and the coring is carried out and the seismic horizon data is iteratively updated;

[0129] The seismic layer data is output.

[0130] Optionally, obtaining seismic horizon data based on the seismic image includes:

[0131] obtaining a plurality of stratigraphic boundary points according to the seismic image;

[0132] Based on the seismic phase similarity and continuity, seismic horizon data are obtained according to the stratigraphic boundary points.

[0133] Optionally, obtaining seismic horizon data according to the stratigraphic boundary points based on seismic phase similarity and continuity includes:

[0134] Generate a number of automatic tracking line segments corresponding to the stratum depth according to all stratum boundary points tracked at each stratum depth;

[0135] The automatically traced line segments of all stratum depths constitute the seismic horizon data.

[0136] Optionally, obtaining a plurality of stratigraphic boundary points according to the seismic image includes:

[0137] Based on a preset sub-image size, dividing the seismic image into a plurality of sub-images;

[0138] Screening all sub-images at each depth to obtain a number of sub-images containing stratum boundary points, and setting the stratum boundary points as seed points;

[0139] Taking the sub-image where the seed point is located as the center, searching for stratum boundary points in a first preset number of sub-images in adjacent channels;

[0140] When a stratum boundary point is found in an adjacent trace, the stratum boundary point is set as a seed point and a cyclic search is performed;

[0141] When no stratum boundary point is found in the adjacent trace, the next adjacent trace is searched until the second preset number of adjacent traces are searched.

[0142] Optionally, the method of screening all sub-images at each depth to obtain a number of sub-images containing stratum boundary points includes:

[0143] The grayscale value of each pixel in the sub-image is compared with the preset pixel value, and the number of pixels whose grayscale value exceeds the preset pixel value is counted. When the number of pixels exceeds the preset threshold, the pixel with the lowest grayscale value in the sub-image is set as the stratum dividing point.

[0144] Optionally, updating the seismic horizon data according to the geotechnical data based on the consistency of seismic events includes:

[0145] Obtaining seismic events near each stratum in the seismic horizon data and the geotechnical data;

[0146] The seismic events of the geotechnical data of each stratum are compared with the seismic events of the seismic layer data. If the seismic events are inconsistent, the seismic layer data are updated according to the geotechnical data.

[0147] Optionally, the number of strata in the geotechnical data is different from the number of strata in the seismic horizon data, further comprising:

[0148] The strata of the geotechnical data and the strata of the seismic horizon data are compared to obtain the missing strata in the seismic horizon data, and then the missing strata are added to the seismic horizon data.

[0149] An embodiment of the present invention also provides a computer-readable storage medium, on which is stored a program for automatically generating sea breeze geological modeling layers based on image recognition. When the program for automatically generating sea breeze geological modeling layers based on image recognition is executed by a processor, the steps of any one of the methods for automatically generating sea breeze geological modeling layers based on image recognition provided in an embodiment of the present invention are implemented.

[0150] It should be understood that the sequence numbers of the steps in the above embodiments do not imply a specific order of execution; the order of execution of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0151] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the above-mentioned device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated into one processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of the present invention. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0152] In the above embodiments, the description of each embodiment has its own focus. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant description of other embodiments.

[0153] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians may use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present invention.

[0154] In the embodiments provided by the present invention, it should be understood that the disclosed apparatus / terminal device and method can be implemented in other ways. For example, the apparatus / terminal device embodiments described above are merely illustrative. For example, the division of the modules or units described above is merely a logical functional division. In actual implementation, other division methods may be used. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not implemented.

[0155] If the above-mentioned integrated module / unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present invention implements all or part of the process in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The above-mentioned computer program can be stored in a computer-readable storage medium. When the computer program is executed by the processor, it can implement the steps of the above-mentioned various method embodiments. Among them, the above-mentioned computer program includes computer program code, and the above-mentioned computer program code can be in source code form, object code form, executable file or some intermediate form. The above-mentioned computer-readable medium may include: any entity or device capable of carrying the above-mentioned computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal and software distribution medium. It should be noted that the content contained in the above-mentioned computer-readable storage medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction.

[0156] The embodiments described above are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, it should be understood by those skilled in the art that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features thereof may be replaced by equivalents. However, these modifications or replacements do not deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included in the scope of protection of the present invention.

Claims

1. A method for automatically generating sea breeze geological modeling horizons based on image recognition, characterized in that: The method comprises: Conduct engineering geophysical surveys along the wind turbine locations to obtain seismic images; Based on the seismic image, obtaining seismic horizon data; Determine the coring depth based on the seismic horizon data and perform core drilling to obtain geotechnical data; Comparing the seismic horizon data and the stratigraphic depth of each stratigraphic layer in the geotechnical data to obtain the similarity of each stratigraphic layer, and obtaining a comprehensive similarity based on the similarities of all stratigraphic layers; Based on the consistency of the seismic phase axis, the seismic layer data is updated according to the geotechnical data; When the comprehensive similarity is less than a set threshold, the coring depth of the next station is determined according to the seismic horizon data, and the coring is carried out and the seismic horizon data is iteratively updated; outputting the seismic horizon data; The step of obtaining seismic horizon data based on the seismic image comprises: obtaining a plurality of stratigraphic boundary points according to the seismic image; Based on the seismic phase similarity and continuity, seismic horizon data are obtained according to the stratigraphic boundary points; The step of obtaining a plurality of stratigraphic boundary points according to the seismic image comprises: Based on a preset sub-image size, dividing the seismic image into a plurality of sub-images; Screening all sub-images at each depth to obtain a number of sub-images containing stratum boundary points, and setting the stratum boundary points as seed points; Taking the sub-image where the seed point is located as the center, searching for stratum boundary points in a first preset number of sub-images in adjacent channels; When a stratum boundary point is found in an adjacent trace, the stratum boundary point is set as a seed point and a cyclic search is performed; When no stratum boundary point is found in the adjacent trace, the next adjacent trace is searched until the second preset number of adjacent traces are searched.

2. The method for automatically generating sea breeze geological modeling horizons based on image recognition according to claim 1, wherein: The method of obtaining seismic horizon data based on the stratigraphic boundary points based on seismic phase similarity and continuity includes: Generate a number of automatic tracking line segments corresponding to the stratum depth according to all stratum boundary points tracked at each stratum depth; The automatically traced line segments of all stratum depths constitute the seismic horizon data.

3. The method for automatically generating sea breeze geological modeling horizons based on image recognition according to claim 1, wherein: The method of screening all sub-images at each depth to obtain a number of sub-images containing stratum boundary points includes: The grayscale value of each pixel in the sub-image is compared with the preset pixel value, and the number of pixels whose grayscale value exceeds the preset pixel value is counted. When the number of pixels exceeds the preset threshold, the pixel with the lowest grayscale value in the sub-image is set as the stratum dividing point.

4. The method for automatically generating sea breeze geological modeling horizons based on image recognition according to claim 1, wherein: The updating of the seismic horizon data according to the geotechnical data based on the consistency of the seismic events includes: Obtaining seismic events near each stratum in the seismic horizon data and the geotechnical data; The seismic events of the geotechnical data of each stratum are compared with the seismic events of the seismic layer data. If the seismic events are inconsistent, the seismic layer data are updated according to the geotechnical data.

5. The method for automatically generating sea breeze geological modeling horizons based on image recognition according to claim 4, wherein: The number of strata in the geotechnical data is different from the number of strata in the seismic horizon data, and further includes: The strata of the geotechnical data and the strata of the seismic horizon data are compared to obtain the missing strata in the seismic horizon data, and then the missing strata are added to the seismic horizon data.

6. The automatic generation system of sea breeze geological modeling horizon based on image recognition is characterized by: The system is used to implement the steps of the method for automatically generating sea breeze geological modeling layers based on image recognition according to any one of claims 1 to 5, and the system includes: Seismic imaging module, used to conduct engineering geophysical surveys along the wind turbine locations and obtain seismic images; A seismic horizon module, configured to obtain seismic horizon data based on the seismic image; A geotechnical data module is used to determine the coring depth according to the seismic horizon data and to perform core drilling to obtain geotechnical data; a comprehensive similarity module, for comparing the seismic horizon data and the stratigraphic depth of each stratigraphic layer in the geotechnical data, obtaining the similarity of each stratigraphic layer, and obtaining a comprehensive similarity based on the similarities of all stratigraphic layers; An updating module, configured to update the seismic horizon data according to the geotechnical data based on the consistency of the seismic events; A comparison module, configured to determine a coring depth for a next station based on the seismic horizon data, perform coring drilling, and iteratively update the seismic horizon data when the comprehensive similarity is less than a set threshold; The result module is used to output the seismic layer data.

7. Intelligent terminal, characterized in that, The intelligent terminal includes a memory, a processor, and an image-recognition-based automatic generation program for sea breeze geological modeling layers, which is stored in the memory and can be run on the processor. When the image-recognition-based automatic generation program for sea breeze geological modeling layers is executed by the processor, the steps of the image-recognition-based automatic generation method for sea breeze geological modeling layers as described in any one of claims 1 to 5 are implemented.

8. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a program for automatically generating sea breeze geological modeling layers based on image recognition. When the program for automatically generating sea breeze geological modeling layers based on image recognition is executed by the processor, the steps of the method for automatically generating sea breeze geological modeling layers based on image recognition as described in any one of claims 1 to 5 are implemented.

Images