CN110208861B - Prediction method and device for constructing soft coal development area - Google Patents

Abstract

The present application provides a prediction method and device for constructing a soft coal development area, wherein the method includes: acquiring three-dimensional seismic data and logging curves in a research area; using an ant colony tracking algorithm to analyze the three-dimensional seismic data to obtain an ant data volume ;According to 3D seismic data and logging curve, perform seismic inversion to obtain logging data volume; extract the ant attribute value and logging attribute value of each target point in the target coal seam from the ant data volume and logging data volume respectively, and use the The ant attribute value corresponding to each target point is fused with the logging attribute value to obtain the fusion value of each target point in the target coal seam; at least one is divided on the plane of the target coal seam according to the relationship between the fusion value of each target point and the set threshold. The area is compared with the pre-obtained positions of structural soft coal, and then the development area of structural soft coal is determined from at least one area.

Description

A prediction method and device for structural soft coal development area

technical field

The present application relates to the technical field of geological exploration, and in particular, to a method and device for predicting the structure of a soft coal development area.

Background technique

Tectonic soft coal refers to coal that deforms under the action of tectonic stress, that is, under the action of different stress-strain environments and tectonic stress, the physical structure, chemical structure and optical characteristics of coal will change significantly, resulting in Different structural characteristics, different types of structural deformation coal. At this stage, there is still a lack of research on the prediction of tectonic soft coal development areas.

SUMMARY OF THE INVENTION

The purpose of the embodiments of the present application is to provide a method and device for predicting a structural soft coal development area, so as to predict the structural soft coal development area in an underground rock formation.

In a first aspect, an embodiment of the present application provides a prediction method for constructing a soft coal development area, including: acquiring 3D seismic data and logging curves in a study area; using an ant colony tracking algorithm to analyze the 3D seismic data to obtain Ant data body, the ant data body is a collection of ant attribute values at each position in the stratum of the study area, and the ant attribute value indicates whether there is a fault at the position; according to the three-dimensional seismic data and the logging curve Perform seismic inversion constrained by logging curves to obtain a logging data volume, which is a collection of logging attribute values at each location in the stratum of the study area; from the ant data volume and the logging data, respectively The ant attribute value and logging attribute value of each target point in the target coal seam are extracted from the body, and the ant attribute value corresponding to each target point is fused with the logging attribute value to obtain the fusion value of each target point in the target coal seam; The relationship between the fusion value of the target point and the set threshold value divides at least one area on the plane of the target coal seam, and compares the pre-obtained position of the existing structural soft coal with the position of the at least one area, and according to the comparison result From the at least one region, a development region of structural soft coal is determined.

The ant data volume can reflect the fracture structure in the underground rock strata. The inventors have analyzed multiple locations with structural soft coal revealed on the spot, and found that the structural soft coal is mostly located in the fault development or fault edge position, that is to say, the ant data It can reflect the development of structural soft coal to a certain extent, and the ant data volume and the logging data volume are integrated to predict the structural soft coal by combining the distribution of faults and the lithology changes shown by logging. It will be more accurate than the prediction results obtained from a single attribute value.

In an optional implementation manner of the first aspect, the logging curve includes a density curve and a natural gamma curve, and a seismic inversion constrained by the logging curve is performed according to the three-dimensional seismic data and the logging curve. performing a seismic inversion constrained by the density curve according to the three-dimensional seismic data and the density curve to obtain a density data volume, and, according to the three-dimensional seismic data and the natural gamma Perform seismic inversion constrained by the natural gamma curve to obtain a natural gamma data volume. The density data volume and the natural gamma data volume are a collection of density values at each location in the stratum of the study area, respectively. and the set of natural gamma values; the ant attribute value and logging attribute value of each target point in the target coal seam are extracted from the ant data body and the logging data body respectively, and the ant attribute value corresponding to each target point is combined with The logging attribute values are fused, including: extracting the ant attribute value, density value and natural gamma value of each target point in the target coal seam from the ant data volume, density data volume and natural gamma data volume, respectively. The ant attribute value, density value and natural gamma value corresponding to the point are fused.

Through experiments conducted by the inventor on the density data volume and the natural gamma data volume respectively, it is found that the density values of the multiple gas outburst points (that is, it can be considered that there is structural soft coal) disclosed in the research area are relatively large. Based on this finding, the target The density value of each target point of the coal seam is compared with the density distribution interval of structural soft coal, and it is found that the obtained prediction result matches the actual gas outburst point well, so the change of density is used as one of the indicators of structural soft coal prediction; On the other hand, it is also found that in the development area of tectonic soft coal, the natural gamma value of the rock at the top of the coal seam is low. Since natural gamma can indicate the sand-mud ratio of the rock layer, it can also indirectly indicate the development of structural soft coal. Therefore, combining the above two logging attributes for prediction, the accuracy of the prediction results is high.

In an optional implementation manner of the first aspect, before performing the seismic inversion constrained by the natural gamma curve according to the three-dimensional seismic data and the natural gamma curve, the method further includes: The natural gamma curve is smoothed.

After the natural gamma curve is smoothed, the distribution of thick sand and mud layers can be highlighted, and at the same time, the inversion speed can be improved.

In an optional implementation manner of the first aspect, performing seismic inversion constrained by the logging curve according to the three-dimensional seismic data and the well logging curve, includes: using a probabilistic neural network model to perform an analysis on the three-dimensional seismic data Seismic inversion of data and well log curves.

In an optional implementation manner of the first aspect, before using a probabilistic neural network model to perform seismic inversion on the three-dimensional seismic data and the logging curve, the method further includes: using the data of each borehole in the study area. The density curve and the natural gamma curve train and cross-validate the probabilistic neural network model to determine the parameters of the probabilistic neural network model.

In an optional implementation manner of the first aspect, the probabilistic neural network model is trained by using the density curve and natural gamma curve of each borehole in the study area, including: The probabilistic neural network model is trained on the conditional density curve and natural gamma curve, wherein the preset condition means that the degree of change of the curve is greater than the preset degree.

The curves with little change in the logging curves can be considered to not reflect the changes of formation lithology, and these curves do not need to participate in the training of the neural network model, so as to avoid negative effects on the prediction results.

In a second aspect, an embodiment of the present application provides a prediction device for constructing a soft coal development area, including: a data acquisition module for acquiring 3D seismic data and logging curves in the study area; a data processing module for using ant colonies The tracking algorithm analyzes the three-dimensional seismic data to obtain an ant data volume, and performs seismic inversion constrained by the logging curve according to the three-dimensional seismic data and the logging curve to obtain a logging data volume, wherein, The ant data body is a collection of ant attribute values at each position in the stratum of the study area, the ant attribute value indicates whether there is a fault at the position, and the logging data body is the ant attribute value at each position in the stratum of the study area. A collection of logging attribute values; a data fusion module, used to extract the ant attribute values and logging attribute values of each target point in the target coal seam from the ant data body and the logging data body respectively, and combine the ants corresponding to each target point. The attribute value and the logging attribute value are fused to obtain the fusion value of each target point of the target coal seam; the prediction module is used to divide at least one on the plane of the target coal seam according to the relationship between the fusion value of each target point and the set threshold value. area, comparing the pre-obtained location where structural soft coal exists with the location of the at least one area, and determining a development area of structural soft coal from the at least one area according to the comparison result.

In an optional implementation manner of the second aspect, the logging curve includes a density curve and a natural gamma curve, and the data processing module is specifically configured to: perform a calculation based on the three-dimensional seismic data and the density curve. The density curve is constrained seismic inversion to obtain a density data volume, and, according to the three-dimensional seismic data and the natural gamma curve, a seismic inversion constrained by the natural gamma curve is performed to obtain a natural gamma data volume, so The density data body and the natural gamma data body are respectively a set of density values and a set of natural gamma values at each position in the stratum of the study area; the data fusion module is specifically used for: respectively from the ant data body, The ant attribute value, density value and natural gamma value of each target point in the target coal seam are extracted from the density data body and natural gamma data body, and the ant attribute value, density value and natural gamma value corresponding to each target point are calculated. fusion.

In an optional implementation manner of the second aspect, the data processing module is further configured to: perform smoothing processing on the natural gamma curve.

In an optional implementation manner of the second aspect, the data processing module is specifically configured to: perform seismic inversion on the three-dimensional seismic data and the logging curve by using a probabilistic neural network model.

Description of drawings

In order to explain the technical solutions of the embodiments of the present application more clearly, the following briefly introduces the accompanying drawings that need to be used in the embodiments of the present application. It should be understood that the following drawings only show some embodiments of the present application, therefore It should not be regarded as a limitation of the scope. For those of ordinary skill in the art, other related drawings can also be obtained from these drawings without any creative effort.

1 is a flow chart of a method for predicting a structural soft coal development area provided by an embodiment of the application;

Fig. 2 is the plan view that reflects the fracture condition on the target coal seam obtained according to the ant data volume;

3 is a schematic diagram of a prediction device for constructing a soft coal development area provided by an embodiment of the application;

FIG. 4 is a schematic diagram of an electronic device according to an embodiment of the present application.

Detailed ways

The technical solutions in the embodiments of the present application will be described below with reference to the accompanying drawings in the embodiments of the present application.

Example

Structural soft coal is deformed coal in which the coal seam is broken or deformed with strong ductility and shrinkage under the action of tectonic stress. Its special physical and chemical structure determines its characteristics of high gas content and low permeability. Generally, coalbed methane is filled in the crushed voids of structural soft coal, so that coal mining areas with structural soft coal often become dangerous areas of gas outburst, which may endanger the mining safety of mines. In view of this, the embodiment of the present application provides a prediction method for constructing a soft coal development area, which can provide guidance for practical application scenarios such as gas outburst prediction in mines and coalbed methane exploration and development. Referring to FIG. 1 , the method includes the following steps:

Step 101: Acquire 3D seismic data and logging curves in the study area.

Among them, the study area is the geographical area where this method will be implemented to predict the development area of structural soft coal, and the three-dimensional seismic data is the processed seismic data (such as post-stack migration data, Pre-stack time migration data, etc.), the logging curve is the curve formed by the geophysical parameters of the rock formation measured by the logging equipment during the drilling process, reflecting the logging characteristics of different lithologies and different horizons. In this implementation In an example, at least one of a density curve and a natural gamma curve can be selected for the logging curve. Of course, other types of logging curves can also be used for prediction.

Step 102 : using the ant colony tracking algorithm to analyze the three-dimensional seismic data to obtain the ant data volume.

The ant data volume is a collection of ant attribute values at each location in the underground rock formation in the study area. The meaning of each ant attribute value is whether there is a fault at the location, which means that the use of three-dimensional ant data volume can reflect the entire research. Faults and fissures in the subsurface of the region.

The ant colony tracking algorithm simulates the behavior of natural ant colonies to mark the crawling trajectory in order to optimize the search path for food, and put the ants into the seismic data volume formed by the three-dimensional seismic data to search for possible underground faults. The fracture information is captured in the data volume to form a fracture response describing the situation of the underground fault, that is, the ant data volume. The basic principle of the algorithm is: spread a large number of ants in the seismic data volume, when some ants find the fracture traces that meet the preset fracture conditions, they will release a certain signal (which can be understood as pheromone), and call ants in other areas to concentrate It is tracked at the fracture until the tracking and identification of the fracture is completed, and other positions that do not meet the preset fracture conditions will not be marked and signaled, and finally an ant data body with clear fracture traces will be formed. As shown in Figure 2, Figure 2 shows a plan view of the target coal seam extracted from the ant data volume along the target coal seam, which reflects the fracture situation on the target coal seam. From the plan view, the distribution of the faults on the target coal seam can be clearly seen. The depth indicates the severity of the failure of the coal seam fault.

The reason for the formation of structural soft coal is the fracture of the coal seam, which causes the original primary coal to be destroyed to form structural soft coal, and because the broken space of the structural soft coal is filled with coalbed methane, gas outburst is very likely to occur, so it can be determined according to whether there is gas outburst. The phenomenon distinguishes primary coal and structural soft coal, that is to say, when a gas outburst point is found at a certain position during the mining process, it can be considered that structural soft coal exists at this point. The inventor's research found that most of the gas outbursts in a certain study area are located in the fault development or fault edge position. It can be seen that the distribution of faults and fractures can indicate the damage position of the stress concentration to the coal seam. Therefore, it can be considered that the distribution of faults is related to the fault distribution. There is a certain relationship between the development of structural soft coal. Therefore, faults can be used as one of the prediction indicators when predicting structural soft coal, and the ant data volume can be used to explain the distribution of underground faults. Therefore, the ant data volume can be used for structural soft coal. coal forecast.

Step 103 : perform seismic inversion constrained by the logging curve according to the three-dimensional seismic data and the logging curve to obtain a logging data volume.

The logging data volume represents a three-dimensional set of logging attribute values at each position in the stratum of the study area. When the logging curve is a density curve and/or a natural gamma curve, the obtained logging data volume corresponds to the density data. volume and/or natural gamma data volume, and the following specifically takes the density data volume and the natural gamma data volume as examples for description.

There are many ways of seismic inversion, including but not limited to recursive inversion, sparse pulse inversion, feature inversion, neural network inversion, etc., and how to perform it according to 3D seismic data and logging curves. For inversion, reference may be made to the prior art, which will not be described here. In this embodiment, a probabilistic neural network (Probabilistic Neural Network, PNN) model may be used for seismic inversion. Before inversion, the probabilistic neural network model is trained and cross-validated by using the density curve and natural gamma curve of each borehole in the study area to determine the parameters of the probabilistic neural network model (including learning parameters and hyperparameters). It should be noted that the density curve and natural gamma curve participating in the training should meet certain conditions, that is, the degree of change of the curve should be greater than the preset degree. It can be considered that these curves do not reflect the changes in formation lithology, so they are not allowed to participate in the training of the neural network model, so as to avoid negative effects on the prediction results.

Prior to this, the inventor conducted long-term experiments on the density data volume and the natural gamma data volume respectively, extracted the target coal seam level information from the obtained density data volume, and analyzed the target coal seam and its upper and lower 2ms inversion time windows. The variation of the average density value within the thickness range of the target coal seam (the arithmetic average of the density values within the thickness range centered on each target point on the target coal seam) is obtained, and the plane distribution of the target coal seam is obtained. The density values above are compared with the density variation range of tectonic soft coal. If the density value is within the density variation range of tectonic soft coal, it is considered that there is tectonic soft coal at this point. During a certain test, comparing the seven gas outburst points revealed in the study area, it was found that the density values of the seven gas outburst points were all relatively large (the density values were between 1.43-1.47g/ ^cm3 , while The density variation of the target coal seam is between 1.379-1.466g/cm ³ ), which indicates that the method of constructing soft coal prediction using the density value is feasible, and the final obtained prediction results match the actual gas outburst points. It is better, so in this embodiment, the change of density is used as one of the indicators for the prediction of structural soft coal. On the other hand, after researching the natural gamma data volume, the inventor found that in the development area of structural soft coal, the natural gamma value of the rock at the top of the coal seam is low, that is, the sandstone is relatively developed, and the natural gamma value of the rock formation is relatively low. The sand-mud ratio has an indicator function, and it can also indirectly indicate the development of structural soft coal. Combining the two logging attributes, density and natural gamma, can make predictions more accurate.

Step 104: Extract the ant attribute value and the logging attribute value of each target point in the target coal seam from the ant data body and the logging data body, respectively.

Step 105: Integrate the ant attribute value corresponding to each target point with the logging attribute value to obtain the fusion value of each target point in the target coal seam.

Extract attribute values along the coal seam from the three-dimensional ant data volume, density data volume and natural gamma data volume, and obtain the ant attribute value, density value and natural gamma value corresponding to each target point on the target coal seam, and further In this embodiment, a multi-information fusion algorithm is used to associate, correlate and integrate the three attribute values corresponding to each target point that reflect changes in structural soft coal according to certain conditions to form a new fusion value, which can reflect more accurately Changes in the structure of soft coal, and form the plane distribution of the target coal seam. Each target point on the plane distribution of the coal seam has a fusion value. Matching one by one, the development of structural soft coal can be reflected from the change of fusion value.

For the above-mentioned multi-information fusion algorithm, reference may be made to the implementation of the prior art, which will not be described here.

Step 106: According to the relationship between the fusion value of each target point and the set threshold, at least one area is divided on the plane of the target coal seam.

First, judge the relationship between the fusion value of each target point and the set threshold in turn. If the fusion value in a certain range is greater than the set threshold, the target points in this range are divided into the same area. If the fusion value within the range is not greater than the set threshold, the target points within this range are divided into another area. After the judgment of each target point on the target coal seam is completed, at least one can be divided on the plane of the target coal seam. area, the at least one area can be understood as defining the area formed by all target points greater than the set threshold as one area (this area may include multiple areas that are not continuous with each other), and all the areas not greater than the set threshold The area formed by the thresholded target points is defined as another area, that is, these two areas represent the developed area and the underdeveloped area of tectonic soft coal referred to below.

It should be noted that the variation range of the fusion value in different study areas may be different, so the above set thresholds need to be adjusted according to the actual geological conditions of the study area, so that the divided areas can be closer to the actual situation.

Step 107: Comparing the pre-obtained location where structural soft coal exists with the location of at least one area, and determining a development area of structural soft coal from the at least one area according to the comparison result.

At least one area divided on the target coal seam represents the actual geographic area in the study area, so the geographic location of each area can be compared with the geographic locations of multiple gas outburst points that have been discovered. If all gas outburst points are found are located in a certain area (or the ratio of the number of gas outburst points in a certain area to the total number of actual gas outburst points is found to be higher than a certain ratio, such as 80%), this area can be determined as a structure The development area of soft coal, and the other area is determined as the underdeveloped area of structural soft coal (indicating that this area is primary coal with better coal seam retention).

Optionally, after determining the development of tectonic soft coal represented by these two areas, the obtained prediction results can be visualized, that is, a color picture is formed, in which the development area of tectonic soft coal is displayed in a more obvious way. The color is highlighted, and the underdeveloped areas of structural soft coal are represented in another color, so that the prediction results can be reflected more intuitively.

The inventor applied the prediction method provided in this embodiment to make a field prediction in a certain research area, and compared the excavation data, and found that the prediction results match well with the actual three collapse columns and six faults, which proves that the accuracy of the prediction results is high. , and according to the prediction results reflected in the picture, it is found that the structural soft coal in the study area covers more than 3/4 of the entire study area and has a wide development range. It can be seen that the prediction method provided in this embodiment can accurately describe the distribution of structural soft coal, and based on the distribution of structural soft coal, it can also provide important theoretical and technical support for practical application scenarios such as mine gas outburst prediction and coalbed methane exploration and development.

Further, in an experiment, the entire inversion process was analyzed under the same computing power, and the inventor found that the density curve was less smooth during density inversion, and the inversion took 7 days. The reflection of coal seam is clear and can reflect sand bodies of about 3-5m. The inversion results have high reflection accuracy for thin layers, and can be used for small changes in the target coal seam and lithology changes in the near range of the coal seam roof; during natural gamma inversion, for The natural gamma curve has been smoothed, and the smoothed natural gamma curve has a certain degree of decline in the ability to identify thin layers, but highlights the distribution of thick sand and mud layers, and also brings about an improvement in the inversion speed. The inversion time used is shortened to 4 hours, so the method also includes a step of smoothing the gamma curve before using it for seismic inversion.

It should be noted that this embodiment is based on the analysis of the reasons for the formation of structural soft coal, and uses the distribution of faults to reflect structural soft coal. However, if only the ant data volume is used for prediction, then if there is no fault at a certain position Therefore, it is impossible to accurately judge whether there is structural soft coal at the location, and even if there is a fault at a certain position, it is impossible to accurately determine which area of the structural soft coal is located within the fault range. The embodiment provides a multi-attribute fusion prediction scheme, and at the same time uses the distribution of faults, changes in density and natural gamma to reflect the development of structural soft coal, and because the fusion value cannot be unified with structural soft coal. For comparison, in this embodiment, the change of the fusion value is also used to match the actual gas outburst points, so as to determine the development area of structural soft coal.

It should also be noted that, due to the application of 3D seismic data in the above scheme, compared with coal samples, boreholes, logging and other data that can only represent a point or a line, 3D seismic data volume can improve the accuracy of lateral prediction. , and the distribution of structural soft coal in a certain area away from the borehole (or in the unexposed area of the coal seam) can also be accurately predicted.

Based on the same inventive concept, the embodiment of the present application also provides a prediction device for constructing a soft coal development area. Referring to FIG. 3 , the device includes:

The data acquisition module 201 is used for acquiring 3D seismic data and logging curves in the study area;

The data processing module 202 is used to analyze the three-dimensional seismic data by using the ant colony tracking algorithm to obtain the ant data volume, and to perform seismic inversion constrained by the logging curve according to the three-dimensional seismic data and the logging curve to obtain the logging data The ant data body is the set of ant attribute values at each position in the stratum of the study area, the ant attribute value indicates whether there is a fault at the position, and the logging data body is the logging data at each position in the stratum of the study area. A collection of attribute values;

The data fusion module 203 is used to extract the ant attribute value and logging attribute value of each target point in the target coal seam from the ant data body and the logging data body respectively, and combine the ant attribute value and logging attribute corresponding to each target point. The fusion value of each target point of the target coal seam is obtained;

The prediction module 204 is configured to divide at least one area on the plane of the target coal seam according to the relationship between the fusion value of each target point and the set threshold value, and compare the pre-obtained position of the existing structural soft coal with the position of the at least one area, And according to the comparison result, the development area of structural soft coal is determined from at least one area.

Optionally, the logging curve includes a density curve and a natural gamma curve, and the data processing module 202 is specifically configured to: perform seismic inversion constrained by the density curve according to the three-dimensional seismic data and the density curve to obtain a density data volume, and, according to the The 3D seismic data and natural gamma curve are subjected to seismic inversion constrained by the natural gamma curve to obtain a natural gamma data volume. The density data volume and the natural gamma data volume are the density values at each location in the stratum of the study area The data fusion module 203 is specifically used for: extracting the ant attribute value, density value and natural gamma value of each target point in the target coal seam from the ant data body, density data body and natural gamma data body respectively. Gamma value, and fuse the ant attribute value, density value and natural gamma value corresponding to each target point.

Optionally, the data processing module 202 is further configured to: smooth the natural gamma curve.

Optionally, the data processing module 202 is specifically configured to: use a probabilistic neural network model to perform seismic inversion on the three-dimensional seismic data and logging curves.

The basic principle and the technical effect produced by the above-mentioned prediction device for constructing a soft coal development area are the same as those of the previous method embodiment. The corresponding content will not be repeated here.

Referring to FIG. 4, this embodiment provides an electronic device 300, including a processor 301 and a memory 302. The memory 302 stores at least one instruction, at least one program, code set or instruction set, at least one instruction, at least one program, The code set or instruction set is loaded and executed by the processor 301 to implement the prediction method for constructing a soft coal development area provided by the above embodiments. The electronic device 300 may further include a communication interface 303 and a communication bus 304 , wherein the processor 301 , the memory 302 and the communication interface 303 communicate with each other through the communication bus 304 .

Memory 302 may include high-speed random access memory (as a cache), and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other volatile solid state storage device. Communication bus 304 is a circuit that connects the described elements and enables transmission between the elements. For example, the processor 301 receives commands from other elements through the communication bus 304, decodes the received commands, and performs computation or data processing according to the decoded commands. The communication interface 303 connects the electronic device 300 with other network devices, user equipment, and networks. For example, the communication interface 303 may be wired or wirelessly connected to a network to connect to external other network devices or user equipment. Wireless communication may include at least one of the following: WIFI, Bluetooth, cellular communication, Global System for Mobile communication (GSM), etc., and wired communication may include at least one of the following: Universal Serial Bus (Universal Serial Bus, USB), High Definition Multimedia Interface (High Definition Multimedia Interface, HDMI), asynchronous transmission standard interface (Recommended Standard232, RS-232) and so on.

In the embodiments provided in this application, it should be understood that the disclosed apparatus and method may be implemented in other manners. The apparatus embodiments described above are only illustrative. For example, the division of the units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components may be combined or Can be integrated into another system, or some features can be ignored, or not implemented. On the other hand, the shown or discussed mutual coupling or direct coupling or communication connection may be through some communication interfaces, indirect coupling or communication connection of devices or units, which may be in electrical, mechanical or other forms.

In addition, units described as separate components may or may not be physically separated, and components shown as units may or may not be physical units, that is, may be located in one place, or may be distributed to multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution in this embodiment.

Furthermore, each functional module in each embodiment of the present application may be integrated together to form an independent part, or each module may exist alone, or two or more modules may be integrated to form an independent part.

It should be noted that, if the functions are implemented in the form of software function modules and sold or used as independent products, they may be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application or part of the technical solution can be embodied in the form of a software product, and the software product is stored in a storage medium and includes several instructions to make a computer device (which may be a personal computer) , server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, Read-Only Memory (ROM), Random Access Memory (RAM), magnetic disk or optical disk and other media that can store program codes.

In this document, relational terms such as first and second, etc. are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such existence between these entities or operations. The actual relationship or sequence.

The above descriptions are merely examples of the present application, and are not intended to limit the protection scope of the present application. For those skilled in the art, various modifications and changes may be made to the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of this application shall be included within the protection scope of this application.

Claims (8)

1. A prediction method for constructing a soft coal development zone, comprising:

acquiring three-dimensional seismic data and a logging curve in a research area;

analyzing the three-dimensional seismic data by using an ant colony tracking algorithm to obtain an ant data body, wherein the ant data body is a set of ant attribute values at each position in the stratum of the research area, and the ant attribute values represent whether faults exist at the position;

performing seismic inversion with the logging curve as constraint according to the three-dimensional seismic data and the logging curve to obtain a logging data volume, wherein the logging data volume is a set of logging attribute values at each position in the stratum of the research area;

extracting ant attribute values and well logging attribute values of all target points in the target coal bed from the ant data body and the well logging data body respectively, and fusing the ant attribute values and the well logging attribute values corresponding to all the target points to obtain fused values of all the target points of the target coal bed;

dividing at least one region on the plane of the target coal bed according to the relation between the fusion value of each target point and a set threshold value, comparing the position where the constructed soft coal exists, which is obtained in advance, with the position of the at least one region, and determining a development region for constructing the soft coal from the at least one region according to the comparison result;

the logging curve comprises a density curve and a natural gamma curve, seismic inversion with the logging curve as constraint is carried out according to the three-dimensional seismic data and the logging curve, and a logging data body is obtained, and the method comprises the following steps:

performing seismic inversion with a density curve as constraint according to the three-dimensional seismic data and the density curve to obtain a density data volume, and performing seismic inversion with a natural gamma curve as constraint according to the three-dimensional seismic data and the natural gamma curve to obtain a natural gamma data volume, wherein the density data volume and the natural gamma data volume are respectively a set of density values and a set of natural gamma values at each position in a stratum of a research area;

the method for extracting the ant attribute values and the logging attribute values of all target points in the target coal seam from the ant data body and the logging data body respectively and fusing the ant attribute values and the logging attribute values corresponding to all the target points comprises the following steps:

and extracting ant attribute values, density values and natural gamma values of all target points in the target coal bed from the ant data volume, the density data volume and the natural gamma data volume respectively, and fusing the ant attribute values, the density values and the natural gamma values corresponding to all the target points.

2. The method of claim 1, wherein prior to performing natural gamma curve-constrained seismic inversion from the three-dimensional seismic data and the natural gamma curve, the method further comprises:

and smoothing the natural gamma curve.

3. The method of claim 1, wherein performing a log-constrained seismic inversion from the three-dimensional seismic data and the log comprises:

and performing seismic inversion on the three-dimensional seismic data and the logging curve by utilizing a probabilistic neural network model.

4. The method of claim 3, wherein prior to performing seismic inversion on the three-dimensional seismic data and well logs using a probabilistic neural network model, the method further comprises:

and training and cross-verifying the probabilistic neural network model by using the density curve and the natural gamma curve of each drill hole in the research area to determine the parameters of the probabilistic neural network model.

5. The method of claim 4, wherein training the probabilistic neural network model using the density curve and the natural gamma curve for each borehole in the region of interest comprises:

and training the probabilistic neural network model by using a density curve and a natural gamma curve of each drill hole in the research area, wherein the density curve and the natural gamma curve meet preset conditions, and the preset conditions mean that the change degree of the curves is greater than the preset degree.

6. A prediction apparatus for constructing a soft coal development zone, comprising:

the data acquisition module is used for acquiring three-dimensional seismic data and a logging curve in a research area;

the data processing module is used for analyzing the three-dimensional seismic data by utilizing an ant colony tracking algorithm to obtain an ant data body, and performing seismic inversion with a logging curve as a constraint according to the three-dimensional seismic data and the logging curve to obtain a logging data body, wherein the ant data body is a set of ant attribute values at each position in a stratum of a research area, the ant attribute values represent whether a fault exists at the position, and the logging data body is a set of logging attribute values at each position in the stratum of the research area;

the data fusion module is used for extracting ant attribute values and logging attribute values of all target points in the target coal seam from the ant data body and the logging data body respectively, and fusing the ant attribute values and the logging attribute values corresponding to all the target points to obtain fusion values of all the target points of the target coal seam;

the prediction module is used for dividing at least one region on the plane of the target coal bed according to the relation between the fusion value of each target point and a set threshold value, comparing the position where the constructed soft coal exists, which is obtained in advance, with the position of the at least one region, and determining a development region for constructing the soft coal from the at least one region according to the comparison result;

the logging curve comprises a density curve and a natural gamma curve, and the data processing module is specifically used for:

performing seismic inversion with a density curve as constraint according to the three-dimensional seismic data and the density curve to obtain a density data volume, and performing seismic inversion with a natural gamma curve as constraint according to the three-dimensional seismic data and the natural gamma curve to obtain a natural gamma data volume, wherein the density data volume and the natural gamma data volume are respectively a set of density values and a set of natural gamma values at each position in a stratum of a research area;

the data fusion module is specifically configured to: and extracting ant attribute values, density values and natural gamma values of all target points in the target coal bed from the ant data volume, the density data volume and the natural gamma data volume respectively, and fusing the ant attribute values, the density values and the natural gamma values corresponding to all the target points.

7. The apparatus of claim 6, wherein the data processing module is further configured to: and smoothing the natural gamma curve.

8. The apparatus of claim 6, wherein the data processing module is specifically configured to: and performing seismic inversion on the three-dimensional seismic data and the logging curve by utilizing a probabilistic neural network model.

Images