Geological stratification method and device for salt-gypsum strata

Abstract

The invention provides a salt-gypsum layer geological stratification method and device. The method comprises the steps that current well drilling information of a to-be-measured well is acquired; the obtained well drilling information is input into a salt-gypsum bed geological strata recognition model, a recognition result output by the salt-gypsum bed geological strata recognition model is obtained, and the recognition result is used for representing whether the current horizon of the well to be logged is the salt-gypsum bed geology or not; if the identification result represents that the geology of the salt-gypsum bed is not the geology of the salt-gypsum bed, searching the next horizon information of the horizon information corresponding to the identification result in the known horizon information of the adjacent well of the to-be-logged well; and if the next horizon information is the salt-gypsum layer geology, the time interval for obtaining the next drilling information of the well to be measured is gradually shortened. According to the method, the time interval for acquiring the drilling information next time is gradually shortened through the salt-gypsum bed geological strata identification model and the drilling information, and the salt-gypsum bed geological strata can be accurately and efficiently determined.

Description

Technical Field

[0001] The present application relates to the field of petroleum exploration technology, and in particular to a method and device for geologically blocking salt-gypsum layers. Background Art

[0002] Drilling deep wells (over 6,000 meters) into salt-gypsum formations presents numerous technical challenges, one of which is geologically stuck salt-gypsum formations. In some oilfields, drilling often faces untimely and inaccurate geologically stuck salt-gypsum formations, severely restricting drilling speed and safety.

[0003] In the geological layer identification of salt-gypsum layers, the following two methods are currently mainly used. Method 1: Predict the top, bottom and thickness of the gypsum-salt layer based on the seismic data of the area to be tested, and perform inversion prediction of the internal lithology of the gypsum-salt body, and finally realize the geological layer identification of the salt-gypsum layer in combination with the logging data. Method 2: Collect the first sampling rock cuttings at the first location of the extremely thick gypsum-salt rock to be tested, and detect the content of chemical elements contained in the first sampling rock cuttings; if the content of magnesium ions and chloride ions in the first sampling rock cuttings and the content of magnesium ions and chloride ions in the previous sampling rock cuttings meet the preset conditions, then calculate the first salt bottom index corresponding to the extremely thick gypsum-salt rock to be tested based on the content of chemical elements contained in the first sampling rock cuttings; determine the identification layer of the salt bottom of the extremely thick gypsum-salt rock based on the first salt bottom index.

[0004] However, when using the first method to identify the geological layer of the salt-gypsum layer, the inversion process requires subjective judgment by on-site experts, which carries the risk of misjudgment and reduces the accuracy of the geological layer identification of the salt-gypsum layer. The second method, which uses the changes in the magnesium and chloride ion content in the sampled cuttings and the first salt bottom index to determine the salt bottom of the thick gypsum salt rock, can improve the accuracy of the geological layer identification of the salt-gypsum layer. However, this method uses elemental logging technology, and the sampling of the cuttings requires a period of time for quantitative analysis. There is a certain time difference between the sampling of the cuttings and the cuttings at the bottom of the well, which leads to the delay of the geological layer identification of the salt-gypsum layer. Summary of the Invention

[0005] The purpose of the embodiments of the present application is to provide a method and device for geological layer identification of salt-gypsum layers to improve the accuracy and efficiency of geological layer identification of salt-gypsum layers.

[0006] To solve the above technical problems, the embodiments of the present application provide the following technical solutions:

[0007] In a first aspect, the present application provides a salt-gypsum layer geological layer identification method, the method comprising: obtaining current drilling information of a well to be logged; inputting the drilling information into a salt-gypsum layer geological layer identification model to obtain an identification result output by the salt-gypsum layer geological layer identification model, wherein the identification result is used to characterize whether the current layer position of the well to be logged is a salt-gypsum layer geology, wherein the salt-gypsum layer geological layer identification model is an error back propagation neural network model (BP Network) trained using drilling information and rock cuttings logging data corresponding to the well to be logged and the drilled portion of wells in the area where the well to be logged is located; if the identification result indicates that it is not a salt-gypsum layer geology, searching for the next layer information corresponding to the identification result in the known layer information of the neighboring wells of the well to be logged; if the next layer information is a salt-gypsum layer geology, gradually shortening the time interval for obtaining the next drilling information of the well to be logged.

[0008] Compared with the prior art, the salt-gypsum layer geological layer identification method provided in the first aspect of the present application is obtained by training the salt-gypsum layer geological layer identification model using known drilling information and rock cuttings logging data. Therefore, the salt-gypsum layer geological layer identification model can accurately identify whether the current drilling is to the salt-gypsum layer geology based on the current drilling information. In addition, drilling information such as the well number, wellbore parameters, and drilling parameters can be directly obtained during the drilling process without requiring excessive waiting time. Therefore, the efficiency of the salt-gypsum layer geological layer identification in deep wells can also be improved. And when it is determined that the current layer is not the salt-gypsum layer geology, when the next layer is determined to be the salt-gypsum layer geology through the stratigraphic information of the adjacent well, the time interval for obtaining the drilling information next time is gradually shortened to ensure that the drilling information can be obtained as soon as the salt-gypsum layer geology is entered, thereby achieving the salt-gypsum layer geological layer identification and improving the accuracy of the salt-gypsum layer geological layer identification in deep wells. In summary, the salt-gypsum layer geological layer identification method provided in the embodiment of the present application can achieve accurate and efficient determination of the salt-gypsum layer geological layer identification in deep wells.

[0009] In other embodiments provided in the present application, the error back propagation neural network model is a network structure with three hidden layers; before the drilling information is input into the salt-gypsum layer geological card layer identification model, the method also includes: obtaining drilling information and rock cuttings logging data corresponding to the well to be tested and the drilled part of the well in the area where the well to be tested is located; dividing the drilling information and rock cuttings logging data corresponding to the drilled part according to the formation lithology and the well body, and obtaining drilling information and rock cuttings logging data corresponding to different formation lithologies and different well bodies; deleting abnormal values ​​in the drilling information and rock cuttings logging data corresponding to different formation lithologies and different well bodies, and supplementing missing values ​​in the drilling information and rock cuttings logging data corresponding to different formation lithologies and different well bodies to obtain training data; using the drilling information in the training data as input type data and the rock cuttings logging data in the training data as output type data, training the error back propagation neural network model, and determining the model whose performance parameters after training are greater than the preset parameters as the salt-gypsum layer geological identification model.

[0010] The model uses three hidden layers, which can adapt to various dimensional training requirements without making the model too large, improving model accuracy and processing efficiency. Furthermore, during model training, the training data is divided according to stratum lithology, which improves the accuracy and efficiency of outlier detection in the training data and the precision of missing value supplementation. This in turn improves the efficiency and accuracy of training data preprocessing, thereby improving model accuracy and ultimately the accuracy of the geological layering of the salt-gypsum layer.

[0011] In other embodiments provided in the present application, obtaining drilling information and rock cuttings logging data corresponding to the drilled portion of the well to be logged and the wells in the area where the well to be logged is located includes: obtaining drilling information and rock cuttings logging data from the drilling logs, geological daily reports, drilling-while-drilling engineering parameters and logging data of the well to be logged and the wells in the area where the well to be logged is located; the method also includes: obtaining one or more of vertical pressure, casing pressure, resistivity, acoustic wave, gamma, element content logging data, and sidewall pickup data from the drilling logs, geological daily reports, drilling-while-drilling engineering parameters and logging data of the well to be logged and the wells in the area where the well to be logged is located, and the vertical pressure, casing pressure, resistivity, acoustic wave, gamma, element content logging data, and sidewall pickup data are used for model training.

[0012] The model's training data is obtained through drilling logs, daily geological reports, while-drilling engineering parameters, and logging data, enabling accurate and rapid acquisition of training data. Furthermore, the additional use of vertical pressure, casing pressure, resistivity, acoustic wave, gamma, element content logging data, and sidewall logging data in the training data enriches the training data, thereby improving model accuracy and ultimately enhancing the accuracy of geological logging of salt-gypsum layers.

[0013] In other embodiments provided in the present application, there are multiple adjacent wells, and the weight corresponding to the layer information of each adjacent well is negatively correlated with the distance between the corresponding adjacent well and the well to be measured; the next layer information of the layer information corresponding to the identification result is searched for in the known layer information of the adjacent wells of the well to be measured, including: searching for the next candidate layer information of the layer information corresponding to the identification result in the known layer information of each adjacent well of the well to be measured, weighting the candidate layer information corresponding to each adjacent well with the weight to obtain different candidate layer information and its corresponding coefficients; and determining the candidate layer information corresponding to the maximum coefficient as the next layer information.

[0014] By configuring a weight for each adjacent well and weighting the weights of all adjacent wells and the next layer information, the layer information with the highest weight is selected as the next layer information, thereby improving the accuracy of determining the next layer information of the well to be measured.

[0015] In other embodiments provided in the present application, after searching for the next layer information corresponding to the identification result in the known layer information of the adjacent wells of the well to be measured, the method also includes: if the next layer information is not salt-gypsum layer geology, extending the time interval for obtaining the next drilling information of the well to be measured.

[0016] When it is determined that the next layer of the well to be measured may not be a salt-gypsum layer, the data acquisition time interval is increased, the number of identification times of the salt-gypsum layer geological card layer is reduced, and the resource overhead of the salt-gypsum layer geological card layer identification model is reduced.

[0017] In other embodiments provided in the present application, the drilling information includes wellbore parameters and drilling parameters; the wellbore parameters include: well depth and well inclination; the drilling parameters include: hook load, torque, drilling speed, drilling pressure and rotation speed.

[0018] Well depth and inclination can simply and clearly characterize the wellbore parameters, and hook load, torque, drilling speed, drilling pressure and rotational speed can simply and clearly characterize the drilling parameters. Therefore, the input type data of the model can be obtained more quickly, and the model can be used to more quickly and accurately calculate whether the gypsum layer geology has been drilled, thereby improving the efficiency and accuracy of gypsum layer geological layer identification.

[0019] According to a second aspect of the present application, a salt-gypsum layer geological layer identification device is provided, which includes: an acquisition module for acquiring current drilling information of a well to be measured; a layer identification module for inputting the acquired drilling information into a salt-gypsum layer geological layer identification model to obtain an identification result output by the salt-gypsum layer geological layer identification model, wherein the identification result is used to characterize whether the current layer position of the well to be measured is a salt-gypsum layer geology, wherein the salt-gypsum layer geological layer identification model is an error back propagation neural network model trained using drilling information and rock cuttings logging data corresponding to the well to be measured and the drilled part of the well in the area where the well to be measured is located; a search module for searching for the next layer information corresponding to the layer information of the identification result in the known layer information of the adjacent wells of the well to be measured if the identification result indicates that it is not a salt-gypsum layer geology; and a processing module for shortening the time interval for acquiring the next drilling information of the well to be measured if the next layer information is a salt-gypsum layer geology.

[0020] A third aspect of the present application provides a computer device, comprising a memory, a processor, and a computer program stored in the memory, wherein the processor executes the computer program to implement the method in the first aspect.

[0021] A fourth aspect of the present application provides a computer-readable storage medium having a computer program stored thereon, which implements the method in the first aspect when executed by a processor.

[0022] A fifth aspect of the present application provides a computer program product, comprising a computer program, which implements the method in the first aspect when executed by a processor.

[0023] The salt-gypsum layer geological layer identification device provided in the second aspect, the computer equipment provided in the third aspect, the computer-readable storage medium provided in the fourth aspect, and the computer program product provided in the fifth aspect of this application have the same or similar beneficial effects as the salt-gypsum layer geological layer identification method provided in the first aspect. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] The above and other objects, features and advantages of the exemplary embodiments of the present application will become readily understood by reading the detailed description below with reference to the accompanying drawings. In the accompanying drawings, several embodiments of the present application are shown in an exemplary and non-limiting manner, and the same or corresponding reference numerals represent the same or corresponding parts, wherein:

[0025] Figure 1 The process diagram of the geological layer blocking method of the salt-gypsum layer in the embodiment of this application is as follows: Figure 1 ;

[0026] Figure 2 The process diagram of the geological layer blocking method of the salt-gypsum layer in the embodiment of this application is as follows: Figure 2 ;

[0027] Figure 3This is a schematic diagram of the model training in the embodiment of the present application;

[0028] Figure 4 This is a schematic diagram of determining the next layer information in an embodiment of the present application;

[0029] Figure 5 This is an example diagram of determining the next layer information in an embodiment of the present application;

[0030] Figure 6 This is an example diagram of the completion of the card layer operation in the embodiment of the present application;

[0031] Figure 7 This is a schematic diagram of the structure of the salt-gypsum layer geological layer device in the embodiment of this application. Figure 1 ;

[0032] Figure 8 This is a schematic diagram of the structure of the salt-gypsum layer geological layer device in the embodiment of this application. Figure 2 ;

[0033] Figure 9 Schematic diagram of the structure of the computer device in the embodiment of the present application. DETAILED DESCRIPTION

[0034] The following describes exemplary embodiments of the present application in more detail with reference to the accompanying drawings. Although exemplary embodiments of the present application are shown in the accompanying drawings, it should be understood that the present application can be implemented in various forms and should not be limited by the embodiments described herein. Instead, these embodiments are provided to enable a more thorough understanding of the present application and to fully convey the scope of the present application to those skilled in the art.

[0035] It should be noted that, unless otherwise specified, the technical or scientific terms used in this application should have the common meanings understood by those skilled in the art to which this application belongs.

[0036] Currently, deep-well drilling often encounters geological jams in gypsum layers. For these jams, predictions are made either through inversion using seismic data or through quantitative analysis of real-time rock cuttings sampling. However, seismic inversion prediction relies on subjective judgment, which can reduce the accuracy of deep-well salt-gypsum geological jams. Real-time rock cuttings sampling and quantitative analysis are time-consuming, reducing the real-time nature of deep-well salt-gypsum geological jams.

[0037] In view of this, the embodiments of the present application provide a salt-gypsum layer geological layer identification method, device, computer equipment, computer-readable storage medium and computer program product, which train the error back propagation neural network model through the drilled data of the well to be measured and other wells in the area to obtain a salt-gypsum layer geological layer identification model, thereby using the currently obtained drilling information such as well number, wellbore parameters and drilling parameters to determine whether the salt-gypsum layer geology is drilled through the salt-gypsum layer geological layer identification model, thereby achieving accurate determination of the salt-gypsum layer geological layer in deep wells without wasting more time, thereby improving the efficiency of salt-gypsum layer geological layer identification in deep wells.

[0038] It should be noted here that all components, data and related processing methods involved in this application are authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data comply with the relevant laws, regulations and standards of relevant countries and regions.

[0039] First, the salt-gypsum layer geological layer blocking method provided in the embodiment of the present application is described in detail.

[0040] Figure 1 The process diagram of the geological layer blocking method of the salt-gypsum layer in the embodiment of this application is as follows: Figure 1 , see Figure 1 As shown, the method may include:

[0041] S11: Obtain the current drilling information of the well to be tested.

[0042] In one possible implementation, the drilling information includes drilling parameters, where the drilling parameters include hook load, torque, drilling speed, drilling pressure and rotation speed, and may also include the geographical location information of the well to be measured, and further, may also include well depth and well inclination.

[0043] In another possible implementation, the drilling information includes the well number, wellbore parameters, and drilling parameters; wherein the well number is used to identify the area to which the well belongs and different wells in the same area. The well number here is specifically used to represent the geographic location information of the well to be measured, and the well number corresponding to the same geographic location information is unique.

[0044] Optionally, the well sign includes a first well sign identifier and a second well sign identifier, the first well sign identifier is used to identify the area to which the well belongs, and the second well sign identifier is used to identify different wells in the same area.

[0045] Specifically, the embodiment of the present application is described in detail by taking the drilling information including the well number, wellbore parameters and drilling parameters as an example.

[0046] The wells to be tested here are wells that are currently being drilled and require gypsum layer geological testing.

[0047] During the drilling process of the well to be tested, when geological logging of the gypsum layer is required, the well number, wellbore parameters, and drilling parameters can be obtained from the drilling data. The drilling data here can refer to the data recorded during the drilling design process. The well number, wellbore parameters, and drilling parameters can also be obtained directly from the field. Field acquisition here can refer to acquisition through various measuring devices both above and below the wellbore. For example, the well number can be acquired through a camera, wellbore parameters through wellbore sensors, and drilling parameters through drill pipe sensors. Of course, the well number, wellbore parameters, and drilling parameters can also be acquired using a combination of drilling data and field acquisition. This combined acquisition can mean acquiring them simultaneously and then selecting one, or acquiring them one at a time.

[0048] The well number here refers to the number of the well to be tested, which is determined according to the drilling project.

[0049] The wellbore parameters here refer to parameters related to the wellbore and are not specifically limited here.

[0050] The drilling parameters here refer to parameters related to the drilling process, and are not specifically limited here.

[0051] S12: Input the drilling information into the salt-gypsum layer geological card layer recognition model to obtain a recognition result output by the salt-gypsum layer geological card layer recognition model. The recognition result is used to characterize whether the current layer of the well to be measured is a salt-gypsum layer geology. The salt-gypsum layer geological card layer recognition model is an error back propagation neural network model trained using the drilling information and cuttings logging data corresponding to the well to be measured and the drilled part of the well in the area where the well to be measured is located.

[0052] Optionally, during specific training, an initial error back propagation neural network model is first constructed, and then the error back propagation neural network model is trained using drilling information corresponding to the well to be tested and the drilled portion of the well in the area where the well to be tested is located.

[0053] Optionally, when formally adopting the salt-gypsum geological layer identification model for gypsum geological layer identification, model training is required to obtain the salt-gypsum geological layer identification model. Specifically, during training, an initial error back-propagation neural network model is first constructed. The error back-propagation neural network model is then trained using well numbers, wellbore parameters, drilling parameters, and cuttings logging data corresponding to the well to be tested and the drilled portion of the well within the area where the well is located.

[0054] The cuttings logging data herein may refer to the analysis of cuttings carried by drilling fluid, analysis of cuttings sampled from the wellbore wall, or rock formation information obtained through detection wave analysis.

[0055] During training, each set of well numbers, wellbore parameters, drilling parameters, and cuttings logging data is considered a piece of training data. Multiple pieces of training data are divided into a training set, a test set, and a validation set according to preset ratios. The specific values ​​for these ratios can be determined based on actual needs and are not specified here. The well numbers, wellbore parameters, and drilling parameters in the training data serve as input data, while the cuttings logging data serves as output data, completing model training.

[0056] The currently acquired well number, wellbore parameters, and drilling parameters are input into the salt-gypsum layer geology identification model. Based on the well number, wellbore parameters, and drilling parameters, the model predicts whether the current formation is a gypsum layer. If the model predicts yes, the current drilling of the well under test is determined to have entered the gypsum layer, thus achieving a gypsum layer identification. If the model predicts no, the current drilling of the well under test has not yet entered the gypsum layer, and further drilling is required. The well number, wellbore parameters, and drilling parameters are then acquired to further identify the gypsum layer.

[0057] S13: Determine whether the identification result is characterized as salt-gypsum layer geology. If so, execute S14; if not, execute S15.

[0058] Since the identification results output by the salt-gypsum layer geology card layer identification model are generally yes or no, or information such as 0 or 1, when making a specific judgment, a pre-set correspondence relationship can be used to determine whether the identification result represents salt-gypsum geology. This correspondence relationship specifically includes each specific identification result and its corresponding information on whether it represents gypsum geology. For example, the correspondence relationship includes: 1 - gypsum geology, 0 - non-gypsum geology (or other specific geological layers). This allows for the determination of whether the identification result represents salt-gypsum geology.

[0059] S14: Determine whether the well to be tested has currently been drilled into the gypsum layer geology.

[0060] S15: Searching for the next layer information of the layer information corresponding to the identification result in the known layer information of the adjacent wells of the well to be measured.

[0061] Neighboring wells of a well to be tested can refer to the well or wells closest to the well to be tested, or the well or wells that are most similar to the well to be tested. This whole can include one or more of the following: well design, drill pipe parameters, and the production project involved.

[0062] For adjacent wells, the drilled sections contain stratigraphic information corresponding to different depths, known as known horizon information. This stratigraphic information, also known as horizon information, can also be obtained from the identification results. The identified horizon information is searched for within the known horizon information. If the horizon information is found, the horizon information immediately below it is the next horizon to be acquired. If the horizon information is not found, it indicates that the stratigraphic formation at the well being tested is unique, shortening the time interval between the next acquisition of the well number, wellbore parameters, and drilling parameters.

[0063] S16: Determine whether the next layer information is salt-gypsum layer geology. If so, execute S17; if not, execute S18.

[0064] Specifically, the next horizon information can be matched with the gypsum layer geology. If the match is successful, the next horizon information is determined to be gypsum layer geology. A successful match here can mean that the textual similarity between the next horizon information and the description of the gypsum layer geology is greater than a preset similarity. If the match fails, the next horizon information is determined not to be gypsum layer geology.

[0065] S17: gradually shortening the time interval for acquiring the next drilling information of the well to be tested.

[0066] Optionally, the time interval for obtaining the next well number, wellbore parameters and drilling parameters of the well to be tested is gradually shortened.

[0067] The next horizon information is gypsum geology, indicating that the next stratum currently being drilled by the well to be tested may be the gypsum geology. To avoid the situation where the drilling has already entered the gypsum geology for a period of time when the next gypsum geology is stuck, and to ensure that the gypsum geology is stuck right after drilling into the gypsum geology, the time interval for obtaining the next well number, wellbore parameters, and drilling parameters of the well to be tested can be gradually shortened.

[0068] The term "gradually shortening" here means that each time the well number, wellbore parameters, and drilling parameters are acquired, the time interval is shorter than the time interval between the previous acquisitions. For example, when the next horizon information is first determined to be gypsum geology, the well number, wellbore parameters, and drilling parameters are acquired again after 5 seconds, and steps S12-S16 are executed. When the next horizon information is secondly determined to be gypsum geology, the well number, wellbore parameters, and drilling parameters are acquired again after 4 seconds, and steps S12-S16 are executed until the model's recognition result is determined to be gypsum geology in step S13.

[0069] S18: After the preset time interval, continue to obtain drilling information.

[0070] Here, drilling information including the well number, wellbore parameters, and drilling parameters is introduced as an example. If the next layer information is not gypsum layer geology, it means that the current drilling depth of the well to be tested to the gypsum layer geology is still quite a long way. In order to reduce the resource consumption of the model, the time interval for obtaining the next well number, wellbore parameters, and drilling parameters of the well to be tested can be extended or gradually extended. The well number, wellbore parameters, and drilling parameters can also be obtained again at the previous fixed time interval, that is, the well number, wellbore parameters, and drilling parameters can continue to be obtained after the preset time interval.

[0071] As can be seen from the above, the salt-gypsum layer geological layer identification method provided in the embodiment of the present application, since the salt-gypsum layer geological layer identification model is trained using known drilling information and rock cuttings logging data, can accurately identify whether the current drilling is to the salt-gypsum layer geology based on the current drilling information through the salt-gypsum layer geological layer identification model. In addition, the drilling information can be directly obtained during the drilling process without the need for excessive waiting time, and therefore, the efficiency of the salt-gypsum layer geological layer identification in deep wells can also be improved. And when it is determined that the current layer is not the salt-gypsum layer geology, when the next layer is determined to be the salt-gypsum layer geology through the stratigraphic information of the adjacent well, the time interval for the next acquisition of drilling information is gradually shortened to ensure that the drilling information can be obtained as soon as the salt-gypsum layer geology is entered, thereby realizing the salt-gypsum layer geological layer identification and improving the accuracy of the salt-gypsum layer geological layer identification in deep wells. In summary, the salt-gypsum layer geological layer identification method provided in the embodiment of the present application can achieve accurate and efficient determination of the salt-gypsum layer geological layer in deep wells.

[0072] Further, as Figure 1 As a refinement and extension of the method shown, an embodiment of the present application also provides a geological layer blocking method for salt-gypsum layers.

[0073] Figure 2 The process diagram of the geological layer blocking method of the salt-gypsum layer in the embodiment of this application is as follows: Figure 2 , see Figure 2 As shown, the method may include two parts: the first part is a geological identification model for salt-gypsum layers, and the second part is the application of the geological identification model for salt-gypsum layers.

[0074] 1. Training of geological card layer identification model for salt-gypsum layer:

[0075] S21: Obtain well number, well depth, well inclination, hook load, torque, drilling speed, drilling pressure, rotation speed, vertical pressure, casing pressure, resistivity, sonic wave, gamma, element content logging data, cuttings logging data and sidewall carding data from the drilling logs, geological daily reports, drilling parameters and logging data of the well to be tested and the wells in the area where the well to be tested is located.

[0076] The wells within the region of the well to be tested here refer to all wells within the region of the well to be tested. The region here can refer to an area within a preset distance, the project area where the well to be tested is located, a zone with structural characteristics, or an administrative division.

[0077] The well to be logged and the wells in the area where the well is located have corresponding drilling logs, daily geological reports, drilling-while-drilling engineering parameters, and logging data. The well number, depth, inclination, hook load, torque, drilling rate, weight on bit, rotational speed, vertical pressure, casing pressure, resistivity, sonic wave, gamma ray, elemental content logging data, cuttings logging data, and sidewall logging data are obtained from the drilling logs, daily geological reports, drilling-while-drilling engineering parameters, and logging data.

[0078] If no drilling log, geological daily report, drilling-while-drilling engineering parameters or logging data are obtained for a certain well, then the well number, well depth, well inclination, hook load, torque, drilling rate, drilling pressure, rotation speed, vertical pressure, casing pressure, resistivity, sonic wave, gamma, element content logging data, cuttings logging data and sidewall stuck data are obtained from the drilling log, geological daily report, drilling-while-drilling engineering parameters and logging data that can be obtained, or the well number, well depth, well inclination, hook load, torque, drilling rate, drilling pressure, rotation speed, vertical pressure, casing pressure, resistivity, sonic wave, gamma, element content logging data, cuttings logging data and sidewall stuck data are obtained from other well data that can be obtained.

[0079] If the well number, well depth, inclination, hook load, torque, ROP, WOB, rotational speed, vertical pressure, casing pressure, resistivity, acoustic wave, gamma, elemental content logging data, cuttings logging data, and sidewall pickup data are not fully captured from the drilling log, geological daily report, while-drilling engineering parameters, and logging data, then it is sufficient to ensure that the necessary data, including well number, well depth, ROP, inclination, hook load, torque, ROP, WOB, rotational speed, and cuttings logging data, are captured. Non-essential data that is not captured can be ignored or acquired from other sources. Necessary data that is not captured needs to be acquired from other sources or by adding additional measurement equipment.

[0080] Next, we need to preprocess the acquired data, namely, divide, clean and fill.

[0081] S22: The acquired well number, well depth, well inclination, hook load, torque, drilling rate, drilling pressure, rotation speed, vertical pressure, casing pressure, resistivity, acoustic wave, gamma, element content logging data, rock cuttings logging data, and sidewall carding data are divided according to the formation lithology and well body, and the well number, well depth, well inclination, hook load, torque, drilling rate, drilling pressure, rotation speed, vertical pressure, casing pressure, resistivity, acoustic wave, gamma, element content logging data, rock cuttings logging data, and sidewall carding data corresponding to different formation lithology and different well bodies are obtained.

[0082] The lithology here may refer to the properties or names of the rocks mainly contained in the stratum, such as mudstone, sandstone, etc.

[0083] The well body here may refer to an independent well.

[0084] According to the formation lithology and well body, the multiple sets of acquired well number, well depth, well inclination, hook load, torque, drilling speed, drilling pressure, rotation speed, vertical pressure, casing pressure, resistivity, acoustic wave, gamma, element content logging data, cuttings logging data and sidewall carding data are further subdivided to facilitate the subsequent deletion of outliers and supplementation of missing values ​​in the data, thereby improving the efficiency of data preprocessing.

[0085] Well number, depth, inclination, hook load, torque, drilling rate, weight on bit, rotational speed, vertical pressure, casing pressure, resistivity, acoustic wave, gamma ray, elemental content, rock cuttings logging data, and sidewall sampling data can be divided into input data and output data based on their use in model training. Input data includes well number, depth, inclination, hook load, torque, drilling rate, weight on bit, rotational speed, vertical pressure, casing pressure, resistivity, acoustic wave, gamma ray, and elemental content. Output data includes rock cuttings logging data and sidewall sampling data. Rock cuttings logging and sidewall sampling data can be used to determine lithology. In other words, lithology can be used as output data for training.

[0086] Table 1 below is a schematic diagram of the division of the acquired data.

[0087] Table 1

[0088]

[0089] Table 2 below is a second schematic diagram of the division of the acquired data.

[0090] Table 2

[0091]

[0092] Wherein, the above n is any positive integer.

[0093] S23: Deleting outliers from the well numbers, well depths, well inclinations, hook loads, torques, drilling rates, drilling pressures, rotational speeds, vertical pressures, casing pressures, resistivity, acoustic waves, gamma rays, element content logging data, cuttings logging data, and sidewall pickup data corresponding to different formation lithologies and different well bodies, and supplementing missing values ​​from the well numbers, well depths, well inclinations, hook loads, torques, drilling rates, drilling pressures, rotational speeds, vertical pressures, casing pressures, resistivity, acoustic waves, gamma rays, element content logging data, cuttings logging data, and sidewall pickup data corresponding to different formation lithologies and different well bodies to obtain training data.

[0094] When removing outliers, for each group of data after division, you can remove abnormally high values ​​and abnormally low values. Abnormally high values ​​here can refer to values ​​that are higher than the normal value or the highest value among all values. Abnormally low values ​​here can refer to values ​​that are lower than the normal value or the lowest value among all values.

[0095] After deleting outliers, we continue to fill in missing values. Missing values ​​here can refer to values ​​that were not obtained from the beginning, or values ​​that were deleted after being identified as outliers.

[0096] When filling missing values, you can fill them based on the adjacent values ​​of the missing value. For example, you can fill missing values ​​by taking the average of adjacent values, or you can fill missing values ​​based on the pattern of multiple adjacent values.

[0097] For example, suppose that in a certain set of data, the WOB data at 4010 m is missing from the 4000 m-4020 m section. It needs to be supplemented based on the average value of the adjacent data. The specific formula is as follows:

[0098]

[0099] Among them, WOB 缺失 Indicates the bit pressure at the missing position, in MPa, WOB 上 Indicates the drilling pressure above the missing position, in MPa, WOB 下 Indicates the drilling pressure of the well section below the missing position, in MPa.

[0100] S24: The well number, well depth, well inclination, hook load, torque, drilling speed, drilling pressure, rotation speed, vertical pressure, casing pressure, resistivity, acoustic wave, gamma and element content logging data in the training data are used as input type data, and the cuttings logging data and sidewall card collection data in the training data are used as output type data to train the error back propagation neural network model, and the model with performance parameters greater than the preset parameters after training is determined as the salt-gypsum layer geological identification model.

[0101] Here, the error back propagation neural network model adopts a three-hidden-layer network structure, which can meet the learning requirements of data of various dimensions.

[0102] In practical applications, the training data can be divided into training data, test data and validation data in a ratio of 7:2:1, so as to train the error back propagation neural network model, so that the trained model has good lithology recognition function.

[0103] Figure 3 This is a schematic diagram of the model training in the embodiment of this application, see Figure 3As shown in the figure, the model uses a three-hidden layer structure. During training, input data is input into the input layer and output through the output layer. Output data is located in the output layer. During model training, the lithologic data output by the output layer is compared with the output data, and the relevant model parameters are adjusted based on the comparison results until convergence is achieved. Training is completed, resulting in a trained salt-gypsum layer identification model.

[0104] When the accuracy of the salt-gypsum layer geological card identification model obtained after training reaches the preset accuracy, the trained salt-gypsum layer geological card identification model can be put into actual use in subsequent gypsum layer geological card identification. If the trained salt-gypsum layer geological card identification model does not reach the preset accuracy, the trained salt-gypsum layer geological card identification model will continue to be retrained using previous training data or newly acquired training data until the trained salt-gypsum layer geological card identification model reaches the preset accuracy before being put into actual use.

[0105] 2. Application of geological card layer identification model of salt-gypsum layer

[0106] S25: Obtain the current well number, well depth, well inclination, hook load, torque, drilling speed, drilling pressure, rotation speed, vertical pressure, casing pressure, resistivity, sonic wave, gamma and element content logging data of the well to be measured.

[0107] When some of the well logging data such as well number, well depth, well inclination, hook load, torque, drilling speed, drilling pressure, rotation speed, vertical pressure, casing pressure, resistivity, acoustic wave, gamma, and element content cannot be obtained, these data can be omitted and the remaining data that can be obtained can be used to determine the geological village of the gypsum layer.

[0108] S26: inputting the well number, well depth, well inclination, hook load, torque, drilling speed, drilling pressure, rotation speed, vertical pressure, casing pressure, resistivity, acoustic wave, gamma and element content logging data into the salt-gypsum layer geological card layer identification model to obtain an identification result output by the salt-gypsum layer geological card layer identification model.

[0109] S27: Determine whether the identification result is characterized as salt-gypsum layer geology. If so, execute S28; if not, execute S29.

[0110] S28: Determine whether the well to be tested has currently been drilled into the gypsum layer geology.

[0111] S29: searching for the next candidate layer information of the layer information corresponding to the identification result in the known layer information of each adjacent well of the well to be measured.

[0112] For a well to be measured, there may be multiple neighboring wells. For example, there may be multiple wells within a preset range of the well to be measured. Another example is that multiple wells are at the same distance from the well to be measured, and all are the closest distances.

[0113] For each adjacent well, the layer information corresponding to the identification result needs to be searched in its known layer information, and the layer information next to the found layer information is used as the candidate layer information. In other words, the number of candidate layer information that can be found at this time is equal to the number of adjacent wells, or less than the number of candidate layer information (it is possible that the layer information corresponding to the identification result is not found in the known layer information of some adjacent wells).

[0114] Figure 4 This is a schematic diagram of determining the next layer information in the embodiment of this application, see Figure 4 As shown, the well to be tested is being drilled, and the adjacent wells include Well A and Well B. In the active well, the horizon information for Well Depths 1, 2, 3, and 4-1 has been determined: 1, 2, 3, and 3, respectively. When drilling reaches Well Depth 4-2, geological logging of the gypsum layer continues. The known horizon information for Offset Well A includes: Well Depth A1 - Layer A1, Well Depth A2 - Layer A2, Well Depth A3 - Layer A3, and Well Depth A4 - Layer A4. When the active well reaches Well Depth 4-2, the horizon information is calculated based on the model. If the horizon information is still Layer A3, the next horizon information determined from Offset Well A is Layer A4. Similarly, the known horizon information for Offset Well B includes: Well Depth B1 - Layer B1, Well Depth B2 - Layer B2, Well Depth B3 - Layer B3, and Well Depth B4 - Layer B4. When the well is being drilled to a depth of 4-2, the horizon information calculated based on the model is still horizon B3, and the next horizon information determined from the adjacent well B is horizon B4.

[0115] Figure 5 This is an example diagram of determining the next layer information in the embodiment of this application, see Figure 5As shown, the well to be tested is Well X, the active well, and its adjacent wells include Well X-1 and Well X-1. In Well X, the horizons at 3551 m, 3702 m, 4372 m, and 4441 m have been determined, representing the upper mudstone section, the rock salt section, the middle mudstone section, and the middle mudstone section, respectively. When drilling to the next depth, geological logging of the gypsum layer continues. The known horizons for Well X-1 include: the upper mudstone section at 3531 m, the rock salt section at 3702 m, the middle mudstone section at 4569 m, and the gypsum-rock-salt section at 4923 m. When Well X reaches the next depth, the horizons are calculated based on the model. If this horizon is still the middle mudstone section, the next horizon determined from Well X-1 is the gypsum-rock-salt section. Similarly, the known horizons for the adjacent well, X-2, include: 4384 m - upper mudstone, 4542 m - rock salt, 4919 m - middle mudstone, and 5298 m - gypsum-salt. When Well X reaches the next depth, the model calculates the horizons. If the horizon is still the middle mudstone, the next horizon determined from the adjacent well, X-2, is the gypsum-salt.

[0116] To determine the next horizon information, it's necessary to comprehensively consider the candidate horizon information found from the known horizon information of multiple neighboring wells. Specifically, this can be considered in conjunction with the weights assigned to each well's horizon information. The weight assigned to each neighboring well's horizon information is negatively correlated with its distance from the well being measured. In other words, the closer the neighboring well is to the well being measured, the greater the weight assigned to its horizon information.

[0117] S210: Weighting the candidate layer information corresponding to each adjacent well and the weight to obtain different candidate layer information and corresponding coefficients.

[0118] Specifically, the weights of adjacent wells with the same candidate layer information can be added together to obtain different candidate layer information and their corresponding coefficients.

[0119] For example, suppose that neighbor well 1, with a weight of 0.5, has the medium mudstone interval as the candidate horizon, neighbor well 2, with a weight of 0.3, has the gypsum salt interval as the candidate horizon, and neighbor well 3, with a weight of 0.3, has the gypsum salt interval as the candidate horizon. Since neighbor wells 2 and 3 have the same candidate horizon information, the weight of 0.3 for neighbor well 2 and 3 is added together to obtain the gypsum salt interval and its corresponding coefficient of 0.6, and the medium mudstone interval and its corresponding coefficient of 0.5.

[0120] S211: Determine the candidate layer information corresponding to the maximum coefficient as the next layer information.

[0121] Continuing with the above example, at this time, the coefficient 0.6 is the largest, so the gypsum salt section corresponding to the coefficient 0.6 is used as the next layer information of the well to be measured.

[0122] S212: Determine whether the next layer information is salt-gypsum layer geology. If so, execute S213; if not, execute S214.

[0123] S213: gradually shortening the time interval for acquiring the next logging data of the well number, well depth, well inclination, hook load, torque, drilling speed, drilling pressure, rotation speed, vertical pressure, casing pressure, resistivity, acoustic wave, gamma and element content of the well to be measured.

[0124] When drilling progresses steadily, the time interval between two acquisitions of logging data for well number, depth, inclination, hook load, torque, ROP, WOB, rotational speed, vertical pressure, casing pressure, resistivity, acoustic wave, gamma ray, and elemental content can be considered the difference between the two depths. Each time the next horizon is determined to be a gypsum layer, the depth of the next acquisition is moved higher than the original depth.

[0125] Figure 6 This is an example diagram of the end of the card layer operation in the embodiment of this application, see Figure 6 As shown in the figure, assume that in the current well to be tested, the horizon information at 3551m, 3702m, 4372m, 4441m, 4510m, and 4580m has been determined: Upper Mudstone, Rock Salt, Middle Mudstone, Middle Mudstone, Middle Mudstone, and Middle Mudstone, respectively. The known horizon information from the adjacent well on the left includes: Upper Mudstone at 3531m, Rock Salt at 3702m, Middle Mudstone at 4569m, and Gypsum Salt at 4923m. When drilling reaches 4650m, the gypsum layer geological intercalation is continued, that is, the horizon information is calculated based on the model. This horizon information is the Middle Mudstone. At this point, the next horizon information is determined from the adjacent well on the left to be the Gypsum Salt, and the gypsum layer geological intercalation is continued at shorter depth intervals. That is, when drilling reaches 4710m, the horizon information is calculated based on the model. This horizon is the middle mudstone section. The next horizon, identified from the adjacent well on the left, is the gypsum salt section. The depth interval is further shortened to identify the gypsum layer. At 4760 m, the model-based horizon is calculated. This horizon is the gypsum salt section.

[0126] Meanwhile, the known horizons from the adjacent wells on the right include: 4384m - Upper Mudstone Section, 4542m - Rock Salt Section, 4919m - Middle Mudstone Section, and 5298m - Gypsum-Salt Section. At 4650m, the drilling continued with the gypsum-salt section, using the model to calculate the horizon. This horizon was identified as the Middle Mudstone Section. The next horizon, identified from the adjacent wells on the right, was then identified as the Gypsum-Salt Section, and the depth intervals for the gypsum-salt section were further shortened. At 4710m, the model calculated the horizon. This horizon was identified as the Middle Mudstone Section. The next horizon, identified from the adjacent wells on the right, was then identified as the Gypsum-Salt Section, and the depth intervals for the gypsum-salt section were further shortened. At 4760m, the model calculated the horizon. This horizon was identified as the Gypsum-Salt Section.

[0127] When drilling to 4760m was confirmed by two adjacent wells, the model confirmed that the current layer information was the gypsum salt section, indicating that the gypsum layer had been drilled and the gypsum layer geological card had ended.

[0128] S214: Extend the time interval for acquiring the next logging data of the well number, well depth, well inclination, hook load, torque, drilling speed, drilling pressure, rotation speed, vertical pressure, casing pressure, resistivity, acoustic wave, gamma and element content of the well to be measured.

[0129] If the next horizon information currently determined is not a gypsum layer, it means that there are other strata between the current gypsum layer and there is still a long drilling distance. In this case, the time interval for acquiring the next logging data for well number, well depth, well inclination, hook load, torque, drilling rate, drilling pressure, rotation speed, vertical pressure, casing pressure, resistivity, acoustic wave, gamma, and element content can be extended. In other words, after drilling to a deeper depth, the well number, well depth, well inclination, hook load, torque, drilling rate, drilling pressure, rotation speed, vertical pressure, casing pressure, resistivity, acoustic wave, gamma, and element content logging data can be acquired and the layer can be locked. This ensures accurate layer locking while reducing the number of model calculations and thus the model's resource consumption. When the next layer is determined to be gypsum geology, the well number, well depth, well inclination, hook load, torque, drilling speed, drilling pressure, rotation speed, vertical pressure, casing pressure, resistivity, acoustic wave, gamma and element content logging data are obtained at shorter time intervals to lock the layer until the layer is locked.

[0130] At this point, the geological layer blocking method for salt-gypsum layers provided in the embodiments of the present application has been fully described.

[0131] Based on the same inventive concept, an embodiment of the present application also provides a geological layer blocking device for salt-gypsum layers.

[0132] Figure 7 This is a schematic diagram of the structure of the salt-gypsum layer geological layer device in the embodiment of this application. Figure 1 , see Figure 7As shown, the device may include:

[0133] An acquisition module 71 is used to obtain the current drilling information of the well to be tested;

[0134] The layer identification module 72 is configured to input drilling information into a salt-gypsum layer geological layer identification model to obtain an identification result output by the salt-gypsum layer geological layer identification model. The identification result is used to indicate whether the current horizon of the well to be measured is a salt-gypsum layer. The salt-gypsum layer geological layer identification model is an error back propagation neural network model trained using drilling information and rock cuttings logging data corresponding to the well to be measured and the drilled portion of the well in the area where the well to be measured is located.

[0135] A search module 73 is configured to search for the next layer information corresponding to the layer information of the recognition result in the known layer information of the adjacent wells of the well to be measured if the recognition result indicates that the geology is not a salt-gypsum layer;

[0136] The processing module 74 is configured to shorten the time interval for acquiring the next drilling information of the well to be measured if the next horizon information is salt-gypsum geology.

[0137] Further, as Figure 7 As a refinement and expansion of the device shown, an embodiment of the present application also provides a geological layer blocking device for salt-gypsum layers.

[0138] Figure 8 This is a schematic diagram of the structure of the salt-gypsum layer geological layer device in the embodiment of this application. Figure 2 , see Figure 8 As shown, the device may include:

[0139] The training module 81 includes: a collection unit 811, a division unit 812, a deletion and supplementation unit 813 and a training unit 814.

[0140] The acquisition unit 811 is used to obtain drilling information and cuttings logging data corresponding to the well to be logged and the drilled portion of the well in the area where the well to be logged is located.

[0141] The acquisition unit 811 is specifically configured to acquire drilling information and cuttings logging data from drilling logs, geological daily reports, while-drilling engineering parameters, and logging data of the well to be logged and wells in the area where the well to be logged is located.

[0142] The acquisition unit 811 is also used to obtain one or more of vertical pressure, casing pressure, resistivity, acoustic wave, gamma, element content logging data, and sidewall sampling data from drilling logs, geological daily reports, while-drilling engineering parameters, and logging data of the well to be tested and the wells in the area where the well to be tested is located. The vertical pressure, casing pressure, resistivity, acoustic wave, gamma, element content logging data, and sidewall sampling data are used for model training.

[0143] The division unit 812 is used to divide the drilling information and cuttings logging data corresponding to the drilled part according to the formation lithology and well body, and obtain the well number, wellbore parameters, drilling parameters and cuttings logging data corresponding to different formation lithology and different well bodies.

[0144] The deletion and supplementation unit 813 is used to delete abnormal values ​​in the drilling information and rock cuttings logging data corresponding to different formation lithologies and different well bodies, and to supplement missing values ​​in the drilling information and rock cuttings logging data corresponding to different formation lithologies and different well bodies to obtain training data.

[0145] The training unit 814 is used to train the error back propagation neural network model using the drilling information in the training data as input type data and the rock cuttings logging data in the training data as output type data, and determine the model whose performance parameters after training are greater than the preset parameters as the salt-gypsum layer geological card layer identification model.

[0146] The acquisition module 82 is used to obtain the current drilling information of the well to be tested.

[0147] In practical applications, drilling information includes wellbore parameters and drilling parameters; wellbore parameters include: well depth and well inclination; drilling parameters include: hook load, torque, drilling speed, drilling pressure and rotation speed.

[0148] The card layer module 83 is used to input the acquired drilling information into the salt-gypsum layer geological card layer identification model to obtain an identification result output by the salt-gypsum layer geological card layer identification model. The identification result is used to characterize whether the current layer of the well to be measured is a salt-gypsum layer geology. The salt-gypsum layer geological card layer identification model is an error back propagation neural network model trained using the drilling information and rock cuttings logging data corresponding to the well to be measured and the drilled part of the well in the area where the well to be measured is located.

[0149] When there are multiple adjacent wells and the weight corresponding to the layer information of each adjacent well is negatively correlated with the distance between the corresponding adjacent well and the well to be measured, the search module 84 is used to search for the next candidate layer information corresponding to the layer information of the identification result in the known layer information of each adjacent well of the well to be measured if the identification result does not indicate salt-gypsum layer geology; weight the candidate layer information corresponding to each adjacent well and the weight to obtain different candidate layer information and their corresponding coefficients; and determine the candidate layer information corresponding to the maximum coefficient as the next layer information.

[0150] The processing module 85 is configured to shorten the time interval for acquiring the next drilling information of the well to be measured if the next horizon information is salt-gypsum geology.

[0151] The processing module 85 is further configured to extend the time interval for obtaining the next drilling information of the well to be measured if the next horizon information is not salt-gypsum geology.

[0152] It should be noted that the description of the above device embodiment is similar to the description of the above method embodiment and has similar beneficial effects as the method embodiment. For technical details not disclosed in the device embodiment of this application, please refer to the description of the method embodiment of this application for understanding.

[0153] Based on the same inventive concept, an embodiment of the present application also provides a computer device.

[0154] Figure 9 This is a schematic diagram of the structure of the computer device in the embodiment of the present application, see Figure 9 As shown, the computer device may include: a memory 91, a processor 92 and a computer program stored in the memory 91, and the processor 92 executes the computer program to implement the method in the above embodiment.

[0155] It should be noted that the description of the above computer device embodiment is similar to the description of the above method embodiment and has similar beneficial effects as the method embodiment. For technical details not disclosed in the computer device embodiment of this application, please refer to the description of the method embodiment of this application for understanding.

[0156] Based on the same inventive concept, an embodiment of the present application further provides a computer-readable storage medium having a computer program stored thereon, which implements the method of the aforementioned embodiment when executed by a processor.

[0157] It should be noted that the description of the above computer-readable storage medium embodiment is similar to the description of the above method embodiment and has similar beneficial effects as the method embodiment. For technical details not disclosed in the computer-readable storage medium embodiment of this application, please refer to the description of the method embodiment of this application for understanding.

[0158] Based on the same inventive concept, an embodiment of the present application further provides a computer program product, which includes a computer program that implements the method in the aforementioned embodiment when executed by a processor.

[0159] It should be noted that the description of the above computer program product embodiment is similar to the description of the above method embodiment and has similar beneficial effects as the method embodiment. For technical details not disclosed in the computer program product embodiment of this application, please refer to the description of the method embodiment of this application for understanding.

[0160] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

Claims

1. A geological layer blocking method for salt-gypsum layer, characterized in that: The method comprises: Obtain the current drilling information of the well to be tested; Inputting the drilling information into a salt-gypsum layer geological card layer recognition model to obtain a recognition result output by the salt-gypsum layer geological card layer recognition model, wherein the recognition result is used to characterize whether the current horizon of the well to be measured is a salt-gypsum layer geology, wherein the salt-gypsum layer geological card layer recognition model is an error back propagation neural network model trained using drilling information and rock cuttings logging data corresponding to the well to be measured and the drilled portion of the well in the area where the well to be measured is located; If the identification result indicates that the geology is not salt-gypsum layer, searching for the next layer information of the layer information corresponding to the identification result in the known layer information of the adjacent wells of the well to be measured; If the next horizon information is salt-gypsum geology, the time interval for obtaining the next drilling information of the well to be measured is gradually shortened.

2. The method according to claim 1, characterized in that The error back propagation neural network model is a network structure with three hidden layers; Before inputting the drilling information into the salt-gypsum layer geological card layer identification model to obtain the identification result output by the salt-gypsum layer geological card layer identification model, the method further includes: Obtaining drilling information and cuttings logging data corresponding to the well to be logged and the drilled portion of wells in the area where the well to be logged is located; Dividing the drilling information and rock cuttings logging data corresponding to the drilled portion according to formation lithology and wellbore, to obtain drilling information and rock cuttings logging data corresponding to different formation lithologies and different wellbores; Deleting abnormal values ​​in the drilling information and rock cuttings logging data corresponding to the different formation lithologies and different well bodies, and supplementing missing values ​​in the drilling information and rock cuttings logging data corresponding to the different formation lithologies and different well bodies to obtain training data; The drilling information in the training data is used as input type data, and the rock cuttings logging data in the training data is used as output type data to train the error back propagation neural network model, and the model with performance parameters greater than preset parameters after training is determined as the salt-gypsum layer geological card layer identification model.

3. The method according to claim 2, characterized in that The obtaining of drilling information and cuttings logging data corresponding to the well to be logged and the drilled portion of the wells in the area where the well to be logged is located includes: Acquire drilling information and cuttings logging data from drilling logs, geological daily reports, while-drilling engineering parameters, and logging data of the well to be logged and wells in the area where the well to be logged is located; The method further comprises: One or more of vertical pressure, casing pressure, resistivity, acoustic wave, gamma, element content logging data, and sidewall sampling data are obtained from drilling logs, geological daily reports, while-drilling engineering parameters, and logging data of the well to be logged and the wells in the area where the well to be logged is located. The vertical pressure, casing pressure, resistivity, acoustic wave, gamma, element content logging data, and sidewall sampling data are used for model training.

4. The method according to any one of claims 1 to 3, characterized in that There are multiple adjacent wells, and the weight corresponding to the layer information of each adjacent well is negatively correlated with the distance between the corresponding adjacent well and the well to be measured; searching for the next layer information of the layer information corresponding to the identification result in the known layer information of the adjacent wells of the well to be measured, including: Searching for the next candidate layer information of the layer information corresponding to the identification result in the known layer information of each adjacent well of the well to be measured, The candidate layer information corresponding to each adjacent well is weighted with the weight to obtain different candidate layer information and its corresponding coefficient; The candidate layer information corresponding to the maximum coefficient is determined as the next layer information.

5. The method according to any one of claims 1 to 3, characterized in that After searching for the next horizon information of the horizon information corresponding to the identification result in the known horizon information of the adjacent wells of the well to be logged, the method further includes: If the next horizon information is not salt-gypsum geology, the time interval for obtaining the next drilling information of the well to be measured is extended.

6. The method according to any one of claims 1 to 3, characterized in that The drilling information includes wellbore parameters and drilling parameters; The wellbore parameters include: well depth and well inclination; the drilling parameters include: hook load, torque, drilling speed, drilling pressure and rotation speed.

7. A geological layer blocking device for salt-gypsum layer, characterized in that: The device comprises: An acquisition module is used to obtain the current drilling information of the well to be tested; a layer identification module, configured to input the drilling information into a salt-gypsum layer geological layer identification model to obtain an identification result output by the salt-gypsum layer geological layer identification model, wherein the identification result is used to characterize whether the current horizon of the well to be logged is a salt-gypsum layer geology, wherein the salt-gypsum layer geological layer identification model is an error back propagation neural network model trained using drilling information and cuttings logging data corresponding to the well to be logged and the drilled portion of the well in the area where the well to be logged is located; A search module is configured to search for the next layer information corresponding to the layer information of the identification result in the known layer information of the adjacent wells of the well to be measured if the identification result indicates that the geology is not a salt-gypsum layer; The processing module is used to shorten the time interval for obtaining the next drilling information of the well to be measured if the next horizon information is salt-gypsum layer geology.

8. A computer device comprising a memory, a processor, and a computer program stored in the memory, wherein: The processor executes the computer program to implement the steps of the method according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images