Method and device for determining logging lithologic section line, storage medium and program product

Abstract

The invention discloses a logging lithologic section line determination method and device, a storage medium and a program product, the method comprises the following steps: obtaining a first logging curve of a target logging, the first logging curve being constructed based on actual logging values collected at a first sampling interval; the first logging curve comprises at least one of a natural gamma curve, a resistivity curve, an acoustic curve, a density curve and a neutron curve; the first well logging curve is input into a well logging curve generation model to obtain a target well logging lithologic section line of the target well logging, and the well logging curve generation model is obtained by training a machine learning model based on a second well logging curve of the target well logging and a corresponding label well logging lithologic section line; the second logging curve is constructed based on actual logging values collected at a second sampling interval; therefore, fine correction of the lithology of the logging profile is realized.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of oil and gas, and particularly relates to a method and device for determining a well logging lithology profile line, a storage medium and a program product. BACKGROUND

[0002] In geological research, well logging lithology profile is an important basic data, and its accuracy directly affects the reliability of subsequent geological analysis and research conclusions. However, due to the large sampling interval of the target well logging related data itself, the qualitative representation of lithology often has obvious deficiencies, and it is difficult to accurately reflect the true situation of the underground rock formation.

[0003] At present, the correction of well logging lithology profile mainly depends on the intuitive qualitative judgment of the natural gamma, resistivity and other data in the well logging data by artificial. This method requires the well logging personnel to manually read and correct the well logging depth values of up to hundreds of lithology layer data, which is low in work efficiency, and the correction result is easily disturbed by personal experience, subjective judgment and other human factors, and the stability and consistency are difficult to guarantee. Even after the correction by the well logging personnel, there may be many differences between the well logging lithology profile and the lithology identified by the well logging data, such as the deviation of the depth position corresponding to the lithology, the description of some special minerals, etc. Therefore, there is an urgent need for an identification method for well logging lithology profile to improve the efficiency and accuracy of well logging lithology profile correction. SUMMARY

[0004] The present application provides a method and device for determining a well logging lithology profile line, a storage medium and a program product to solve the problem of low efficiency, easy disturbance by human factors and poor correction effect in the related art which depends on the intuitive qualitative judgment of well logging data by artificial.

[0005] According to an aspect of the present application, a method for determining a well logging lithology profile line is provided, which comprises:

[0006] obtaining a first well logging curve of a target well logging, wherein the first well logging curve is constructed based on actual well logging values collected at a first sampling interval; the first well logging curve comprises at least one of a natural gamma curve, a resistivity curve, a sonic curve, a density curve and a neutron curve;

[0007] inputting the first well logging curve into a well logging curve generation model to obtain a target well logging lithology profile line of the target well logging, wherein the well logging curve generation model is obtained by training a machine learning model based on a second well logging curve of the target well logging and a corresponding labeled well logging lithology profile line; the second well logging curve is constructed based on actual well logging values collected at a second sampling interval.

[0008] According to another aspect of the present application, there is provided a device for determining a well logging lithology profile, comprising:

[0009] a well logging curve obtaining module configured to obtain a first well logging curve of a target well logging, wherein the first well logging curve is constructed based on actual well logging values collected at a first sampling interval, and the first well logging curve comprises at least one of a natural gamma ray curve, a resistivity curve, a sonic curve, a density curve and a neutron curve;

[0010] a well logging lithology profile determining module configured to input the first well logging curve into a well logging curve generation model to obtain a target well logging lithology profile of the target well logging, wherein the well logging curve generation model is trained based on a second well logging curve of the target well logging and a corresponding labeled well logging lithology profile, and the second well logging curve is constructed based on actual well logging values collected at a second sampling interval.

[0011] According to another aspect of the present application, there is provided an electronic device, comprising:

[0012] at least one processor; and

[0013] a memory communicatively connected to the at least one processor; wherein

[0014] the memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor to enable the at least one processor to perform the method for determining a well logging lithology profile according to any one of the embodiments of the present application.

[0015] According to another aspect of the present application, there is provided a computer readable storage medium storing computer instructions for enabling a processor to implement the method for determining a well logging lithology profile according to any one of the embodiments of the present application when executed by the processor.

[0016] According to another aspect of the present application, the embodiments of the present disclosure further provide a computer program product comprising a computer program which, when executed by a processor, implements the method for determining a well logging lithology profile according to any one of the embodiments of the present disclosure.

[0017] The technical scheme of the embodiment of the present application firstly acquires a first logging curve of a target logging, wherein the first logging curve is constructed based on actual logging values collected at a first sampling interval; the first logging curve comprises at least one of a natural gamma curve, a resistivity curve, a sonic curve, a density curve and a neutron curve; the first logging curve provides multi-dimensional and quantitative basic data support for fine correction of logging profile lithology, and can more comprehensively reflect formation lithology characteristics; then, the first logging curve is input into a logging curve generation model to obtain a target logging lithology profile line of the target logging, wherein the logging curve generation model is obtained by training a machine learning model based on a second logging curve of the target logging and a corresponding labeled logging lithology profile line; the second logging curve is constructed based on actual logging values collected at a second sampling interval; through autonomous learning and rule mining of the model on logging data, automatic processing of lithology identification and correction is realized, cumbersome operations of manually reading depth values of hundreds of lithology sections are avoided, and logging lithology correction efficiency is greatly improved; through standardized algorithm logic instead of subjective experience judgment, human factors are reduced to interfere with the result, differences between logging profile lithology and logging data in depth correspondence and special mineral description are effectively reduced, accurate automatic homing of lithology is realized, high-quality logging profile lithology data can be quickly output, and reliable data support is provided for efficient decision-making in the whole process of exploration and development.

[0018] It should be understood that the content described in this part is not intended to identify key or important features of the embodiments of the present application, nor is it intended to limit the scope of the present application. Other features of the present application will become apparent from the following description. BRIEF DESCRIPTION OF DRAWINGS

[0019] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed in the embodiment description will be briefly introduced as follows. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0020] Figure 1 is a flowchart of a method for determining a logging lithology profile line according to the first embodiment of the present application;

[0021] Figure 2a is a flowchart of a method for determining a logging lithology profile line according to the second embodiment of the present application;

[0022] Figure 2b is a schematic diagram of logging profile lithology depth correction of a method for determining a logging lithology profile line according to the second embodiment of the present application;

[0023] Figure 2c is a well logging lithology profile line determination method provided by the second embodiment of the present application, and is a schematic diagram of well logging profile lithology correction;

[0024] Figure 2d is a machine learning model training schematic diagram of a well logging lithology profile line determination method provided by the second embodiment of the present application;

[0025] Figure 3 is a structural schematic diagram of a well logging lithology profile line determination device provided by the third embodiment of the present application;

[0026] Figure 4 is a structural schematic diagram of an electronic device for implementing a well logging lithology profile line determination method of the embodiment of the present application. DETAILED DESCRIPTION

[0027] In order to enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, but not all. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor should fall within the scope of protection of the present application.

[0028] It should be noted that the terms "first", "second", "initial", "standard", "label", "target" and the like in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and do not necessarily describe a specific order or sequence. It should be understood that the data thus used can be interchanged under appropriate circumstances, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion, for example, a process, method, system, product or device including a series of steps or units does not necessarily limit to those steps or units clearly listed, but can include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0029] It should be noted that the modification of "one" or "multiple" mentioned in the present disclosure is illustrative but not limiting, and those skilled in the art should understand that unless otherwise explicitly indicated in the context, it should be understood as "one or more".

[0030] The names of the messages or information exchanged between the plurality of devices in the embodiments of the present disclosure are only for illustrative purposes, and are not intended to limit the scope of the messages or information.

[0031] It can be understood that before using the technical solutions disclosed in the embodiments of the present disclosure, the type of personal information involved in the present disclosure, the use range, the use scenario, etc. should be informed to the user and the authorization of the user should be obtained through appropriate means according to relevant laws and regulations.

[0032] For example, in response to receiving the active request of the user, the prompt information is sent to the user to explicitly prompt the user that the operation requested to be performed will require obtaining and using the personal information of the user. Thus, the user can voluntarily choose whether to provide the personal information to the software or hardware such as the electronic device, the application program, the server or the storage medium, etc. performing the operation of the technical solutions of the present disclosure according to the prompt information.

[0033] As an optional but non-limiting implementation manner, in response to receiving the active request of the user, the prompt information can be sent to the user in the form of a pop-up window, and the prompt information can be presented in the form of text in the pop-up window. In addition, the pop-up window can also carry selection controls for the user to select "agree" or "disagree" to provide the personal information to the electronic device.

[0034] It can be understood that the above notification and obtaining of the authorization of the user are only illustrative, and do not limit the implementation manners of the present disclosure, and other manners meeting the relevant laws and regulations can also be applied to the implementation manners of the present disclosure.

[0035] It can be understood that the data (including but not limited to the data itself, the acquisition or use of the data) involved in the present technical solutions should comply with the requirements of the relevant laws and regulations and the relevant provisions.

[0036] Embodiment one

[0037] Figure 1 A flowchart of a method for determining a well logging lithology profile line is provided for the first embodiment of the present application. The present embodiment can be applied to the identification of a mud logging profile lithology. The method can be executed by a well logging lithology profile line determination device. The well logging lithology profile line determination device can be realized in the form of hardware and / or software. Optionally, the well logging lithology profile line determination device is realized by an electronic device, which can be a mobile terminal, a PC terminal, or a server, etc. Figure 1 As shown in the figure, the method can specifically include the following steps.

[0038] S110, acquiring a first logging curve of a target mud logging, wherein the first logging curve is constructed based on actual logging values collected at a first sampling interval; and the first logging curve includes at least one of a natural gamma curve, a resistivity curve, a sonic curve, a density curve, and a neutron curve.

[0039] In the embodiments of the present application, the target logging refers to a single well or well section that needs to be analyzed for lithology and determine the logging lithology profile thereof. The first logging curve can be a curve constructed based on actual logging values collected at a first sampling interval. The actual logging values refer to various physical parameter values actually measured by a logging instrument directly contacting the underground formation or through related physical principles during logging operation on the target logging.

[0040] Optionally, during the logging operation, the underground formation of the target logging can be measured based on a pre-set first sampling interval. After the actual logging values are collected, the first logging curve can be drawn by sorting the actual logging values in depth order. The first sampling interval refers to the distance between two adjacent sampling points in the depth direction when collecting the actual logging values for constructing the first logging curve. The size of the sampling interval directly determines the density of the data collection of the first logging curve. The smaller the interval, the more intensive the data collected, and the more accurate the curve reflects the changes in the formation. The larger the interval, the relatively sparse the data, and the curve may simplify the formation details to some extent. The first sampling interval can be flexibly set based on actual business needs.

[0041] Illustratively, the first logging curve can include, but is not limited to, at least one of the natural gamma curve, the resistivity curve, the sonic curve, the density curve, and the neutron curve, which can be used as basic data to characterize the lithology characteristics of the target logging and reflect the physical properties of the formation from different angles. The natural gamma curve refers to a curve that varies with depth, which is drawn by continuously measuring the intensity of gamma rays generated by the decay of naturally occurring radioactive elements in the formation with a logging instrument capable of detecting gamma rays, and one-to-one corresponding the measured intensity values to the corresponding depth positions. The resistivity curve refers to a curve drawn by measuring the resistivity of the formation rock, i.e., the ability of the formation rock to resist current, using a logging instrument to emit current to the underground formation, and then plotting the resistivity values at different depths in depth order. The sonic curve refers to a curve drawn by associating the information such as velocity, amplitude, and frequency of the sound wave in the rock formation with the corresponding depth, by emitting a sound wave signal to the underground formation with a sonic logging instrument and recording the related information of the sound wave when propagating in the rock formation. The density curve refers to a curve drawn by measuring the scattering of gamma rays after interacting with the formation material with a density logging instrument, calculating the mass per unit volume of the formation rock, i.e., the density, and then plotting the density values at different depths. The neutron curve refers to a curve drawn by measuring the characteristics such as the ability of the formation to slow down fast neutrons, the cross section of the thermal neutrons captured by the formation, and other characteristics, by emitting fast neutrons to the formation with a neutron logging instrument, and then plotting the measurement results by depth.

[0042] S120, input the first logging curve into a logging curve generation model to obtain a target logging lithology profile line of the target logging, wherein the logging curve generation model is trained based on a second logging curve of the target logging and a corresponding labeled logging lithology profile line thereof; and the second logging curve is constructed based on actual logging values collected at a second sampling interval.

[0043] The target logging lithology profile line of the target logging can be a curve output by the logging curve generation model after inputting the first logging curve into the logging curve generation model, and the curve is used to represent the change of the lithology of the stratum corresponding to the target logging with depth.

[0044] After obtaining the first logging curve, the first logging curve can be optionally input as input data into the logging curve generation model that has been pre-trained, and the model is operated and processed to identify various lithologies of the logging profile, and output the target logging lithology profile line of the target logging. The target logging lithology profile line can be used to represent the distribution of different lithologies in the depth direction in the underground stratum corresponding to the target logging, and provide direct lithology reference data for subsequent logging profile lithology correction and geological analysis work.

[0045] The logging curve generation model can be trained based on the second logging curve of the target logging and the corresponding labeled logging lithology profile line thereof, so that the model can directly focus on key information for learning. By continuously adjusting the model parameters, the model can learn the internal correlation between the second logging curve and the labeled logging lithology profile line, and generate a logging lithology profile line corresponding thereto that can reflect the change of the lithology of the stratum corresponding to the target logging.

[0046] The second logging curve refers to a logging curve obtained by arranging and drawing actual logging values collected at a second sampling interval in a depth order during logging. The second sampling interval can be flexibly set according to actual business requirements. Optionally, the second sampling interval can be the same as or different from the first sampling interval, and can reflect the physical properties of the stratum from different data densities. The second logging curve can include at least one of logging curves such as a natural gamma curve, a resistivity curve, a sonic curve, a density curve, and a neutron curve, and can provide a diversified data basis for model training.

[0047] The labeled logging lithology profile line can be a standard output value corresponding to the second logging curve when training the logging curve generation model, and is used to guide the model to learn the correlation between the logging curve and the lithology profile line.

[0048] Optionally, the machine learning model can include a model type such as a multilayer perceptron model. The multilayer perceptron model is a type of neural network model, which is composed of an input layer, one or more hidden layers, and an output layer. Each layer contains a number of neurons, and the neurons are connected through weights. Through the connection and calculation between multiple layers of neurons, nonlinear transformation and pattern recognition of input data can be achieved.

[0049] Taking the multilayer perceptron model as an example, after inputting the first logging curve into the logging curve generation model, the first logging curve can be received by the input layer of the logging curve generation model and transmitted to the next layer. The number of input nodes of the input layer can be determined by the type characteristics dimension of the logging curve, and each input node in the input layer can represent a logging curve feature. By setting the number of nodes of the input layer to correspond one-to-one with the dimension of the logging curve feature, comprehensive data reception and effective data transmission are ensured.

[0050] Further, feature extraction and nonlinear transformation can be performed by the hidden layers between the input layer and the output layer in the logging curve generation model. Each hidden layer contains a plurality of neuron nodes, each neuron is connected to all nodes of the previous layer, and the nonlinear transformed value is output through weighted summation and activation function processing. Optionally, the number of hidden layers and the number of neurons in each hidden layer can be adjusted according to actual business requirements to achieve optimal performance. For example, the initial value of the number of hidden layer neurons can be set to two to three times the number of input layer nodes.

[0051] Finally, the output layer can receive signals from the last hidden layer and output the prediction result of the model, i.e., the target logging lithology profile. The number of nodes of the output layer corresponds to the number of lithology categories. For example, if there are six lithologies such as mudstone, silty mudstone, argillaceous siltstone, fine sandstone, limestone, and coal, the output layer can be set to include six nodes, each node corresponding to the prediction probability of a lithology. Optionally, in the case of multiple lithology categories, segmented processing or similar lithology classification can be used to reduce the number of lithology identifications or classify similar lithologies into the same lithology, thereby reducing the difficulty of identification and improving the generalization ability of the model.

[0052] Through the setting of the model structure, the number of input layer nodes corresponds to the number of selected logging curve features, the number of hidden layers is adjusted according to actual requirements, and the number of output layer nodes matches the number of lithology categories in the logging profile, so that the model can learn the rules of lithology identification.

[0053] Specifically, the working principle of the multi-layer perceptron model can include two processes of forward propagation and backward propagation, which can realize the mapping from the input data to the prediction result and the optimization of the model parameters in cooperation.

[0054] In the forward propagation process, the input data is transmitted from the input layer, processed layer by layer by the neurons of each hidden layer, and then transmitted to the output layer, and finally the prediction result of the model is obtained. Specifically, each neuron can receive the output of the previous layer for weighted summation, and perform nonlinear conversion through an activation function to obtain the output result of the current layer and transmit it to the next layer of neurons. In the embodiment of the present application, the input layer receives each logging value of the second logging curve, and after layer-by-layer operation of the hidden layer, the predicted lithology profile line data is generated by the output layer, so as to realize the feature mapping from the logging curve to the lithology profile line.

[0055] Optionally, the forward propagation can be divided into two stages of hidden layer processing and output layer processing. In the hidden layer processing stage, the input layer transmits data to the hidden layer, each neuron of the hidden layer calculates the weighted sum, and applies an activation function to obtain the output of the hidden layer. Each hidden layer neuron in the multi-layer perceptron usually uses an activation function to increase the nonlinear representation ability of the model, which includes a linear transformation with weights and bias, so that the multi-layer perceptron can approximate any complex nonlinear function, thereby capturing the complex correlation between the logging curve and the logging lithology profile line. For example, assuming that the data transmitted by the input layer is represented by a vector, the corresponding output result of the hidden layer is f(w1*X+b1), wherein w1*X+b1 is the weighted sum, the function f can be an activation function such as a sigmoid function or a Relu function, w1 is the connection weight between the input layer and the hidden layer, and b1 is the bias of the hidden layer neuron.

[0056] After the calculation of the hidden layer is completed, the data is then transmitted to the output layer, the output layer further takes the output of the hidden layer as input, repeats the similar operation process, calculates the weighted sum of each neuron of the output layer, and applies an activation function to obtain the final prediction result. In the current output layer processing stage, the activation function can be a function type such as a Softmax function, which can convert a K-dimensional vector containing any real number into another K-dimensional probability distribution vector, so that the range of each element is between (0, 1), and the sum of all elements is 1, so that the model output can be directly interpreted as the prediction probability of different lithology categories.

[0057] For an input vector X = [X1, X2, …, Xn], the Softmax function can convert it into an output vector Y = [Y1, Y2, …, Yn]. i i ​], wherein the conversion formula of the Softmax function can be as follows:

[0058]

[0059] Here, is the exponential function of the i-th element X i in the input vector X, is the sum of the exponentials of all elements in the input vector X.

[0060] The Softmax function can amplify the difference between larger elements in the input vector through the exponential function, and normalize all exponentials through the denominator, thereby converting the result into a probability distribution, so that the model can clearly output the prediction probability of different lithologies, providing a quantitative basis for subsequent lithology judgment.

[0061] The back propagation process is used to optimize the model parameters during training, so that the model can accurately identify the lithology. Specifically, first, the error between the predicted value of the output layer and the label log lithology profile line can be calculated according to the loss function, and the loss function can be cross-entropy loss, mean square error loss, etc. function type; then, through the chain rule, the error is propagated from the output layer to the input layer, and the contribution of each layer of neuron connection weight to the error is calculated layer by layer, and according to the size of the error contribution, the weights and biases of each layer are updated and adjusted using gradient descent and other optimization algorithms to reduce the prediction error value.

[0062] During training, through repeated iteration of the forward propagation and back propagation processes, until the prediction error of the model reaches the preset threshold or the number of training times meets the requirements, so that the model can accurately learn the complex relationship between the well logging curve and the lithology profile line, and provide reliable model support for subsequent generation of target well logging lithology profile lines based on the first well logging curve.

[0063] Optionally, the well logging curve can be standardized before being input into the model to eliminate the dimensional differences between different feature data, so that the model can treat each feature more fairly during training, effectively improving the training effect of the model and the final prediction accuracy.

[0064] Through training the well logging curve generation model, not only can the lithology be accurately identified, but also a more accurate target well logging lithology profile line can be generated through deep learning, which deeply integrates the rich information in the well logging data in the layer interface division, and perfectly matches the well logging depth, providing solid technical support for accurate correction of log profile lithology, so that subsequent geological analysis, resource evaluation and other work can be based on more reliable lithology data, greatly improving the efficiency and accuracy of related work.

[0065] The technical scheme of the embodiment of the present application firstly acquires a first logging curve of a target logging, wherein the first logging curve is constructed based on actual logging values collected at a first sampling interval; the first logging curve comprises at least one of a natural gamma curve, a resistivity curve, a sonic curve, a density curve and a neutron curve; the first logging curve provides multi-dimensional and quantitative basic data support for fine correction of logging profile lithology, and can more comprehensively reflect formation lithology characteristics; then, the first logging curve is input into a logging curve generation model to obtain a target logging lithology profile line of the target logging, wherein the logging curve generation model is obtained by training a machine learning model based on a second logging curve of the target logging and a corresponding labeled logging lithology profile line; the second logging curve is constructed based on actual logging values collected at a second sampling interval; through autonomous learning and rule mining of the model on logging data, automatic processing of lithology identification and correction is realized, cumbersome operations of manually reading hundreds of lithology layer depth values are avoided, and logging lithology correction efficiency is greatly improved; through standardized algorithm logic to replace subjective experience judgment, human factors are reduced to interfere with the result, differences between logging profile lithology and logging data in depth correspondence and special mineral description are effectively reduced, accurate automatic homing of lithology is realized, high-quality logging profile lithology data can be quickly output, and reliable data support is provided for efficient decision-making in the whole process of exploration and development.

[0066] Embodiment two

[0067] Fig. 2 is a flowchart of a method for determining a logging lithology profile line according to an embodiment of the present application, which further describes the training process of the logging curve generation model. Optionally, the logging curve generation model is trained in the following manner: determining a plurality of rocks involved in the target logging based on profile data of the target logging, determining an initial logging lithology profile line according to the lithology categories of the rocks and corresponding preset lithology codes of the rocks; constructing a standard logging lithology profile line of the target logging according to a second logging curve of the target logging, standard logging values corresponding to each of the rocks and the preset lithology codes; taking the standard logging lithology profile line as a correction baseline, performing depth correction on the initial logging lithology profile line to obtain a labeled logging lithology profile line; training a machine learning model according to the second logging curve and the labeled logging lithology profile line to obtain the logging curve generation model. For specific embodiments, please refer to the description of the present embodiment. Wherein, the same or similar technical features as the foregoing embodiments are not described herein. As shown in the figure, the method can specifically include: Figure 2a

[0068] S210, determining a plurality of rocks involved in the target logging based on profile data of the target logging, and determining an initial logging lithology profile line according to lithology categories of the rocks and corresponding preset lithology codes of the rocks.​

[0069] In the embodiments of the present application, the profile data of the target logging refers to a series of data related to the underground geological profile corresponding to the target logging, which can be obtained by geological logging, drilling coring and other ways. The profile data of the target logging contains information such as the depth, thickness and lithological composition of the stratum in the geological profile, which can be used as an important basis for determining the rock types involved in the target logging and understanding the overall structure of the stratum, and lays a geological foundation for the construction and analysis of the subsequent lithological profile line.

[0070] The various rocks involved in the target logging are different types of rocks existing in the geological profile of the target logging, which have different lithological characteristics and can be used as the basic unit for analysis of the lithological profile line. Further, the rocks can be classified according to their lithological characteristics to obtain multiple rock categories.

[0071] Alternatively, the lithological profile can be digitized, i.e. the lithology is classified and coded according to the rock categories of different regions or actual business needs to obtain preset lithology codes, so as to improve the processing efficiency of logging data. Each preset lithology code uniquely corresponds to a specific lithology category.

[0072] Specifically, different types of lithology categories can be defined according to their lithological granularity from fine to coarse, with the lithology code defined from small to large, and the preset lithology code corresponding to different lithology categories is set. For example, the lithology code can be defined as 5 for bauxite, 10 for bauxitic mudstone, 20 for mudstone, 25 for carbonaceous mudstone, 28 for siltstone, 30 for argillaceous siltstone, 35 for siltstone, 40 for fine sandstone, 45 for medium sandstone, 50 for coarse sandstone, 55 for gravel-bearing sandstone, 60 for conglomerate, 65 for argillaceous dolomite, 70 for marl, 75 for gypsum, 80 for dolomitic sandstone, 85 for dolomite, 90 for limestone, and 100 for special lithology such as coal seam.

[0073] After obtaining the preset lithology codes corresponding to each lithology category, the various rock categories involved in the target logging can be determined based on the profile data of the target logging, and the preset lithology code corresponding to each lithology category can be determined according to the lithology category of the rock, and the initial logging lithological profile line can be converted into a step-shaped digital curve by arranging the lithology codes in depth order through a macro program prepared in advance.

[0074] Alternatively, the accuracy of each lithology depth of the target logging can be set as the sampling interval of the logging curve to determine the lithology category corresponding to each depth interval.

[0075] S220, constructing a standard logging lithology profile of the target logging according to the second logging curve of the target logging, the standard logging value corresponding to each rock, and the preset lithology code.

[0076] The standard logging value refers to a theoretical value that can represent the typical logging characteristics of the rock category, which is determined in advance through statistical analysis by experiment or actual logging measurement. The standard logging value can be a skeleton logging value corresponding to each rock category. The standard logging lithology profile can be a lithology profile constructed by comprehensively combining the second logging curve of the target logging, the standard logging value corresponding to each rock, and the preset lithology code. The construction process fully combines the actual logging curve data and the standard characteristics of the rock, and has high accuracy and reliability, and can be used as a benchmark for correcting the initial logging lithology profile.

[0077] On the basis of the above scheme, optionally, the step of constructing the standard logging lithology profile of the target logging according to the second logging curve of the target logging, the standard logging value corresponding to each rock, and the preset lithology code comprises: determining the content of each rock according to the actual logging value of the target logging at each second sampling interval and the standard logging value corresponding to each rock, respectively, determining the logging lithology value of each second sampling interval according to the content of the plurality of rocks and the preset lithology code; and constructing the standard logging lithology profile of the target logging according to the plurality of second sampling intervals and the corresponding logging lithology values.

[0078] Optionally, the depth range of the target logging can be pre-divided into a plurality of continuous depth sections with a certain length, and lithology analysis can be performed on each depth section, so that the construction of the standard logging lithology profile is more accurate. Optionally, the depth section can be divided according to the second sampling interval.

[0079] Specifically, for the depth section corresponding to each second sampling interval of the target logging, the content of each rock can be determined according to the actual logging value of the target logging at the second sampling interval and the standard logging value corresponding to each rock based on the following formula:

[0080]

[0081] T is the actual logging value of the target logging at the second sampling interval; V i is the content of the i-th rock; R i is the standard logging value corresponding to the i-th rock; and n is the total number of lithology types.

[0082] Optionally, the actual logging value T can be determined based on logging values of multiple logging curves in the second sampling interval, such as a natural gamma curve, an acoustic curve, a density curve, and a neutron curve.

[0083] Further, R i may be the standard logging value of the i-th rock corresponding to different logging curves.

[0084] Here, taking the natural gamma curve, the acoustic curve, the density curve, and the neutron curve corresponding to the mudstone, the sandstone, and the limestone as examples, the following formulas can be obtained:

[0085] T GR = V 泥岩 × R GR泥岩 + V 砂岩 × R GR砂岩 + V 灰岩 × R GR灰岩 ;

[0086] T DEN = V 泥岩 × R DEN泥岩 + V 砂岩 × R DEN砂岩 + V 灰岩 × R DEN灰岩 ;

[0087] T CNL = V 泥岩 × R CNL泥岩 + V 砂岩 × R CNL砂岩 + V 灰岩 × R CNL灰岩 ;

[0088] T AC = V 泥岩 × R AC泥岩 + V 砂岩 × R AC砂岩 + V 灰岩 × R AC灰岩 ;

[0089] V 泥岩 + V 砂岩 + V 灰岩 = 1;

[0090] wherein GR represents the natural gamma curve, T GR represents the natural gamma value corresponding to the natural gamma curve in the second sampling interval; DEN represents the density curve, T DEN represents the density value corresponding to the density curve in the second sampling interval; CNL represents the neutron curve, T CNL represents the neutron value corresponding to the neutron curve in the second sampling interval; and AC represents the acoustic curve, T ACThe sound wave value corresponding to the sound wave curve representing the second sampling interval.

[0091] The content of each rock can be the proportion of the total rock volume of a certain rock in the interval within a certain second sampling interval, which reflects the distribution quantity and proportion of the rock in the depth interval. By inverting the logging values of each depth interval divided according to the second sampling interval and the standard logging values of each rock type of the target logging, the content of each rock type can be inversely deduced.

[0092] Through the correlation calculation of the actual logging value and the standard logging value, the content calculation has a clear quantitative basis, the subjective judgment error is reduced, the superposition effect of the logging value is considered, the rationality of the total sum of the rock content is ensured, and the reliability of the calculation result is improved.

[0093] Further, the logging lithology value of each second sampling interval of the target logging can be determined according to the content of the plurality of rocks and the preset lithology code of the second sampling interval. The logging lithology value of the second sampling interval is a value determined by comprehensively considering the content of the plurality of rocks in the second sampling interval and the corresponding preset lithology code. The logging lithology value can be used to reflect the lithology characteristics of the corresponding second sampling interval as a whole. Through the calculation of the logging lithology value, the complex lithology combination in different depth intervals can be simplified as a quantifiable index, so as to facilitate the representation and analysis in the lithology profile line.

[0094] On the basis of the above scheme, optionally, the logging lithology value of the second sampling interval is determined according to the content of the plurality of rocks and the preset lithology code, comprising: for each lithology type of the rock, determining a target lithology value of the rock according to the content of the rock and the preset lithology code of the lithology type; and summing the target lithology values corresponding to the plurality of lithology types to obtain the logging lithology value of the second sampling interval.

[0095] The target lithology value can be obtained by multiplying the content of each lithology type of rock and the preset lithology code of the lithology type. The target lithology value can not only reflect the lithology type of the rock, but also reflect the content proportion of the rock in the second sampling interval.

[0096] Specifically, the logging lithology value of the second sampling interval can be calculated based on the following formula:

[0097]

[0098] Wherein, CLITH is the logging lithology value of the second sampling interval; V i is the content corresponding to the i-th rock type; NC iis a preset lithology code corresponding to the i-th rock category; V i ×NC i is a target lithology value corresponding to the i-th rock category.

[0099] The target lithology value is determined by the rock content and the preset lithology code, and the logging lithology value is obtained by summation, so that the logging lithology value can reflect the proportion weight of different rocks, embody the complexity of lithology composition, convert the qualitative lithology category into a quantitative lithology value, and facilitate the construction of a lithology profile line and model processing.

[0100] After obtaining the logging lithology values corresponding to the plurality of second sampling intervals, the standard logging lithology profile line of the target logging can be constructed by sequentially drawing the plurality of second sampling intervals and their corresponding logging lithology values in depth order, if necessary.

[0101] By dividing the second sampling interval, the logging lithology value is calculated for each interval separately, which realizes the fine processing of the lithology profile line construction, determines the lithology value by combining the rock content and the preset lithology code, quantifies the association between the lithology composition and the code, and makes the standard logging lithology profile line more objective and interpretable.

[0102] S230, taking the standard logging lithology profile line as a correction baseline, performing depth correction on the initial logging lithology profile line to obtain a labeled logging lithology profile line.

[0103] The labeled logging lithology profile line can be understood as a lithology profile line obtained by a series of correction processes based on the initial logging lithology profile line and taking the standard logging lithology profile line as a correction baseline. Since it has been accurately corrected, it has high accuracy. In the process of training the logging curve generation model, it can be used as a standard output corresponding to the second logging curve. By comparing the difference between the lithology profile line generated by the model according to the second logging curve and the labeled logging lithology profile line, the model parameters are continuously adjusted, so that the correct association between the logging curve and the lithology profile line is learned.

[0104] On the basis of the above-mentioned scheme, the labeled logging lithology profile line can be obtained by taking the standard logging lithology profile line as a correction baseline and performing depth correction on the initial logging lithology profile line, including: determining a plurality of depth correction lines, taking the standard logging lithology profile line as a correction baseline, and performing deformation processing on the initial logging lithology profile line along the depth direction according to the plurality of depth correction lines to obtain a labeled logging lithology profile line, wherein the top and bottom depth interfaces of the labeled logging lithology profile line and the initial logging lithology profile line have the same depth.

[0105] The correction baseline refers to the standard logging lithology profile line, which can be used as a reference for depth correction of the initial logging lithology profile line.

[0106] Specifically, the standard logging lithology profile line can be taken as a benchmark for the correction degree of the logging lithology profile line, a plurality of depth correction lines can be determined through automatic depth correction or manual calibration correction, etc., to determine the correction amount of the initial logging lithology profile line at different depths, and then the initial logging lithology profile line can be subjected to deformation processing such as depth translation, compression or elongation according to the plurality of depth correction lines, so that the initial logging lithology profile line is as close as possible to the standard logging lithology profile line, and a labeled logging lithology profile line is obtained. The depth correction process can be as shown in Figure 2b .

[0107] In the correction process of the initial logging lithology profile line, it is necessary to ensure that the top and bottom depth interfaces of the labeled logging lithology profile line and the initial logging lithology profile line are the same. The top depth interface refers to the initial logging lithology profile line starting depth position. The bottom depth interface refers to the initial logging lithology profile line bottom depth position. The top and bottom depth interfaces of the logging represent the actual data of the drilling engineering, and the depth is not recommended to be moved.

[0108] The deformation processing of the initial logging lithology profile line by the depth correction line, combined with the standard logging lithology profile line as the baseline, makes the correction process have a clear reference, ensures the accuracy of the labeled logging lithology profile line, and at the same time ensures that the top and bottom depth interfaces do not change, retains the boundary integrity of the geological body, and avoids the distortion of the geological structure caused by the correction.

[0109] S240, training a machine learning model according to the second logging curve and the labeled logging lithology profile line to obtain the logging curve generation model.

[0110] Optionally, the second logging curve can be taken as the input of the machine learning model, and the labeled logging lithology profile line can be taken as the output, the machine learning model can be trained to obtain the logging curve generation model, as shown in Figure 2d .

[0111] Wherein, the logging curve and the profile data of the target logging are both collected according to their corresponding sampling intervals. Since the sampling interval determines the collection density of the data in the depth direction, even if the interval is small, a single sampling point or a small range of data is difficult to fully cover the subtle changes of the formation lithology, and the profile data more reflects the macro geological characteristics, and has limitations in fine description of local lithology, so when the lithology is qualitatively judged only by relying on these original data, the representativeness may not be ideal.

[0112] Further, the second logging curve is one of the training input data for constructing the logging curve generation model, which contains rich formation physical property information, and can capture the deep law between the logging data and the lithology through the associated learning with the labeled logging lithology profile line in the model training process.

[0113] Optionally, the logging curve can be input into the trained logging curve generation model, and the model can continuously operate based on the learned rules to output a lithology profile line that can fully reflect the continuous change of the formation lithology with depth, effectively making up for the deficiency of the original data in the qualitative representation of lithology.

[0114] S250, acquiring a first logging curve of a target logging, wherein the first logging curve is constructed based on actual logging values collected at a first sampling interval; and the first logging curve includes at least one of a natural gamma curve, a resistivity curve, a sonic curve, a density curve, and a neutron curve.

[0115] S260, inputting the first logging curve into a logging curve generation model to obtain a target logging lithology profile line of the target logging, wherein the logging curve generation model is trained based on a second logging curve of the target logging and a corresponding label logging lithology profile line of the target logging; and the second logging curve is constructed based on actual logging values collected at a second sampling interval.

[0116] Optionally, after obtaining the target logging lithology profile line, the logging profile lithology can be corrected according to the accuracy of the actual business requirement. The correction result can be shown as Figure 2c

[0117] Specifically, for the cored well section in the logging profile, when the accuracy requirement is low and rapid correction is required, the initial logging lithology profile line itself can not be modified, and only the initial logging lithology profile line is compared with the standard logging lithology profile line to achieve accurate depth correction.

[0118] Specifically, the label logging lithology profile line obtained after the initial logging lithology profile line is corrected in depth can be taken as a standard, and a small amount of missing lithology layers can be supplemented or a part of the depth corresponding to the preset lithology code can be modified by copying part of the target logging lithology profile line data and pasting it to the label logging lithology profile line, so that the layer section that is missed in the judgment process can be processed when the field logging personnel reviews the cuttings.

[0119] Specifically, when the lithology similarity of the target logging lithology profile line and the label logging lithology profile line is high and is recognized by the field logging professional technician, the target logging lithology profile line can also be taken as a basis, and the inconsistent positions of a small amount of target logging lithology profile lines can be edited and modified by referring to the label logging lithology profile line.

[0120] ​After obtaining the corrected logging lithology profile line of the target logging lithology profile line or the standard logging lithology profile line, the logging lithology profile line data obtained finally can be converted into lithology section data through a preset macro program, and the lithology codes corresponding to each section are replaced with lithology category names according to the preset lithology codes, so as to realize accurate correction of the logging profile lithology.

[0121] The technical scheme of the embodiment of the present application firstly determines the rocks involved in the target logging based on the profile data of the target logging, determines the initial logging lithology profile line according to the lithology categories of the rocks and the preset lithology codes corresponding to the rocks, can ensure that the initial logging lithology profile line has a solid geological basis and provides a reliable starting point for subsequent correction, and can realize standardized representation of the lithology through the preset lithology codes, so as to facilitate unified processing and operation of data; then, the standard logging lithology profile line of the target logging is constructed according to the second logging curve of the target logging, the standard logging values corresponding to each of the rocks and the preset lithology codes; the standard logging lithology profile line has both objectivity and representativeness by fully integrating the actual logging data and the standard characteristics of the rocks, and fully quantifies the correlation between the rock logging characteristics and the lithology, thereby providing a precise reference benchmark for subsequent depth correction; then, the initial logging lithology profile line is corrected in depth by taking the standard logging lithology profile line as a correction baseline, and a labeled logging lithology profile line is obtained; the initial logging lithology profile line can be effectively corrected for possible deviations, the accuracy of the logging lithology profile line is significantly improved, the labeled logging lithology profile line not only retains the geological background of the initial logging lithology profile line, but also can reflect the actual situation according to the logging data, thereby providing a high-quality label for model training; finally, the machine learning model is trained according to the second logging curve and the labeled logging lithology profile line, and the logging curve generation model is obtained; the machine learning model is trained by using the second logging curve and the labeled logging lithology profile line, so that the model can fully learn the internal laws between the logging curve data and the lithology profile line, improve the prediction ability of the model for the lithology, and through the supervised training mode, the target logging lithology profile line output by the model can be more consistent with the actual geological situation, thereby enhancing the practicability of the model.

[0122] Embodiment three

[0123] Figure 3 A structure schematic diagram of a logging lithology profile line determination device provided by the third embodiment of the present application. The device is used to execute the logging lithology profile line determination method provided by any of the above embodiments. The device and the logging lithology profile line determination method of each of the above embodiments belong to the same inventive concept. Details not described in the embodiment of the logging lithology profile line determination device can be referred to the above embodiment of the logging lithology profile line determination method. For example, Figure 3As shown, the device comprises: a logging curve acquisition module 310 and a logging lithology profile line determination module 320.

[0124] The logging curve acquisition module 310 is configured to acquire a first logging curve of a target logging, wherein the first logging curve is constructed based on actual logging values collected at a first sampling interval; and the first logging curve comprises at least one of a natural gamma curve, a resistivity curve, a sonic curve, a density curve, and a neutron curve.

[0125] The technical scheme of the embodiment of the present application first acquires, by the logging curve acquisition module 310, a first logging curve of a target logging, wherein the first logging curve is constructed based on actual logging values collected at a first sampling interval; and the first logging curve comprises at least one of a natural gamma curve, a resistivity curve, a sonic curve, a density curve, and a neutron curve, thereby providing multi-dimensional and quantitative basic data support for fine correction of logging profile lithology and enabling more comprehensive reflection of formation lithology characteristics.

[0126] On the basis of the above scheme, optionally, the device further comprises a well logging curve generation model training module. Wherein, the well logging curve generation model training module comprises an initial logging lithology profile line determination submodule, a standard well logging lithology profile line construction submodule, an initial logging lithology profile line correction submodule and a model training submodule. Wherein, the initial logging lithology profile line determination submodule is configured to determine the rocks involved in the target logging based on the profile data of the target logging, and determine the initial logging lithology profile line according to the lithology categories of the rocks and the corresponding preset lithology codes; the standard well logging lithology profile line construction submodule is configured to construct the standard well logging lithology profile line of the target logging according to the second well logging curve of the target logging, the standard well logging values corresponding to each of the rocks and the preset lithology codes; the initial logging lithology profile line correction submodule is configured to correct the depth of the initial logging lithology profile line based on the standard well logging lithology profile line as the correction baseline, and obtain the labeled logging lithology profile line; and the model training submodule is configured to train the machine learning model according to the second well logging curve and the labeled logging lithology profile line, and obtain the well logging curve generation model.

[0127] On the basis of the above scheme, optionally, the standard well logging lithology profile line construction submodule comprises a well logging lithology value determination unit and a standard well logging lithology profile line construction unit. Wherein, the well logging lithology value determination unit is configured to determine the content of each of the rocks according to the actual well logging values of the target logging at the second sampling interval and the standard well logging values corresponding to each of the rocks respectively, and determine the well logging lithology value of the second sampling interval according to the contents of the rocks and the preset lithology codes; and the standard well logging lithology profile line construction unit is configured to construct the standard well logging lithology profile line of the target logging according to the second sampling interval and the corresponding well logging lithology values.

[0128] On the basis of the above scheme, optionally, the well logging lithology value determination unit is configured to determine the content of each of the rocks according to the actual well logging values of the target logging at the second sampling interval and the standard well logging values corresponding to each of the rocks respectively based on the following formula:

[0129]

[0130] Wherein, T is the actual well logging value of the target logging at the second sampling interval; V i is the content of the i-th rock; R i is the standard well logging value corresponding to the i-th rock; and n is the total number of lithology types.

[0131] On the basis of the above-mentioned scheme, optionally, the well logging lithology value determination unit comprises a target lithology value determination sub-unit and a well logging lithology value determination sub-unit. The target lithology value determination sub-unit is configured to determine, for each lithology type of the rock, a target lithology value of the rock according to the content of the rock and a preset lithology code of the lithology type of the rock; and the well logging lithology value determination sub-unit is configured to perform summation operation on the target lithology values corresponding to the plurality of lithology types to obtain a well logging lithology value of the second sampling interval and form a standard well logging lithology profile line.

[0132] On the basis of the above-mentioned scheme, optionally, the initial mud logging lithology profile line correction sub-module comprises an initial mud logging lithology profile line correction unit. The initial mud logging lithology profile line correction unit is configured to determine a plurality of depth correction lines, take the standard well logging lithology profile line as a correction baseline, perform deformation processing on the initial mud logging lithology profile line in a depth direction according to the plurality of depth correction lines to obtain a labeled mud logging lithology profile line, and the top and bottom depth interfaces of the labeled mud logging lithology profile line and the initial mud logging lithology profile line have the same depth.

[0133] On the basis of the above-mentioned scheme, optionally, the machine learning model comprises a multilayer perceptron model.

[0134] The well logging lithology profile line determination device provided in the embodiments of the present application can execute the well logging lithology profile line determination method provided in any of the embodiments of the present application, and has the corresponding function modules and beneficial effects of the execution method.

[0135] Embodiment four

[0136] Figure 4 A structural schematic diagram of an electronic device 10 that can be used to implement embodiments of the present application is shown. The electronic device is intended to represent various forms of digital computers, such as laptops, desktops, tablets, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device can also represent various forms of mobile devices, such as personal digital assistants, cellular telephones, smart phones, wearable devices (e.g., headsets, glasses, watches, etc.), and other similar computing devices. The components shown here, their connections and relationships, and their functions, are meant to be examples only, and are not intended to limit the implementations of the present application described and / or claimed in this document.

[0137] As Figure 4As shown, the electronic device 10 includes at least one processor 11, and a memory, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., communicatively connected to the at least one processor 11, where the memory stores a computer program executable by the at least one processor. The processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or loaded into the random access memory (RAM) 13 from the storage unit 18. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0138] Various components in the electronic device 10 are connected to the I / O interface 15, including an input unit 16, such as a keyboard, a mouse, etc., an output unit 17, such as various types of displays, a speaker, etc., a storage unit 18, such as a magnetic disk, an optical disk, etc., and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network, such as the Internet, and / or various telecommunication networks.

[0139] The processor 11 can be various general and / or special-purpose processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 performs various methods and processes described above, such as the method of determining a well logging lithology profile line.

[0140] In some embodiments, the method of determining a well logging lithology profile line can be implemented as a computer program tangibly embodied in a computer readable storage medium, such as the storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed onto the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the method of determining a well logging lithology profile line described above can be performed. Alternatively, in other embodiments, the processor 11 can be configured to perform the method of determining a well logging lithology profile line by any other appropriate means, such as by means of firmware.

[0141] The various embodiments of the systems and techniques described above can be implemented in digital electronic circuitry, integrated circuitry, a field programmable gate array (FPGA), an application specific integrated circuit (ASIC), a system on a chip (SOC), a load programmable logic device (CPLD), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include implementation in one or more computer programs that are executable and / or interpretable on a programmable system including at least one programmable processor, which can be special or general purpose, coupled to receive data and instructions from, and to transmit data and instructions to, a storage system, at least one input device, and at least one output device.

[0142] Computer programs used to implement the processes of the application can be written in any combination of one or more programming languages. These computer programs can be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the computer program

[0143] In the context of the present application, a computer-readable storage medium can be a tangible medium that can contain or store computer programs for use by or in connection with an instruction execution system, apparatus, or device. Computer-readable storage media can include, but are not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium can be a machine-readable signal medium. More specific examples of the machine-readable storage medium will include one or more lines of electrical connections, portable computer disks, hard disk drives, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or Flash memory), optical fibers, portable compact disc read-only memories (CD-ROMs), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0144] To provide for interaction with a user, the systems and techniques described here can be implemented on an electronic device having a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user and a keyboard and a pointing device (e.g., a mouse or a trackball) by which the user can provide input to the electronic device. Other kinds of devices can be used to provide for interaction with a user as well; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form, including acoustic, speech, or tactile input.

[0145] The systems and techniques described here can be implemented in a computing system that includes a back end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front end component (e.g., a user computer having a graphical user interface or a Web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back end, middleware, or front end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0146] The computing system can include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. A server can be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system, to solve the defects of large management difficulty and weak business scalability in traditional physical host and VPS service.

[0147] In particular, the processes described above with reference to the flow charts can be implemented as computer software programs. For example, embodiments of the application include a computer program product comprising a computer program carried on a non-transitory computer-readable medium, the computer program comprising program code for executing the methods illustrated by the flow charts. In such embodiments, the computer program can be downloaded and installed from a network via the communication unit 19, or installed from the storage unit 18, or installed from the ROM 12. When the computer program is executed by the processor 11, the above-described functions defined in the methods of the embodiments of the application are performed.

[0148] It should be understood that the various forms of flow shown above can be used to reorder, add, or remove steps. For example, the steps recited in the present application can be performed in parallel, in series, or in a different order, as long as the desired results of the technical solutions of the present application can be achieved, which are not limited herein.

[0149] The above detailed description does not constitute a limitation on the protection scope of the present application. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent replacements, and improvements made within the spirit and principles of the present application shall be included in the protection scope of the present application.

Claims

1. A method for determining well logging lithological profiles, characterized in that, include: A first logging curve for the target well is obtained, wherein the first logging curve is constructed based on actual logging values ​​collected at a first sampling interval; the first logging curve includes at least one of a natural gamma curve, a resistivity curve, an acoustic curve, a density curve, and a neutron curve; The first logging curve is input into the logging curve generation model to obtain the target logging lithology profile of the target well. The logging curve generation model is obtained by training a machine learning model based on the second logging curve of the target well and its corresponding labeled logging lithology profile. The second logging curve is constructed based on the actual logging values ​​collected at the second sampling interval.

2. The method for determining well logging lithological profiles according to claim 1, characterized in that, The well logging curve generation model was trained in the following manner: Based on the profile data of the target logging, the various rocks involved in the target logging are determined, and the initial logging lithology profile line is determined according to the lithology category of the rock and its corresponding preset lithology code; Based on the second logging curve of the target well, the standard logging value corresponding to each type of rock, and the preset lithology code, construct the standard logging lithology profile of the target well; Using the standard logging lithology profile as the correction baseline, the initial logging lithology profile is depth-corrected to obtain the labeled logging lithology profile; The machine learning model is trained based on the second logging curve and the lithological profile of the tag logging to obtain the logging curve generation model.

3. The method for determining well logging lithological profiles according to claim 2, characterized in that, The step of constructing the standard logging lithology profile of the target well based on the second logging curve of the target well, the standard logging value corresponding to each type of rock, and the preset lithology code includes: For each second sampling interval of the target logging, the content of each rock is determined according to the actual logging value of the target logging at the second sampling interval and the standard logging value corresponding to each rock. The logging lithology value of the second sampling interval is determined according to the content of multiple rocks and the preset lithology code. The standard logging lithology profile of the target well is constructed based on multiple second sampling intervals and their corresponding logging lithology values.

4. The method for determining well logging lithology profiles according to claim 3, characterized in that, The content of each rock is determined based on the actual logging value of the target rock at the second sampling interval and the standard logging value corresponding to each rock, according to the following formula: Where T is the actual logging value of the target well at the second sampling interval; V i R represents the content of the i-th type of rock; i is the standard logging value corresponding to the i-th rock type; n is the total number of lithology types.

5. The method for determining well logging lithological profiles according to claim 3, characterized in that, The step of determining the logging lithology value of the second sampling interval based on the content of the various rocks and the preset lithology code includes: For each type of rock, a target lithology value is determined based on the rock's content and a preset lithology code for its lithology type. The logging lithology values ​​corresponding to the various lithology types are summed to obtain the logging lithology values ​​for the second sampling interval.

6. The method for determining well logging lithological profiles according to claim 2, characterized in that, The process of using the standard logging lithology profile as a correction baseline to perform depth correction on the initial logging lithology profile to obtain the labeled logging lithology profile includes: Multiple depth correction lines are determined, and the standard logging lithology profile line is used as the correction baseline. The initial logging lithology profile line is deformed along the depth direction according to the multiple depth correction lines to obtain a labeled logging lithology profile line. The top depth interface and bottom depth interface of the labeled logging lithology profile line and the initial logging lithology profile line have the same depth.

7. The method for determining well logging lithological profiles according to claim 1, characterized in that, The machine learning model includes a multilayer perceptron model.

8. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the method for determining logging lithology profiles according to any one of claims 1-7.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that cause a processor to execute the method for determining logging lithology profiles as described in any one of claims 1-7.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements the method for determining logging lithology profiles as described in any one of claims 1-7.

Images