Drilling fluid reservoir protection performance optimization method and system based on data association analysis

Abstract

The invention provides a drilling fluid reservoir protection performance optimization method and system based on data association analysis. The method comprises the following steps: performing attribution analysis on an association relationship between an initial drilling fluid parameter and a target permeability recovery value; constructing a multiple regression model between all the target drilling fluid controllable parameters and the target permeability recovery value; calculating based on the multiple regression model to obtain an optimal multiple regression equation; respectively generating parameter diagram nodes and node edges according to the target drilling fluid controllable parameters, and obtaining a parameter diagram structure of the target drilling fluid controllable parameters; and constructing a parameter optimization graph network in combination with the parameter graph structure and the optimal multiple regression equation, inputting the initial drilling fluid parameters into the trained parameter optimization graph network to obtain optimal drilling fluid parameters output by the parameter optimization graph network, and adjusting the initial drilling fluid formula into the optimal drilling fluid formula according to the optimal drilling fluid parameters. The method has the effect of efficiently and accurately optimizing the protection performance of the drilling fluid reservoir.

Description

Technical Field

[0001] The invention belongs to the technical field of reservoir protection in the petroleum industry, and specifically relates to a method and system for optimizing drilling fluid reservoir protection performance based on data association analysis. Background Art

[0002] As a key fluid in drilling engineering, the performance of drilling fluid directly affects the efficiency, safety and economy of drilling. During the entire process of oil and gas drilling and completion, the solid and liquid phases in the working fluid invade the reservoir, destroying the physical-chemical balance of the reservoir, damaging the reservoir, and blocking the oil and gas flow channel, making it difficult or even impossible to find oil and gas reservoirs, and seriously reducing the production of discovered oil and gas reservoirs. Therefore, reservoir protection has now become the key to fully releasing the production capacity of gas fields. However, when drilling fluid invades, it is very easy to cause solid phase invasion and damage to reservoir sensitivity. As the well deepens, the solid content of the drilling fluid continues to increase, and the various properties of the drilling fluid change, causing the reservoir damage to intensify.

[0003] In traditional drilling operations, the design and optimization of drilling fluid formulas mainly rely on the experience of field engineers and simple test methods. Engineers usually select a basic formula based on formation characteristics, drilling depth, temperature and pressure, and then adjust the performance of the drilling fluid by adding various additives. This process often requires multiple tests and adjustments, which is time-consuming and costly. As oil and gas exploration and development extend to complex geological conditions and deep layers, traditional methods are increasingly unable to meet the needs of efficient and accurate drilling. Summary of the invention

[0004] The present invention provides a method and system for optimizing the protection performance of drilling fluid reservoirs based on data association analysis, so as to solve the problems of high cost and long time consumption in the process of optimizing the protection performance of drilling fluid reservoirs.

[0005] In a first aspect, the present invention provides a method for optimizing the reservoir protection performance of drilling fluid based on data association analysis, the method comprising the following steps:

[0006] Obtaining an initial drilling fluid formula and initial drilling fluid parameters of a target drilling fluid, and determining a target permeability recovery value corresponding to the target drilling fluid according to the initial drilling fluid formula and the initial drilling fluid parameters;

[0007] Based on a preset parameter data set, an attribution analysis is performed on the correlation between the initial drilling fluid parameters and the target permeability recovery value, and according to the attribution analysis result, a target drilling fluid controllable parameter having an associated influence on the target permeability recovery value is screened out from all the initial drilling fluid parameters, wherein the parameter data set includes multiple groups of drilling fluid parameters and multiple groups of permeability recovery values ​​corresponding to the drilling fluid parameters;

[0008] Taking the target permeability recovery value as a dependent variable and all the target drilling fluid controllable parameters as independent variables, constructing a multivariate regression model between all the target drilling fluid controllable parameters and the target permeability recovery value;

[0009] Based on the multiple regression model and using the parameter data set, an optimal multiple regression equation between all the target drilling fluid controllable parameters and the target permeability recovery value is calculated;

[0010] Generate parameter graph nodes with each of the target drilling fluid controllable parameters respectively, and generate node features of the parameter graph nodes and node edges between the parameter graph nodes in combination with the attribution analysis results and the optimal multiple regression equation to obtain the parameter graph structure of the target drilling fluid controllable parameters;

[0011] Constructing a parameter optimization graph network by combining the parameter graph structure and the optimal multivariate regression equation, and training the parameter optimization graph network by using the parameter data set until the difference between the permeability recovery value predicted by the parameter optimization graph network and the actual permeability recovery value reaches a minimum value;

[0012] The initial drilling fluid parameters are input into the trained parameter optimization graph network to obtain the optimal drilling fluid parameters output by the parameter optimization graph network, and the initial drilling fluid formula is adjusted to the optimal drilling fluid formula according to the optimal drilling fluid parameters.

[0013] Optionally, the attribution analysis of the correlation between the initial drilling fluid parameters and the target permeability recovery value based on a preset parameter data set, and screening out target drilling fluid controllable parameters having an associated influence on the target permeability recovery value from all the initial drilling fluid parameters according to the attribution analysis result comprises the following steps:

[0014] Preliminarily screening out the controllable drilling fluid parameters associated with the target permeability recovery value from the initial drilling fluid parameters through a core flow experiment;

[0015] Based on a preset parameter data set and in combination with the Pearson linear correlation analysis method and the Shapley nonlinear correlation analysis method, the data correlation between all the controllable drilling fluid parameters and the target permeability recovery value is analyzed, and the controllable drilling fluid parameters whose data correlation is greater than a preset threshold are taken as target controllable drilling fluid parameters.

[0016] Optionally, the target drilling fluid controllable parameters include basic drilling fluid parameters, rheological parameters, solid phase parameters and liquid phase parameters, the basic drilling fluid parameters include drilling fluid density and linear expansion height, the rheological parameters include apparent viscosity, plastic viscosity, dynamic shear force and dynamic-plastic ratio, the solid phase parameters include solid phase content and solid phase particle size, the liquid phase parameters include HTHP water loss or API water loss, and the liquid phase parameters also include pH value, surface tension and cation concentration.

[0017] Optionally, the step of analyzing the data correlation between all the controllable drilling fluid parameters and the target permeability recovery value based on a preset parameter data set and in combination with a Pearson linear correlation analysis method and a Shapley nonlinear correlation analysis method, and taking the controllable drilling fluid parameters having a data correlation greater than a preset threshold as target controllable drilling fluid parameters comprises the following steps:

[0018] Based on a preset parameter data set and using a Pearson linear correlation analysis method, a first Pearson correlation coefficient between each of the controllable parameters of the drilling fluid and the target permeability recovery value is calculated respectively;

[0019] If there are multiple linearly correlated parameters with the same first Pearson correlation coefficient among the controllable parameters of the drilling fluid, retain any one of the linearly correlated parameters and screen out all other linearly correlated parameters;

[0020] The Shapley nonlinear correlation analysis method is used to calculate the Shapley values ​​between each of the controllable parameters of the drilling fluid after screening and the target permeability recovery value;

[0021] If the Shapley value is greater than a preset Shapley threshold, the corresponding drilling fluid controllable parameter is used as a target drilling fluid controllable parameter;

[0022] If the Shapley value is less than the Shapley threshold, the corresponding controllable parameter of the drilling fluid is screened out.

[0023] Optionally, for any one of the controllable parameters of the drilling fluid, the calculation formula of the first Pearson correlation coefficient is as follows:

[0024]

[0025] Where: R1 represents the first Pearson correlation coefficient, n represents the parameter data volume of the controllable parameters of the drilling fluid, x i represents the value of the i-th controllable parameter of the drilling fluid, represents the average value of all the controllable parameters of the drilling fluid, y i represents the i-th permeability recovery value, Represents the average value of permeability recovery.

[0026] Optionally, the calculation formula of the Shapley value is as follows:

[0027]

[0028] Where: φ j (val) represents the controllable parameter x of the drilling fluid j The Shapley value of x j ∈X,X={x1,x2,...,x p}, S represents the removal of the controllable parameter x of the drilling fluid j The subset formed by all other controllable parameters of the drilling fluid is, |S| represents the number of parameters in the subset S, p represents the number of parameters of all controllable parameters of the drilling fluid, val(S∪{x j}) represents the subset S and the controllable parameter x of the drilling fluid j The contribution generated by forming an alliance, val(S) represents the contribution generated by subset S.

[0029] Optionally, the generating of parameter graph nodes with each of the target drilling fluid controllable parameters respectively, and generating node features of the parameter graph nodes and node edges between the parameter graph nodes in combination with the attribution analysis results and the optimal multiple regression equation, to obtain the parameter graph structure of the target drilling fluid controllable parameters comprises the following steps:

[0030] Generate parameter graph nodes respectively with each of the target drilling fluid controllable parameters, and generate node features of the parameter graph nodes according to target correlation factors between the target drilling fluid controllable parameters and the target permeability recovery values, wherein the target correlation factors include the independent variable coefficients of the optimal multiple regression equation and the Shapley values ​​calculated by the Shapley nonlinear correlation analysis method;

[0031] The mutual information values ​​between all the target drilling fluid controllable parameters are calculated based on the parameter data set;

[0032] Based on the Pearson linear correlation analysis method and according to the parameter data set, node association edges between the various parameter graph nodes are constructed, and the node edge weights of the node association edges are determined in combination with the corresponding mutual information values ​​to obtain the parameter graph structure of the target drilling fluid controllable parameters.

[0033] Optionally, the node association edges between the parameter graph nodes are constructed based on the Pearson linear correlation analysis method and according to the parameter data set, and the node edge weights of the node association edges are determined in combination with the corresponding mutual information values ​​to obtain the parameter graph structure of the target drilling fluid controllable parameters, including the following steps:

[0034] For any two target parameter map nodes among all the parameter map nodes, a second Pearson correlation coefficient between the two target parameter map nodes is calculated according to the drilling fluid parameter data corresponding to the two target parameter map nodes in the parameter data set;

[0035] If the absolute value of the second Pearson correlation coefficient is less than a preset edge generation threshold, no node association edge is constructed between the two target parameter graph nodes;

[0036] If the absolute value of the second Pearson correlation coefficient is greater than the edge generation threshold, constructing a node association edge between two target parameter graph nodes;

[0037] For each of the node-associated edges, a node edge weight of the node-associated edge is calculated according to the second Pearson correlation coefficient and the mutual information value of the two parameter graph nodes corresponding to the node-associated edge;

[0038] The parameter graph structure of the target drilling fluid controllable parameters is constructed by combining all the parameter graph nodes and all the node associated edges.

[0039] Optionally, the step of calculating the node edge weight of the node association edge according to the second Pearson correlation coefficient and the mutual information value of the two parameter graph nodes corresponding to the node association edge comprises the following steps:

[0040] Normalizing the mutual information values ​​of the two parameter graph nodes corresponding to the node association edge;

[0041] The absolute value of the second Pearson correlation coefficient and the normalized mutual information value are weighted averaged to obtain the node edge weight of the node-associated edge.

[0042] In the second aspect, the present invention also provides a drilling fluid reservoir protection performance optimization system based on data association analysis, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the drilling fluid reservoir protection performance optimization method based on data association analysis as described in the first aspect is implemented.

[0043] The beneficial effects of the present invention are:

[0044] Compared with the prior art, the technical solution of the present invention has many beneficial effects and significantly improves the efficiency and accuracy of drilling fluid formulation optimization. The details are as follows:

[0045] 1. The present invention introduces data-driven and machine learning methods, making full use of historical data and experience, greatly improving the scientificity and reliability of the optimization process. By establishing a parameter data set and performing attribution analysis, this method can quickly identify key parameters that have a significant impact on the permeability recovery value, avoiding the risk of ignoring certain important factors in traditional methods. This data-based screening process not only improves the targeted optimization, but also can discover some potential, non-intuitive influencing factors, providing new ideas for optimizing drilling fluid formulations.

[0046] 2. The present invention adopts an innovative method combining multiple regression model and graph network, which can more comprehensively capture the complex relationship between various parameters. The multiple regression model can reflect the quantitative impact of each parameter on the permeability recovery value, while the parameter graph structure further describes the interaction between parameters. This combination makes the optimization process no longer limited to the adjustment of a single parameter, but can take into account the synergistic effect between parameters, thereby obtaining a more comprehensive and accurate optimization result.

[0047] 3. The present invention realizes a complete closed loop from data to model and then to optimization by constructing and training a parameter optimization graph network. This method can not only accurately predict the permeability recovery value under different parameter combinations, but also quickly recommend the optimal parameter configuration according to the initial conditions. This greatly shortens the optimization cycle, improves efficiency, and also reduces dependence on manual experience, making the optimization process more objective and repeatable.

[0048] 4. This method is highly adaptable and scalable. As new data continues to accumulate, the model can continue to learn and update, and its prediction and optimization capabilities will continue to improve. This means that this method can adapt to different geological conditions and drilling requirements, and provide strong support for the optimization of drilling fluid formulations in various complex situations.

[0049] In summary, this drilling fluid formulation optimization method based on data-driven and machine learning not only improves the efficiency and accuracy of optimization, but also provides a more intelligent and personalized solution for drilling projects, which is expected to bring significant economic and technical benefits in improving drilling efficiency, reducing costs, and protecting oil and gas reservoirs. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] Figure 1 This is a flow chart of a method for optimizing drilling fluid reservoir protection performance based on data association analysis in one embodiment of the present application.

[0051] Figure 2 A schematic diagram of the Pearson correlation coefficient matrix of drilling fluid reservoir pollution correlation factors in one embodiment of the present application.

[0052] Figure 3This is a schematic diagram of the Shapley value ranking of the controllable parameters of the drilling fluid in one embodiment of the present application. DETAILED DESCRIPTION

[0053] The following will be combined with the drawings in the embodiments of the present application to clearly describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, rather than all the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments in the present application belong to the scope of protection of this application.

[0054] The terms "first", "second", etc. in the specification and claims of the present application are used to distinguish similar objects, and are not used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable under appropriate circumstances, so that the embodiments of the present application can be implemented in an order other than those illustrated or described here, and the objects distinguished by "first", "second", etc. are generally of one type, and the number of objects is not limited. For example, the first object can be one or more. In addition, "and / or" in the specification and claims represents at least one of the connected objects, and the character " / " generally indicates that the objects associated with each other are in an "or" relationship.

[0055] Figure 1 FIG. 1 is a flow chart of a method for optimizing the drilling fluid reservoir protection performance based on data association analysis in one embodiment. It should be understood that although Figure 1 The steps in the flowchart are shown in sequence as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified in this document, there is no strict order restriction for the execution of these steps, and these steps can be executed in other orders. Moreover, Figure 1 At least part of the steps in the above method may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be executed in turn or alternately with other steps or at least part of the sub-steps or stages of other steps. Figure 1 As shown, a method for optimizing drilling fluid reservoir protection performance based on data association analysis disclosed in the present invention specifically includes the following steps:

[0056] S101. Obtain an initial drilling fluid formula and initial drilling fluid parameters of a target drilling fluid, and determine a target permeability recovery value corresponding to the target drilling fluid according to the initial drilling fluid formula and the initial drilling fluid parameters.

[0057] Among them, the initial drilling fluid formula and initial drilling fluid parameters of the target drilling fluid are first obtained. The initial drilling fluid formula usually includes the base fluid type (such as water-based, oil-based or synthetic-based), various additives (such as thickeners, fluid loss reducers, lubricants, etc.) and their proportions. The initial drilling fluid parameters include physical and chemical properties such as density, viscosity, water loss, pH value, etc. These data can be obtained through laboratory testing or on-site sampling and analysis. For example, density can be measured with a mud balance, viscosity can be measured with a Marsh funnel or a rotational viscometer, and water loss can be measured by an API fluid loss test.

[0058] After obtaining these data, a permeability recovery experiment is conducted. The specific operation is to first saturate the core sample with crude oil and measure its initial permeability K1; then soak the core with the target drilling fluid for a period of time (such as 24 hours) to simulate the process of contact between the drilling fluid and the reservoir rock; finally, reversely displace the drilling fluid with crude oil to measure the termination permeability K2 of the core. The permeability recovery value calculation formula is: Permeability recovery value = (K2 / K1) × 100%. For example, the initial permeability K1 of a core sample is 10mD. After soaking in drilling fluid and reverse displacement, the termination permeability K2 is 8mD, then the permeability recovery value is (8 / 10) × 100% = 80%. The purpose of this step is to establish the relationship between the initial drilling fluid formula and its reservoir protection performance (characterized by the permeability recovery value). In this way, the degree of influence of the current drilling fluid formula on the reservoir can be quantitatively evaluated, providing a benchmark for subsequent optimization.

[0059] S102. Based on the preset parameter data set, an attribution analysis is performed on the correlation between the initial drilling fluid parameters and the target permeability recovery value, and according to the attribution analysis result, a target drilling fluid controllable parameter having a correlation influence with the target permeability recovery value is screened out from all the initial drilling fluid parameters.

[0060] Among them, in this step, first of all, a preset parameter data set needs to be prepared. This data set should contain multiple sets of drilling fluid parameters and their corresponding permeability recovery values. For example, there can be 100 sets of drilling fluids with different formulations, each of which contains parameters such as density, viscosity, pH value, solid content, and the corresponding permeability recovery values ​​obtained through experiments. This data set can come from historical data, laboratory test results, or field application data. Next, this data set is used to perform attribution analysis on the correlation between the initial drilling fluid parameters and the target permeability recovery values. The purpose of attribution analysis is to identify which parameters have a significant impact on the permeability recovery value. A variety of statistical methods can be used here, such as correlation analysis, principal component analysis (PCA), or random forest feature importance.

[0061] Taking correlation analysis as an example, the Pearson correlation coefficient between each parameter and the permeability recovery value can be calculated. The correlation coefficient ranges from -1 to 1, and the closer the absolute value is to 1, the stronger the correlation is. For example, assuming that the correlation coefficients of some parameters and the permeability recovery value are as follows:

[0062] Correlation coefficient between density and permeability recovery value: -0.75

[0063] Correlation coefficient between viscosity and permeability recovery value: -0.60

[0064] Correlation coefficient between pH value and permeability recovery value: 0.30

[0065] Correlation coefficient between solid content and permeability recovery value: -0.80

[0066] According to the above correlation coefficients, it can be preliminarily judged that the solid content and density have a greater impact on the permeability recovery value.

[0067] In order to consider the possible nonlinear relationship, nonlinear correlation indicators such as mutual information can also be used. The larger the mutual information value, the higher the degree of mutual dependence between the two variables. On the basis of attribution analysis, a threshold is set to screen out parameters with significant correlation. For example, parameters with an absolute value of correlation coefficient greater than 0.5 or a mutual information value ranking in the top 50% can be selected as target drilling fluid controllable parameters. The effect of this step is to screen out the key parameters that have a significant impact on the permeability recovery value from many drilling fluid parameters. This not only simplifies the subsequent optimization process, but also helps engineers better understand the relationship between drilling fluid performance and reservoir protection. For example, if it is found that solid content is the most critical factor, then in subsequent optimization, the focus can be on how to control and adjust the solid content. Through this data-driven approach, the deviation caused by subjective judgment can be avoided, and the pertinence and efficiency of optimization can be improved. At the same time, this method is also highly adaptable, and the screening criteria can be flexibly adjusted according to different reservoir characteristics and drilling fluid systems.

[0068] S103. Taking the target permeability recovery value as the dependent variable and all target drilling fluid controllable parameters as independent variables, a multivariate regression model between all target drilling fluid controllable parameters and the target permeability recovery value is constructed.

[0069] Among them, the target permeability recovery value is taken as the dependent variable, and all the selected target drilling fluid controllable parameters are taken as independent variables to construct a multivariate regression model. This model aims to quantify the influence of each parameter on the permeability recovery value and establish a mathematical expression that can predict the permeability recovery value. The general form of the multivariate regression model is:

[0070] Y=β0+β1X1+β2X2+…+βnXn+ε

[0071] Among them, Y is the dependent variable (permeability recovery value), X1, X2,…, Xn are independent variables (various target drilling fluid controllable parameters), β0 is the intercept, β1, β2,…, βn are the regression coefficients of each independent variable, and ε is the error term.

[0072] The construction process of the above multivariate regression model usually includes the following steps:

[0073] Data preparation: The screened target drilling fluid controllable parameters and corresponding permeability recovery values ​​are organized into a format suitable for regression analysis.

[0074] Model assumption testing: Check whether the data meets the basic assumptions of multiple regression, such as linear relationship, independence of error terms, homoscedasticity, and normal distribution.

[0075] Multicollinearity check: Calculate the correlation coefficient or variance inflation factor (VIF) between the independent variables to ensure that there is no serious multicollinearity between the independent variables.

[0076] Model fitting: Estimate regression coefficients using the method of least squares or other appropriate method.

[0077] Model evaluation: The coefficient of determination (R 2 ), adjust R 2 , F test and other indicators were used to evaluate the goodness of fit and significance of the model.

[0078] Residual analysis: Check the distribution of residuals to ensure that the model meets basic assumptions.

[0079] The effect of this step is to obtain a mathematical model that can quantitatively describe the relationship between drilling fluid parameters and permeability recovery values. This model can not only be used to predict the permeability recovery values ​​under different parameter combinations, but also intuitively reflect the direction and degree of influence of each parameter through the size and sign of the regression coefficient.

[0080] For example, if the resulting multiple regression model is:

[0081] Permeability recovery value = 120-0.05×density-0.02×viscosity-0.1×solid content+0.03×pH value;

[0082] It shows that the increase of density, viscosity and solid content will lead to a decrease in permeability recovery value, while the increase of pH value will slightly increase the permeability recovery value. At the same time, it can be seen from the absolute value of the coefficient that the solid content has the greatest impact, followed by density.

[0083] S104. Based on the multivariate regression model and using the parameter data set, the optimal multivariate regression equation between all target drilling fluid controllable parameters and the target permeability recovery value is calculated.

[0084] In this step, based on the previously constructed multiple regression model, the optimal multiple regression equation is calculated using the parameter data set. This process is actually a further optimization and refinement of the initial regression model, with the goal of obtaining a mathematical expression that can most accurately describe the relationship between drilling fluid parameters and permeability recovery values. In order to evaluate the performance of this optimal equation, the coefficient of determination (R 2 ), root mean square error (RMSE) and other indicators. For example, the effect of this step is to obtain an optimized and more accurate mathematical model, so as to more accurately predict the permeability recovery value under given drilling fluid parameters. It can also quickly evaluate the potential impact of different drilling fluid formulations, identify the most effective parameter adjustment direction to improve the permeability recovery value, and find a balance between multiple goals, such as minimizing the use of certain expensive additives while ensuring sufficient permeability recovery value.

[0085] S105. Generate parameter graph nodes with each target drilling fluid controllable parameter respectively, and generate node features of the parameter graph nodes and node edges between the parameter graph nodes in combination with the attribution analysis results and the optimal multiple regression equation to obtain the parameter graph structure of the target drilling fluid controllable parameters.

[0086] Among them, first, the corresponding parameter map nodes are generated for each target drilling fluid controllable parameter. These parameters include key indicators such as density, viscosity, water loss, pH value, etc. When generating nodes, it is necessary to consider the characteristics and influence range of each parameter. For example, the density node may contain information such as numerical range and unit; the viscosity node may contain viscosity values ​​at different shear rates, etc. Next, the characteristics of these nodes are enriched by combining the results of the attribution analysis previously performed. The attribution analysis may reveal the contribution of each parameter to the performance of the drilling fluid, and this information can be used as an important attribute of the node. For example, if the attribution analysis shows that density has the greatest impact on permeability recovery, then the density node may be given a higher weight or priority.

[0087] At the same time, the optimal multiple regression equation is used to further define the node characteristics. Specifically, the coefficient of each parameter in the equation can be used as an important feature of the parameter node, reflecting the degree of influence of the parameter on the target variable. After defining the node characteristics, the next step is to determine the edges between the nodes. These edges represent the relationship and influence between the parameters. The properties of the edges can be defined by analyzing the correlation and interaction between the parameters. For example, if a strong correlation is found between density and viscosity, the edge connecting the two nodes may be given a higher weight. The direction of the edge can be determined based on the cause-effect relationship. If it can be determined that the change of a certain parameter will lead to the change of another parameter, it can be represented by a directed edge.

[0088] Finally, all this information is integrated to form a complete parameter graph structure. This graph structure not only contains the characteristics of each parameter, but also reflects the complex relationship network between the parameters. For example, this graph structure can be represented by an adjacency matrix, where the elements in the matrix represent the weights or other properties of the edges between nodes. The parameter graph structure constructed in this way provides a strong foundation for the subsequent optimization process. It not only captures the independent characteristics of each parameter, but also reflects the interaction between the parameters, so as to more comprehensively describe the complexity of the drilling fluid system. This structure enables the subsequent optimization algorithm to better understand and utilize the relationship between the parameters, so as to find a better drilling fluid formula.

[0089] S106. Construct a parameter optimization graph network by combining the parameter graph structure and the optimal multivariate regression equation, and train the parameter optimization graph network using the parameter data set until the difference between the permeability recovery value predicted by the parameter optimization graph network and the actual permeability recovery value reaches a minimum.

[0090] Among them, after obtaining the parameter graph structure, the next step is to combine this structure with the optimal multiple regression equation to construct a parameter optimization graph network. The goal of this network is to accurately predict the permeability recovery value and ultimately be used to optimize the drilling fluid parameters. The construction process first requires converting the parameter graph structure into a trainable neural network model. Each parameter node can be regarded as a neuron in the network, and the edges between the nodes correspond to the connections between the neurons. The features of the nodes can be used as the initial weights or biases of the neurons, while the attributes of the edges can be used to initialize the connection weights. The optimal multiple regression equation plays a key role in this process. It can be used to design the network's loss function to ensure that the network's output is consistent with the prediction results of the regression equation. Specifically, the last layer of the network can be designed as a linear activation function so that its output form is consistent with the regression equation.

[0091] Next is the training process of the network. The network is trained using a parameter data set that contains various drilling fluid parameter combinations and their corresponding actual permeability recovery values. The training process uses a back-propagation algorithm to continuously adjust the weights and biases in the network to minimize the difference between the predicted and actual values.

[0092] Specifically, the mean square error (MSE) can be used as the loss function:

[0093]

[0094] Among them, y i is the actual permeability recovery value, is the permeability recovery value predicted by the network, and n is the number of samples.

[0095] During the training process, you can use optimization algorithms such as gradient descent to update network parameters. For example, using the stochastic gradient descent (SGD) algorithm, the formula for updating parameters in each iteration is:

[0096]

[0097] Among them, θ represents the network parameters, α is the learning rate, is the gradient of the loss function with respect to the parameters.

[0098] The training process needs to be iterated continuously until the difference between the network's predicted value and the actual value reaches a preset threshold. The selection of this threshold requires a balance between the accuracy of the model and the risk of overfitting. For example, it can be set to stop training when the validation set loss no longer decreases for multiple consecutive epochs. In order to improve the generalization ability of the model, some regularization techniques can be used, such as L1 / L2 regularization, Dropout, etc. At the same time, cross-validation is used to evaluate the performance of the model to ensure that the model performs well on unseen data.

[0099] S107. Input the initial drilling fluid parameters into the trained parameter optimization graph network to obtain the optimal drilling fluid parameters output by the parameter optimization graph network, and adjust the initial drilling fluid formula to the optimal drilling fluid formula according to the optimal drilling fluid parameters.

[0100] After completing the training of the parameter optimization graph network, the next step is to use this network to optimize the drilling fluid formulation. First, the initial drilling fluid parameters are converted into a format suitable for network input. This first requires standardizing or normalizing the data to ensure that all input parameters are on the same scale. For example, min-max normalization can be used:

[0101]

[0102] Among them, X is the normalized value, x is the original parameter value, and x min and x max are the minimum and maximum values ​​of the parameter in the training data, respectively.

[0103] Next, the normalized parameters are input into the trained parameter optimization graph network. Based on these inputs, the network will perform a series of forward propagation calculations and finally output the predicted permeability recovery value and the corresponding optimal parameter combination. In order to find the optimal parameter combination, the gradient ascent method can be used. Specifically, the weights of the network are fixed, but the input parameters are allowed to change, and then the gradient of the output (permeability recovery value) to the input parameters is calculated. According to this gradient, the input parameters are gradually adjusted to maximize the output value. During the optimization process, the physical constraints of the parameters need to be considered. For example, the density cannot be negative and the pH value is usually within a specific range. The optimization results can be ensured to conform to physical reality by adding constraints or using appropriate activation functions.

[0104] The optimization process may require multiple iterations until the permeability recovery value no longer increases significantly or the preset number of iterations is reached. After each iteration, check whether the new parameter combination is better than the previous one. A threshold can be used to determine whether the improvement is significant, for example:

[0105]

[0106] Here, ∈ is a small positive number, such as 0.001.

[0107] After obtaining the optimal parameters, they need to be converted back to the original scale. Finally, the initial drilling fluid formula is adjusted according to the optimal parameters obtained. This process needs to consider the feasibility and economy of actual operation. For example, if the optimal density is higher than the initial density, the density can be increased by adding weighting materials such as barite; if the optimal pH value is lower than the initial value, an appropriate amount of acidic substances can be added to adjust it. During the adjustment process, attention should be paid to the mutual influence between the parameters. For example, adding a certain additive may affect both density and viscosity. Therefore, multiple fine-tuning may be required when adjusting the formula, and key parameters should be tested after each adjustment to ensure that they meet the optimization results. Through this process, the initial drilling fluid formula is optimized to a formula that can maximize permeability recovery. This method combines data-driven machine learning technology with traditional drilling fluid formula adjustment experience to find the optimal formula more accurately and efficiently, thereby improving drilling efficiency and reducing drilling risks.

[0108] In one embodiment, performing attribution analysis on the correlation between the initial drilling fluid parameters and the target permeability recovery value based on a preset parameter data set, and screening out the target drilling fluid controllable parameters having a correlation influence on the target permeability recovery value from all the initial drilling fluid parameters according to the attribution analysis results includes the following steps:

[0109] The controllable drilling fluid parameters associated with the target permeability recovery value are preliminarily screened out from the initial drilling fluid parameters through core flow experiments;

[0110] Based on the preset parameter data set and combined with the Pearson linear correlation analysis method and the Shapley nonlinear correlation analysis method, the data correlation between all drilling fluid controllable parameters and the target permeability recovery value is analyzed, and the drilling fluid controllable parameters with data correlation greater than the preset threshold are taken as the target drilling fluid controllable parameters.

[0111] In this embodiment, the core flow experiment is an important method to simulate the interaction between drilling fluid and rock under formation conditions, and is used to preliminarily screen out the controllable parameters of drilling fluid associated with the target permeability recovery value. This experimental process first requires the preparation of representative core samples, which are usually obtained from the target formation or artificially made with cores similar to the properties of the target formation. The core samples need to be pre-processed, including cleaning, drying, saturation and other steps to ensure the consistency and repeatability of the experimental conditions.

[0112] The experimental device usually includes a core holder, a pressure vessel, a pump system, a pressure sensor, and a flow meter. The core is placed in a pressure vessel that simulates the formation pressure and temperature, and drilling fluids of different formulations are injected into the core at a specific flow rate through the pump system. During the injection process, the pressure difference between the inlet and outlet and the flow rate change are continuously monitored, and these data are used to calculate the permeability change of the core. The experimental process is usually divided into the following stages: first, the initial permeability of the core is measured, then the drilling fluid is injected to simulate the drilling process, and then the core is flushed with a cleaning fluid (such as brine) to simulate the production process, and finally the core permeability is measured again.

[0113] In the experiment, the different parameters of the drilling fluid (such as density, viscosity, pH value, solid content, etc.) were changed to observe their effects on the permeability recovery value. For example, other parameters can be kept unchanged and only the drilling fluid density can be changed from 1.0 g / cm 3 To 1.5g / cm 3 , increase by 0.1g / cm each time 3, observe the changes in permeability recovery values ​​under different densities. Similarly, the viscosity can be changed from 10mPa·s to 50mPa·s, the pH value can be changed from 7 to 11, etc., and the changes in permeability recovery values ​​can be recorded respectively. Through this systematic parameter change experiment, it is possible to preliminarily identify which parameters have a significant effect on the permeability recovery value. For example, if it is found that the permeability recovery value shows a clear downward trend with the increase in density, then it can be preliminarily judged that density is an important related parameter. On the contrary, if the change of a certain parameter has little effect on the permeability recovery value, then this parameter may not be a key factor.

[0114] Through the core flow experiment, a set of parameters that may be related to the permeability recovery value can be screened out from the initial many drilling fluid parameters, that is, the drilling fluid controllable parameters associated with the target permeability recovery value. After completing the preliminary screening of the core flow experiment, the next step is to conduct a more in-depth and systematic data correlation analysis of all possible related drilling fluid controllable parameters. This step uses two complementary analysis methods: Pearson linear correlation analysis and Shapley nonlinear correlation analysis to comprehensively evaluate the relationship between the parameters and the target permeability recovery value. Prior to this, it is necessary to analyze based on a preset parameter data set. This data set usually contains a large amount of historical data or experimental data, covering various drilling fluid parameter combinations and their corresponding permeability recovery values. The quality of the data set directly affects the reliability of the analysis results, so the data needs to be preprocessed, including removing outliers, processing missing data, and standardization.

[0115] The Pearson linear correlation analysis method is used to evaluate the strength of the linear relationship between the parameter and the permeability recovery value. The value of the correlation coefficient r is between -1 and 1. The closer the absolute value is to 1, the stronger the linear correlation is. A positive value indicates a positive correlation, and a negative value indicates a negative correlation. However, in practice, there may be a complex nonlinear relationship between the parameter and the permeability recovery value. Therefore, the Shapley nonlinear correlation analysis method is introduced to supplement it. The higher the Shapley value, the greater the contribution of the parameter to the predicted permeability recovery value. Combining the results of these two analysis methods, the correlation between each parameter and the permeability recovery value can be comprehensively evaluated. Usually a preset threshold is set, such as the absolute value of the Pearson correlation coefficient is greater than 0.5 or the Shapley value is greater than 0.1, and the parameters that meet the conditions are identified as the target drilling fluid controllable parameters. The advantage of this dual analysis method is that it takes into account both simple linear relationships and possible complex nonlinear relationships. In this way, the truly important drilling fluid parameters can be identified more accurately, providing a reliable basis for the subsequent optimization process.

[0116] In one embodiment, based on a preset parameter data set and in combination with the Pearson linear correlation analysis method and the Shapley nonlinear correlation analysis method, the data correlation between all drilling fluid controllable parameters and the target permeability recovery value is analyzed, and the drilling fluid controllable parameters with data correlation greater than a preset threshold are used as target drilling fluid controllable parameters, including the following steps:

[0117] Based on the preset parameter data set and using the Pearson linear correlation analysis method, the first Pearson correlation coefficient between each drilling fluid controllable parameter and the target permeability recovery value is calculated respectively;

[0118] If there are multiple linearly correlated parameters with the same first Pearson correlation coefficient among the controllable parameters of the drilling fluid, any one of the linearly correlated parameters is retained and all other linearly correlated parameters are screened out;

[0119] The Shapley nonlinear correlation analysis method is used to calculate the Shapley values ​​between each drilling fluid controllable parameter after screening and the target permeability recovery value.

[0120] If the Shapley value is greater than the preset Shapley threshold, the corresponding drilling fluid controllable parameter is used as the target drilling fluid controllable parameter;

[0121] If the Shapley value is less than the Shapley threshold, the corresponding controllable parameters of the drilling fluid are screened out.

[0122] In this embodiment, for any controllable parameter of drilling fluid, the calculation formula of the first Pearson correlation coefficient is as follows:

[0123]

[0124] Where: R1 represents the first Pearson correlation coefficient, n represents the parameter data volume of the controllable parameters of the drilling fluid, x i represents the value of the controllable parameter of the i-th drilling fluid, represents the average value of all controllable parameters of drilling fluid, y i represents the i-th permeability recovery value, Represents the average value of permeability recovery.

[0125] In this embodiment, the calculation formula of the Shapley value is as follows:

[0126]

[0127] Where: φ j (val) represents the controllable parameter x of drilling fluid j The Shapley value of x j ∈X,X={x1,x2,...,x p}, S represents the removal of the controllable parameters x of the drilling fluid jThe subset formed by all other drilling fluid controllable parameters, |S| represents the number of parameters in the subset S, p represents the number of parameters of all drilling fluid controllable parameters, val(S∪{x j}) represents the subset S and the controllable parameter x of the drilling fluid j The contribution generated by forming an alliance, val(S) represents the contribution generated by subset S.

[0128] In one embodiment, based on all the above embodiments, an example is given for attribution analysis of deepwater water-based drilling fluid contamination of reservoirs:

[0129] Through core flow experiments, controllable parameters of drilling fluid are screened out from many initial drilling fluid parameters, including basic parameters of drilling fluid, rheological parameters, solid phase parameters and liquid phase parameters. The basic parameters of drilling fluid include drilling fluid density and linear expansion height. The rheological parameters include apparent viscosity, plastic viscosity, dynamic shear force, dynamic-plastic ratio and static shear force. The solid phase parameters include solid content and solid particle size. The liquid phase parameters include API water loss, HTHP water loss, pH value, surface tension and cation concentration.

[0130] The parameter data set used in this embodiment is the performance parameters measured for drilling fluids with a density of 1.5 g / cm3 to 2.0 g / cm3. All parameters are standardized to eliminate the influence of the original data type on the analysis process. The solid content and cation concentration are directly taken as actual values ​​and expressed as decimals. The permeability recovery value, filtration loss, inhibition, rheological properties, etc. are processed by the linear normalization method. The processed data set data is detailed in Table 1 below.

[0131] Table 1 Controllable parameters and permeability recovery values ​​of drilling fluids with density of 1.5 g / cm3 to 2.0 g / cm3

[0132]

[0133]

[0134] According to the data in Table 1 above, the first Pearson correlation coefficient between each drilling fluid controllable parameter and the permeability recovery value is calculated, as shown in Figure 2 As shown, Figure 2 The first column or the first row is the first Pearson correlation coefficient, among which there are 6 factors that are positively correlated with the reservoir protection performance (i.e., permeability recovery value) (the first Pearson correlation coefficient is positive). Among the negatively correlated factors (the first Pearson correlation coefficient is negative), both API water loss and HTHP water loss are -0.85, which can be regarded as linear correlation factors and contain repeated information. Therefore, API water loss or HTHP water loss is randomly eliminated. In this embodiment, API water loss is eliminated.

[0135] Then, the Shapley nonlinear correlation analysis of the controllable parameters of the drilling fluid is performed to calculate the Shapley values ​​of each controllable parameter of the drilling fluid, such as Figure 3 As shown, in this embodiment, the Shapley threshold is preset to 0.2, so the static shear force (GEL) with a Shapley value less than 0.2 is screened out. After screening, the target drilling fluid controllable parameters include basic drilling fluid parameters, rheological parameters, solid phase parameters and liquid phase parameters. The basic drilling fluid parameters include drilling fluid density and linear expansion height, the rheological parameters include apparent viscosity, plastic viscosity, dynamic shear force and dynamic plastic ratio, the solid phase parameters include solid content and solid particle size, and the liquid phase parameters include HTHP water loss, pH value, surface tension and cation concentration.

[0136] The target permeability recovery value is used as the dependent variable, and all the selected target drilling fluid controllable parameters are used as independent variables to construct a multivariate regression model. The optimal multivariate regression equation between all target drilling fluid controllable parameters and the target permeability recovery value is calculated using the parameter data set in Table 1 above:

[0137] Kr=0.4367σ+0.8799AV-0.4594Gu-0.8148HTHP+0.6184Inh-0.7325pH

[0138] +0.6362Li+0.5684DPR-0.3219YP+0.2384PV-0.1580ρ+0.1426Kation

[0139] Where Kr is the target permeability recovery value; σ is the surface tension; AV is the apparent viscosity; Gu is the solid content; HTHP is the high temperature and high pressure filtration loss; Inh is the linear expansion height; pH is the acidity and alkalinity; Li is the solid phase average diameter; DPR is the dynamic plastic ratio; YP is the dynamic shear force; PV is the plastic viscosity; ρ is the drilling fluid density; Kation is the cation concentration.

[0140] In one embodiment, each target drilling fluid controllable parameter is used to generate a parameter graph node, and the node features of the parameter graph nodes and the node edges between the parameter graph nodes are generated by combining the attribution analysis results and the optimal multiple regression equation, and the parameter graph structure of the target drilling fluid controllable parameter is obtained, which includes the following steps:

[0141] Generate parameter map nodes with each target drilling fluid controllable parameter respectively, and generate node characteristics of the parameter map nodes according to target correlation factors between the target drilling fluid controllable parameter and the target permeability recovery value, wherein the target correlation factors include the independent variable coefficient of the optimal multiple regression equation and the Shapley value calculated by the Shapley nonlinear correlation analysis method;

[0142] The mutual information values ​​between all target drilling fluid controllable parameters are calculated based on the parameter data set;

[0143] Based on the Pearson linear correlation analysis method and the parameter data set, the node association edges between the nodes of each parameter graph are constructed, and the node edge weights of the node association edges are determined in combination with the corresponding mutual information values ​​to obtain the parameter graph structure of the controllable parameters of the target drilling fluid.

[0144] In this embodiment, for each target drilling fluid controllable parameter, a corresponding parameter map node is created. The characteristics of these nodes are composed of two parts: the independent variable coefficient of the optimal multiple regression equation and the Shapley value calculated by the Shapley nonlinear correlation analysis method. The optimal multiple regression equation is to find the parameter combination that can best predict the target permeability recovery value by analyzing historical data. For example, assuming that the obtained regression equation is Y=0.5X1+0.3X2-0.2X3+0.1X4, where Y is the target permeability recovery value, X1, X2, X3, and X4 represent different drilling fluid parameters, then these coefficients (0.5, 0.3, -0.2, 0.1) are used as a feature of the corresponding node. At the same time, the contribution of each parameter to the target permeability recovery value is calculated using the Shapley nonlinear correlation analysis method. The Shapley value reflects the average marginal contribution of the parameter to the result in different combinations, and its calculation involves all possible parameter combinations. For example, for parameter X1, its Shapley value may be 0.4, indicating that X1 contributes 40% of the predictive power on average when considering all possible parameter combinations. These Shapley values ​​serve as another feature of the node. In this way, each parameter graph node contains two key indicators that reflect its importance and influence, laying the foundation for subsequent graph structure analysis.

[0145] Next, the mutual information values ​​between all target drilling fluid controllable parameters are calculated based on the parameter data set. Mutual information is a method to measure the degree of mutual dependence between two random variables. It can capture nonlinear relationships and is therefore more comprehensive than a simple correlation coefficient. For each pair of parameters, such as density (X) and API water loss (Y), the mutual information I (X; Y) is calculated as:

[0146] I(X;Y)=ΣΣp(x,y)*log(p(x,y) / (p(x)p(y))

[0147] Where p(x,y) is the joint probability distribution of X and Y, and p(x) and p(y) are the marginal probability distributions of X and Y, respectively. In actual calculations, the histogram method or kernel density estimation can be used to approximate these probability distributions. For example, assuming there are 100 sets of data, the value range of each parameter is divided into 10 equally spaced intervals, and then the frequency of each interval is counted to estimate the probability distribution. The larger the calculated mutual information value, the higher the degree of mutual dependence between the two parameters. For example, if the mutual information value of density and API water loss is 0.8, and the mutual information value of density and apparent viscosity is 0.3, this means that the relationship between density and API water loss is closer than that with apparent viscosity. These mutual information values ​​will play an important role in the subsequent construction of the edge weights of the parameter graph, helping to identify important associations between parameters.

[0148] Finally, the associated edges between the nodes of the parameter graph are constructed based on the Pearson linear correlation analysis method, and the weight of the edge is determined by combining the mutual information value, so as to obtain a complete parameter graph structure. For each pair of parameters, if the absolute value of its Pearson correlation coefficient exceeds the preset threshold (for example, 0.5), an edge is added between the nodes corresponding to the two parameters. The weight of the edge is determined by the absolute value of the correlation coefficient and the previously calculated mutual information value. The weighted average method can be used. For example, if the correlation coefficient between density and API water loss is -0.7, the normalized mutual information value is 0.8, and α = 0.6, the weight of the edge between them is 0.6*0.7+0.4*0.8 = 0.74. In this way, the final parameter graph not only reflects the linear relationship between the parameters, but also contains nonlinear interdependence information, providing a comprehensive description of the parameter relationship for subsequent analysis and optimization. This parameter graph structure can intuitively display the complex relationship network between the various drilling fluid parameters, help identify key parameters and parameter groups, and provide an important basis for drilling fluid formulation optimization and performance prediction.

[0149] In one embodiment, based on the Pearson linear correlation analysis method and according to the parameter data set, node association edges between the nodes of each parameter graph are constructed, and the node edge weights of the node association edges are determined in combination with the corresponding mutual information values, and the parameter graph structure of the controllable parameters of the target drilling fluid is obtained, including the following steps:

[0150] For any two target parameter map nodes among all parameter map nodes, the second Pearson correlation coefficient between the two target parameter map nodes is calculated according to the drilling fluid parameter data corresponding to the two target parameter map nodes in the parameter data set;

[0151] If the absolute value of the second Pearson correlation coefficient is less than the preset edge generation threshold, the node association edge between the two target parameter graph nodes is not constructed;

[0152] If the absolute value of the second Pearson correlation coefficient is greater than the edge generation threshold, a node association edge between two target parameter graph nodes is constructed;

[0153] For each node-associated edge, the node edge weight of the node-associated edge is calculated according to the second Pearson correlation coefficient and mutual information value of the two parameter graph nodes corresponding to the node-associated edge;

[0154] The parameter graph structure of the controllable parameters of the target drilling fluid is constructed by combining all parameter graph nodes and all node associated edges.

[0155] In this embodiment, for any two target parameter graph nodes in the parameter graph, it is first necessary to calculate the second Pearson correlation coefficient between them. The calculation method of the second Pearson correlation coefficient is the same as that of the first Pearson correlation coefficient. This process can also be performed based on the parameter data set in Table 1 in the aforementioned embodiment. The calculated second Pearson correlation coefficient is as follows: Figure 2 shown.

[0156] Next, based on the absolute value of the calculated second Pearson correlation coefficient, decide whether to construct a node association edge between the two target parameter graph nodes. This step introduces a preset edge generation threshold to screen important parameter associations. If the absolute value of the second Pearson correlation coefficient is less than this threshold, no association edge is constructed between the two nodes. On the contrary, if it is greater than the threshold, an association edge is constructed. For example, assuming that the set edge generation threshold is 0.5, if the absolute value of the second Pearson correlation coefficient of density and API water loss is 0.7, then an association edge is constructed between the two parameter nodes; and if the absolute value of the second Pearson correlation coefficient of density and apparent viscosity is 0.3, no association edge is constructed. This method can effectively filter out parameter pairs with weak correlation, simplify the parameter graph structure, and highlight important parameter relationships. The implementation effect of this step is to obtain a preliminary parameter relationship network, which only contains parameter pairs with strong correlation.

[0157] For each retained node-related edge, the next step is to calculate its node edge weight. This weight takes into account the second Pearson correlation coefficient and the mutual information value to more comprehensively describe the strength of the relationship between parameters. This calculation method considers both the linear correlation between parameters and the nonlinear mutual information, thereby obtaining a more comprehensive and accurate measure of the strength of the relationship. Finally, all parameter graph nodes and the calculated node-related edges are combined to construct a complete parameter graph structure of the target drilling fluid controllable parameters. This parameter graph is a complex network, in which each node represents a drilling fluid parameter, the edges between nodes represent the relationship between parameters, and the weight of the edge reflects the strength of the relationship. For example, parameters such as density, API water loss, and apparent viscosity can be used as nodes, and the associated edges between them are determined based on the results of the previous calculation. This graph structure intuitively shows the relationship and influence between various parameters. By analyzing this graph structure, key parameters and important parameter combinations can be identified, providing an important reference for the optimization of drilling fluid formulation. For example, it can be found which parameters have strong correlations, so as to predict the possible changes of other parameters when adjusting a certain parameter; it can also identify relatively independent parameter groups, which helps to simplify the control and prediction model of drilling fluid performance. This method of constructing a parameter graph structure integrates a variety of statistical and information theory tools, which can comprehensively capture the complex relationships between parameters and provide a solid data foundation and analysis framework for subsequent drilling fluid optimization and performance prediction.

[0158] In one embodiment, calculating the node edge weight of the node association edge according to the second Pearson correlation coefficient and the mutual information value of the two parameter graph nodes corresponding to the node association edge includes the following steps:

[0159] Normalize the mutual information values ​​of the two parameter graph nodes corresponding to the node association edge;

[0160] The absolute value of the second Pearson correlation coefficient and the normalized mutual information value are weighted averaged to obtain the node edge weight of the node-associated edge.

[0161] In this embodiment, the mutual information values ​​of the two parameter graph nodes corresponding to the node association edge are first normalized. The purpose of normalization is to adjust the mutual information value to a unified scale, which is convenient for comparison and combination with the second Pearson correlation coefficient. The normalization method can adopt minimum-maximum normalization, and the formula is: normalized mutual information value = (original mutual information value-minimum mutual information value) / (maximum mutual information value-minimum mutual information value). For example, if the mutual information value range of all parameter pairs is between 0.2 and 0.8, then for a pair of parameters with a mutual information value of 0.5, its normalized value is (0.5-0.2) / (0.8-0.2)=0.5. Secondly, the absolute value of the second Pearson correlation coefficient and the normalized mutual information value are weighted averaged to obtain the final node edge weight. The calculation formula can be expressed as: Node edge weight = α*|Second Pearson correlation coefficient|+(1-α)*Normalized mutual information value, where α is a weight coefficient between 0 and 1, which is used to adjust the proportion of the two indicators in the final weight. For example, if α is set to 0.6, the absolute value of the second Pearson correlation coefficient of a pair of parameters is 0.7, and the normalized mutual information value is 0.5, then the node edge weight is 0.6*0.7+0.4*0.5=0.62.

[0162] The present invention also discloses a drilling fluid reservoir protection performance optimization system based on data association analysis, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the drilling fluid layer plate protection performance optimization method based on data association analysis described in any one of the above-mentioned embodiments.

[0163] Among them, the processor can adopt a central processing unit (CPU). Of course, according to actual usage, other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. can also be adopted. The general-purpose processor can adopt a microprocessor or any conventional processor, etc., and this application does not impose any restrictions on this.

[0164] Among them, the memory can be an internal storage unit of a computer device, such as a hard disk or memory of a computer device, or an external storage device of a computer device, such as a plug-in hard disk, a smart memory card (SMC), a secure digital card (SD) or a flash memory card (FC) equipped on the computer device, etc., and the memory can also be a combination of an internal storage unit and an external storage device of a computer device. The memory is used to store computer programs and other programs and data required by the computer device. The memory can also be used to temporarily store data that has been output or is to be output, and this application does not impose any restrictions on this.

[0165] A person skilled in the art should understand that the discussion of any of the above embodiments is merely illustrative and is not intended to imply that the scope of protection of the present application is limited to these examples. In line with the concept of the present application, the technical features in the above embodiments or different embodiments may be combined, the steps may be implemented in any order, and there are many other variations of different aspects of one or more embodiments of the present application as described above, which are not provided in detail for the sake of simplicity.

[0166] One or more embodiments of the present application are intended to cover all such substitutions, modifications and variations that fall within the broad scope of the present application. Therefore, any omissions, modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of one or more embodiments of the present application should be included in the protection scope of the present application.

Claims

1. A method for optimizing drilling fluid reservoir protection performance based on data association analysis, characterized in that: The steps include: Obtaining an initial drilling fluid formula and initial drilling fluid parameters of a target drilling fluid, and determining a target permeability recovery value corresponding to the target drilling fluid according to the initial drilling fluid formula and the initial drilling fluid parameters; Based on a preset parameter data set, an attribution analysis is performed on the correlation between the initial drilling fluid parameters and the target permeability recovery value, and according to the attribution analysis result, a target drilling fluid controllable parameter having an associated influence on the target permeability recovery value is screened out from all the initial drilling fluid parameters, wherein the parameter data set includes multiple groups of drilling fluid parameters and multiple groups of permeability recovery values ​​corresponding to the drilling fluid parameters; Taking the target permeability recovery value as a dependent variable and all the target drilling fluid controllable parameters as independent variables, constructing a multivariate regression model between all the target drilling fluid controllable parameters and the target permeability recovery value; Based on the multiple regression model and using the parameter data set, an optimal multiple regression equation between all the target drilling fluid controllable parameters and the target permeability recovery value is calculated; Generate parameter graph nodes with each of the target drilling fluid controllable parameters respectively, and generate node features of the parameter graph nodes and node edges between the parameter graph nodes in combination with the attribution analysis results and the optimal multiple regression equation to obtain the parameter graph structure of the target drilling fluid controllable parameters; Constructing a parameter optimization graph network by combining the parameter graph structure and the optimal multivariate regression equation, and training the parameter optimization graph network by using the parameter data set until the difference between the permeability recovery value predicted by the parameter optimization graph network and the actual permeability recovery value reaches a minimum value; The initial drilling fluid parameters are input into the trained parameter optimization graph network to obtain the optimal drilling fluid parameters output by the parameter optimization graph network, and the initial drilling fluid formula is adjusted to the optimal drilling fluid formula according to the optimal drilling fluid parameters.

2. The method for optimizing drilling fluid reservoir protection performance based on data association analysis according to claim 1, characterized in that: The attribution analysis of the correlation between the initial drilling fluid parameters and the target permeability recovery value based on the preset parameter data set, and screening out the target drilling fluid controllable parameters having a correlation influence with the target permeability recovery value from all the initial drilling fluid parameters according to the attribution analysis result, comprises the following steps: Preliminarily screening out the controllable drilling fluid parameters associated with the target permeability recovery value from the initial drilling fluid parameters through a core flow experiment; Based on a preset parameter data set and in combination with the Pearson linear correlation analysis method and the Shapley nonlinear correlation analysis method, the data correlation between all the controllable drilling fluid parameters and the target permeability recovery value is analyzed, and the controllable drilling fluid parameters whose data correlation is greater than a preset threshold are taken as target controllable drilling fluid parameters.

3. The method for optimizing drilling fluid reservoir protection performance based on data association analysis according to claim 1 or 2, characterized in that: The target drilling fluid controllable parameters include basic drilling fluid parameters, rheological parameters, solid phase parameters and liquid phase parameters. The basic drilling fluid parameters include drilling fluid density and linear expansion height. The rheological parameters include apparent viscosity, plastic viscosity, dynamic shear force and dynamic-plastic ratio. The solid phase parameters include solid phase content and solid phase particle size. The liquid phase parameters include HTHP water loss or API water loss. The liquid phase parameters also include pH value, surface tension and cation concentration.

4. The method for optimizing drilling fluid reservoir protection performance based on data association analysis according to claim 2, characterized in that: The method of analyzing the data correlation between all the controllable drilling fluid parameters and the target permeability recovery value based on the preset parameter data set and combining the Pearson linear correlation analysis method and the Shapley nonlinear correlation analysis method, and taking the controllable drilling fluid parameters with data correlation greater than a preset threshold as the target controllable drilling fluid parameters comprises the following steps: Based on a preset parameter data set and using a Pearson linear correlation analysis method, a first Pearson correlation coefficient between each of the controllable parameters of the drilling fluid and the target permeability recovery value is calculated respectively; If there are multiple linearly correlated parameters with the same first Pearson correlation coefficient among the controllable parameters of the drilling fluid, retain any one of the linearly correlated parameters and screen out all other linearly correlated parameters; The Shapley nonlinear correlation analysis method is used to calculate the Shapley values ​​between each of the controllable parameters of the drilling fluid after screening and the target permeability recovery value; If the Shapley value is greater than a preset Shapley threshold, the corresponding drilling fluid controllable parameter is used as a target drilling fluid controllable parameter; If the Shapley value is less than the Shapley threshold, the corresponding controllable parameter of the drilling fluid is screened out.

5. The method for optimizing drilling fluid reservoir protection performance based on data association analysis according to claim 4 is characterized in that: For any of the controllable parameters of the drilling fluid, the calculation formula of the first Pearson correlation coefficient is as follows: Where: R1 represents the first Pearson correlation coefficient, n represents the parameter data volume of the controllable parameters of the drilling fluid, x i represents the value of the i-th controllable parameter of the drilling fluid, represents the average value of all the controllable parameters of the drilling fluid, y i represents the i-th permeability recovery value, Represents the average value of permeability recovery.

6. The method for optimizing drilling fluid reservoir protection performance based on data association analysis according to claim 4, characterized in that: The calculation formula of the Shapley value is as follows: Where: φ j (val) represents the controllable parameter x of the drilling fluid j The Shapley value of x j ∈X,X={x1,x2,...,x p }, S represents the removal of the controllable parameter x of the drilling fluid j The subset formed by all other controllable parameters of the drilling fluid is, |S| represents the number of parameters in the subset S, p represents the number of parameters of all controllable parameters of the drilling fluid, val(S∪{x j }) represents the subset S and the controllable parameter x of the drilling fluid j The contribution generated by forming an alliance, val(S) represents the contribution generated by subset S.

7. The method for optimizing drilling fluid reservoir protection performance based on data association analysis according to claim 2, characterized in that: The step of generating parameter graph nodes with each of the target drilling fluid controllable parameters respectively, and generating node features of the parameter graph nodes and node edges between the parameter graph nodes in combination with the attribution analysis results and the optimal multiple regression equation, to obtain the parameter graph structure of the target drilling fluid controllable parameters comprises the following steps: Generate parameter graph nodes respectively with each of the target drilling fluid controllable parameters, and generate node features of the parameter graph nodes according to target correlation factors between the target drilling fluid controllable parameters and the target permeability recovery values, wherein the target correlation factors include the independent variable coefficients of the optimal multiple regression equation and the Shapley values ​​calculated by the Shapley nonlinear correlation analysis method; The mutual information values ​​between all the target drilling fluid controllable parameters are calculated based on the parameter data set; Based on the Pearson linear correlation analysis method and according to the parameter data set, node association edges between the various parameter graph nodes are constructed, and the node edge weights of the node association edges are determined in combination with the corresponding mutual information values ​​to obtain the parameter graph structure of the target drilling fluid controllable parameters.

8. The method for optimizing drilling fluid reservoir protection performance based on data association analysis according to claim 5, characterized in that: The step of constructing node association edges between the nodes of the parameter graph based on the Pearson linear correlation analysis method and according to the parameter data set, and determining the node edge weights of the node association edges in combination with the corresponding mutual information values ​​to obtain the parameter graph structure of the controllable parameters of the target drilling fluid comprises the following steps: For any two target parameter map nodes among all the parameter map nodes, a second Pearson correlation coefficient between the two target parameter map nodes is calculated according to the drilling fluid parameter data corresponding to the two target parameter map nodes in the parameter data set; If the absolute value of the second Pearson correlation coefficient is less than a preset edge generation threshold, no node association edge is constructed between the two target parameter graph nodes; If the absolute value of the second Pearson correlation coefficient is greater than the edge generation threshold, constructing a node association edge between two target parameter graph nodes; For each of the node-associated edges, a node edge weight of the node-associated edge is calculated according to the second Pearson correlation coefficient and the mutual information value of the two parameter graph nodes corresponding to the node-associated edge; The parameter graph structure of the target drilling fluid controllable parameters is constructed by combining all the parameter graph nodes and all the node associated edges.

9. The method for optimizing drilling fluid reservoir protection performance based on data association analysis according to claim 8, characterized in that: The step of calculating the node edge weight of the node association edge according to the second Pearson correlation coefficient and the mutual information value of the node association edge corresponding to two of the parameter graph nodes comprises the following steps: Normalizing the mutual information values ​​of the two parameter graph nodes corresponding to the node association edge; The absolute value of the second Pearson correlation coefficient and the normalized mutual information value are weighted averaged to obtain the node edge weight of the node-associated edge.

10. A drilling fluid reservoir protection performance optimization system based on data association analysis, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the method for optimizing the drilling fluid reservoir protection performance based on data association analysis as described in any one of claims 1 to 9 is implemented.

Images