Intelligent well completion optimization design method and device based on multi-objective optimization

Abstract

The invention discloses an intelligent well completion optimization design method and device based on multi-objective optimization, and the method comprises the steps: carrying out the clustering of a first data set according to a weighted clustering model, carrying out the evaluation of the geological sweet spots of all clusters after clustering, and obtaining the evaluation result of the geological sweet spots, the first data set comprises physical property parameters of each reservoir along the depth of the horizontal well, and the weighted clustering model is constructed according to the weight of the physical property parameters of each reservoir; according to an engineering dessert evaluation result and a preset segment length constraint, a fracturing segment is divided, and the engineering dessert evaluation result is determined according to geomechanical parameters; and in the divided fracturing sections, solving a multi-objective function constructed according to the geological dessert evaluation result, the engineering dessert evaluation result and the preset cluster spacing constraint, and performing well completion optimization design according to the objective solving result of the multi-objective function. According to the method, well completion optimization design can be efficiently, finely and intelligently carried out.

Description

Technical Field

[0001] The present invention relates to the technical field of reservoir stimulation and reconstruction, and particularly to an intelligent well completion optimization design method and device based on multi-objective optimization. Background Art

[0002] Refined and intelligent well completion optimization design is crucial for the development and reconstruction of unconventional oil reservoirs.

[0003] However, when the existing technology uses a clustering algorithm to identify and evaluate sweet spots, a large amount of manpower and time costs are required to interpret the clustering results, which limits the ability to optimize well completion design based on sweet spots. Moreover, the existing technology mostly adopts geometric or single well completion design methods, making it difficult to achieve balanced fracturing reconstruction. That is, the existing well completion optimization design methods have problems such as low intelligence and efficiency, poor design effects, and difficulty in achieving balanced fracturing reconstruction.

[0004] In response to the above problems, no effective solution has been proposed yet. Summary of the Invention

[0005] Embodiments of this specification provide an intelligent well completion optimization design method and device based on multi-objective optimization to solve the problems of low intelligence and efficiency, poor design effects, and difficulty in achieving balanced fracturing reconstruction in the existing well completion optimization design methods.

[0006] In a first aspect, embodiments of this specification provide an intelligent well completion optimization design method based on multi-objective optimization, including:

[0007] Clustering a first data set according to a weighted clustering model, and evaluating the geological sweet spots of each cluster after clustering to obtain a geological sweet spot evaluation result. The first data set includes various reservoir physical property parameters along the horizontal well depth, and the weighted clustering model is constructed according to the weights of various reservoir physical property parameters;

[0008] Dividing fracturing sections according to the engineering sweet spot evaluation result and a preset section length constraint, where the engineering sweet spot evaluation result is determined according to geological mechanics parameters;

[0009] In the divided fracturing sections, solve a multi-objective function constructed according to the geological sweet spot evaluation result, the engineering sweet spot evaluation result, and a preset cluster spacing constraint, and perform well completion optimization design according to the objective solution result of the multi-objective function.

[0010] In some embodiments, the method further includes:

[0011] Calculating the correlation coefficient between each reservoir physical property parameter and the oil production profile data;

[0012] Determining the sum of the absolute values of the correlation coefficients between each reservoir physical property parameter and the oil production profile data;

[0013] Determine the weights of each reservoir physical property parameter according to the sum of the correlation coefficients and the absolute values of the correlation coefficients between the reservoir physical property parameters and the oil production profile data.

[0014] In some embodiments, the weighted clustering model is constructed according to the weights of each reservoir physical property parameter, including:

[0015] Construct a weighted Euclidean distance function, a criterion function, and a rating function according to the weights of each reservoir physical property parameter;

[0016] Construct a weighted clustering model according to the weighted Euclidean distance function, the criterion function, and the rating function.

[0017] In some embodiments, the clustering of the first data set according to the weighted clustering model includes:

[0018] Select a preset number of clustering centers from the first data set;

[0019] According to the weighted Euclidean distance function, calculate the weighted Euclidean distance from each first sample point in the first data set to the clustering center, and each first sample point corresponds to the reservoir physical property parameters at different horizontal well depths;

[0020] Compare the weighted Euclidean distances, and according to the comparison results, divide each first sample point into the clustering cluster corresponding to the weighted Euclidean distance less than the preset distance threshold;

[0021] According to the criterion function, select a new clustering center from the clustering clusters;

[0022] Repeat the process of calculating the weighted Euclidean distance, dividing each first sample point, and selecting a new clustering center until the number of iterations reaches the preset iteration number threshold or the selected new clustering center does not change, and obtain the first clustering result after clustering;

[0023] The evaluation of the geological sweet spots of each clustering cluster after clustering to obtain the geological sweet spot evaluation result includes:

[0024] Use the rating function to evaluate the geological sweet spots after clustering in the first clustering result to obtain the geological sweet spot evaluation result.

[0025] In some embodiments, the use of the rating function to evaluate the geological sweet spots after clustering in the first clustering result to obtain the geological sweet spot evaluation result includes:

[0026] Use the rating function to determine the weighted geological sweet spot index of each clustering cluster in the first clustering result;

[0027] Compare the weighted geological sweet spot indexes of each clustering cluster, and sort the comparison results of the weighted geological sweet spot indexes in descending order to obtain the sorting result of the weighted geological sweet spot indexes;

[0028] According to the sorting results of the weighted geological sweet spot index, the corresponding geological sweet spots are rated at different levels to obtain the geological sweet spot evaluation results, and the geological sweet spot evaluation results include geological sweet spot category labels.

[0029] In some embodiments, the engineering sweet spot evaluation results include the geomechanical strength along the horizontal well depth; correspondingly, the dividing of fracturing sections according to the engineering sweet spot evaluation results and the preset section length constraint includes:

[0030] Construct a second data set according to the geomechanical strength along the horizontal well depth and the well depth, and each second sample point in the second data set corresponds to different well depths and the geomechanical strength at different horizontal well depths;

[0031] Construct a geomechanical similarity term according to the geomechanical strength of the second sample points and the average geomechanical strength of all second sample points;

[0032] Construct a section length penalty term according to the well depth range of the fracturing section and the preset section length constraint;

[0033] Construct an objective function for dividing the fracturing section according to the geomechanical similarity term and the section length penalty term;

[0034] Use the dynamic programming algorithm to solve the objective function to determine the segmentation points of the fracturing section;

[0035] Divide the fracturing section according to the segmentation points to obtain the fracturing section division result, and the fracturing section division result includes section labels.

[0036] In some embodiments, the method further includes:

[0037] Determine the geological sweet spot weights according to the geological sweet spot category labels in the geological sweet spot evaluation results;

[0038] Identify the fracturing sections according to the section labels in the fracturing section division results and impose constraints on the fracturing clusters within the fracturing sections, so that the constrained fracturing clusters are within the preset section depth range;

[0039] Generate candidate regions according to the geomechanical strength along the horizontal well depth, and generate candidate clusters from the candidate regions;

[0040] Take the sum of the geological sweet spot weights being greater than the preset weight threshold as the first objective, the geomechanical similarity term being less than the preset variance threshold as the second objective, and the preset cluster spacing requirement as the constraint condition;

[0041] Construct a multi-objective function according to the first objective, the second objective and the constraint condition.

[0042] In some embodiments, solving the multi-objective function constructed according to the geological sweet spot evaluation result, the engineering sweet spot evaluation result, and the preset cluster spacing constraint includes:

[0043] Adopt a multi-objective optimization algorithm to solve the multi-objective function, and determine the objective solution result of the multi-objective function from the candidate clusters;

[0044] The well completion optimization design according to the objective solution result of the multi-objective function includes:

[0045] Use the objective solution result as the target design scheme of the fracturing clusters in the fracturing section, and perform well completion optimization design according to the target design scheme of the fracturing clusters.

[0046] In a second aspect, an intelligent well completion optimization design device based on multi-objective optimization provided by an embodiment of this specification includes:

[0047] A geological sweet spot evaluation module, configured to cluster a first data set according to a weighted clustering model, and evaluate the geological sweet spots of each clustering cluster after clustering to obtain a geological sweet spot evaluation result, where the first data set includes various reservoir physical property parameters along the horizontal well depth, and the weighted clustering model is constructed according to the weights of the various reservoir physical property parameters;

[0048] A fracturing section division module, configured to divide the fracturing section according to the engineering sweet spot evaluation result and the preset section length constraint, where the engineering sweet spot evaluation result is determined according to the geomechanical parameters;

[0049] A well completion optimization design module, configured to solve the multi-objective function constructed according to the geological sweet spot evaluation result, the engineering sweet spot evaluation result, and the preset cluster spacing constraint within the divided fracturing section, and perform well completion optimization design according to the objective solution result of the multi-objective function.

[0050] In a third aspect, an embodiment of this specification also provides a computer-readable storage medium, on which computer program instructions are stored, and when the computer program instructions are executed by a processor, the steps of the above-mentioned intelligent well completion optimization design method based on multi-objective optimization are implemented.

[0051] The embodiments of this specification provide an intelligent completion optimization design method and device based on multi-objective optimization. First, cluster the first data set according to the weighted clustering model, and evaluate the geological sweet spots of each cluster after clustering to obtain the geological sweet spot evaluation result. The first data set includes various reservoir physical property parameters along the horizontal well depth, and the weighted clustering model is constructed according to the weights of the various reservoir physical property parameters. Then, divide the fracturing sections according to the engineering sweet spot evaluation result and the preset section length constraint, where the engineering sweet spot evaluation result is determined according to the geomechanical parameters. Finally, within the divided fracturing sections, solve the multi-objective function constructed according to the geological sweet spot evaluation result, the engineering sweet spot evaluation result, and the preset cluster spacing constraint, and perform completion optimization design according to the objective solution result of the multi-objective function. In the embodiments of this specification, by introducing the weighted clustering model, there is no need to spend a large amount of manpower and time costs to interpret the clustering results, and the intelligent evaluation of geological sweet spots can be realized. Through the geomechanical parameters, the engineering sweet spot evaluation can be accurately carried out to determine the engineering sweet spot evaluation result, and combined with the preset section length constraint, the intelligent design of the fracturing sections can be realized, solving the problem of non-uniform fracture initiation caused by the traditional design method using geometry or a single fracturing section spacing. By solving the multi-objective function, intelligent and refined completion optimization design can be realized, improving the engineering applicability. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the following drawings are only some embodiments of the present invention, and for those of ordinary skill in the art, without creative efforts, other drawings can be obtained according to these drawings. In the drawings:

[0053] Figure 1 is a schematic flow chart of an intelligent completion optimization design method based on multi-objective optimization provided by the embodiments of this specification;

[0054] Figure 2 is a schematic diagram of an embodiment applying an intelligent completion optimization design method based on multi-objective optimization provided by the embodiments of this specification in a scenario example;

[0055] Figure 3 is a schematic diagram of the structural composition of an intelligent completion optimization design device based on multi-objective optimization provided by the embodiments of this specification;

[0056] Figure 4 is a schematic diagram of the structural composition of an electronic device provided by the embodiments of this specification. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0057] To enable those skilled in the art to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of this specification. Obviously, the described embodiments are only a part of the embodiments of this specification, rather than all the embodiments. Based on the embodiments in this specification, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the scope of protection of this specification.

[0058] Unconventional oil and gas resources dominated by shale play an increasingly important role in energy supply. Multi-stage hydraulic fracturing is a key technology for developing unconventional reservoirs. Implementing an effective well completion design plays a crucial role in the development and transformation of unconventional oil reservoirs, and its goal is to achieve balanced production increase in each fracturing stage. A prerequisite for an effective fracturing design is to accurately evaluate the sweet spots (areas with good geological and engineering characteristics). Identifying these sweet spots and optimizing the well completion design are crucial for targeting high-quality reservoirs and achieving uniform fracture initiation and propagation.

[0059] The concept of "sweet spot" is widely used in oil and gas exploration and development, and can include geological sweet spots and engineering sweet spots. Geological sweet spots refer to areas with high hydrocarbon content and good rock physical properties, and are usually evaluated using parameters such as clay content, total organic carbon, porosity, and permeability. Engineering sweet spots refer to areas that are conducive to efficient hydraulic fracturing, and rely on geomechanical indicators such as Young's modulus, Poisson's ratio, and in-situ stress for evaluation. However, the strong non-linear relationships and complexities of these parameters make it challenging to distinguish their relative importance.

[0060] Currently, there are few studies that comprehensively consider the "double sweet spots" of geology and engineering and apply them to well completion design. In these studies, common methods are to use single-factor evaluation methods, multi-factor correlation analysis methods, or radar area models to determine the classification thresholds of optimal parameters, thereby constructing a coupled classification array of geological sweet spots and engineering sweet spots to form a comprehensive "double sweet spot" evaluation table. Based on this evaluation table, in the fracturing stages favorable for the "double sweet spots", the number of perforation clusters (or called fracturing clusters) increases, and in the fracturing stages unfavorable for the "double sweet spots", the perforation clusters are sparse. However, this method has great limitations in evaluating and balancing geological and engineering sweet spots: on the one hand, these classification thresholds often vary depending on the selected method and reservoir characteristics, presenting challenges such as non-uniqueness and limited regional applicability. On the other hand, although the cluster density is increased in the high-quality "double sweet spot" fracturing stages, a geometric or single design is adopted to locate the clusters within each fracturing stage without considering the variation of the fracture initiation pressure between clusters. More and more monitoring data show that traditional geometric or single well completion designs are difficult to achieve balanced fracturing transformation.

[0061] With the application of artificial intelligence in oil and gas exploration and development, clustering algorithms have become a promising method for sweet spot identification. However, it is difficult to distinguish and integrate geological sweet spots and engineering sweet spots, and a great deal of effort is required to combine mechanistic understanding to explain the clustering results, which limits its ability to comprehensively consider the "dual sweet spots" in well completion optimization design.

[0062] In summary, the existing well completion optimization design methods have problems such as low intelligence and efficiency, poor design effects, and difficulty in achieving balanced fracturing transformation.

[0063] To solve the above problems, the embodiments of this specification provide an intelligent well completion optimization design method and device based on multi-objective optimization. First, cluster the first data set according to a weighted clustering model, and evaluate the geological sweet spots of each cluster after clustering to obtain a geological sweet spot evaluation result. The first data set includes various reservoir physical property parameters along the horizontal well depth, and the weighted clustering model is constructed according to the weights of the various reservoir physical property parameters. Then, divide the fracturing sections according to the engineering sweet spot evaluation result and the preset section length constraint, and the engineering sweet spot evaluation result is determined according to the geomechanical parameters. Finally, within the divided fracturing sections, solve the multi-objective function constructed according to the geological sweet spot evaluation result, the engineering sweet spot evaluation result, and the preset cluster spacing constraint, and perform well completion optimization design according to the objective solution result of the multi-objective function.

[0064] By introducing a weighted clustering model, it is not necessary to spend a great deal of human and time costs to explain the clustering results, and intelligent evaluation of geological sweet spots can be achieved. Through geomechanical parameters, accurate evaluation of engineering sweet spots can be carried out to determine the engineering sweet spot evaluation result, and then combined with the preset section length constraint, intelligent design of fracturing sections can be realized, solving the problem of unbalanced fracture initiation caused by the traditional design method using geometry or a single fracturing section spacing. By solving the multi-objective function, intelligent and refined well completion optimization design can be achieved, improving engineering applicability.

[0065] It should be noted that the terms "first", "second", etc. in the specification and claims of this application are used to distinguish similar objects and do not necessarily need to describe a specific order or sequence. It should be understood that such used data can be interchanged under appropriate circumstances for the embodiments of this application described herein.

[0066] It can be understood that the above method provided by the embodiments of this specification can be applied to an electronic device, which can refer to an electronic device with data calculation, processing, and storage capabilities. The electronic device can be a terminal such as a PC (Personal Computer), tablet computer, smart phone, wearable device, intelligent robot, etc.; it can also be a server. Among them, the server can be an independent physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing cloud computing services.

[0067] Referring to Figure 1 As shown, the embodiments of this specification provide an intelligent well completion optimization design method based on multi-objective optimization. Specifically, when implemented, the method may include the following:

[0068] S101: Cluster the first data set according to the weighted clustering model, and evaluate the geological sweet spots of each cluster after clustering to obtain a geological sweet spot evaluation result. The first data set includes various reservoir physical property parameters along the horizontal well depth, and the weighted clustering model is constructed according to the weights of the various reservoir physical property parameters.

[0069] In some embodiments, before the above S101, it is possible to first collect easily available and valuable data during drilling, well completion, and production processes, such as logging data, drilling data, and monitoring data after fracturing. Among them, logging data may include, but is not limited to: gamma ray logging (GR), density logging (DEN), acoustic logging (DT), neutron logging (CNL), resistivity logging (RT). Drilling data may include, but is not limited to: weight on bit (WOB), torque (T), rotary speed (N), rate of penetration (ROP), bit diameter (Ab). Monitoring data may include, but is not limited to: oil production profile data obtained through tracer diagnosis and fluid distribution data obtained through fiber optic monitoring.

[0070] Since the quality of the collected data has a greater impact on the performance of the subsequent built models and algorithms, and the original data usually contains discontinuities and anomalies caused by the environment, instrument performance, and human errors, it is necessary to perform data preprocessing on the collected data. Data preprocessing may include: using the KNN algorithm to fill in outliers and missing values in the collected data, unifying the accuracy of logging data and drilling data to 0.125m, etc., which are not specifically limited in this specification.

[0071] After that, reservoir physical property parameters and geomechanical parameters can be calculated based on the preprocessed drilling data and / or logging data. The specific calculation formulas can refer to the existing technology, and will not be elaborated in this specification. Among them, the reservoir physical property parameters can include at least one of the following: shale content, porosity, oil saturation, and permeability. The geomechanical parameters can include at least one of the following: bottom-hole mechanical specific energy and minimum horizontal principal stress. The reservoir physical property parameters can be used to evaluate geological sweet spots, and the geomechanical parameters can be used to evaluate engineering sweet spots. The reservoir physical property parameters and geomechanical parameters can be stored in ascending order of well depth, with an interval of 0.125 m. The reservoir physical property parameters and geomechanical parameters can effectively characterize the flow capacity, storage performance, and mechanical characteristics of the reservoir, and are calculated from oilfield logging and drilling data without the need for a dedicated logging program, ensuring the practical applicability of large-scale on-site implementation.

[0072] After that, in order to reduce noise and improve the reliability of subsequent clustering evaluation, noise reduction and smoothing processing can be performed on the reservoir physical property parameters and geomechanical parameters.

[0073] For example: Since the curves of the reservoir physical property parameters all represent spatially ordered data along the wellbore depth, and the depth axis is analogized to a time series, empirical mode decomposition (EMD) can be preferably used to perform noise reduction processing on the reservoir physical property parameters. The specific processing process is as follows:

[0074] 1) IMF extraction: Iteratively extract the signal extreme value envelopes to generate IMF components with frequencies from high to low;

[0075] 2) Noise component identification: Calculate the sample entropy values of the first two-order IMFs. If the entropy value exceeds the threshold of 1.2, it is determined as the noise-dominated component;

[0076] 3) Signal reconstruction: After removing the noise IMFs, superimpose the remaining IMFs and the residual term to obtain the denoised reservoir physical property parameters.

[0077] Then, standardization processing is performed on the reservoir physical property parameters after noise reduction processing. The specific method can refer to the existing technology and will not be elaborated in this specification. By using the standardization method, the reservoir physical property parameters can be converted into a standard normal distribution with a mean of 0 and a standard deviation of 1, eliminating the influence of different parameter dimensions on the data while maintaining the data distribution characteristics unchanged.

[0078] In some embodiments, before the above S101, in specific implementation, it may further include:

[0079] Calculate the correlation coefficient between each reservoir physical property parameter and the oil production profile data;

[0080] Determine the sum of the absolute values of the correlation coefficients between each reservoir physical property parameter and the oil production profile data;

[0081] Determine the weights of each reservoir physical property parameter according to the sum of the correlation coefficients and the absolute values of the correlation coefficients between the reservoir physical property parameters and the oil production profile data.

[0082] Specifically, first construct the first data set X1 according to each reservoir physical property parameter (such as: shale content V sh , porosity f, oil saturation So, permeability K) along the horizontal well depth:

[0083]

[0084] Among them, each row vector x i corresponds to the vector of each reservoir physical property parameter (φ, S o , k, V sh ) of the i-th first sample point.

[0085] Then, correlation analysis can be performed on each reservoir physical property parameter and the oil production profile data to calculate the correlation coefficients between each reservoir physical property parameter and the oil production profile data. Since the relationship between reservoir physical properties and oil production profile data is usually non-linear, the Spearman method can be selected to perform correlation analysis on each reservoir physical property parameter after noise reduction and smoothing processing and the oil production profile data in the monitoring data, and calculate the Spearman correlation coefficient. The Spearman method is a non-parametric statistical method that can evaluate monotonic relationships (linear or non-linear) without the assumption of normality and is robust to outliers. Specifically, the correlation coefficients between each reservoir physical property parameter and the oil production profile data can be calculated according to the following formula:

[0086]

[0087] Among them, r is the correlation coefficient; is the rank difference between the observed values of the j-th reservoir physical property parameter and the oil production profile data; n is the number of first sample points. Among them, the determination method of the rank difference can be: sort the reservoir physical property parameters and the oil production profile data, determine the ranks of the sorted reservoir physical property parameters and the ranks of the sorted oil production profile data, and then take the difference between the two to determine the rank difference between the observed values of the reservoir physical property parameters and the oil production profile data.

[0088] The sum of the absolute values of the correlation coefficients between each reservoir physical property parameter and the oil production profile data can be determined according to the following formula:

[0089]

[0090] The weights of each reservoir physical property parameter can be determined according to the following formula based on the correlation coefficients and the sum of the absolute values of the correlation coefficients between the reservoir physical property parameters and the oil production profile data (allocate weights according to the absolute values of the correlation coefficients and ensure that the sum of the weights of each reservoir physical property parameter is equal to 1):

[0091]

[0092] where w j is the weight of the j-th reservoir physical property parameter; r j is the correlation coefficient between the j-th reservoir physical property parameter and the oil production profile data; p is the total number of reservoir physical property parameters; |r j | is the absolute value of the correlation coefficient of the j-th reservoir physical property parameter; is the sum of the absolute values of the correlation coefficients between each reservoir physical property parameter and the oil production profile data.

[0093] In some embodiments, the weighted clustering model in S101 above is constructed according to the weights of each reservoir physical property parameter. In specific implementation, it may include:

[0094] Construct a weighted Euclidean distance function, a criterion function, and a rating function according to the weights of each reservoir physical property parameter; <s

[0095] Construct a weighted clustering model according to the weighted Euclidean distance function, the criterion function, and the rating function.

[0096] Specifically, the weighted Euclidean distance function can be constructed according to the following formula:

[0097]

[0098] where D(x i , c J ) is the weighted Euclidean distance, which can be used as the weighted Euclidean distance function; x i is the vector of each reservoir physical property parameter of the i-th first sample point; c J is the centroid of the J-th clustering cluster; p is the total number of reservoir physical property parameters; |w j | is the absolute value of the weight of the j-th reservoir physical property parameter; x ij is the j-th reservoir physical property parameter vector of the i-th first sample point; c Jj is the centroid of the j-th reservoir physical property parameter of the J-th clustering cluster. Among them, the weighted Euclidean distance function can be used to evaluate the distance between each first sample point and the corresponding cluster center within each clustering cluster. In order to enhance the influence of key rock physical property parameters on the clustering process, the weighted Euclidean distance can be used as the similarity measure between samples.

[0099] The criterion function can be constructed according to the following formula:

[0100]

[0101] where WSSE is the weighted sum of squared errors of K clusters, which can be used as the criterion function; K is the total number of preset clustering clusters; x iis the vector of reservoir physical property parameters for the i-th first sample point; C J are all the first samples belonging to the J-th clustering cluster; p is the total number of reservoir physical property parameters; |w j | is the absolute value of the weight of the j-th reservoir physical property parameter; x ij is the j-th reservoir physical property parameter vector of the i-th first sample point; c Jj is the centroid of the j-th reservoir physical property parameter of the J-th clustering cluster. Among them, K can be determined based on the "elbow method". When K is lower than a suitable value, increasing K will cause a significant reduction in WSSE, but when K exceeds this value, the reduction in WSSE can be ignored, and this value is the optimal K. A criterion function can be used to evaluate the clustering effect.

[0102] The rating function can be constructed according to the following formula:

[0103]

[0104] Among them, WGSSI J is the weighted geological sweet spot index of the clustering cluster J, which can be used as the rating function; f is the porosity; So is the oil saturation; K is the permeability; V sh is the shale content; w j is the weight of the j-th reservoir physical property parameter; is the 25th percentile of the j-th reservoir physical property parameter in the J-th clustering cluster; is the 75th percentile of the j-th reservoir physical property parameter in the J-th clustering cluster. Among them, the horizontal well interval is divided into K different clusters, but their relative quality cannot be directly evaluated. In order to quantitatively evaluate the reservoir quality and link the clustering results with the mechanism understanding, the weighted geological sweet spot index (WGSSI) is proposed. This index integrates the weights obtained from the correlation of oil production contributions to reflect the relative contributions of petrophysical parameters to reservoir performance. In order to minimize the influence of outliers, the interquartile range (i.e., the 25th to 75th percentiles) of the normalized values of each reservoir physical property parameter within each clustering cluster can be analyzed. The larger the WGSSI J value, the better the geological sweet spot and the more favorable the reservoir quality for production.

[0105] After that, based on the weighted Euclidean distance function, criterion function, and rating function, a mechanism-guided weighted K-medoids clustering model or algorithm can be constructed to achieve intelligent identification of geological sweet spots that conforms to mechanism cognition. The K-medoids clustering algorithm can improve the clustering effect by repeatedly replacing the reference points of the clustering cluster centers with each data point. Correlation analysis is performed on the physical property parameters of each reservoir and the oil production profile data to construct a weighted distance function, criterion function, and rating function that emphasize the key physical property parameters of the reservoir. This dual focus on the clustering center and the weighted function can enhance the robustness to outliers and better capture potential geological mechanisms.

[0106] In some embodiments, the clustering of the first data set according to the weighted clustering model in S101 above may specifically include:

[0107] Select a preset number of clustering centers from the first data set;

[0108] According to the weighted Euclidean distance function, calculate the weighted Euclidean distances from each first sample point in the first data set to the clustering centers, where each first sample point corresponds to the physical property parameters of each reservoir at different horizontal well depths;

[0109] Compare the weighted Euclidean distances, and according to the comparison results, divide each first sample point into the clustering cluster corresponding to the weighted Euclidean distance less than the preset distance threshold;

[0110] According to the criterion function, select new clustering centers from the clustering clusters;

[0111] Repeat the process of calculating the weighted Euclidean distance, dividing each first sample point, and selecting new clustering centers until the number of iterations reaches the preset iteration number threshold or the selected new clustering centers do not change, to obtain the first clustering result after clustering;

[0112] The evaluation of the geological sweet spots in each clustering cluster after clustering in S101 above to obtain the geological sweet spot evaluation result may specifically include:

[0113] Use the rating function to evaluate the geological sweet spots after clustering in the first clustering result to obtain the geological sweet spot evaluation result.

[0114] In some embodiments, the use of the rating function to evaluate the geological sweet spots after clustering in the first clustering result to obtain the geological sweet spot evaluation result may specifically include: [[ID=V28]]

[0115] Use the rating function to determine the weighted geological sweet spot index of each clustering cluster in the first clustering result;

[0116] Compare the weighted geological sweet spot indices of each clustering cluster, sort the comparison results of the weighted geological sweet spot indices in descending order to obtain the sorting result of the weighted geological sweet spot indices;

[0117] According to the sorting result of the weighted geological sweet spot indices, rate the corresponding geological sweet spots into different levels to obtain the geological sweet spot evaluation result, and the geological sweet spot evaluation result includes the geological sweet spot category label.

[0118] Specifically, the steps of the weighted K-medoids clustering algorithm (i.e., the above-mentioned weighted clustering model) for clustering the first data set are as follows:

[0119] 1) Initialization: Randomly select a preset number (e.g., K) of clustering centers from the first data set.

[0120] 2) Weighted Euclidean distance assignment: According to the weighted Euclidean distance function, calculate the weighted Euclidean distance from each first sample point to the K clustering centers, compare the weighted Euclidean distances, and divide them into the clustering cluster with the smallest weighted Euclidean distance (i.e., the weighted Euclidean distance is less than the preset distance threshold, and the preset distance threshold can be set according to actual needs, and this specification does not make specific limitations on this) according to the comparison result.

[0121] 3) Clustering center update: For each clustering cluster, select a new clustering cluster center by minimizing the criterion function WSSE.

[0122] 4) Iteration: Repeat steps 2)-3) until convergence (the selected new clustering center does not change) or the number of iterations reaches the preset iteration number threshold, and the preset iteration number threshold can be set according to actual needs, and this specification does not make specific limitations on this.

[0123] 5) Result: Use the rating function to label the first clustering result, and divide or rate the geological sweet spots into four categories (Ⅰ, Ⅱ, Ⅲ, Ⅳ), corresponding to "first level (high quality)", "second level (good)", "third level (general)", "fourth level (poor)" in sequence, corresponding to the weighted geological sweet spot index WGSSI. Specifically, the rating function can be used first to determine the weighted geological sweet spot indices of each clustering cluster in the first clustering result, then compare the weighted geological sweet spot indices of each clustering cluster, sort them in descending order according to the comparison result of the weighted geological sweet spot indices, and then rate the corresponding geological sweet spots into different levels according to the sorting result of the weighted geological sweet spot indices to obtain the geological sweet spot evaluation result. For example, the one with the most forward sorting has the largest weighted geological sweet spot index and the best geological sweet spot, and it can be rated as a first-level geological sweet spot. The one with the most backward sorting has the smallest weighted geological sweet spot index and the worst geological sweet spot, and it can be rated as a fourth-level geological sweet spot, etc. Among them, Ⅰ, Ⅱ, Ⅲ, Ⅳ can be used as the geological sweet spot category labels.

[0124] The main objective of geological sweet spot identification and evaluation is to delineate reservoirs with good reservoir flow capacity and reservoir properties (such as high porosity, high oil saturation, high permeability, and low clay content or low shale content). Clustering algorithms are usually used to divide well sections with similar reservoir properties into the same category. However, Euclidean-based unsupervised clustering techniques usually assign the same weights to reservoir rock physical property parameters, ignoring their different contributions to production dynamics. To address this limitation, this application constructs a mechanism-guided weighted clustering model according to the weights of each reservoir physical property parameter. Compared with traditional techniques, it can focus on reservoir physical property parameters that have a great impact on oil production, reduce the influence of reservoir physical property parameters with little impact on oil production on the clustering results, and achieve intelligent evaluation of geological sweet spots.

[0125] S102: Divide the fracturing sections according to the engineering sweet spot evaluation results and the preset section length constraint, where the engineering sweet spot evaluation results are determined according to geomechanical parameters.

[0126] In some embodiments, the engineering sweet spot evaluation results in S102 above are determined according to geomechanical parameters. In specific implementation, it may include:

[0127] Determine the geomechanical strength according to the bottom-hole mechanical specific energy and the minimum horizontal principal stress according to the following formula:

[0128] P Geo = MSE b + S hmin

[0129] Where P Geo is the geomechanical strength, Mpa; MSE b is the bottom-hole mechanical specific energy, Mpa; S hmin is the minimum horizontal principal stress, Mpa;

[0130] Evaluate the engineering sweet spot according to the distribution of the geomechanical strength to obtain the engineering sweet spot evaluation results.

[0131] Specifically, the bottom-hole mechanical specific energy MSE b can be used as a characterization of the reservoir rock mechanical strength and can effectively evaluate the crack resistance of the rock under different pressure conditions. The minimum horizontal principal stress S hmin plays a key role in the initiation and propagation of fractures and affects the deformation and failure modes of the rock. By considering these two factors comprehensively, the geomechanical characteristics of the reservoir can be evaluated more comprehensively, providing a scientific basis for engineering design, and finally forming engineering sweet spot parameters, which provides an important basis for the optimization design of well completion. The above geomechanical strength distribution can intuitively display the engineering sweet spots of the horizontal well section.

[0132] In some embodiments, each perforation cluster in a certain fracturing stage along the horizontal well has a corresponding fracture initiation pressure. When the wellbore pressure exceeds this threshold, the corresponding fracture will initiate. The fracture initiation condition can be expressed as:

[0133] P w >T str,eff,c +s init,c +Ds e,c +Ds i,c

[0134] where P w is the pressure in the wellbore (MPa); T str,eff,c is the effective tensile strength (MPa); s init,c is the stress shadow of the previous stage (MPa); Ds e,c is the stress shadow of other fractures in the same stage (MPa); Ds i,c is the initial magnitude of the minimum principal stress at the cluster (MPa).

[0135] In the fracturing initiation stage, when the fractures have not yet propagated extensively and the interference between fractures can be ignored, the fracture initiation pressure condition can be further simplified as:

[0136] P W 'V≥P Geo =MSE b +S hmin

[0137] where P W ' is the fracture initiation pressure, Mpa.

[0138] The engineering sweet spot can also be evaluated based on the geomechanical strength distribution and the fracture initiation pressure to obtain the engineering sweet spot evaluation result. For example: Moderate geologic strength and low fracture initiation pressure indicate high fracturing efficiency and controllable fractures, and can be preferentially developed. The corresponding engineering sweet spot can be rated as a first-level (high-quality) engineering sweet spot. Excessively high / low geologic strength or high fracture initiation pressure indicates high fracturing risk and is not recommended for development. The corresponding engineering sweet spot can be rated as a non-sweet spot, etc.

[0139] In some embodiments, the engineering sweet spot evaluation result in S102 above may include the geomechanical strength along the horizontal well depth; correspondingly, dividing the fracturing stage according to the engineering sweet spot evaluation result and the preset section length constraint in S102 above may include:

[0140] Constructing a second data set based on the geomechanical strength along the horizontal well depth and the well depth, where each second sample point in the second data set corresponds to different well depths and the geomechanical strength at different horizontal well depths;

[0141] Construct a geomechanical similarity term based on the geomechanical strength of the second sample points and the average geomechanical strength of all the second sample points;

[0142] Construct a section length penalty term according to the well depth range of the fracturing section and the preset section length constraint;

[0143] Construct an objective function for dividing the fracturing section based on the geomechanical similarity term and the section length penalty term;

[0144] Solve the objective function by using a dynamic programming algorithm to determine the segmentation points of the fracturing section;

[0145] Divide the fracturing section according to the segmentation points to obtain the fracturing section division result, where the fracturing section division result includes section labels.

[0146] Specifically, the geomechanical strength and well depth along the horizontal well depth can be collected first to construct or form a second data set where x I corresponds to the well depth and geomechanical strength information of the I-th second sample point. Determine the preset section length constraint, such as setting the target section length interval [a, b].

[0147] Then, according to the geomechanical strength X Q of the I-th second sample point in the well depth set S I in the Q-th fracturing section and the average geomechanical strength m Q of all the second sample points in the Q-th fracturing section, construct a geomechanical similarity term according to the following formula, that is, for the Q-th fracturing section, the mean square error of its internal sample X I can be expressed as:

[0148]

[0149] where the geomechanical similarity term can be used to measure the difference in geomechanical strength between well sections in the same fracturing section, and the sum of squared errors is used as the measurement index in this application.

[0150] Then, according to the well depth range L Q of the Q-th fracturing section and the preset section length constraint L target (i.e., the target section length interval, such as [a, b]), construct a section length penalty term Penalty(L Q ) according to the following formula:

[0151] Penalty(L Q )=(L Q -L target ) 2

[0152] Among them, to ensure that the well depth range of each fracturing stage falls within the target stage length interval [a, b] (this interval can be determined according to the geological and engineering characteristics of different blocks), when there is a deviation between the actual stage length and the target stage length (such as the median of the interval), the above-mentioned stage length penalty term can be introduced.

[0153] Then, according to the geomechanics similarity term and the stage length penalty term Penalty(L Q ), the objective function for dividing the fracturing stages is constructed according to the following formula:

[0154]

[0155] Among them, M is the objective function for dividing the fracturing stages; K is the total number of fracturing stages (i.e., the total number of clustering clusters); S Q is the set of well depths within the Qth fracturing stage; X I is the geomechanics strength of the Ith second sample point; m Q is the average geomechanics strength of all second sample points within the Qth fracturing stage; λ is the weight factor for regulating the balance between the geomechanics similarity term and the stage length penalty term; L Q is the well depth range of the Qth fracturing stage.

[0156] After that, the dynamic programming algorithm (DP algorithm) can be used to solve the objective function M to determine the segmentation points of the fracturing stages. Furthermore, the fracturing stages can be divided according to the segmentation points of the fracturing stages to obtain the fracturing stage division result. The specific steps are as follows:

[0157] 1) State definition: Let D I represent the optimal objective function value of the first I second sample points (sample indices from 0 to I - 1), and record the best segmentation point seg[I], that is, the index at the end of the previous segment.

[0158] 2) State transition: For each second sample point I, only consider the candidate starting point G such that the well depth difference = Depth[I - 1] - Depth[G] falls within the target stage length interval [a, b], and calculate the objective function value M(G, I) within the interval [G, I). The state transition equation is:

[0159]

[0160] 3) Global optimal solution and backtracking: After using dynamic programming to recursively calculate D(n), the optimal segmentation boundary index is obtained through backtracking to determine the starting and ending positions of each fracturing stage, thereby realizing the intelligent division of the fracturing stages.

[0161] For example: Suppose there are the following well depth and geomechanics strength data (constituting the second dataset):

[0162]

[0163] The target segment length interval [a, b] = [150, 250], and the weight factor λ = 1.

[0164] Step 1. Initialization:

[0165] D(0) = 0

[0166] seg[0] = -1

[0167] Step 2. State transition:

[0168] For each second sample point I from 1 to 9, calculate D I :

[0169] For I = 1:

[0170] The candidate starting point G = 0

[0171] Calculate M(0, 1) = 40000;

[0172] D(1) = D(0) + M(0, 1) == 0 + 40000 = 40000

[0173] seg[1] = 0

[0174] For I = 2:

[0175] The candidate starting point G = 0, 1

[0176] Calculate M(0, 2) and M(1, 2);

[0177] Select the minimum:

[0178] D(2) = min(D(0) + M(0, 2), D(1) + M(1, 2))

[0179] Update seg[2]

[0180] Repeat the above process until I = 9.

[0181] Step 3. Backtracking: Obtain the optimal segmentation boundary index through backtracking to determine the start and end positions (segmentation points) of each fracturing stage, so as to divide the fracturing stages. Among them, the fracturing stage division result can include segment labels.

[0182] The above dynamic programming algorithm is an effective method for solving sequential optimization problems, especially suitable for finding the global optimal segmentation in a non-convex solution space. The dynamic programming algorithm divides the second data set (including well depth and geomechanical strength along the horizontal well depth) into K segments, and finds the optimal segment division solution by minimizing the objective function. Its goal is to divide the wellbore into fracturing segments, while ensuring that the geomechanical properties within the fracturing segments are as similar as possible and meeting the predetermined segment length requirements. By using the dynamic programming algorithm, well segments with similar geomechanical strengths can be divided into the same fracturing segment. This method integrates well depth data and geomechanical strength indicators, while maintaining the spatial continuity of reservoir intervals. Taking the similar geomechanical strength within the segment as the objective function and imposing a segment length constraint penalty term according to construction requirements, it realizes the intelligent division of fracturing segments and provides support for the intelligent optimization selection of subsequent perforation clusters.

[0183] S103: Within the divided fracturing segments, solve the multi-objective function constructed based on the geological sweet spot evaluation result, engineering sweet spot evaluation result, and preset cluster spacing constraint, and perform well completion optimization design according to the objective solution result of the multi-objective function.

[0184] In some embodiments, before the above S103, in specific implementation, it may further include:

[0185] Determine the geological sweet spot weight according to the geological sweet spot category label in the geological sweet spot evaluation result;

[0186] Identify the fracturing segments according to the segment labels in the fracturing segment division result and impose constraints on the fracturing clusters within the fracturing segments, so that the constrained fracturing clusters are within the preset segment depth range;

[0187] Generate candidate regions according to the geomechanical strength along the horizontal well depth, and generate candidate clusters from the candidate regions;

[0188] Take the sum of the geological sweet spot weights being greater than the preset weight threshold as the first objective, the geomechanical similarity term being less than the preset variance threshold as the second objective, and the preset cluster spacing requirement as the constraint condition;

[0189] Construct a multi-objective function according to the first objective, the second objective, and the constraint condition.

[0190] Specifically, according to the geological sweet spot category label, the geological sweet spot weight W can be determined according to the following formula:

[0191] W i = 5 - Class i

[0192] Among them, when i = 1, it is the Ⅰ label (first-level Class), and the maximum weight W1 = 4 is obtained. When i = 4, it is the Ⅳ label (fourth-level Class), and the maximum weight W4 = 1 is obtained. This geological sweet spot weight will be used to construct a multi-objective function, so as to perform multi-objective optimization to screen perforation clusters or fracturing clusters.

[0193] Then, segment labels can be used to identify fracturing segments, and constraints are imposed on the fracturing clusters within each fracturing segment. In this way, all fracturing clusters within a fracturing segment must be located within a preset segment depth range:

[0194]

[0195] Among them, is the well depth coordinate of the Jth clustering cluster in the nth fracturing segment.

[0196] Then, engineering sweet spot labels (geomechanical strength along the horizontal well depth) can be used to generate candidate regions. Different from the traditional fixed threshold method, the candidate regions in this application are dynamically defined: the second sample points within the range of the engineering sweet spot average value m ± 10% are determined as high-quality engineering sweet spot regions P Eng , and are the input sample sets used for subsequent clustering:

[0197] P Eng ∈[0.9m n , 1.1m n

[0198] Then, the DBSCAN clustering algorithm can be selected to further refine and select reasonable initial cluster centers within the candidate regions (that is, generate candidate clusters from the candidate regions), so as to create better convergence conditions for subsequent multi-objective optimization. Among them, DBSCAN can automatically identify clusters according to data density without defining the number of clusters. DBSCAN can automatically identify high-density areas, ensuring that candidate clusters do not cross well sections with drastic changes in geomechanical properties. Specifically, the steps of generating candidate clusters using the DBSCAN clustering algorithm are as follows:

[0199] Step 1: Data standardization:

[0200] Within the candidate region, the two-dimensional data composed of Depth and Pgeo is standardized so that DBSCAN can perform clustering on an unbiased scale.

[0201] ​Among them, the hyperparameters to be set are the neighborhood radius eps and the minimum number of samples min_samples. eps (neighborhood radius): It can be used to define the density reachable range of a point. This value can be adjusted according to the distribution characteristics of the data, and the common value range is 0.1 - 0.5. In this paper, it is set to 0.3. min_samples (minimum number of samples): It sets the minimum number of sample points that a cluster should contain to ensure that only sufficiently dense clusters are formed. For candidate region data points with a small number (<1000), the common value range is 3 - 5. In this paper, it is set to 5.

[0202] Step 2. Clustering and noise filtering:

[0203] DBSCAN identifies the density reachable relationship of data points according to eps and min_samples, classifies the interconnected high-density regions into the same cluster, and marks the low-density regions as noise points (label = -1). Filter out the noise points that do not belong to any dense region.

[0204] Step 3. Generation of candidate cluster centers:

[0205] Generate a set of candidate cluster centers, representing the dense regions of the best points of high-quality engineering, which meet the predefined engineering standards.

[0206] By optimizing the cluster centers (generating candidate clusters), it can provide a well-constrained and physically meaningful initial solution space for subsequent multi-objective optimization.

[0207] Then, the sum of the geological sweet spot weights being greater than the preset weight threshold can be used as the first objective (i.e., maximizing the geological sweet spot score) to ensure that the selected cluster centers correspond to regions with favorable reservoir conditions. Specifically, the construction formula of the first objective f1 is as follows:

[0208]

[0209] where, W i is the geological sweet spot weight of the i-th first sample point; S J is the set of first sample points of the J-th clustering cluster.

[0210] The geological mechanics similarity term being less than the preset variance threshold can be used as the second objective (i.e., minimizing the variance of geological mechanics strength). This objective minimizes the difference in geological mechanics strength between clusters to ensure that the clusters exhibit similar mechanical properties. Specifically, the construction formula of the second objective f2 is as follows:

[0211]

[0212] where, X I is the geological mechanics strength of the I-th second sample point; m Qis the average geomechanical strength of all the second sample points within the Qth fracturing stage; S Q is the well depth set within the Qth fracturing stage.

[0213] The preset cluster spacing requirement can be used as a constraint condition. To prevent the selected cluster spacing from being too close or too far, the adjacent clusters must maintain a spacing of 10m - 30m to reduce fracture interference and stimulation efficiency. Specifically, when the depth difference is less than 10m or greater than 30m, the following fixed penalty is imposed:

[0214] 10m £ |c J -c J+1 | £ 30m

[0215] where c J is the well depth of the Jth clustering cluster.

[0216] Finally, a multi-objective function can be constructed based on the first objective, the second objective, and the constraint conditions.

[0217] In some embodiments, the solution in the above S103 for the multi-objective function constructed based on the geological sweet spot evaluation result, the engineering sweet spot evaluation result, and the preset cluster spacing constraint may, in specific implementation, include:

[0218] Adopt a multi-objective optimization algorithm to solve the multi-objective function, and determine the objective solution result of the multi-objective function from the candidate clusters;

[0219] The well completion optimization design according to the objective solution result of the multi-objective function in the above S103 may, in specific implementation, include:

[0220] Take the objective solution result as the design scheme of the fracturing clusters within the fracturing stage, and conduct well completion optimization design according to the design scheme of the fracturing clusters.

[0221] Specifically, a multi-objective optimization algorithm (such as: NSGA-II algorithm) can be used to solve the multi-objective function, and the optimal solution result (i.e., the objective solution result) of the multi-objective function can be determined from the candidate clusters as the target design scheme of the fracturing clusters or perforating clusters. The target design scheme may include the optimal perforating cluster set, and thus can provide key inputs for intelligent well completion design to ensure the optimal perforating position and quantity.

[0222] Among them, the specific steps of the NSGA-II algorithm are as follows:

[0223] 1) Population encoding and initialization: The candidate solutions are encoded as binary vectors, and each gene corresponds to a candidate cluster (1 represents selection, 0 represents exclusion). The initial population size is set to 100, and it is initialized to be 50% biased towards a random distribution.

[0224] 2) Fitness evaluation: For each individual, calculate the geological sweet spot score and the variance of geomechanical strength by allocating data to clusters according to the nearest depth. Integrate spatial constraints into the objective function value.

[0225] 3) Non-dominated sorting and crowding distance: All individuals are sorted using non-dominated sorting to generate the Pareto front. Within each Pareto front, calculate the crowding distance to maintain population diversity.

[0226] 4) Selection, crossover, and mutation: Use binary tournament selection with crowding comparison. Apply simulated binary crossover (SBX) and stochastic exponential mutation to generate offspring. The crossover probability is set to 0.7, and the mutation probability is set to 0.3.

[0227] 5) Population update and iteration: Combine the parent population and the offspring population, and use non-dominated sorting and crowding distance to select the next generation. This process is iterated 100 generations or until convergence.

[0228] 6) Optimal solution extraction and post-processing: Extract the Pareto optimal set from the final population, select an optimal individual from it, apply a small random perturbation to the selected clusters, and obtain the final optimized cluster set.

[0229] Since the optimization of perforation clusters requires comprehensive consideration of geological sweet spots, engineering sweet spots, and construction constraints, which is a typical non-linear optimization problem, it is necessary to construct reasonable objective functions and constraint conditions. This application first uses the threshold method to obtain ±10% of the average geomechanical strength within the fracturing section, and based on the threshold and the collar position, obtains a candidate cluster set. Then, the DBCAN density clustering algorithm is used to generate candidate cluster centers. As a density-based clustering method, DBSCAN does not require pre-defining the number of clusters and can autonomously identify high-density regions, thus preventing candidate clusters from spanning well sections with significant changes in geomechanical strength, and finally forming a candidate cluster set. Then, the NSGA-II multi-objective optimization algorithm is used to construct a multi-objective function with the minimum difference in geomechanical strength of the optimized clusters within the section (from the perspective of engineering sweet spots), the maximization of geological sweet spot scores, and the penalty term for the construction cluster spacing requirements. Use Pareto front search in the candidate clusters to generate the optimal set, which is the optimal perforation cluster set. Finally, a specific completion plan can be formulated according to the optimized perforation cluster design plan to ensure the maximization of fracturing and production effects.

[0230] For example: Suppose a certain fracturing section contains the following 10 sample points:

[0231]

[0232] First, perform data processing:

[0233] [[ID=**27]]1. Geological sweet spot weight assignment:

[0234] Classi = Class1 = Ⅰ(Weight 4), Ⅱ(Weight 3), Ⅲ(Weight 2), Ⅳ(Weight 1).

[0235] For example: The weight W1 of sample 1 is 4, and the weight W4 of sample 4 is 1

[0236] 2. Intra-segment constraint:

[0237] All clusters must be within the depth range of segment 1 (2000m - 2050m).

[0238] 3. Generation of candidate areas for engineering sweet spots:

[0239] Calculate the mean m of the engineering sweet spot strength as 31.9MPa, with a dynamic range of 31.9 ± 3.19MPa (i.e., 28.7 - 35.1MPa);

[0240] Screen samples that meet the conditions: Sample 1 (35), 2 (32), 3 (30), 5 (36), 7 (33), 8 (34), 9 (37).

[0241] Candidate area samples: Sample 1, 2, 3, 5, 7, 8, 9.

[0242] Then, perform initialization of candidate clusters based on DBSCAN:

[0243] 1. Data standardization:

[0244] Standardize the well depth (Depth) and the geological sweet spot weight (Pgeo) to eliminate the influence of dimensions.

[0245] 2. DBSCAN parameter setting:

[0246] eps = 0.3 (neighborhood radius), min_samples = 5 (minimum number of samples).

[0247] 3. Clustering results:

[0248] Cluster 1: Sample 1 (2000m), 2 (2005m), 3 (2010m), 5 (2020m), 7 (2030m), 8 (2035m);

[0249] Cluster 2: Sample 9 (2040m);

[0250] Noise point: Sample 5 (2020m) is filtered due to insufficient density (assumed).

[0251] 4. Extraction of candidate cluster centers:

[0252] Center of Cluster 1: Well depth 2016.7m, mean of geological sweet spot weight 3.5;

[0253] Cluster 2 center: well depth 2040m, geological sweet spot weight 4.

[0254] Then, conduct perforation cluster optimization based on NSGA-II:

[0255] 1. Optimization objectives and constraints:

[0256] Objective 1: Minimize the variance of geomechanical strength among clusters;

[0257] Objective 2: Maximize the total score of geological sweet spot evaluation;

[0258] Constraint: The cluster spacing needs to be within the range of 10 - 30m.

[0259] 2. Set NSGA-II parameters:

[0260] Population size: 100, number of iterations: 100;

[0261] Crossover probability: 0.7, mutation probability: 0.3.

[0262] 3. Instance optimization process:

[0263] 1) Population coding:

[0264] The candidate clusters are Cluster 1 and Cluster 2, encoded as a binary vector (e.g., [1,0] means selecting Cluster 1)

[0265] 2) Fitness calculation:

[0266] Scenario 1: Select Cluster 1 and Cluster 2 (encoding [1,1]).

[0267] Geomechanical strength variance: Cluster 1 (30.8 - 36MPa), Cluster 2 (37MPa), the variance is large.

[0268] Geological sweet spot score: Cluster 1 weight sum = 4 + 3 + 4 + 4 = 15, Cluster 2 = 4, total score = 19.

[0269] Constraint penalty: Cluster spacing = 2040 - 2016.7 = 23.3m (met, no penalty).

[0270] Scenario 2: Only select Cluster 1 (encoding [1,0]).

[0271] Geomechanical strength variance: Intra-cluster variance of Cluster 1 = 2.8.

[0272] Geological sweet spot score = 15.

[0273] There is no cluster spacing constraint (only a single cluster).

[0274] 3) Pareto front solution:

[0275] Solution A (select Cluster 1 + Cluster 2): Total score is 19, with a high variance.

[0276] Solution B (only select Cluster 1): Total score is 15, with a low variance.

[0277] 4) Optimal solution selection:

[0278] If giving priority to balancing the total score and variance, select Solution A and apply a random perturbation (such as adjusting the center of Cluster 1 to 2015m).

[0279] Finally, through the collaborative optimization of DBSCAN and NSGA-II, Cluster 1 (2000 - 2035m) is finally selected as the optimal perforation cluster, which has a high geological sweetness score (15), a low variance of geomechanical strength (2.8), and meets the in-segment depth constraint. If multiple clusters are required, the distance between candidate clusters needs to be adjusted or the constraint conditions need to be relaxed.

[0280] Each embodiment in this specification is described in a progressive manner. The same or similar parts among the embodiments can be referred to each other, and the key point of each embodiment is to illustrate the differences from other embodiments. Specifically, reference can be made to the descriptions of the relevant previous embodiments, and details will not be repeated here.

[0281] The above is an explanation of this method. However, it should be noted that this specific embodiment is only for better explaining this application and describes a specific embodiment of the specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be executed in a different order from that in the embodiments and still achieve the desired results. Additionally, the processes depicted in the drawings do not necessarily require the specific order or consecutive order shown to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be beneficial.

[0282] In a specific implementation scenario, refer to Figure 2 As shown, the process of the intelligent well completion optimization design method based on multi-objective optimization can be as follows:

[0283] I. Data processing

[0284] Collect easily obtained and valuable data during drilling, well completion, and production processes, such as logging data (0.125m), drilling data (1m), and monitoring data after fracturing. Use Exploratory Data Analysis (EDA) to understand the structure, distribution, and quality of logging data and drilling data through statistical methods and visualization. Then, perform preprocessing on logging data and drilling data, such as unified measurement, outlier handling, and missing value filling. Calculate reservoir physical property parameters and geomechanical parameters based on the preprocessed drilling data and / or logging data. Further, perform smoothing and noise reduction processing on reservoir physical property parameters and geomechanical parameters to form a single-well dataset. The monitoring data after fracturing can include tracer monitoring and fiber optic monitoring. Tracer detection can obtain the oil production contribution rate / section (i.e., oil production profile data), and fiber optic monitoring can obtain the fluid distribution volume / cluster, which can be used for monitoring and interpretation.

[0285] II. Models and Algorithms

[0286] First, perform a correlation analysis on each reservoir physical property parameter and oil production profile data, calculate the Spearman correlation coefficient, and then determine the weights of each reservoir physical property parameter. Then, construct a weighted Euclidean distance function, a criterion function, and a rating function based on the weights of each reservoir physical property parameter. Then, based on the weighted Euclidean distance function, the criterion function, and the rating function, construct a mechanism-guided weighted K-medoids clustering model or algorithm. Among them, determine the total number of preset clustering clusters K based on the "elbow method". The weighted Euclidean distance function and the criterion function can be used for clustering, and the rating function can be used to evaluate the geological sweet spots after clustering in the first clustering result to obtain the geological sweet spot evaluation result.

[0287] The geological mechanical strength can be determined according to the bottom hole mechanical specific energy MSE b and the minimum horizontal principal stress S hmin and then the engineering sweet spot evaluation can be carried out. The objective function for dividing the fracturing section can be constructed according to the geomechanical similarity term (similar geomechanical strength) and the section length penalty term (fracturing section length limit penalty term). Use the dynamic programming algorithm (DP) to solve the objective function for dividing the fracturing section, globally optimize, and determine the start and end positions (section points) of each fracturing section, so that the fracturing section can be divided and the optimization of the fracturing section can be realized.

[0288] After dividing the fracturing sections, the mean value of the geomechanical strength within the fracturing section can be obtained using the threshold method, and candidate cluster clusters can be obtained based on the threshold and collar positions. Then, the DBCAN density clustering algorithm is used to generate candidate cluster centers, and finally, initial candidate clusters or candidate clusters are formed. A multi-objective function is constructed according to the geological sweet spot evaluation results, engineering sweet spot evaluation results, and preset cluster spacing requirements (cluster spacing limit). The NSGA-II multi-objective optimization algorithm is used to further select the optimal perforation cluster set from the candidate clusters on the premise of meeting physical constraints, realizing the optimization design of perforation clusters, and thus providing key inputs for intelligent well completion design to ensure the optimal perforation position and quantity.

[0289] By using correlation analysis to quantify the relationship between reservoir physical property parameters and oil production profile data, a mechanism-guided weighted Euclidean clustering is constructed, and a mechanism-guided weighted clustering model is established, so that a more geology-principle-compliant sweet spot evaluation can be carried out.

[0290] By constructing an objective function for dividing the fracturing sections according to the geomechanical similarity term and section length penalty term, not only the geomechanical strength is considered, but also the constraints of the fracturing section length and spatial continuity are integrated, which enables the DP algorithm to automatically generate a reasonable fracturing section design without manual intervention.

[0291] Based on the candidate clusters generated by the threshold method and DBSCAN density clustering, a multi-objective optimization algorithm is used to incorporate geological sweet spots, engineering sweet spots, and perforation cluster spacing into its objective function and penalty terms. This can not only ensure that the candidate clusters have similar geomechanical conditions, but also maximize the quality of geological sweet spots, reduce interference between fractures and collar damage, thereby improving the stimulation effectiveness.

[0292] Although this specification provides method operation steps or device structures as described in the following embodiments or as shown in the attached Figure 3 figures, more or fewer operation steps or module units may be included in the method or device based on routine or non-creative labor. In steps or structures where there is no necessary causal relationship logically, the execution order of these steps or the module structure of the device is not limited to the execution order or module structure shown in the embodiments of this specification or the attached figures. When the described method or module structure is applied to actual devices, servers, or terminal products, it can be executed sequentially or in parallel according to the method or module structure shown in the embodiments or the attached figures (for example, in an environment of parallel processors or multi-threaded processing, even including distributed processing and server cluster implementation environments). Based on the above intelligent well completion optimization design method based on multi-objective optimization, an embodiment of an intelligent well completion optimization design device based on multi-objective optimization is also proposed in the embodiments of this specification. As Figure 3 shown, the device may specifically include the following modules:

[0293] The geological sweet spot evaluation module 301 can be used to cluster the first data set according to a weighted clustering model and evaluate the geological sweet spots of each cluster after clustering to obtain a geological sweet spot evaluation result. The first data set includes various reservoir physical property parameters along the horizontal well depth, and the weighted clustering model is constructed based on the weights of various reservoir physical property parameters.

[0294] The fracturing stage division module 302 can be used to divide fracturing stages according to the engineering sweet spot evaluation result and a preset stage length constraint. The engineering sweet spot evaluation result is determined based on geological mechanics parameters.

[0295] The well completion optimization design module 303 can be used to solve a multi-objective function constructed based on the geological sweet spot evaluation result, the engineering sweet spot evaluation result, and a preset cluster spacing constraint within the divided fracturing stages, and perform well completion optimization design according to the objective solution result of the multi-objective function.

[0296] In some embodiments, before the above-mentioned geological sweet spot evaluation module 301, it can specifically be used to calculate the correlation coefficient between each reservoir physical property parameter and the oil production profile data; determine the sum of the absolute values of the correlation coefficients between each reservoir physical property parameter and the oil production profile data; and determine the weight of each reservoir physical property parameter according to the correlation coefficient between the reservoir physical property parameter and the oil production profile data and the sum of the absolute values of the correlation coefficients.

[0297] In some embodiments, the above-mentioned geological sweet spot evaluation module 301 can specifically be used to construct a weighted Euclidean distance function, a criterion function, and a rating function according to the weights of each reservoir physical property parameter; and construct a weighted clustering model according to the weighted Euclidean distance function, the criterion function, and the rating function.

[0298] In some embodiments, the above-mentioned geological sweet spot evaluation module 301 can specifically further be used to select a preset number of cluster centers from the first data set; calculate the weighted Euclidean distance from each first sample point in the first data set to the cluster centers according to the weighted Euclidean distance function, where each first sample point corresponds to various reservoir physical property parameters at different horizontal well depths; compare the weighted Euclidean distances, and divide each first sample point into the corresponding cluster cluster where the weighted Euclidean distance is less than a preset distance threshold according to the comparison result; select new cluster centers from the cluster clusters according to the criterion function; repeat the process of calculating the weighted Euclidean distance, dividing each first sample point, and selecting new cluster centers until the number of iterations reaches a preset iteration number threshold or the selected new cluster centers do not change, to obtain the first clustering result after clustering; and use the rating function to evaluate the geological sweet spots after clustering in the first clustering result to obtain a geological sweet spot evaluation result.

[0299] In some embodiments, the above-mentioned geological sweet spot evaluation module 301 may specifically further be configured to use a rating function to determine the weighted geological sweet spot index of each clustering cluster in the first clustering result; compare the weighted geological sweet spot indices of each clustering cluster, perform a descending order on the comparison result of the weighted geological sweet spot indices to obtain the sorting result of the weighted geological sweet spot indices; according to the sorting result of the weighted geological sweet spot indices, rate the corresponding geological sweet spots into different levels to obtain the geological sweet spot evaluation result, and the geological sweet spot evaluation result includes geological sweet spot category labels.

[0300] In some embodiments, the above-mentioned engineering sweet spot evaluation result includes the geomechanical strength along the horizontal well depth; correspondingly, the above-mentioned fracturing stage division module 302 may specifically be configured to construct a second data set according to the geomechanical strength along the horizontal well depth and the well depth, and each second sample point in the second data set corresponds to different well depths and the geomechanical strength at different horizontal well depths; construct a geomechanical similarity term according to the geomechanical strength of the second sample points and the average geomechanical strength of all second sample points; construct a stage length penalty term according to the well depth range of the fracturing stage and the preset stage length constraint; construct an objective function for dividing the fracturing stage according to the geomechanical similarity term and the stage length penalty term; use a dynamic programming algorithm to solve the objective function to determine the segmentation points of the fracturing stage; divide the fracturing stage according to the segmentation points to obtain the fracturing stage division result, and the fracturing stage division result includes stage labels.

[0301] In some embodiments, before the above-mentioned completion optimization design module 303, it may specifically be configured to determine the geological sweet spot weight according to the geological sweet spot category label in the geological sweet spot evaluation result; identify the fracturing stage according to the stage label in the fracturing stage division result and impose constraints on the fracturing clusters within the fracturing stage so that the constrained fracturing clusters are within the preset stage depth range; generate candidate regions according to the geomechanical strength along the horizontal well depth, and generate candidate clusters from the candidate regions; use the sum of the geological sweet spot weights being greater than a preset weight threshold as the first objective, the geomechanical similarity term being less than a preset variance threshold as the second objective, and the preset cluster spacing requirement as the constraint condition; construct a multi-objective function according to the first objective, the second objective and the constraint condition.

[0302] In some embodiments, the above-mentioned completion optimization design module 303 may specifically be configured to use a multi-objective optimization algorithm to solve the multi-objective function, and determine the objective solution result of the multi-objective function from the candidate clusters; use the objective solution result as the target design scheme for the fracturing clusters within the fracturing stage, and perform completion optimization design according to the target design scheme of the fracturing clusters.

[0303] As can be seen from the above, an intelligent well completion optimization design device based on multi-objective optimization provided by the embodiments of this specification can achieve the automated and intelligent design of the positions of fracturing stages and perforation clusters, thereby providing a new technical approach for the optimized well completion design of unconventional oil and gas reservoirs and having important engineering applicability.

[0304] The embodiments of this specification also provide an electronic device based on the above intelligent well completion optimization design method based on multi-objective optimization, including a processor and a memory for storing processor-executable programs / instructions. When specifically implemented, the processor may execute the following steps according to the programs / instructions: clustering a first data set according to a weighted clustering model, and evaluating the geological sweet spots of each cluster after clustering to obtain a geological sweet spot evaluation result, where the first data set includes various reservoir physical property parameters along the horizontal well depth, and the weighted clustering model is constructed according to the weights of the various reservoir physical property parameters; dividing fracturing stages according to the engineering sweet spot evaluation result and a preset section length constraint, where the engineering sweet spot evaluation result is determined according to geological mechanics parameters; in the divided fracturing stages, solving a multi-objective function constructed according to the geological sweet spot evaluation result, the engineering sweet spot evaluation result, and a preset cluster spacing constraint, and performing well completion optimization design according to the objective solution result of the multi-objective function.

[0305] In order to be able to complete the above instructions more accurately, refer to Figure 4 As shown, the embodiments of this specification also provide another specific electronic device, where the electronic device includes a network communication port 401, a processor 402, and a memory 403, and the above structures are connected by internal cables so that each structure can perform specific data interactions.

[0306] Among them, the processor 402 may specifically be used to cluster a first data set according to a weighted clustering model, and evaluate the geological sweet spots of each cluster after clustering to obtain a geological sweet spot evaluation result, where the first data set includes various reservoir physical property parameters along the horizontal well depth, and the weighted clustering model is constructed according to the weights of the various reservoir physical property parameters; dividing fracturing stages according to the engineering sweet spot evaluation result and a preset section length constraint, where the engineering sweet spot evaluation result is determined according to geological mechanics parameters; in the divided fracturing stages, solving a multi-objective function constructed according to the geological sweet spot evaluation result, the engineering sweet spot evaluation result, and a preset cluster spacing constraint, and performing well completion optimization design according to the objective solution result of the multi-objective function.

[0307] The memory 403 may specifically be used to store the corresponding instruction programs.

[0308] In this embodiment, the network communication port 401 can be bound to different communication protocols, so as to send or receive different data through virtual ports. For example, the network communication port can be a port responsible for web data communication, a port responsible for FTP data communication, or a port responsible for mail data communication. In addition, the network communication port can also be a physical communication interface or communication chip. For example, it can be a wireless mobile network communication chip, such as GSM, CDMA, etc.; it can also be a Wifi chip; it can also be a Bluetooth chip.

[0309] In this embodiment, the processor 402 can be implemented in any suitable manner. For example, the processor can be in the form of, for example, a microprocessor or a processor, and a computer-readable medium storing computer-readable program code (such as software or firmware) executable by the (micro)processor, logic gates, switches, application specific integrated circuit (ASIC), programmable logic controller, and embedded microcontroller, etc. This specification does not make any limitations.

[0310] In this embodiment, the memory 403 can include multiple levels. In a digital system, anything that can store binary data can be a memory; in an integrated circuit, a circuit with a storage function without a physical form is also called a memory, such as RAM, FIFO, etc.; in a system, a storage device with a physical form is also called a memory, such as a memory module, TF card, etc.

[0311] The embodiments of this specification also provide a computer storage medium based on the above intelligent well completion optimization design method based on multi-objective optimization. The computer storage medium stores computer programs / instructions, which when executed, implement: clustering a first data set according to a weighted clustering model, and evaluating the geological sweet spots of each cluster after clustering to obtain a geological sweet spot evaluation result. The first data set includes various reservoir physical property parameters along the horizontal well depth, and the weighted clustering model is constructed according to the weights of various reservoir physical property parameters; dividing fracturing sections according to the engineering sweet spot evaluation result and a preset section length constraint, and the engineering sweet spot evaluation result is determined according to geological mechanics parameters; within the divided fracturing sections, solving a multi-objective function constructed according to the geological sweet spot evaluation result, the engineering sweet spot evaluation result, and a preset cluster spacing constraint, and performing well completion optimization design according to the objective solution result of the multi-objective function.

[0312] In this embodiment, the above storage medium includes, but is not limited to, random access memory (RAM), read-only memory (ROM), cache, hard disk drive (HDD), or memory card. The memory can be used to store computer program instructions. The network communication unit can be set according to the standards specified by the communication protocol and is an interface for network connection and communication.

[0313] In this embodiment, the functions and effects specifically implemented by the program instructions stored in the computer storage medium can be explained by comparison with other embodiments and will not be elaborated here.

[0314] Although this specification provides method operation steps as described in the embodiments or flowcharts, more or fewer operation steps may be included based on conventional or non-creative means. The step order listed in the embodiments is only one way among the execution orders of numerous steps and does not represent the only execution order. When the actual device or client product is executed, it can be executed in the order of the methods shown in the embodiments or the drawings or in parallel (for example, in a parallel processor or multi-threaded processing environment, or even in a distributed data processing environment). The terms "include", "comprise" or any other variant thereof are intended to cover non-exclusive inclusion, so that a process, method, product or device including a series of elements not only includes those elements, but also includes other elements not explicitly listed, or further includes elements inherent to such process, method, product or device. Without more limitations, the presence of additional identical or equivalent elements in the process, method, product or device including the said elements is not excluded. The words such as first, second, etc. are used to represent names and do not represent any specific order.

[0315] Those skilled in the art also know that in addition to implementing the controller in the form of pure computer-readable program code, the method steps can be logically programmed to enable the controller to implement the same functions in the form of logic gates, switches, application-specific integrated circuits, programmable logic controllers, embedded microcontrollers, etc. Therefore, such a controller can be regarded as a hardware component, and the devices included therein for implementing various functions can also be regarded as the structures within the hardware component. Or even, the devices for implementing various functions can be regarded as either software modules for implementing the method or structures within the hardware component.

[0316] This specification can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, classes, etc. that perform specific tasks or implement specific abstract data types. This specification can also be practiced in a distributed computing environment where tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media including storage devices.

[0317] From the description of the above embodiments, those skilled in the art can clearly understand that this specification can be implemented by means of software plus a necessary general hardware platform. Based on such an understanding, the technical solution of this specification can essentially be embodied in the form of a software product, which can be stored in a storage medium such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions for causing a computer device (which can be a personal computer, mobile terminal, server, or network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments of this specification.

[0318] The various embodiments in this specification are described in a progressive manner. For the same or similar parts between the various embodiments, reference can be made to each other, and the key point of each embodiment is to illustrate the differences from other embodiments. This specification can be used in many general or special computer system environments or configurations. For example: personal computers, server computers, handheld or portable devices, tablet devices, multi-processor systems, microprocessor-based systems, set-top boxes, programmable electronic devices, network PCs, minicomputers, mainframe computers, distributed computing environments including any of the above systems or devices, and so on.

[0319] Although this specification is depicted through embodiments, those of ordinary skill in the art know that this specification has many variations without departing from the spirit of this specification, and it is hoped that the appended claims will include these variations without departing from the spirit of this specification.

Claims

1. An intelligent well completion optimization design method based on multi-objective optimization, characterized in that Including: Clustering the first data set according to a weighted clustering model, and evaluating the geological sweet spots of each cluster after clustering to obtain a geological sweet spot evaluation result. The first data set includes various reservoir physical property parameters along the horizontal well depth, and the weighted clustering model is constructed according to the weights of the various reservoir physical property parameters; Dividing the fracturing sections according to the engineering sweet spot evaluation result and a preset section length constraint, where the engineering sweet spot evaluation result is determined according to geomechanical parameters; Within the divided fracturing sections, solve a multi-objective function constructed according to the geological sweet spot evaluation result, the engineering sweet spot evaluation result, and a preset cluster spacing constraint, and perform well completion optimization design according to the objective solution result of the multi-objective function.

2. The method according to claim 1, wherein The method further includes: Calculating the correlation coefficient between each reservoir physical property parameter and the oil production profile data; Determining the sum of the absolute values of the correlation coefficients between each reservoir physical property parameter and the oil production profile data; Determining the weights of the various reservoir physical property parameters according to the correlation coefficient and the sum of the absolute values of the correlation coefficients between the reservoir physical property parameters and the oil production profile data.

3. The method according to claim 1, characterized in that The weighted clustering model is constructed according to the weights of the various reservoir physical property parameters, including: Constructing a weighted Euclidean distance function, a criterion function, and a rating function according to the weights of the various reservoir physical property parameters; Constructing a weighted clustering model according to the weighted Euclidean distance function, the criterion function, and the rating function.

4. The method according to claim 3, wherein The clustering of the first data set according to the weighted clustering model includes: Selecting a preset number of clustering centers from the first data set; Calculating the weighted Euclidean distance from each first sample point in the first data set to the clustering centers according to the weighted Euclidean distance function, where each first sample point corresponds to the various reservoir physical property parameters at different horizontal well depths; Comparing the weighted Euclidean distances, and according to the comparison result, dividing each first sample point into the clustering cluster corresponding to the weighted Euclidean distance less than a preset distance threshold; Selecting new clustering centers from the clustering clusters according to the criterion function; Repeating the process of calculating the weighted Euclidean distance, dividing each first sample point, and selecting new clustering centers until the number of iterations reaches a preset iteration number threshold or the selected new clustering centers do not change, to obtain the first clustering result after clustering; The evaluation of the geological sweet spots of each cluster after clustering to obtain a geological sweet spot evaluation result includes: Evaluating the geological sweet spots after clustering in the first clustering result using the rating function to obtain a geological sweet spot evaluation result.

5. The method according to claim 4, wherein The evaluation of the geological sweet spots after clustering in the first clustering result using the rating function to obtain a geological sweet spot evaluation result includes: Using the rating function to determine the weighted geological sweet spot index of each cluster in the first clustering result; Comparing the weighted geological sweet spot indexes of each cluster, sorting the comparison results of the weighted geological sweet spot indexes in descending order to obtain a sorting result of the weighted geological sweet spot indexes; According to the sorting result of the weighted geological sweet spot indexes, rating the corresponding geological sweet spots into different levels to obtain a geological sweet spot evaluation result, where the geological sweet spot evaluation result includes geological sweet spot category labels.

6. The method according to claim 1, wherein The engineering sweet spot evaluation result includes the geomechanical strength along the horizontal well depth; correspondingly, the dividing of the fracturing sections according to the engineering sweet spot evaluation result and a preset section length constraint includes: Construct a second data set according to the geomechanical strength and well depth along the horizontal well depth, where each second sample point in the second data set corresponds to different well depths and geomechanical strengths at different horizontal well depths; Construct a geomechanical similarity term according to the geomechanical strength of the second sample points and the average geomechanical strength of all second sample points; Construct a segment length penalty term according to the well depth range of the fracturing section and the preset segment length constraint; Construct an objective function for dividing the fracturing section according to the geomechanical similarity term and the segment length penalty term; Use the dynamic programming algorithm to solve the objective function and determine the segmentation points of the fracturing section; Divide the fracturing section according to the segmentation points to obtain the fracturing section division result, where the fracturing section division result includes segment labels.

7. The method according to claim 1, characterized in that, The method further includes: Determine the geologic sweet spot weight according to the geologic sweet spot category label in the geologic sweet spot evaluation result; Identify the fracturing section according to the segment label in the fracturing section division result and impose constraints on the fracturing clusters within the fracturing section so that the constrained fracturing clusters are within the preset section depth range; Generate candidate regions according to the geomechanical strength along the horizontal well depth and generate candidate clusters from the candidate regions; Take the sum of the geologic sweet spot weights being greater than the preset weight threshold as the first objective, the geomechanical similarity term being less than the preset variance threshold as the second objective, and the preset cluster spacing requirement as the constraint condition; Construct a multi-objective function according to the first objective, the second objective and the constraint condition.

8. The method according to claim 7, wherein The solution of the multi-objective function constructed according to the geologic sweet spot evaluation result, the engineering sweet spot evaluation result and the preset cluster spacing constraint includes: Use the multi-objective optimization algorithm to solve the multi-objective function and determine the objective solution result of the multi-objective function from the candidate clusters; The completion optimization design according to the objective solution result of the multi-objective function includes: Take the objective solution result as the target design scheme of the fracturing clusters within the fracturing section and perform completion optimization design according to the target design scheme of the fracturing clusters.

9. An intelligent well completion optimization design device based on multi-objective optimization, characterized in that, Includes: A geologic sweet spot evaluation module, configured to cluster the first data set according to the weighted clustering model and evaluate the geologic sweet spots of each clustering cluster after clustering to obtain a geologic sweet spot evaluation result, where the first data set includes various reservoir physical property parameters along the horizontal well depth, and the weighted clustering model is constructed according to the weights of the various reservoir physical property parameters; A fracturing section division module, configured to divide the fracturing section according to the engineering sweet spot evaluation result and the preset segment length constraint, where the engineering sweet spot evaluation result is determined according to the geomechanical parameters; A completion optimization design module, configured to solve the multi-objective function constructed according to the geologic sweet spot evaluation result, the engineering sweet spot evaluation result and the preset cluster spacing constraint within the divided fracturing section and perform completion optimization design according to the objective solution result of the multi-objective function.

10. A computer-readable storage medium having computer program instructions stored thereon, characterized in that, The computer program instructions, when executed by a processor, implement the steps of the method according to any one of claims 1 to 8.

Images