Superhigh-temperature well cementation cement performance optimizing method and system

Abstract

The invention provides a performance optimization method and system for ultrahigh-temperature well cementation cement, and relates to the field of artificial intelligence, and the method comprises the steps: obtaining a performance influence characteristic and compressive strength sample data set of the ultrahigh-temperature well cementation cement; taking the performance influence characteristics of the ultra-high-temperature well cementation cement as input characteristics, taking the compressive strength of the ultra-high-temperature well cementation cement as an output target, and determining an optimal model from a set machine learning model library according to the influence coefficient of the input characteristics on the output target; determining an influence coefficient of each performance influence characteristic on compressive strength; and screening the target characteristics with the influence coefficients greater than a set influence threshold value, and generating an adjusting and optimizing scheme of the ultrahigh-temperature well cementation cement according to the influence coefficients of the target characteristics. The mechanical property of the ultrahigh-temperature well cementation cement can be adjusted and optimized on the basis of the adjusting and optimizing scheme, so that the ultrahigh-temperature well cementation cement can adapt to different application scenes, and the application requirements under the scenes of normal temperature, high temperature, ultrahigh temperature and the like are met.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence, and in particular to a method and system for optimizing the performance of ultra-high temperature cementing cement. Background Art

[0002] At present, there are many factors that affect ultra-high temperature cementing, including but not limited to cement grade, water-cement ratio (also known as w / c ratio), calcium-silicon-aluminum ratio (also known as Ca / Si / Al ratio), amount of sand added, curing time and curing temperature, among which the curing time and curing temperature include conventional curing temperature, conventional temperature curing time, high temperature curing temperature, high temperature curing time, etc.

[0003] The application performance and compressive resistance of ultra-high temperature cementing cement are required to be high, and it is difficult to determine the optimal design scheme for ultra-high temperature cementing cement in different application scenarios based on many factors. Summary of the invention

[0004] The purpose of the present application is to provide a method and system for optimizing the performance of ultra-high temperature cementing cement, which can effectively optimize the performance of ultra-high temperature cementing cement.

[0005] In order to solve the above technical problems, the present application provides a method for optimizing the performance of ultra-high temperature cementing cement, and the specific technical solution is as follows:

[0006] Obtaining a sample data set of performance influencing characteristics and compressive strength of the ultra-high temperature cementing cement;

[0007] Determining the ultra-high temperature cement performance influencing characteristics in the compressive strength sample data set;

[0008] Taking the ultra-high temperature cementing cement performance influencing feature as an input feature, taking the compressive strength of the ultra-high temperature cementing cement as an output target, and determining the optimal model from a set machine learning model library according to the influence relationship of the input feature on the output target;

[0009] Under the performance testing conditions of the optimal model, determining the influence coefficient of each of the ultra-high temperature cementing cement performance influencing characteristics on the compressive strength of the ultra-high temperature cementing cement;

[0010] The target features whose influence coefficients are greater than a set influence threshold value among the characteristics influencing the performance of the ultra-high temperature cementing cement are screened, and an optimization scheme for the ultra-high temperature cementing cement is generated according to the influence coefficients of the target features.

[0011] Optionally, after obtaining the performance influencing characteristics and compressive strength sample data set of the ultra-high temperature cementing cement, the method further includes:

[0012] determining the performance influencing features and abnormal data in the compressive strength sample data set;

[0013] The abnormal data are eliminated to obtain effective performance influencing features and compressive strength sample data sets.

[0014] Optionally, determining the performance influencing feature and abnormal data in the compressive strength sample data set includes:

[0015] Generating a marginal histogram between the input features and the output targets;

[0016] The data with a higher degree of dispersion in the marginal histogram is regarded as abnormal data.

[0017] Optionally, determining the performance influencing feature and abnormal data in the compressive strength sample data set includes:

[0018] For any type of data in the compressive strength sample data set, determine the first quartile and the third quartile;

[0019] Determining an interquartile range based on the first quartile and the third quartile;

[0020] Determine the upper and lower limits of outliers based on the interquartile range;

[0021] Abnormal data in the corresponding type of data is eliminated based on the upper and lower limits.

[0022] Optionally, determining the optimal model from a set machine learning model library according to the influence relationship of the input feature on the output target includes:

[0023] Determine the evaluation index of each machine learning model in the set machine learning model library; the evaluation index includes any combination of the coefficient of determination, mean absolute error, mean square error and root mean square error;

[0024] The cross-validation method is used to compare the evaluation indicators and determine the optimal model.

[0025] Optionally, determining the influence coefficient of each of the ultra-high temperature cementing cement performance influencing characteristics on the compressive strength of the ultra-high temperature cementing cement includes:

[0026] The Shapley additive interpretation analysis method is used to determine the influence coefficient of each of the ultra-high temperature cementing cement performance influencing characteristics on the compressive strength of the ultra-high temperature cementing cement.

[0027] Optionally, after determining the influence coefficient of each of the ultra-high temperature cementing cement performance influencing characteristics on the compressive strength of the ultra-high temperature cementing cement, the method further includes:

[0028] A performance prediction model of the ultra-high temperature cementing cement is generated according to the influence coefficients of the characteristics influencing the performance of the ultra-high temperature cementing cement and the optimal model; the performance prediction model is used to predict the compressive strength of the ultra-high temperature cementing cement.

[0029] The present application also provides a performance tuning system for ultra-high temperature cementing cement, comprising:

[0030] A data acquisition module, used to acquire performance influencing characteristics and compressive strength sample data sets of the ultra-high temperature cementing cement;

[0031] A feature determination module, used to determine the ultra-high temperature cement performance influencing features in the compressive strength sample data set;

[0032] A model determination module, for taking the ultra-high temperature cementing cement performance influencing feature as an input feature, taking the compressive strength of the ultra-high temperature cementing cement as an output target, and determining the optimal model from a set machine learning model library according to the influence relationship of the input feature on the output target;

[0033] A coefficient calculation module, used to determine the influence coefficient of each of the ultra-high temperature cementing cement performance influencing characteristics on the compressive strength of the ultra-high temperature cementing cement under the performance detection conditions of the optimal model;

[0034] The tuning module is used to screen the target features whose influence coefficients are greater than the set influence thresholds among the ultra-high temperature cementing cement performance influencing features, and generate a tuning plan for the ultra-high temperature cementing cement according to the influence coefficients of the target features.

[0035] Optionally, the model determination module includes:

[0036] A model evaluation unit, used to determine the evaluation index of each machine learning model in the set machine learning model library; the evaluation index includes any combination of the coefficient of determination, mean absolute error, mean square error and root mean square error;

[0037] The model validation unit is used to compare the evaluation indicators using a cross-validation method to determine the optimal model.

[0038] Optionally, the performance tuning system further includes:

[0039] The performance prediction module is used to generate a performance prediction model of the ultra-high temperature cementing cement according to the influence coefficient of each of the ultra-high temperature cementing cement performance influencing characteristics and the optimal model, so as to predict the compressive strength of the ultra-high temperature cementing cement.

[0040] The present application provides a performance tuning method for ultra-high temperature cementing cement, comprising: obtaining performance influencing characteristics and a compressive strength sample data set of the ultra-high temperature cementing cement; determining the performance influencing characteristics of the ultra-high temperature cementing cement in the compressive strength sample data set; using the performance influencing characteristics of the ultra-high temperature cementing cement as input characteristics, and using the compressive strength of the ultra-high temperature cementing cement as an output target, and determining an optimal model from a set machine learning model library according to the influence relationship of the input characteristics on the output target; determining the influence coefficient of each of the ultra-high temperature cementing cement performance influencing characteristics on the compressive strength of the ultra-high temperature cementing cement under the performance detection conditions of the optimal model; screening target characteristics whose influence coefficients are greater than a set influence threshold among the performance influencing characteristics of the ultra-high temperature cementing cement, and generating a tuning plan for the ultra-high temperature cementing cement according to the influence coefficients of each of the target characteristics.

[0041] After obtaining a sample data set of compressive strength of ultra-high temperature cementing cement, the present application determines the various ultra-high temperature cementing cement performance influencing features contained therein that have an impact on the performance of ultra-high temperature cementing cement. After determining the input features and output targets, the various machine learning models in the set machine learning model library are verified to determine the optimal model, and the optimal model is used to determine the influence coefficient of each ultra-high temperature cementing cement performance influencing feature, that is, the ability of each ultra-high temperature cementing cement performance influencing feature to affect the compressive strength of ultra-high temperature cementing cement. Then, an optimization plan is determined by comprehensively considering the performance influencing features of each ultra-high temperature cementing cement. Based on the optimization plan, the mechanical properties of ultra-high temperature cementing cement can be optimized to realize cement slurry system design, so as to ensure that the ultra-high temperature cementing cement can adapt to different application scenarios and meet the application requirements in normal temperature, high temperature, ultra-high temperature and other scenarios.

[0042] The present application also provides a performance tuning system for ultra-high temperature cementing cement, which has the above-mentioned beneficial effects and will not be described in detail here. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.

[0044] Figure 1 A flow chart of a method for optimizing the performance of ultra-high temperature cementing provided in an embodiment of the present application;

[0045] Figure 2 A marginal histogram between the performance influencing characteristics and compressive strength of an ultra-high temperature cementing cement provided in an embodiment of the present application;

[0046] Figure 3 A box plot between cement grade and compressive strength provided for the examples of the present application;

[0047] Figure 4 Schematic diagram of the Pearson correlation coefficient and heat map provided in the embodiments of the present application;

[0048] Figure 5 A scatter plot of the correlation between the actual value and the predicted value provided in the embodiment of the present application;

[0049] Figure 6 A schematic diagram of feature importance analysis provided in an embodiment of the present application;

[0050] Figure 7 A schematic diagram of the SHAP values ​​of the characteristic variables provided in the embodiments of the present application;

[0051] Figure 8 A schematic diagram of a graphical user interface for predicting the mechanical properties of cement provided in an embodiment of the present application;

[0052] Fig. 9 A schematic diagram of the structure of a performance tuning system for ultra-high temperature cementing provided in an embodiment of the present application. DETAILED DESCRIPTION

[0053] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0054] The object information involved in this application, including but not limited to the object device information, object personal information, etc., and data, including but not limited to data used for analysis, stored data, displayed data, etc., are all information and data authorized by the object or fully authorized by all parties, and the collection, use and processing of relevant data must comply with the laws, regulations and standards of relevant countries and regions.

[0055] Figure 1 A flow chart of a method for optimizing the performance of ultra-high temperature cementing provided in an embodiment of the present application, the method comprising:

[0056] S101: Acquire a sample data set of performance influencing characteristics and compressive strength of the ultra-high temperature cementing cement;

[0057] S102: Taking the ultra-high temperature cementing cement performance influencing feature as an input feature, taking the compressive strength of the ultra-high temperature cementing cement as an output target, and determining an optimal model from a set machine learning model library according to the influence relationship between the input feature and the output target;

[0058] S103: Under the performance detection condition of the optimal model, determining the influence coefficient of each of the ultra-high temperature cementing cement performance influencing characteristics on the compressive strength of the ultra-high temperature cementing cement;

[0059] S104: Filtering target features whose influence coefficients are greater than a set influence threshold among the ultra-high temperature cementing cement performance influencing features, and generating an optimization plan for the ultra-high temperature cementing cement according to the influence coefficients of the target features.

[0060] First, the performance influencing characteristics and compressive strength sample data set of ultra-high temperature cementing cement are obtained. There is no limitation on how to obtain the compressive strength sample data, and it can be obtained from a database or literature.

[0061] After that, the characteristics affecting the performance of ultra-high temperature cementing cement in the compressive strength sample data set are determined. The characteristics that can affect the performance of ultra-high temperature cementing cement can be used as the characteristics affecting the performance of ultra-high temperature cementing cement in this application. For example, it may include but is not limited to cement grade, water-cement ratio (also known as w / c ratio), calcium-silicon-aluminum ratio (also known as Ca / Si / Al ratio), amount of sand added, curing time and curing temperature, etc. After determining the characteristics affecting the performance of ultra-high temperature cementing cement, the training set and test set in the data set can be further set to facilitate statistical analysis of each machine learning model.

[0062] In a feasible implementation, after obtaining the performance influencing characteristics and compressive strength sample data set of the ultra-high temperature cementing cement, abnormal data in the performance influencing characteristics and the compressive strength sample data set can also be determined, so as to eliminate the abnormal data and obtain effective performance influencing characteristics and compressive strength sample data sets. The abnormal data described in this application includes data with obvious data abnormalities and invalid data, etc.

[0063] Thereafter, it is necessary to use the ultra-high temperature cementing cement performance influencing characteristics as input characteristics and the compressive strength of the ultra-high temperature cementing cement as output target to perform feature analysis on the ultra-high temperature cementing cement performance influencing characteristics.

[0064] When performing feature analysis on the characteristics affecting the performance of ultra-high temperature cementing cement, marginal histograms, data box plots, Pearson correlation coefficients, and heat maps can be used. If marginal histograms are used, marginal histograms between the input features and the output targets can be generated, so that data with a high degree of dispersion in the marginal histograms can be regarded as abnormal data. Figure 2 , Figure 2 A marginal histogram between the ultra-high temperature cementing performance influencing characteristics and compressive strength provided in an embodiment of the present application, Figure 2 Taking the water-cement ratio (i.e. w / c) as an example, for other ultra-high temperature cementing cement performance influencing characteristics, it can be used Figure 2 Construct marginal histograms as shown to identify abnormal data. If a box plot of the data is used, see Figure 3 , Figure 3 This is a box plot between cement grade and compressive strength provided in the embodiment of the present application. The cement grade is used as the input feature and the compressive strength is used as the output feature. The first quartile and the third quartile are determined; the interquartile range is determined based on the first quartile and the third quartile; the upper and lower limits of the outliers are determined based on the interquartile range, and finally the outliers in the corresponding type of data are eliminated based on the upper and lower limits. Figure 4 , Figure 4 Schematic diagram of the Pearson correlation coefficient and heat map provided in the embodiments of the present application.

[0065] In a feasible implementation of the present application, it is set that the machine learning model library may include five algorithms: XGB (extreme gradient boosting), HGBR (histogram-based gradient boosting regression algorithm), CB (gradient boosting decision tree algorithm optimized for categorical features), ANN (artificial neural network), and TPE-XGB (extreme gradient boosting model tuned by tree structured parzen estimator).

[0066] K-Fold cross validation is a statistical technique used to evaluate or estimate the performance of machine learning models. This application can use a ten-fold cross validation method.

[0067] The coefficient of determination R 2 (Coefficient of Determination), mean absolute error MAE (Mean Absolute Error), mean square error MSE (Mean Squared Error), and root mean square error RMSE (Root Mean Squared Error) are used to evaluate the accuracy of the model. 2 It is a statistical measure used to evaluate the fit of the model to the actual data. MAE, MSE and RMSE are indicators used to measure model prediction. 2 The closer it is to 1, the smaller the MAE, MSE, and RMSE are, and the higher the prediction accuracy of the model is.

[0068] By R 2 , MSE, MAE, and RMSE indicators are compared and analyzed. Compared with the other four machine learning models, the TPE-XGB model shows better performance. In the training set, the R2 The value exceeds 0.95, and the MSE, MAE, and RMSE evaluation indicators are better than other algorithms. 2 It reaches 0.9359, which is closer to 1 than other algorithms. MAE is improved by 3.81%, 26.45%, 36.11%, and 46.88% respectively compared with the other four machine learning algorithms, and the improvement percentages on RMSE are: 2.90%, 21.34%, 29.92%, and 42.35% respectively. Therefore, among the above five machine learning algorithms, the TPE-XGB model is the best. Of course, under different ultra-high temperature cement performance influencing characteristics, and setting different machine learning models contained in the machine learning model library, there may be other models that perform best.

[0069] See also Figure 5 , Figure 5 The scatter plot of the correlation between the actual value and the predicted value provided in the embodiment of the present application shows the correlation between the actual value and the predicted value of various machine learning models through the scatter plot. The machine learning model TPE-XGB shows higher prediction accuracy and produces smaller errors: in the training set, the data points of the model are closely aligned with the 45° ideal line, and the prediction error is within 10%, indicating that the data is closely clustered, highlighting the excellent learning results. This shows that the hybrid model TPE-XGB outperforms the other four machine learning models in generalization performance.

[0070] Thereafter, the Shapley Additive Explanations analysis method can be used to determine the influence coefficient of each of the ultra-high temperature cementing cement performance influencing characteristics on the compressive strength of the ultra-high temperature cementing cement. Shapley Additive Explanations (SHAP) analysis is a method for explaining the output of machine learning models. It provides a global and local explanation for complex machine learning models and is suitable for understanding and explaining the importance and influence of model prediction results.

[0071] See also Figure 6 , Figure 6 This is a schematic diagram of feature importance analysis provided in an embodiment of the present application. Figure 6The average SHAP value of the characteristic variables is shown, reflecting the contribution of the characteristic variables to the prediction results. In the TPE-XGB model, cement grade, w / c and curing time at normal temperature are identified as the most critical variables affecting the mechanical properties of cement, with their average SHAP values ​​of 6.55, 4.92 and 3.96, respectively. In the chemical composition of cementing cement, Al / Si and Ca / Si also significantly affect the mechanical properties of cementing cement, with their average SHAP values ​​of 3.38 and 2.5, respectively. External factors such as curing time at normal temperature and high temperature have less influence. In general, by regulating important parameters such as cement grade, w / c, Al / Si and Ca / Si, it is possible to significantly improve cement performance.

[0072] The influence of the feature variables is not only accurately quantified by the SHAP method, but the influence of the feature values ​​on the prediction results is also clearly shown in Figure 7 in the summary diagram. Figure 7 A schematic diagram of the SHAP values ​​of the characteristic variables provided in the embodiment of the present application, in Figure 7 In the figure, each point corresponds to the SHAP value of a feature instance, and the y-axis represents the features, which are ranked from most to least important for the model prediction. The x-axis represents the SHAP value. In addition, the change in color represents the size of the feature value, with red areas representing high values ​​and blue areas representing low values. The fluctuation of the y-axis depicts the distribution of the feature values. For example, cement grade shows a positive correlation with compressive strength, w / c shows a negative correlation with compressive strength, etc. The behavior of the input features of the machine learning model used is consistent with the actual existing knowledge, thus verifying the authenticity of the TPE-XGB model.

[0073] There is no limitation on how to determine and set the influence threshold. The influence threshold can be set in the same way as the calculation method of the influence coefficient, or the lowest value among the first set number of characteristics with higher influence coefficients in the ultra-high temperature cementing performance influencing characteristics can be taken as the influence threshold. For example, the first three characteristics with higher influence coefficients are taken, and the third largest value of the influence coefficient is taken as the influence threshold.

[0074] In other embodiments of the present application, in order to improve the usability of the machine learning model, a Python-based graphical user interface (GUI) was developed to predict the compressive strength of cement, such as Figure 8 As shown, Figure 8A schematic diagram of a graphical user interface for predicting the mechanical properties of cement for cementing provided in an embodiment of the present application. The graphical user interface can be developed using the Tkinter module in Python, and is combined with the above-mentioned optimal machine learning model TPE-XGB to enable the prediction function. The graphical user interface allows the user to input characteristic data, including Ca / Si / Al ratio, curing time and temperature, and then simply click the prediction button to obtain the mechanical properties prediction data of the cement. The graphical user interface is simple and user-friendly, enabling non-technical users to easily operate and utilize machine learning models. This user-friendly GUI interface for predicting cement compressive strength facilitates quick access to prediction results, thereby improving the practicality of the machine learning model.

[0075] Based on the optimal model determined in the above embodiment, this embodiment further develops prediction software, which can predict the mechanical properties and microscopic properties of cementing cement at normal temperature, high temperature, ultra-high temperature, and thermal recovery wells. On the basis of the above performance tuning method of ultra-high temperature cementing cement, the mechanical properties of ultra-high temperature cementing cement are further regulated based on the prediction and tuning method to achieve cement slurry system design, so as to ensure that ultra-high temperature cementing cement can adapt to different application scenarios and meet the application requirements in scenarios such as normal temperature, high temperature, and ultra-high temperature.

[0076] See also Fig. 9 , Fig. 9 This is a schematic diagram of the structure of a performance tuning system for ultra-high temperature cementing provided in an embodiment of the present application. The present application also provides a performance tuning system for ultra-high temperature cementing, including:

[0077] A data acquisition module, used to acquire performance influencing characteristics and compressive strength sample data sets of the ultra-high temperature cementing cement;

[0078] A feature determination module, used to determine the ultra-high temperature cement performance influencing features in the compressive strength sample data set;

[0079] A model determination module, for taking the ultra-high temperature cementing cement performance influencing feature as an input feature, taking the compressive strength of the ultra-high temperature cementing cement as an output target, and determining the optimal model from a set machine learning model library according to the influence relationship of the input feature on the output target;

[0080] A coefficient calculation module, used to determine the influence coefficient of each of the ultra-high temperature cementing cement performance influencing characteristics on the compressive strength of the ultra-high temperature cementing cement under the performance detection conditions of the optimal model;

[0081] The tuning module is used to screen the target features whose influence coefficients are greater than the set influence thresholds among the ultra-high temperature cementing cement performance influencing features, and generate a tuning plan for the ultra-high temperature cementing cement according to the influence coefficients of the target features.

[0082] Based on the above embodiments, as a preferred embodiment, it also includes:

[0083] The data screening module is used to determine the abnormal data in the performance influencing features and the compressive strength sample data set; remove the abnormal data to obtain the effective performance influencing features and the compressive strength sample data set.

[0084] Based on the above embodiment, as a preferred embodiment, the data screening module includes:

[0085] The discrete data screening unit is used to generate a marginal histogram between the input feature and the output target; and to take the data with a higher degree of discreteness in the marginal histogram as abnormal data.

[0086] Based on the above embodiment, as a preferred embodiment, the data screening module includes:

[0087] The abnormal data screening unit is used to determine the first quartile and the third quartile for any type of data in the compressive strength sample data set; determine the interquartile range according to the first quartile and the third quartile; determine the upper and lower limits of the abnormal value according to the interquartile range; and eliminate the abnormal data in the corresponding type of data based on the upper and lower limits.

[0088] Based on the above embodiment, as a preferred embodiment, the model determination module includes:

[0089] A model evaluation unit, used to determine the evaluation index of each machine learning model in the set machine learning model library; the evaluation index includes any combination of the coefficient of determination, mean absolute error, mean square error and root mean square error;

[0090] The model validation unit is used to compare the evaluation indicators using a cross-validation method to determine the optimal model.

[0091] Based on the above embodiments, as a preferred embodiment, the coefficient calculation module is a module for determining the influence coefficient of each of the ultra-high temperature cementing cement performance influencing characteristics on the compressive strength of the ultra-high temperature cementing cement by using the Shapley additive interpretation analysis method.

[0092] Based on the above embodiments, as a preferred embodiment, it also includes:

[0093] A performance prediction module is used to generate a performance prediction model of the ultra-high temperature cementing cement according to the influence coefficient of each of the ultra-high temperature cementing cement performance influencing characteristics and the optimal model; the performance prediction model is used to predict the compressive strength of the ultra-high temperature cementing cement.

[0094] The various embodiments in the specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referred to each other. For the system provided in the embodiment, since it corresponds to the method provided in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part description.

[0095] Specific examples are used herein to illustrate the principles and implementation methods of the present application, and the description of the above embodiments is only used to help understand the method and core ideas of the present application. It should be pointed out that for ordinary technicians in this technical field, without departing from the principles of the present application, several improvements and modifications can be made to the present application, and these improvements and modifications also fall within the scope of protection of the present application.

[0096] It should also be noted that, in this specification, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "comprise", "include" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the statement "comprises a ..." does not exclude the presence of other identical elements in the process, method, article or device including the element.

Claims

1. A method for optimizing the performance of ultra-high temperature cementing cement, characterized in that: include: Obtaining a sample data set of performance influencing characteristics and compressive strength of the ultra-high temperature cementing cement; Taking the ultra-high temperature cementing cement performance influencing feature as an input feature, taking the compressive strength of the ultra-high temperature cementing cement as an output target, and determining the optimal model from a set machine learning model library according to the influence relationship of the input feature on the output target; Under the performance testing conditions of the optimal model, determining the influence coefficient of each of the ultra-high temperature cementing cement performance influencing characteristics on the compressive strength of the ultra-high temperature cementing cement; The target features whose influence coefficients are greater than a set influence threshold value among the characteristics influencing the performance of the ultra-high temperature cementing cement are screened, and an optimization scheme for the ultra-high temperature cementing cement is generated according to the influence coefficients of the target features.

2. The method for optimizing the performance of ultra-high temperature cementing cement according to claim 1, characterized in that: After obtaining the performance influencing characteristics and compressive strength sample data set of the ultra-high temperature cementing cement, the method further includes: determining the performance influencing features and abnormal data in the compressive strength sample data set; The abnormal data are eliminated to obtain effective performance influencing features and compressive strength sample data sets.

3. The method for optimizing the performance of ultrahigh temperature cementing cement according to claim 2, characterized in that: Determining the performance influencing features and abnormal data in the compressive strength sample data set includes: Generating a marginal histogram between the input features and the output target; The data with a higher degree of dispersion in the marginal histogram is regarded as abnormal data.

4. The method for optimizing the performance of ultrahigh temperature cementing cement according to claim 2, characterized in that: Determining the performance influencing features and abnormal data in the compressive strength sample data set includes: For any type of data in the compressive strength sample data set, determine the first quartile and the third quartile; Determining an interquartile range based on the first quartile and the third quartile; Determine the upper and lower limits of outliers based on the interquartile range; Abnormal data in the corresponding type of data is eliminated based on the upper and lower limits.

5. The method for optimizing the performance of ultra-high temperature cementing cement according to claim 1, characterized in that: Determining the optimal model from the set machine learning model library according to the influence relationship of the input feature on the output target includes: Determine the evaluation index of each machine learning model in the set machine learning model library; the evaluation index includes any combination of the coefficient of determination, mean absolute error, mean square error and root mean square error; The cross-validation method is used to compare the evaluation indicators and determine the optimal model.

6. The method for optimizing the performance of ultra-high temperature cementing cement according to claim 1, characterized in that: Determining the influence coefficient of each of the ultra-high temperature cementing cement performance influencing characteristics on the compressive strength of the ultra-high temperature cementing cement includes: The Shapley additive interpretation analysis method is used to determine the influence coefficient of each of the ultra-high temperature cementing cement performance influencing characteristics on the compressive strength of the ultra-high temperature cementing cement.

7. The method for optimizing the performance of ultrahigh temperature cementing cement according to claim 1, characterized in that: After determining the influence coefficient of each of the ultra-high temperature cementing cement performance influencing characteristics on the compressive strength of the ultra-high temperature cementing cement, the method further includes: A performance prediction model of the ultra-high temperature cementing cement is generated according to the influence coefficients of the characteristics influencing the performance of the ultra-high temperature cementing cement and the optimal model, so as to predict the compressive strength of the ultra-high temperature cementing cement.

8. A performance tuning system for ultra-high temperature cementing, characterized in that: include: A data acquisition module, used to acquire performance influencing characteristics and compressive strength sample data sets of the ultra-high temperature cementing cement; A feature determination module, used to determine the ultra-high temperature cement performance influencing features in the compressive strength sample data set; A model determination module is used to use the ultra-high temperature cementing cement performance influencing characteristics as input characteristics, the compressive strength of the ultra-high temperature cementing cement as an output target, and determine the optimal model from a set machine learning model library according to the influence relationship of the input characteristics on the output target; A coefficient calculation module, used to determine the influence coefficient of each of the ultra-high temperature cementing cement performance influencing characteristics on the compressive strength of each of the ultra-high temperature cementing cements under the performance detection conditions of the optimal model; The tuning module is used to screen the target features whose influence coefficients are greater than the set influence thresholds among the characteristics influencing the performance of the ultra-high temperature cementing cement, and generate a tuning plan for the ultra-high temperature cementing cement according to the influence coefficients of the target features.

9. The performance tuning system for ultra-high temperature cementing according to claim 8, characterized in that: The model determination module comprises: A model evaluation unit, used to determine the evaluation index of each machine learning model in the set machine learning model library; the evaluation index includes any combination of the coefficient of determination, mean absolute error, mean square error and root mean square error; The model validation unit is used to compare the evaluation indicators using a cross-validation method to determine the optimal model.

10. The performance tuning system for ultra-high temperature cementing according to claim 8, characterized in that: Also includes: A performance prediction module is used to generate a performance prediction model of the ultra-high temperature cementing cement according to the influence coefficient of each of the ultra-high temperature cementing cement performance influencing characteristics and the optimal model; the performance prediction model is used to predict the compressive strength of the ultra-high temperature cementing cement.

Images