Well cementation cement slurry performance prediction method and device and computing equipment

Abstract

The invention discloses a well cementation cement slurry performance prediction method and device and computing equipment. The method comprises the steps that to-be-predicted cement slurry admixture formula data are acquired; and inputting to-be-predicted cement paste additive formula data into a pre-trained performance prediction model for processing to obtain cement paste performance prediction data. Through the above mode, the neural network model is trained by using the known data, and the cement paste performance corresponding to the cement paste admixture formula is obtained through prediction of the neural network model, so that the experiment workload can be reduced, and the efficiency of cement paste performance determination can be improved.

Description

Technical Field

[0001] The present application relates to the field of oil and gas exploration, and specifically to a method, device, computing equipment, computer storage medium and computer program product for predicting cement slurry performance. Background Art

[0002] Cementing is the last step in the drilling process. It is an operation to lower high-quality steel pipes and fill cement in the wellbore and steel pipe annulus for the purpose of reinforcing the well wall, ensuring continued safe drilling, isolating oil, gas and water layers, ensuring stratification testing during exploration and reasonable oil and gas production during the entire mining process, so as to avoid accidents such as leakage and seepage.

[0003] The cementing project mainly includes two major tasks. The first is casing installation, that is, when the well is drilled to the predetermined depth and needs cementing, the casing is connected one by one and lowered into the well. The second is cementing, which is the key process after the casing is lowered into the well. Its function is to seal the annular space between the casing and the well wall to isolate the oil, gas and water layers, making the casing a passage for oil and gas to enter the well. Due to the different depths, lithology, temperature and pressure of each well, the performance requirements of the injected cement slurry are different. Therefore, before cementing operations, it is necessary to prepare cement slurry that meets the performance requirements according to the actual well conditions.

[0004] In the prior art, various properties are usually measured through various cement slurry tests in a laboratory environment. However, the cement slurry performance test is time-consuming. Therefore, it takes a long time to conduct a cement slurry performance test for a formula. If there is an urgent well construction, it will delay the construction period and even cause huge economic losses. Moreover, the type and amount of various admixtures added have a huge impact on the performance. Slight changes in the process of preparing cement slurry will cause the final cement slurry performance to change, thus failing to meet the on-site construction requirements. Based on this, the existing cement slurry performance test method is labor-intensive, costly and very time-consuming. Summary of the invention

[0005] In view of the above problems, the present application is proposed to provide a method, apparatus, computing device, computer storage medium and computer program product for predicting cement slurry properties that overcome the above problems or at least partially solve the above problems.

[0006] According to one aspect of the present application, a method for predicting cement slurry performance is provided, comprising:

[0007] Obtaining cement slurry admixture formula data to be predicted;

[0008] The cement slurry admixture formula data to be predicted is input into the pre-trained performance prediction model for processing to obtain cement slurry performance prediction data.

[0009] Optionally, the method further comprises:

[0010] Acquire sample data of cement slurry admixture formula, and acquire cement slurry performance data corresponding to the sample data of cement slurry admixture formula as sample labels;

[0011] The model is trained based on the sample data of cement slurry admixture formula and its sample labels to obtain the performance prediction model.

[0012] Optionally, model training is performed based on cement slurry admixture formula sample data and sample labels to obtain a performance prediction model, further comprising:

[0013] Constructing multiple initial performance prediction models; wherein different initial performance prediction models have different numbers of neuron nodes and / or numbers of hidden layers;

[0014] Each initial performance prediction model is trained according to the sample data of cement slurry admixture formula and its sample labels;

[0015] The performance indicator data of each trained initial performance prediction model are compared, and a performance prediction model is obtained by screening from each trained initial performance prediction model according to the comparison result.

[0016] Optionally, the method further comprises:

[0017] comparing cement slurry performance target data required for the operation with multiple cement slurry performance prediction data;

[0018] According to the comparison result, cement slurry admixture formulation target data is determined from multiple groups of cement slurry admixture formulation data to be predicted corresponding to multiple cement slurry property prediction data.

[0019] Optionally, according to the comparison result, determining the cement slurry admixture formula target data from the multiple groups of cement slurry admixture formula data to be predicted corresponding to the multiple cement slurry property prediction data further includes:

[0020] According to the comparison result, the benchmark cement slurry performance prediction data whose similarity with the cement slurry performance target data meets the preset conditions is determined;

[0021] The cement slurry admixture formulation data to be predicted corresponding to the benchmark cement slurry performance prediction data is determined as the cement slurry admixture formulation target data.

[0022] Optionally, the cement slurry performance prediction data includes: density, cement slurry thickening time, rheological index and / or cement paste compressive strength.

[0023] According to another aspect of the present application, a cementing slurry performance prediction device is provided, comprising:

[0024] An acquisition module, used for acquiring cement slurry admixture formula data to be predicted;

[0025] The prediction module is used to input the cement slurry admixture formula data to be predicted into the pre-trained performance prediction model for processing to obtain cement slurry performance prediction data.

[0026] Optionally, the device further comprises:

[0027] The model building module is used to obtain sample data of cement slurry admixture formula and obtain cement slurry performance data corresponding to the sample data of cement slurry admixture formula as sample labels; model training is performed based on the sample data of cement slurry admixture formula and its sample labels to obtain a performance prediction model.

[0028] Optionally, the model building module is further configured to:

[0029] Constructing multiple initial performance prediction models; wherein different initial performance prediction models have different numbers of neuron nodes and / or numbers of hidden layers;

[0030] Each initial performance prediction model is trained according to the sample data of cement slurry admixture formula and its sample labels;

[0031] The performance indicator data of each trained initial performance prediction model are compared, and a performance prediction model is obtained by screening from each trained initial performance prediction model according to the comparison result.

[0032] Optionally, the device further comprises:

[0033] The iterative back-deduction module is used to compare the cement slurry performance target data required for the operation with multiple cement slurry performance prediction data; based on the comparison result, the cement slurry admixture formula target data is determined from multiple groups of cement slurry admixture formula data to be predicted corresponding to the multiple cement slurry performance prediction data.

[0034] Optionally, the iterative back-stepping module is further used to:

[0035] According to the comparison result, the benchmark cement slurry performance prediction data whose similarity with the cement slurry performance target data meets the preset conditions is determined;

[0036] The cement slurry admixture formulation data to be predicted corresponding to the benchmark cement slurry performance prediction data is determined as the cement slurry admixture formulation target data.

[0037] Optionally, the cement slurry performance prediction data includes: density, cement slurry thickening time, rheological index and / or cement paste compressive strength.

[0038] According to another aspect of the present application, there is provided a computing device, comprising: a processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface communicate with each other via the communication bus;

[0039] The memory is used to store at least one executable instruction, and the executable instruction enables the processor to execute operations corresponding to the above-mentioned cementing slurry performance prediction method.

[0040] According to another aspect of the present application, a computer storage medium is provided, wherein at least one executable instruction is stored in the storage medium, and the executable instruction enables a processor to execute operations corresponding to the above-mentioned cement slurry performance prediction method.

[0041] According to another aspect of the present application, a computer program product is provided, comprising at least one executable instruction, wherein the executable instruction enables a processor to execute operations corresponding to the above-mentioned cement slurry performance prediction method.

[0042] According to the cementing slurry performance prediction method, device, computing device, computer storage medium and computer program product provided in the embodiments of the present application, first, the cement slurry admixture formula data to be predicted is obtained; secondly, the cement slurry admixture formula data to be predicted is input into a pre-trained performance prediction model for processing to obtain cement slurry performance prediction data. In the above manner, the neural network model is trained using known data, and the cement slurry performance corresponding to the cement slurry admixture formula is predicted by the neural network model, which can reduce the experimental workload and improve the efficiency of cement slurry performance measurement.

[0043] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] Various other advantages and benefits will become apparent to those of ordinary skill in the art by reading the detailed description of the preferred embodiments below. The accompanying drawings are only for the purpose of illustrating the preferred embodiments and are not to be considered as limiting the present application. Also, the same reference symbols are used throughout the accompanying drawings to represent the same components. In the accompanying drawings:

[0045] Figure 1 A flow chart showing a method for predicting cement slurry performance provided by an embodiment of the present application is shown;

[0046] Figure 2 A flow chart showing a method for predicting cement slurry performance provided by another embodiment of the present application is shown;

[0047] Figure 3 A schematic diagram of the structure of a performance prediction model provided by an embodiment of the present application is shown;

[0048] Figure 4 A schematic diagram of the structure of a performance prediction model provided by another embodiment of the present application is shown;

[0049] Figure 5 A flow chart showing a method for predicting cement slurry performance provided by another embodiment of the present application is shown;

[0050] Figure 6 A functional structure diagram of a cement slurry performance prediction device provided in an embodiment of the present application is shown;

[0051] Figure 7 A schematic diagram of the structure of a computing device provided in an embodiment of the present application is shown. DETAILED DESCRIPTION

[0052] The exemplary embodiments of the present application will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present application are shown in the accompanying drawings, it should be understood that the present application can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided in order to enable a more thorough understanding of the present application and to fully convey the scope of the present application to those skilled in the art.

[0053] Figure 1 A flow chart of a cement slurry performance prediction method provided in one embodiment of the present application is shown.

[0054] like Figure 1 As shown, the method comprises the following steps:

[0055] Step S110, obtaining cement slurry admixture formula data to be predicted.

[0056] Cement slurry is formed by mixing cement, water and various admixtures. Various admixtures are added to change and improve the performance of cement slurry. The cement slurry admixture formula data to be predicted is the formula data of the cement slurry performance data that is unknown. The cement slurry admixture formula data specifically includes the admixture type information and content data.

[0057] Specifically, a blank group experiment is used to determine the type and amount of admixtures used in the same batch of cement materials, thereby forming multiple groups of cement slurry admixture formula data to be predicted, and different groups of cement slurry admixture formula data to be predicted contain different admixture type information and / or content data.

[0058] Step S120, inputting the cement slurry admixture formula data to be predicted into a pre-trained performance prediction model for processing to obtain cement slurry performance prediction data.

[0059] Among them, the performance prediction model is obtained by pre-training the neural network model according to the training data set. The performance prediction model is used to predict the performance data of cement slurry. Its input features are constructed according to the cement slurry admixture formula data to be predicted, and the output result is the prediction result of the cement slurry performance data.

[0060] Specifically, cement slurry performance data include: density, cement slurry thickening time (the time required for cement slurry to completely solidify from a pumpable liquid state to a non-pumpable solid state), rheological index (the flowability of cement slurry underground) and / or cement paste compressive strength (the compressive strength after solidification to form cement paste). In specific implementation, one or more performance indicators can be set as the output result of the performance prediction model according to actual operation needs.

[0061] In the prior art, various cement slurry tests are performed in a laboratory environment to measure various properties. The thickening time test usually takes 4 to 7 hours, and the compressive strength test requires the cement slurry to be cured for a certain period of time before testing, which usually takes 24 to 48 hours. Therefore, it takes a long time to conduct a cement slurry performance test for a formula. If a well is under urgent construction, the construction period will be delayed, resulting in huge economic losses.

[0062] In summary, according to the cement slurry performance prediction method provided in this embodiment, the cement slurry admixture formula data to be predicted is obtained; the cement slurry admixture formula data to be predicted is input into a pre-trained performance prediction model for processing to obtain cement slurry performance prediction data. In the above manner, the neural network model is trained using known data, and the cement slurry performance corresponding to the cement slurry admixture formula is predicted by the neural network model, which can reduce the experimental workload and improve the efficiency of cement slurry performance measurement.

[0063] Figure 2 FIG. 2 is a flow chart showing a method for predicting cement slurry performance according to another embodiment of the present invention. Figure 2 As shown, the method comprises the following steps:

[0064] Step S210, obtaining sample data of cement slurry admixture formula, and obtaining cement slurry performance data corresponding to the sample data of cement slurry admixture formula as sample labels; performing model training according to the sample data of cement slurry admixture formula and its sample labels to obtain a performance prediction model.

[0065] In the model training stage, cement slurry admixture formula data with known performance data are obtained as sample data, and known performance data of cement slurry admixture formula sample data are obtained as sample labels, and the performance prediction model is obtained by training the cement slurry admixture formula data and its sample labels. The cement slurry admixture formula data and its performance data can be collected in actual operations.

[0066] In an optional manner, the sample data is divided into a training data set and a test data set according to a preset ratio. The training data set is used to train the performance prediction model, and the test data set is used to verify the performance prediction model. For example, 70% of the sample data is divided into the training data set and 30% of the sample data is divided into the test data set.

[0067] In an optional manner, after the original sample data is collected, the sample data is preprocessed, and the preprocessing specifically includes: abnormal data elimination processing, standardization processing, etc.; further, after the sample data is preprocessed, data for constructing model input features are extracted according to predefined data types, thereby obtaining cement slurry admixture formula sample data; further, the cement slurry admixture formula sample data is normalized and then input into the neural network model for training.

[0068] Figure 3 A schematic diagram of the structure of a performance prediction model provided by an embodiment of the present application is shown. Figure 4 A schematic diagram of the structure of a performance prediction model provided by another embodiment of the present application is shown. As shown in the figure, the performance prediction model includes an input layer 30, one or more hidden layers 31, and an output layer 32. The number of hidden layers 31 and the number of neuron nodes 33 in each layer can be set. Among them, for the structural setting of the neural network, if the number of neuron nodes and the number of layers are not set accurately, the model will be inaccurate. Too many neuron nodes will result in overfitting, and too few neuron nodes will result in inaccurate prediction results.

[0069] In an optional manner, a specific implementation method of constructing a performance prediction model includes the following steps: constructing multiple initial performance prediction models; wherein different initial performance prediction models have different numbers of neuron nodes and / or numbers of hidden layers; training each initial performance prediction model according to cement slurry admixture formula sample data and its sample labels; comparing the performance index data of each trained initial performance prediction model, and selecting the performance prediction model from each trained initial performance prediction model according to the comparison result. In this method, multiple different initial performance prediction models are constructed, specifically, the numbers of neuron nodes and / or numbers of hidden layers included are different. Each initial performance prediction model is trained using a training data set, and finally the trained initial performance prediction model with better performance is selected as the performance prediction model for practical application.

[0070] Among them, the performance indicator data of the model include: calculation amount, prediction efficiency and / or prediction accuracy, that is, the performance of the model can be evaluated from one or more dimensions. When evaluating the performance of the model from multiple dimensions, a total performance evaluation score is calculated based on the performance indicators of multiple dimensions, for example, a weighted sum is calculated based on the performance indicators of each dimension and the weights of each dimension as the performance evaluation score, and after completing the training of each initial performance prediction model, the model with the highest performance evaluation score is selected from the trained initial performance prediction model as the performance prediction model. In the above manner, by constructing initial performance prediction models of different structures for training and as alternatives, the performance prediction model with the best performance is finally selected to avoid the phenomenon of inaccurate model prediction or overfitting, which can improve the accuracy and efficiency of model prediction.

[0071] In an optional method, a multi-layer perceptron neural network model (MLPNN model) is used to construct a performance prediction model. The MLPNN model is a feedforward artificial neural network model, which consists of an input layer, one or more hidden layers, and an output layer. The neuron nodes of each layer are fully connected to the neuron nodes of the adjacent layer, but the neuron nodes in the same layer are not connected to each other.

[0072] Step S220, obtaining cement slurry admixture formula data to be predicted; inputting the cement slurry admixture formula data to be predicted into a pre-trained performance prediction model for processing to obtain cement slurry performance prediction data.

[0073] In the model application stage, the cement slurry admixture formula data with unknown performance data is obtained and input into the trained performance prediction model for calculation, and the performance prediction model outputs the predicted data of cement slurry performance. The cement slurry performance prediction data includes: density, cement slurry thickening time, rheological index and / or cement paste compressive strength.

[0074] In an optional manner, after obtaining the initial data to be predicted, the initial data to be predicted is preprocessed, and the preprocessing specifically includes: abnormal data elimination processing, standardization processing, etc. Further, after the initial data to be predicted is preprocessed, data for constructing model input features are extracted according to predefined data types, thereby obtaining cement slurry admixture formula data to be predicted; further, the cement slurry admixture formula data to be predicted is normalized and then input into the performance prediction model for processing.

[0075] Step S230, comparing the cement slurry performance target data required for the operation with a plurality of cement slurry performance prediction data; according to the comparison result, determining the cement slurry admixture formulation target data from a plurality of groups of cement slurry admixture formulation data to be predicted corresponding to the plurality of cement slurry performance prediction data.

[0076] The method of the embodiment of the present application also includes an implementation method for inferring the admixture formula based on the cement slurry performance required for actual construction. Specifically, a performance prediction model is used to predict multiple groups of cement slurry admixture formula data to be predicted, and multiple cement slurry performance prediction data are obtained. The cement slurry performance target data is compared to determine which cement slurry performance prediction data is close to, and the cement slurry admixture formula data to be predicted corresponding to the closer cement slurry performance prediction data is determined as the cement slurry admixture formula target data, which is used to assist in cementing cement slurry design.

[0077] In an optional manner, based on the comparison result, the benchmark cement slurry performance prediction data whose similarity with the cement slurry performance target data meets the preset conditions is determined; and the cement slurry admixture formula data to be predicted corresponding to the benchmark cement slurry performance prediction data is determined as the cement slurry admixture formula target data. In this manner, the cement slurry performance target data is compared with multiple cement slurry performance prediction data for similarity, and the comparison result is the calculated similarity. When the similarity between a cement slurry performance prediction data and the cement slurry performance target data is the largest or ranked in the first N (N is greater than 1) positions, it is determined that the similarity between the cement slurry performance prediction data and the cement slurry performance target data meets the preset conditions, then the cement slurry performance prediction data is determined as the benchmark cement slurry performance prediction data, and the cement slurry admixture formula data to be predicted corresponding to the benchmark cement slurry performance prediction data is determined as the cement slurry admixture formula target data.

[0078] In summary, according to the cementing cement slurry performance prediction method provided in this embodiment, on the one hand, a neural network model is trained using known data to form a set of model algorithms for cement slurry performance prediction, and the trained neural network model is used to predict the cement slurry performance of the cement slurry admixture formula. Under the premise that the cement slurry admixture formula is known and no relevant performance tests are required, the performance prediction of the formula can be completed, thereby avoiding the need to redo a series of performance tests due to changes in the type and / or content of the admixture, improving the efficiency and accuracy of cement slurry performance measurement, and greatly saving time and manpower; on the other hand, by constructing initial performance prediction models of different structures for training and as alternatives, the performance prediction model with the best performance is finally selected, avoiding the phenomenon of inaccurate model prediction or overfitting, and improving the accuracy and efficiency of model prediction; on the other hand, the content of each admixture can be iteratively inferred through the cement slurry performance required for construction, and the cement slurry admixture formula that matches the performance requirements can be quickly obtained, thereby facilitating the cement slurry design of cementing and reducing the cement slurry preparation time.

[0079] Figure 5 FIG. 4 is a flow chart showing a method for predicting cement slurry performance according to another embodiment of the present invention. Figure 5 As shown, the method mainly includes processing in the model training phase and processing in the model application phase.

[0080] In the model training stage, the training of the performance prediction model is mainly completed. The sample data of the cement slurry admixture formula is processed by the normalization module 501 and then input into the multi-layer perceptual neural network model 50 for processing. The multi-layer perceptual neural network model 50 includes an input layer 30, multiple hidden layers 31 and an output layer 32. The output layer 32 outputs the cement slurry performance prediction data. The loss function is further calculated based on the cement slurry performance prediction data and the sample labels. The parameters of the multi-layer perceptual neural network model 50 are adjusted according to the loss function. The above steps are repeated until the iteration termination condition is reached.

[0081] In the model application stage, the prediction processing of cement slurry performance data and the reverse processing of cement slurry admixture formula data are mainly carried out. In the prediction processing of cement slurry performance data, the cement slurry admixture formula data to be predicted is processed by the normalization module 501 and then input into the trained multi-layer perceptual neural network model 51 for processing. The trained multi-layer perceptual neural network model 51 outputs cement slurry performance prediction data, wherein the cement slurry admixture formula data to be predicted can be the standard cement slurry admixture formula data of the construction oil field block. In the reverse processing of cement slurry admixture formula data, the cement slurry performance prediction data and the cement slurry performance target data are input into the iterative reverse module 53 for processing, and finally the cement slurry admixture formula target data is output. For the specific reverse process, please refer to the description in the previous embodiment, which will not be repeated here. The cement slurry performance target data is the required cement slurry performance data set according to the actual geological conditions, thereby realizing the reverse matching of the known cement slurry performance data and improving the cement slurry mixing efficiency.

[0082] Figure 6 The functional structure diagram of the cement slurry performance prediction device provided in the embodiment of the present application is shown. Figure 6 As shown, the device comprises:

[0083] An acquisition module 61 is used to acquire cement slurry admixture formula data to be predicted;

[0084] The prediction module 62 is used to input the cement slurry admixture formula data to be predicted into the pre-trained performance prediction model for processing to obtain cement slurry performance prediction data.

[0085] In an optional manner, the device further includes:

[0086] The model building module is used to obtain sample data of cement slurry admixture formula and obtain cement slurry performance data corresponding to the sample data of cement slurry admixture formula as sample labels; model training is performed based on the sample data of cement slurry admixture formula and its sample labels to obtain a performance prediction model.

[0087] In an optional manner, the model building module is further configured to:

[0088] Constructing multiple initial performance prediction models; wherein different initial performance prediction models have different numbers of neuron nodes and / or numbers of hidden layers;

[0089] Each initial performance prediction model is trained according to the sample data of cement slurry admixture formula and its sample labels;

[0090] The performance indicator data of each trained initial performance prediction model are compared, and a performance prediction model is obtained by screening from each trained initial performance prediction model according to the comparison result.

[0091] In an optional manner, the device further comprises:

[0092] The iterative back-deduction module is used to compare the cement slurry performance target data required for the operation with multiple cement slurry performance prediction data; based on the comparison result, the cement slurry admixture formula target data is determined from multiple groups of cement slurry admixture formula data to be predicted corresponding to the multiple cement slurry performance prediction data.

[0093] In an optional manner, the iterative back-stepping module is further used to:

[0094] According to the comparison result, the benchmark cement slurry performance prediction data whose similarity with the cement slurry performance target data meets the preset conditions is determined;

[0095] The cement slurry admixture formulation data to be predicted corresponding to the benchmark cement slurry performance prediction data is determined as the cement slurry admixture formulation target data.

[0096] In an optional manner, the cement slurry performance prediction data includes: density, cement slurry thickening time, rheological index and / or cement paste compressive strength.

[0097] In summary, according to the cementing cement slurry performance prediction device provided by this embodiment, the cement slurry admixture formula data to be predicted is obtained; and then the cement slurry admixture formula data to be predicted is input into the pre-trained performance prediction model for processing to obtain cement slurry performance prediction data. In the above manner, the neural network model is trained using known data, and the cement slurry performance corresponding to the cement slurry admixture formula is predicted by the neural network model, which can reduce the experimental workload and improve the efficiency of cement slurry performance measurement.

[0098] An embodiment of the present application provides a non-volatile computer storage medium, which stores at least one executable instruction or computer program, which enables a processor to perform operations corresponding to the cementing slurry performance prediction method in any of the above method embodiments.

[0099] An embodiment of the present application provides a computer program product, which includes at least one executable instruction or computer program, and the executable instruction or computer program can enable a processor to perform operations corresponding to the cementing slurry performance prediction method in any of the above method embodiments.

[0100] Figure 7 A schematic diagram of the structure of an embodiment of a computing device of the present application is shown. The specific embodiment of the present application does not limit the specific implementation of the computing device.

[0101] like Figure 7 As shown, the computing device may include: a processor (processor) 702 , a communications interface (Communications Interface) 704 , a memory (memory) 706 , and a communication bus 708 .

[0102] The processor 702, the communication interface 704, and the memory 706 communicate with each other via the communication bus 708. The communication interface 704 is used to communicate with other devices such as a client or other server network elements. The processor 702 is used to execute the program 710, which can specifically execute the relevant steps in the above-mentioned embodiment of the cementing slurry performance prediction method for computing equipment.

[0103] Specifically, the program 710 may include program codes, which include computer operation instructions.

[0104] The processor 702 may be a central processing unit (CPU), or an application-specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present application. The one or more processors included in the computing device may be processors of the same type, such as one or more CPUs; or may be processors of different types, such as one or more CPUs and one or more ASICs.

[0105] The memory 706 is used to store the program 710. The memory 706 may include a high-speed RAM memory, and may also include a non-volatile memory (non-volatile memory), such as at least one disk memory.

[0106] The program 710 can be specifically used to enable the processor 702 to execute the cementing slurry performance prediction method in any of the above method embodiments. The specific implementation of each step in the program 710 can refer to the corresponding description of the corresponding steps and units in the cementing slurry performance prediction embodiment, which will not be repeated here. Those skilled in the art can clearly understand that for the convenience and simplicity of description, the specific working process of the above-described equipment and modules can refer to the corresponding process description in the above-mentioned method embodiment, which will not be repeated here.

[0107] The algorithm or display provided here are not inherently related to any specific computer, virtual system or other equipment. Various general systems can also be used together with the teaching based on this. According to the above description, it is obvious to construct the structure required for this type of system. In addition, the present application embodiment is not directed to any specific programming language yet. It should be understood that various programming languages ​​can be utilized to realize the content of the present application described here, and the above description of specific languages ​​is to disclose the best mode of implementation of the present application.

[0108] In the description provided herein, a large number of specific details are described. However, it is understood that the embodiments of the present application can be practiced without these specific details. In some instances, well-known methods, structures and techniques are not shown in detail so as not to obscure the understanding of this description.

[0109] Similarly, it should be understood that in order to streamline the present application and aid in understanding one or more of the various inventive aspects, in the above description of the exemplary embodiments of the present application, the various features of the embodiments of the present application are sometimes grouped together into a single embodiment, figure, or description thereof. However, the disclosed method should not be interpreted as reflecting the following intention: the claimed application requires more features than the features explicitly recited in each claim. More specifically, as reflected in the claims, the inventive aspects lie in less than all the features of the single embodiment disclosed above. Therefore, the claims that follow the specific embodiment are hereby expressly incorporated into the specific embodiment, with each claim itself serving as a separate embodiment of the present application.

[0110] Those skilled in the art will appreciate that the modules in the devices in the embodiments may be adaptively changed and arranged in one or more devices different from the embodiments. The modules or units or components in the embodiments may be combined into one module or unit or component, and in addition they may be divided into a plurality of submodules or subunits or subcomponents. Except that at least some of such features and / or processes or units are mutually exclusive, all features disclosed in this specification (including the accompanying claims, abstracts and drawings) and all processes or units of any method or device disclosed in this manner may be combined in any combination. Unless otherwise expressly stated, each feature disclosed in this specification (including the accompanying claims, abstracts and drawings) may be replaced by an alternative feature providing the same, equivalent or similar purpose.

[0111] In addition, those skilled in the art will appreciate that, although some embodiments herein include certain features included in other embodiments but not other features, the combination of features of different embodiments is meant to be within the scope of the present application and form different embodiments. For example, in the claims, any one of the claimed embodiments may be used in any combination.

[0112] The various component embodiments of the present application can be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. It should be understood by those skilled in the art that a microprocessor or digital signal processor (DSP) can be used in practice to implement some or all functions of some or all components according to the embodiments of the present application. The application can also be implemented as a device or apparatus program (e.g., computer program and computer program product) for executing a part or all of the methods described herein. Such a program implementing the present application can be stored on a computer-readable medium, or can have the form of one or more signals. Such a signal can be downloaded from an Internet website, or provided on a carrier signal, or provided in any other form.

[0113] It should be noted that the above embodiments illustrate the present application rather than limit the present application, and that those skilled in the art may design alternative embodiments without departing from the scope of the appended claims. In the claims, any reference symbol between brackets shall not be constructed as a limitation on the claims. The word "comprising" does not exclude the presence of elements or steps not listed in the claims. The word "one" or "an" preceding an element does not exclude the presence of multiple such elements. The present application may be implemented by means of hardware including several different elements and by means of a suitably programmed computer. In a unit claim that lists several devices, several of these devices may be embodied by the same hardware item. The use of the words first, second, and third, etc. does not indicate any order. These words may be interpreted as names. The steps in the above embodiments, unless otherwise specified, should not be understood as limitations on the order of execution.

Claims

1. A method for predicting cement slurry performance, characterized in that: include: Obtaining cement slurry admixture formula data to be predicted; The cement slurry admixture formula data to be predicted is input into a pre-trained performance prediction model for processing to obtain cement slurry performance prediction data.

2. The method for predicting cement slurry performance according to claim 1, characterized in that: The method further comprises: Acquire sample data of cement slurry admixture formula, and acquire cement slurry performance data corresponding to the sample data of cement slurry admixture formula as sample labels; Model training is performed based on the cement slurry admixture formula sample data and its sample labels to obtain the performance prediction model.

3. The method for predicting cement slurry performance according to claim 2, characterized in that: The model training is performed according to the cement slurry admixture formula sample data and its sample labels to obtain the performance prediction model further comprising: Constructing multiple initial performance prediction models; wherein different initial performance prediction models have different numbers of neuron nodes and / or numbers of hidden layers; Training each initial performance prediction model according to the cement slurry admixture formula sample data and its sample labels; The performance indicator data of each trained initial performance prediction model are compared, and the performance prediction model is obtained by screening from each trained initial performance prediction model according to the comparison result.

4. The method for predicting cement slurry performance according to any one of claims 1 to 3, characterized in that: The method further comprises: comparing cement slurry performance target data required for the operation with multiple cement slurry performance prediction data; According to the comparison result, cement slurry admixture formulation target data is determined from the multiple groups of cement slurry admixture formulation data to be predicted corresponding to the multiple cement slurry property prediction data.

5. The method for predicting cement slurry performance according to claim 4, characterized in that: The step of determining cement slurry admixture formulation target data from the plurality of groups of cement slurry admixture formulation data to be predicted corresponding to the plurality of cement slurry performance prediction data according to the comparison result further comprises: Determining, based on the comparison result, benchmark cement slurry performance prediction data whose similarity to the cement slurry performance target data meets preset conditions; The cement slurry admixture formula data to be predicted corresponding to the benchmark cement slurry performance prediction data is determined as the cement slurry admixture formula target data.

6. The method for predicting cement slurry performance according to any one of claims 1 to 3, characterized in that: The cement slurry performance prediction data include: density, cement slurry thickening time, rheological index and / or cement paste compressive strength.

7. A cementing slurry performance prediction device, characterized in that: include: An acquisition module, used for acquiring cement slurry admixture formula data to be predicted; The prediction module is used to input the cement slurry admixture formula data to be predicted into a pre-trained performance prediction model for processing to obtain cement slurry performance prediction data.

8. A computing device comprising: A processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface communicate with each other via the communication bus; The memory is used to store at least one executable instruction, and the executable instruction enables the processor to perform operations corresponding to the cementing slurry performance prediction method according to any one of claims 1-6.

9. A computer storage medium, wherein at least one executable instruction is stored in the storage medium, and the executable instruction enables a processor to execute operations corresponding to the cementing slurry performance prediction method according to any one of claims 1 to 6.

10. A computer program product, comprising at least one executable instruction, wherein the executable instruction enables a processor to execute operations corresponding to the method for predicting cement slurry properties according to any one of claims 1 to 6.

Images