Well leakage accident real-time prediction method and device, electronic equipment and storage medium

Abstract

The invention discloses a real-time prediction method and device for a well leakage accident, electronic equipment and a storage medium, and aims to search optimal parameters of an SVM (Support Vector Machine) by improving simulated annealing and support rapid updating of a classification model, so that prediction of a well leakage prediction model is more accurate and real-time. According to the well leakage prediction method based on the SVM support vector machine, the intelligent level of accident early warning is remarkably enhanced based on the SVM support vector machine. Moreover, the optimal parameters of the SVM are searched on the basis of an improved simulated annealing method, the network parameter adjustment process is automated, and the early warning accuracy is greatly improved. Meanwhile, the prediction effect is verified by integrating the field operation data, and the iterative upgrade of the SVM well leakage prediction model is accelerated, so that the real-time update and rapid prediction capability of the SVM well leakage prediction model are ensured, and the method can be widely applied to the technical field of data processing.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to a method, device, electronic equipment and storage medium for real-time prediction of well leakage accidents. Background Art

[0002] In the field of drilling operations, traditional technical solutions mainly rely on intuitive assessments by experts based on data transmitted in real time by sensors. Such assessments not only integrate rich field experience in drilling, but also aim to identify drilling conditions and warn of potential accidents. However, despite the profound practical wisdom contained in this approach, its scope of application and effectiveness are subject to many limitations.

[0003] Specifically, the shortcomings of the existing technical solutions are mainly reflected in the following aspects:

[0004] There is a delay in early warning response: The current early warning system is highly dependent on manual analysis and judgment, resulting in low processing efficiency, insufficient emergency response, and difficulty in achieving a rapid response to potential risks. This delay may have serious consequences in an emergency and even endanger the safety of personnel and equipment.

[0005] Data analysis becomes more difficult: With the deepening of drilling operations and the continuous development of sensor technology, the amount of data is growing exponentially, and the data dimensions are also expanding rapidly. This greatly increases the complexity and difficulty of manually processing and understanding data, which seriously affects the accuracy and efficiency of data analysis.

[0006] Slow iterative upgrade of classification models: The existing classification models lag significantly in iterative upgrades. Due to the lack of immediate integration and update of field operation data, the overall data set cannot reflect the latest drilling conditions in a timely manner, which in turn affects the timeliness and accuracy of the iterative update of the model. This may result in the model performing poorly in dealing with emerging drilling problems and potential risks. Summary of the invention

[0007] The present invention aims to solve the problem of related technical limitations at least to a certain extent. To this end, the present invention proposes a real-time prediction method, device, electronic device and storage medium for well leakage accidents, which can efficiently and accurately predict well leakage accidents in real time.

[0008] On the one hand, an embodiment of the present invention provides a real-time prediction method for lost circulation accidents, comprising:

[0009] Acquire a drilling data set; the data set includes multiple sets of feature data and labeling information of whether a well leakage accident occurs in the set of data;

[0010] Randomly generate key parameters in a preset interval; key parameters include regularization coefficients and kernel parameters;

[0011] The preset support vector machine is set by key parameters, and then the support vector machine is iteratively upgraded through simulated annealing strategy based on the data set to obtain the target support vector machine;

[0012] Acquire real-time feature data of the drilling site, input the real-time feature data into the target support vector machine to predict and obtain the well leakage prediction result;

[0013] Responding to the verification instruction of the target object, obtaining the accuracy of the well leakage prediction result;

[0014] The accuracy includes correctness and error; when the accuracy is error, the well leakage prediction result is corrected according to the verification instruction;

[0015] Associating the real-time feature data with the well leakage prediction results and adding them to the data set; performing attenuation update on the preset update threshold based on the accuracy;

[0016] When the next prediction node is reached, the step of obtaining real-time feature data of the drilling site is returned until the update threshold is less than or equal to 0, the target parameters are reset, and the step of randomly generating key parameters in a preset interval is returned to continuously update the target support vector machine; the target parameters include the update threshold.

[0017] Optionally, a preset support vector machine is set by key parameters, and then the support vector machine is iteratively upgraded by a simulated annealing strategy based on the data set to obtain a target support vector machine, including the following steps:

[0018] The preset support vector machine is set through key parameters, and then the support vector machine is trained using the data set to obtain a support vector machine model; fitness evaluation is performed based on the training results of the data set to obtain the prediction accuracy of the support vector machine model;

[0019] When the prediction accuracy is greater than the target threshold, the target threshold is updated by the prediction accuracy, and the prediction accuracy is used as the historical accuracy of the next round, and the key parameters are used as the optimal parameters and historical parameters; otherwise, based on the prediction accuracy and the historical accuracy of the previous round, the acceptance probability of the key parameters is determined in combination with the current temperature; when the acceptance probability meets the preset conditions, the prediction accuracy is used as the historical accuracy of the next round, and the key parameters are used as historical parameters;

[0020] Add 1 to the number of iterations, update the historical parameters based on the preset rules, use the updated results as key parameters, and return to execute the steps of setting the preset support vector machine through the key parameters until the number of iterations reaches the threshold;

[0021] Attenuate the current temperature based on the preset attenuation rate, set the number of iterations to 0, return to the step of executing the support vector machine preset by setting the key parameters, until the current temperature reaches the temperature threshold, and output the optimal parameters;

[0022] By setting the support vector machine with optimal parameters, the target support vector machine is obtained;

[0023] The target parameters include the number of iterations and the current temperature; the number of iterations is initialized and reset to 0, and the current temperature is initialized and reset to the preset maximum temperature.

[0024] Optionally, the training result includes the accident prediction result of each set of feature data in the data set; performing fitness evaluation based on the training result of the data set to obtain the prediction accuracy of the vector machine model includes the following steps:

[0025] Compare the accident prediction results and annotation information corresponding to each set of feature data in the data set;

[0026] The number of correctly predicted samples is obtained based on the comparison results, and the prediction accuracy of the vector machine model is obtained based on the ratio of the number of samples to the total number of samples in the data set.

[0027] Optionally, based on the prediction accuracy and the historical accuracy of the previous round, the acceptance probability of the key parameters is determined in combination with the current temperature, including the following steps:

[0028] The index value is obtained based on the ratio of the difference between the previous round's historical accuracy and the predicted accuracy to the current temperature;

[0029] Taking the natural constant as the base and the exponential value as the exponent, the acceptance probability of the key parameter is obtained by performing exponential operation based on the base and the exponent;

[0030] Among them, the preset condition represents whether the acceptance probability is greater than the random probability; the random probability is randomly generated within a preset range.

[0031] Optionally, updating the historical parameters based on a preset rule includes the following steps:

[0032] Performing a first update on the regularization coefficient according to the ratio of the product of the first random number and the number of iterations to the number threshold;

[0033] The first update characterization uses the sum of the regularization coefficient and the ratio as the regularization coefficient;

[0034] Performing a second update on the kernel parameters according to a second random number;

[0035] The second update characterization uses the sum of the kernel parameter and the second random number as the kernel parameter.

[0036] Optionally, the well leakage prediction result includes the occurrence of well leakage and the non-occurrence of well leakage; when the accuracy is wrong, the well leakage prediction result is corrected according to the verification instruction, including the following steps:

[0037] When the well loss prediction result is wrongly predicted as sending well loss, the well loss prediction result is corrected to no well loss;

[0038] When the well leakage prediction result is erroneously predicted as no well leakage is sent, the well leakage prediction result is corrected to the well leakage occurring.

[0039] Optionally, performing a decay update on a preset update threshold based on the accuracy comprises the following steps:

[0040] When the accuracy is correct, the difference between the update threshold and the first attenuation parameter is used as the update threshold, otherwise, the difference between the update threshold and the second attenuation parameter is used as the update threshold;

[0041] The first decay parameter is determined based on the inverse of a preset maximum number of failures, and the second decay parameter is determined based on the inverse of a preset maximum number of successes.

[0042] On the other hand, an embodiment of the present invention provides a real-time prediction device for lost circulation accidents, comprising:

[0043] The first module is used to obtain a drilling data set; the data set includes multiple sets of feature data and labeling information of whether a well leakage accident occurs in the data set;

[0044] The second module is used to randomly generate key parameters in a preset interval; the key parameters include regularization coefficients and kernel parameters;

[0045] The third module is used to set the preset support vector machine through key parameters, and then iteratively upgrade the support vector machine through simulated annealing strategy based on the data set to obtain the target support vector machine;

[0046] The fourth module is used to obtain real-time feature data of the drilling site, and input the real-time feature data into the target support vector machine to predict the well leakage prediction result;

[0047] A fifth module is used to obtain the accuracy of the well leakage prediction result in response to the verification instruction of the target object;

[0048] The accuracy includes correctness and error; when the accuracy is error, the well leakage prediction result is corrected according to the verification instruction;

[0049] The sixth module is used to associate the real-time feature data with the well leakage prediction result and add it to the data set; based on the accuracy, the preset update threshold is updated attenuated;

[0050] The seventh module is used to return to the step of obtaining real-time feature data of the drilling site when reaching the next prediction node, until the update threshold is less than or equal to 0, reset the target parameters, return to the step of randomly generating key parameters in a preset interval, and continuously update the target support vector machine; the target parameters include the update threshold.

[0051] On the other hand, an embodiment of the present invention provides an electronic device, including: a processor and a memory; the memory is used to store programs; the processor executes the program to implement the above-mentioned real-time prediction method for well leakage accidents.

[0052] On the other hand, an embodiment of the present invention provides a computer storage medium, in which a program executable by a processor is stored. When the program executable by the processor is executed by the processor, it is used to implement the above-mentioned real-time prediction method for well leakage accidents.

[0053] The embodiment of the present invention obtains a drilling data set; the data set includes multiple groups of feature data and labeling information of whether a well leakage accident occurs under the data set; key parameters are randomly generated in a preset interval; the key parameters include regularization coefficients and kernel parameters; a preset support vector machine is set by the key parameters, and then the support vector machine is iteratively upgraded through a simulated annealing strategy based on the data set to obtain a target support vector machine; real-time feature data of the drilling site is obtained, and the real-time feature data is input into the target support vector machine to predict the well leakage prediction result; in response to the verification instruction of the target object, the accuracy of the well leakage prediction result is obtained; wherein the accuracy includes correctness and error; when the accuracy is an error, the well leakage prediction result is corrected according to the verification instruction; the real-time feature data is associated with the well leakage prediction result and added to the data set; based on the accuracy, the preset update threshold is attenuated and updated; when the next prediction node is reached, the step of obtaining the real-time feature data of the drilling site is returned to be executed until the update threshold is less than or equal to 0, the target parameter is reset, and the step of randomly generating key parameters in the preset interval is returned to be executed, and the target support vector machine is continuously updated; the target parameter includes the update threshold. The present invention includes the following beneficial effects:

[0054] Improve prediction accuracy: By iteratively upgrading the support vector machine through the simulated annealing strategy and combining it with real-time feature data for prediction, it is possible to more accurately predict lost circulation accidents, reduce the probability of false alarms and missed alarms, and improve the safety and efficiency of drilling operations.

[0055] Automation and intelligence: The solution realizes the automation and intelligence of drilling leakage prediction, reduces manual intervention, improves response speed, and enables faster response measures in emergency situations to reduce accident risks.

[0056] Dynamic learning and updating: By continuously adding real-time feature data and prediction results to the data set, and dynamically updating model parameters and update thresholds based on prediction accuracy, the support vector machine can continuously learn and adapt to changes in the drilling site, maintaining the timeliness of prediction capabilities.

[0057] Flexibility and adaptability: The key parameters in the scheme (such as regularization coefficients and kernel parameters) are randomly generated within a preset interval, which increases the flexibility of the model, enables it to adapt to different drilling environments and conditions, and improves the generalization ability of predictions.

[0058] Closed-loop feedback mechanism: The prediction results are verified and corrected through the verification instructions of the target object, forming a closed-loop feedback mechanism, which helps to detect and correct prediction errors in a timely manner and further improve the prediction accuracy and reliability of the model.

[0059] In summary, this technical solution achieves efficient and accurate prediction of drilling leakage accidents through intelligent and automated methods, and has the ability to dynamically learn and adapt, which is of great significance for improving the safety and efficiency of drilling operations. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] The accompanying drawings are used to provide a further understanding of the technical solution of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the technical solution of the present invention and do not constitute a limitation on the technical solution of the present invention.

[0061] Figure 1 A schematic diagram of an implementation environment for real-time prediction of lost circulation accidents provided by an embodiment of the present invention;

[0062] Figure 2 A schematic flow chart of a real-time prediction method for a lost circulation accident provided by an embodiment of the present invention;

[0063] Figure 3 A schematic diagram of an example of a support vector machine type provided by an embodiment of the present invention;

[0064] Figure 4 A schematic diagram of the expansion process of iteratively upgrading a support vector machine using a simulated annealing strategy provided in an embodiment of the present invention;

[0065] Figure 5 A schematic diagram of the expansion process of fitness evaluation provided by an embodiment of the present invention;

[0066] Figure 6 A schematic diagram of an expansion process of updating historical parameters provided by an embodiment of the present invention;

[0067] Figure 7 A schematic diagram of a process flow for correcting a lost circulation prediction result provided by an embodiment of the present invention;

[0068] Figure 8 A schematic diagram of the overall process principle of the real-time prediction method for lost circulation accidents provided by an embodiment of the present invention;

[0069] Fig. 9A schematic diagram of the structure of a real-time prediction device for lost circulation accidents provided by an embodiment of the present invention;

[0070] Fig.10 A schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0071] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0072] It should be noted that, although the functional modules are divided in the system schematic diagram and the logical order is shown in the flowchart, in some cases, the steps shown or described may be performed in a different order than the module division in the system or the order in the flowchart. The terms "first / S100", "second / S200", etc. in the specification, claims and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence.

[0073] Reference to "embodiments" in the present invention means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present invention. The appearance of the phrase in various places in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described in the present invention may be combined with other embodiments.

[0074] It is understandable that the real-time prediction method for well leakage accidents provided in the embodiment of the present invention can be applied to any computer device with data processing and computing capabilities, and this computer device can be various terminals or servers. When the computer device in the embodiment is a server, the server is an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN (Content Delivery Network), and big data and artificial intelligence platforms. Optionally, the terminal is a smart phone, a tablet computer, a laptop computer, a desktop computer, etc., but is not limited to this.

[0075] To facilitate the understanding of the technical solution of the present invention, the specific terms of the technical features that may appear in the embodiments of the present invention are first explained:

[0076] The simulated annealing algorithm is derived from solid annealing. It is a probability-based algorithm that heats the solid to a sufficiently high temperature and then slowly cools it. When heated, the particles inside the solid become disordered as the temperature rises, and the internal energy increases. When slowly cooled, the particles gradually become ordered and reach equilibrium at each temperature. The simulated annealing algorithm is a general optimization algorithm. In theory, the algorithm has probabilistic global optimization performance and has been widely used in engineering, such as production scheduling, control engineering and other fields.

[0077] Support Vector Machines (SVM) is a classic machine learning method. Figure 3 As shown in the figure, it includes linearly separable, hard interval, soft interval and linear inseparable types. With its excellent generalization ability and effective handling of nonlinear problems, it shows great potential in the fields of pattern recognition, classification and regression analysis. Its core concept is to construct an optimal decision boundary, which can not only clearly divide samples of different categories, but also has the maximum interval, in order to enhance the prediction performance of the model on unknown data. For nonlinear problems, SVM uses kernel techniques to map to high-dimensional space to achieve effective separation. It is suitable for small to medium-sized data sets and high-dimensional feature spaces.

[0078] Well leakage refers to the phenomenon that drilling fluid (commonly known as mud) accidentally leaks into the formation due to geological reasons or improper technical operations during the drilling process. Well leakage not only poses a pollution risk to the ecological environment, but may also cause serious consequences such as damage to equipment and endanger the safety of operators. It may even cause the situation to deteriorate to a blowout, triggering a chain reaction and ultimately causing the borehole to lose its function. In the early years, well leakage prediction was highly dependent on the subjective judgment made by technicians based on real-time data from sensors, which required technicians to have profound practical experience. However, manual judgment is inevitably affected by subjective bias and has limitations.

[0079] like Figure 1 FIG. 1 is a schematic diagram of an implementation environment provided by an embodiment of the invention. Figure 1 The implementation environment includes at least one terminal 102 and a server 101. The terminal 102 and the server 101 can be connected to a network wirelessly or wired to complete data transmission and exchange.

[0080] Server 101 can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers. It can also be a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN (Content Delivery Network), as well as big data and artificial intelligence platforms.

[0081] In addition, the server 101 can also be a node server in the blockchain network. Blockchain is a new application model of computer technologies such as distributed data storage, peer-to-peer transmission, consensus mechanism, and encryption algorithm.

[0082] The terminal 102 may be a smart phone, a tablet computer, a laptop computer, a desktop computer, a smart speaker, a smart watch, etc., but is not limited thereto. The terminal 102 and the server 101 may be directly or indirectly connected via wired or wireless communication, which is not limited in the embodiment of the present invention.

[0083] Based on the example Figure 1 In the implementation environment shown, an embodiment of the present invention provides a real-time prediction method for well leakage accidents. The following is explained using the application of the real-time prediction method for well leakage accidents in the server 101 as an example. It can be understood that the real-time prediction method for well leakage accidents can also be applied to the terminal 102.

[0084] Reference Figure 2 , Figure 2 The flowchart of the real-time prediction method for well leakage accidents applied to a server provided in an embodiment of the present invention, the execution subject of the real-time prediction method for well leakage accidents can be any of the aforementioned computer devices (including servers or terminals). Figure 2 , the method comprises the following steps:

[0085] S100, obtaining a drilling data set;

[0086] The data set includes multiple sets of feature data and labeling information of whether a well leakage accident occurs under the set of data;

[0087] For example, in some specific implementations, the data set sources of the drilling data used in the present invention are mainly divided into two parts: historical data and field operation data, which together constitute the data set. Among them, the first acquisition is usually acquired as historical data.

[0088] The historical data mainly comes from public data at home and abroad, and multiple sets of data records collected from daily drilling reports, daily mud reports, completion reports and other materials. Some data show that leakage occurs during the drilling process, while some data show that the drilling process is normal.

[0089] Field operation data is the front-line operation data. First, the SVM well leakage prediction model is used to predict whether the drilling will have well leakage. Then, the result is manually determined to be correct. Whether the prediction is correct or wrong, the data will be added to the drilling data set. When the data prediction continues to be correct, the SVM well leakage prediction model will be updated regularly according to the configuration; when the data prediction fails, if certain conditions are met, the SVM well leakage prediction model will be triggered to update. That is, in the subsequent prediction application process, the data set can be updated through each real-time data.

[0090] Each set of data includes multiple characteristics such as lithology, pore size, porosity, pore pressure, fracture pressure, shear stress, gel strength, pump pressure, drill bit speed, primary fracture direction, and whether drilling leakage has occurred under this set of data.

[0091] S200, randomly generating key parameters in a preset interval; the key parameters include regularization coefficients and kernel parameters;

[0092] For example, in some specific implementations, key parameters of the SVM support vector machine include two parameters: a regularization coefficient C and a kernel parameter g.

[0093] Regularization coefficient C: It is an important hyperparameter in SVM, which determines the model's tolerance for errors. It determines the model's tolerance for errors. A larger C value will cause the model to penalize more for misclassification and may overfit the data. A smaller C value will cause the model to penalize less for misclassification and may underfit the data. There is no fixed range for the value of C, which depends on the complexity of the data set problem. In practical applications, the value of C is between (0,10 8 ].

[0094] Kernel parameter g: It determines the width of the Gaussian kernel function, which affects the performance of the SVM model. A larger g value will result in a higher degree of fit of the model to the data, which may overfit the data. A smaller g value will result in a lower degree of fit of the model to the data, which may underfit the data. There is no fixed range for the value of g, which depends on the complexity of the data set problem. In practical applications, the value of g is between (0,10 2 ].

[0095] Through in-depth data query, in the present invention, the value range of the regularization coefficient C can be (0,100], and the value range of the kernel parameter g is (0,1].

[0096] The key parameter NewPara is generated for the first time and initialized using the following formula, where R(0,100) represents a random floating point number from (0,100] and R(0,1) represents a random floating point number from (0,1].

[0097] C=R(0,100)

[0098] g=R(0,1)

[0099] NewPara={C,g}

[0100] S300, setting a preset support vector machine through key parameters, and then iteratively upgrading the support vector machine through a simulated annealing strategy based on the data set to obtain a target support vector machine;

[0101] It should be noted that in some embodiments, Figure 4 As shown, step S300 may include the following steps: S301, set a preset support vector machine through key parameters, and then use the data set to train the support vector machine to obtain a vector machine model; perform fitness evaluation based on the training result of the data set to obtain the prediction accuracy of the vector machine model; S302, when the prediction accuracy is greater than the target threshold, update the target threshold through the prediction accuracy, use the prediction accuracy as the historical accuracy of the next round, and use the key parameters as the optimal parameters and historical parameters; otherwise, based on the prediction accuracy and the historical accuracy of the previous round, determine the acceptance probability of the key parameters in combination with the current temperature; when the acceptance probability meets the preset conditions, use the prediction accuracy as the historical accuracy of the next round, and use the key parameters as the historical parameters. historical parameters; S303, add 1 to the number of iterations, update the historical parameters based on the preset rules, use the updated results as the key parameters, return to the steps of setting the preset support vector machine through the key parameters, until the number of iterations reaches the number threshold; S304, attenuate the current temperature based on the preset attenuation rate, set the number of iterations to 0, return to the steps of setting the preset support vector machine through the key parameters, until the current temperature reaches the temperature threshold, and output the optimal parameters; S305, set the support vector machine through the optimal parameters to obtain the target support vector machine; wherein the target parameters include the number of iterations and the current temperature; the initialization and reset of the number of iterations are both 0, and the initialization and reset of the current temperature are both the preset maximum temperature.

[0102] In some embodiments, the training results include accident prediction results for each set of feature data in the data set; Figure 5 As shown, fitness evaluation is performed based on the training results of the data set to obtain the prediction accuracy of the vector machine model, which may include the following steps: S3011, comparing the accident prediction results and annotation information corresponding to each group of feature data in the data set; S3012, obtaining the number of correctly predicted samples based on the comparison results, and obtaining the prediction accuracy of the vector machine model based on the ratio of the number of samples to the total number of samples in the data set.

[0103] Among them, in some embodiments, based on the prediction accuracy and the historical accuracy of the previous round, combined with the current temperature, determining the acceptance probability of the key parameters can include the following steps: obtaining an exponential value based on the ratio of the difference between the historical accuracy of the previous round and the prediction accuracy and the current temperature; taking the natural constant as the base and the exponential value as the exponent, and performing an exponential operation based on the base and the exponent to obtain the acceptance probability of the key parameters; wherein the preset condition characterizes whether the acceptance probability is greater than the random probability; the random probability is randomly generated within a preset range.

[0104] Among them, in some embodiments, such as Figure 6 As shown, updating historical parameters based on preset rules may include the following steps: S3031, performing a first update on the regularization coefficient according to the ratio of the product of the first random number and the number of iterations to the number threshold; wherein the first update characterizes taking the sum of the regularization coefficient and the ratio as the regularization coefficient; S3032, performing a second update on the kernel parameter according to the second random number; wherein the second update characterizes taking the sum of the kernel parameter and the second random number as the kernel parameter.

[0105] Among them, the first random number and the second random number can use normal(0,1), which means a normally distributed random number with a mean of 0 and a standard deviation of 1. In some embodiments, in order to avoid excessive deviation in parameter updates, the results of the first update and the second update can be processed with respect to preset extreme points (i.e., the update range), for example, the maximum extreme point is taken if it is greater than the update range, and the minimum extreme point is taken if it is less than the update range.

[0106] For example, in some specific implementations, the overall process principle of step S300 can be implemented as follows:

[0107] Update the SVM prediction model. Based on the latest data set and the clear SVM support vector machine key parameter NewPara, the lost circulation prediction SVM support vector machine model (i.e., vector machine model) is obtained through training based on the latest data set.

[0108] Calculate the prediction accuracy based on the SVM prediction model. Traverse each array group of the latest data set, input it into the SVM support vector machine model, obtain the prediction result, and then compare it with the actual result. The present invention uses the prediction accuracy P as the fitness function for evaluation, with a value between [0,1]. The larger the score, the better the model performance. The calculation formula is as follows. Where TrueSize represents the number of correct predictions. DataSetSize represents the number of data in the latest data set.

[0109]

[0110] In general, taking the current data set as the benchmark and the current NewPara as the input, the prediction accuracy P of the output result is calculated. NewPara , which is the fitness function value.

[0111] Determine whether the new parameters are better than the current parameters. NewPara >P BestPara , it means that the network model of NewPara performs better and accepts the new parameters, otherwise it is judged whether the acceptance probability is met. Note that BestPara here represents the best performance parameter of the BP network model so far. Among them, P BestPara (i.e., the target threshold) can be directly set to the prediction accuracy obtained by the first process, or directly set to a negative value to ensure that the process can be iteratively updated during the iteration process.

[0112] Receive new parameters. This means that better parameters have been found, and choose to update BestPara (i.e. the optimal parameter), P BestPara , CurrPara (i.e. historical parameters) and P CurrPara (i.e. the historical accuracy rate of the next round). Refer to the following formula:

[0113] BestPara=NewPara

[0114] P BestPara =P NewPara

[0115] CurrPara=NewPara

[0116] P CurrPara =P NewPara

[0117] Determine whether the acceptance probability is met. That is, the parameter variable NewPara found this time does not perform as expected. At this time, choose to accept NewPara with a certain probability. The probability formula is as follows, where NowTemp represents the current temperature, which gradually decreases.

[0118]

[0119] Then calculate a [0,1] random probability r. If prob is greater than r, accept new parameters according to the probability. Otherwise, determine whether the iteration upper limit is met.

[0120] Receive new parameters based on probability. At this time, choose to update CurrPara and P CurrPara , refer to the following formula:

[0121] CurrPara=NewPara

[0122] P CurrPara =PNewPara

[0123] Determine whether the iteration upper limit is satisfied. The process of updating the SVM prediction model to receive new parameters according to probability is the innermost loop. Each time it is executed, the iteration count is incremented by one. If the iteration count exceeds the maximum value MaxIterCnt (i.e., the count threshold, which can be customized, default is 100), lower the temperature; otherwise, determine whether the temperature lower limit is reached.

[0124] Lower the temperature. After the innermost loop is executed, temperature decay is performed. NowTemp represents the current temperature, initialized to MaxTemp (i.e., the preset maximum temperature, which can be customized, default is 100), and the minimum value is MinTemp (i.e., the temperature threshold, which can be customized, and MinTemp < MaxTemp, default is 1). The decay formula is as follows:

[0125] NowTemp = DecayRate * NowTemp

[0126] Where DecayRate represents the decay rate, and its value range is [0, 1), which can be customized, default is 0.99.

[0127] Determine whether the temperature lower limit is reached. The process of updating the SVM prediction model to lower the temperature is the middle loop. Each time it is executed, the temperature decays once. When NowTemp ≤ MinTemp, that is, the current temperature has reached the temperature lower limit, it means that the optimal parameter value has been found, and at this time, the entire simulated annealing search process ends, and the optimal parameters of the SVM prediction model are found. Otherwise, based on CurrPara, generate new NewPara. Each parameter executes the following formula to complete the generation of new variables, and then return to execute the first step of updating the SVM prediction model to implement the process loop.

[0128]

[0129] NewPara C = min(100, max(0, NewPara C ))

[0130] NewPara g = CurrPara g + normal(0, 1)

[0131] NewPara g = min(1, max(0, NewPara g ))。

[0132] Where normal(0,1) represents a normal distribution with a mean of 0 and a standard deviation of 1, MaxInterCnt is the maximum number of iterations of simulated annealing, and i represents the current i-th iteration.

[0133] Find the optimal parameters of the SVM prediction model. When this step is reached, the entire simulated annealing process is completed, indicating that the optimal parameters BestPara have been obtained.

[0134] BestPara={C,g}

[0135] Finally, the SVM prediction model is updated. In the above steps, the latest data set is obtained, and the key parameter BestPara of the SVM support vector machine is clarified. Based on the latest data set, the lost circulation prediction SVM support vector machine model (i.e., the target support vector machine) is obtained through training.

[0136] S400, acquiring real-time characteristic data of the drilling site, and inputting the real-time characteristic data into a target support vector machine for prediction to obtain a well leakage prediction result;

[0137] For example, in some specific implementations, first, real-time data is obtained: real-time data here is obtained from on-site drilling reports, mud reports, completion reports and other materials, or from on-site monitoring systems, and belongs to front-line real-time operation data. Each set of data includes multiple characteristics such as lithology, pore size, porosity, pore pressure, fracture pressure, shear stress, gel strength, pump pressure, drill bit speed, and primary fracture direction.

[0138] These data can be manually transcribed according to needs, or automatically generated by the monitoring system. Based on these data, they are input into the well leakage prediction SVM support vector machine model to make on-site well leakage prediction.

[0139] S500, in response to a verification instruction of a target object, obtaining the accuracy of a lost circulation prediction result;

[0140] The accuracy includes correctness and error; when the accuracy is error, the well leakage prediction result is corrected according to the verification instruction;

[0141] It should be noted that the results of the well leakage prediction include the occurrence of well leakage and the absence of well leakage. Figure 7 As shown, when the accuracy is wrong, the well leakage prediction result is corrected according to the verification instruction, which can include the following steps: S501, when the well leakage prediction result is incorrectly predicted as sending well leakage, the well leakage prediction result is corrected to no well leakage; S502, when the well leakage prediction result is incorrectly predicted as no well leakage is sent, the well leakage prediction result is corrected to the occurrence of well leakage.

[0142] For example, in some specific implementations, based on real-time data, input into the well leakage prediction SVM support vector machine model to make on-site well leakage prediction. Then, it can be combined with artificial experience to determine whether the prediction result is correct. If the prediction result is correct, the real-time data is directly added to the data set, that is, the data set is updated. If the prediction result is wrong, the result is modified to be correct, and then the real-time data is added to the data set, that is, the data set is updated.

[0143] S600, associating the real-time characteristic data with the well leakage prediction result and adding them to the data set; performing attenuation update on the preset update threshold value based on the accuracy;

[0144] It should be noted that, in some embodiments, the attenuation update of the preset update threshold based on accuracy may include the following steps: when the accuracy is correct, the difference between the update threshold and the first attenuation parameter is used as the update threshold; otherwise, the difference between the update threshold and the second attenuation parameter is used as the update threshold; wherein the first attenuation parameter is determined based on the inverse of the preset maximum number of failures, and the second attenuation parameter is determined based on the inverse of the preset maximum number of successes.

[0145] For example, in some specific implementations, the update threshold value Delt is a default value (can be customized and is 1 by default). The SVM model update threshold value Delt indicates whether an update is required. If Delt>0, it means that an update is not required for the time being, otherwise an update is required immediately.

[0146] Based on real-time data prediction, if the prediction fails, the Delt update formula is as follows:

[0147]

[0148] Based on real-time data prediction, if the prediction is successful, the Delt update formula is as follows:

[0149]

[0150] Among them, MaxFailCnt represents the maximum number of failed predictions (can be customized, the default is 50), MaxSuccCnt represents the maximum number of successful predictions (can be customized, the default is 200, usually, MaxFailCnt <MaxSuccCnt)。

[0151] In general, assuming that the number of failures of the current model is FailCnt and the number of successes is SuccCnt, if This indicates that the model needs to be updated.

[0152] S700, when reaching the next prediction node, return to the step of obtaining real-time feature data of the drilling site until the update threshold is less than or equal to 0, reset the target parameters, return to the step of randomly generating key parameters in a preset interval, and continuously update the target support vector machine; the target parameters include the update threshold.

[0153] In order to explain the principle of the technical solution of the present invention in detail, the overall process of the present invention is described below in combination with some specific embodiments. It is easy to understand that the following is an explanation of the technical principle of the present invention and cannot be regarded as a limitation of the present invention.

[0154] In view of the shortcomings of the prior art, the present invention proposes a real-time prediction method for well leakage accidents, which finds the optimal parameters of SVM support vector machine by improving simulated annealing and supports rapid update of classification model, so as to make the prediction of well leakage prediction model more accurate and real-time. Figure 8 As shown, the method includes:

[0155] Step 1: Get the latest data set. The drilling data used in this article mainly consists of historical data and field operation data, which together constitute the data set.

[0156] The historical data mainly comes from public data at home and abroad, and multiple sets of data records collected from daily drilling reports, daily mud reports, completion reports and other materials. Some data show that leakage occurs during the drilling process, while some data show that the drilling process is normal.

[0157] Field operation data is the front-line operation data. First, the SVM well leakage prediction model is used to predict whether the drilling will have well leakage, and then the result is manually determined to be correct. Whether the prediction is correct or wrong, the data will be added to the drilling data set. When the data prediction continues to be correct, the SVM well leakage prediction model will be updated regularly according to the configuration; when the data prediction fails, if certain conditions are met, the SVM well leakage prediction model will be triggered to update.

[0158] Each set of data includes multiple characteristics such as lithology, pore size, porosity, pore pressure, fracture pressure, shear stress, gel strength, pump pressure, drill bit speed, primary fracture direction, and whether drilling leakage has occurred under this set of data.

[0159] Here, it should be noted that the iterative update of the SVM well leakage prediction model and the prediction results based on the SVM well leakage prediction model are independent of each other, that is, they do not affect each other. When the iterative update of the SVM well leakage prediction model is not completed, the prediction model uses the previous version of the model; when the iterative update is completed, it will trigger the prediction model version update, and the well leakage prediction will be temporarily stopped during the version update. After the update, the latest version of the model will be used.

[0160] Step 2: Randomly generate new parameters. The key parameters of the SVM support vector machine include the regularization coefficient C and the kernel parameter g.

[0161] Regularization coefficient C: It is an important hyperparameter in SVM, which determines the model's tolerance for errors. It determines the model's tolerance for errors. A larger C value will cause the model to penalize more for misclassification and may overfit the data. A smaller C value will cause the model to penalize less for misclassification and may underfit the data. There is no fixed range for the value of C, which depends on the complexity of the data set problem. In practical applications, the value of C is between (0,10 8 ].

[0162] Kernel parameter g: It determines the width of the Gaussian kernel function, which affects the performance of the SVM model. A larger g value will result in a higher degree of fit of the model to the data, which may overfit the data. A smaller g value will result in a lower degree of fit of the model to the data, which may underfit the data. There is no fixed range for the value of g, which depends on the complexity of the data set problem. In practical applications, the value of g is between (0,10 2 ].

[0163] Through in-depth data query, in this article, the value range of the regularization coefficient C is (0,100], and the value range of the kernel parameter g is (0,1].

[0164] If step 2 is executed for the first time (CurrPara has not yet completed initialization), the initialization is completed using the following formula, where R(0,100) represents a random floating point number from (0,100] and R(0,1) represents a random floating point number from (0,1].

[0165] C=R(0,100)

[0166] g=R(0,1)

[0167] NewPara={C,g}

[0168] If step 2 is executed for the second time or later, NewPara is generated based on CurrPara, and each parameter executes the following formula to complete the generation of new variables. Where normal(0,1) represents a normal distribution with a mean of 0 and a standard deviation of 1, MaxInterCnt is the maximum number of iterations of simulated annealing, and i represents the current i-th iteration.

[0169]

[0170] NewPara C =min(100,max(0,NewPara C ))

[0171] NewPara g =CurrPara g +normal(0,1)

[0172] NewPara g =min(1,max(0,NewPara g ))

[0173] Finally, the initialization of the parameter NewPara is completed, and go to step 4.

[0174] Step 3: Update the SVM prediction model. In step 1, the latest data set was obtained; in step 2, the key parameter NewPara of the SVM support vector machine was determined. Based on the latest data set, the SVM support vector machine model for lost circulation prediction was obtained through training.

[0175] Step 4: Calculate the prediction accuracy based on the SVM prediction model. Traverse each array group of the latest data set, input it into the SVM support vector machine model, get the prediction results, and then compare them with the actual results. This article uses the prediction accuracy P as the fitness function for evaluation, with a value between [0,1]. The larger the score, the better the model performance. The calculation formula is as follows.

[0176] TrueSize indicates the number of correct predictions. DataSetSize indicates the number of the latest dataset data.

[0177]

[0178] In general, taking the current data set as the benchmark and the current NewPara as the input, the prediction accuracy P of the output result is calculated. NewPara , which is the fitness function value.

[0179] Step 5: The new parameters are better than the current parameters. If P NewPara >P BestPara , it means that the network model of NewPara performs better, go to step 6, otherwise go to step 7. Note that BestPara here is the parameter with the best performance of the BP network model so far.

[0180] Step 6: Receive new parameters. This means that better parameters have been found. Choose to update BestPara, P BestPara , CurrPara and P CurrPara . Refer to the following formula.

[0181] BestPara=NewPara

[0182] P BestPara =P NewPara

[0183] CurrPara = NewPara

[0184] P CurrPara = P NewPara

[0185] Step 7: Meet the acceptance probability. That is, the parameter variable NewPara found this time performs worse than expected. At this time, it is selected to accept NewPara with a certain probability. The probability formula is as follows, where NowTemp represents the current temperature and gradually decreases.

[0186]

[0187] Then calculate a random probability r in [0, 1]. If prob is greater than r, go to Step 8; otherwise, go to Step 9.

[0188] Step 8: Accept the new parameter according to the probability. At this time, it is selected to update CurrPara and P CurrPara , referring to the following formula.

[0189] CurrPara = NewPara

[0190] P CurrPara = P NewPara

[0191] Step 9: Meet the iteration upper limit. Steps 2 to 8 are the innermost loop. Each time it is executed, the iteration count is incremented by one. If the iteration count exceeds the maximum value MaxIterCnt (which can be customized, default is 100), go to Step 10; otherwise, go to Step 2.

[0192] Step 10: Decrease the temperature. After the innermost loop is executed, temperature decay is performed. NowTemp represents the current temperature, initialized to MaxTemp (which can be customized, default is 100), and the minimum value is MinTemp (which can be customized, and MinTemp < MaxTemp, default is 1). The decay formula is as follows:

[0193] NowTemp = DecayRate * NowTemp

[0194] where DecayRate represents the decay rate, with a value range of [0, 1), which can be customized, default is 0.99.

[0195] Step 11: Reach the lower limit of temperature. Steps 2 to 10 are the middle layer loops. Each time they are executed, the temperature decays once. When NowTemp≤MinTemp, that is, the current temperature has reached the lower limit of temperature, it means that the optimal parameter value has been found. At this time, the entire simulated annealing search process ends and goes to step 12, otherwise go to step 2.

[0196] Step 12: Find the optimal parameters of the SVM prediction model. When this step is reached, the entire simulated annealing process is completed, indicating that the optimal parameters BestPara have been obtained.

[0197] BestPara={C,g}

[0198] Step 13: Update the SVM prediction model. In step 1, the latest data set was obtained; in step 12, the key parameter BestPara of the SVM support vector machine was determined. Based on the latest data set, the SVM support vector machine model for lost circulation prediction was obtained through training.

[0199] At the same time, the SVM model update threshold Delt is reset to the default value (which can be customized and the default value is 1). The SVM model update threshold Delt indicates whether an update is needed. If Delt>0, it means that no update is needed for the time being, otherwise it needs to be updated immediately.

[0200] Step 14: Get real-time data. Real-time data here is obtained from on-site drilling reports, mud reports, completion reports and other materials, or from the on-site monitoring system, and is real-time operation data on the front line. Each set of data includes multiple characteristics such as lithology, pore size, porosity, pore pressure, fracture pressure, shear stress, gel strength, pump pressure, drill bit speed, and primary fracture direction.

[0201] These data can be manually transcribed according to needs, or automatically generated by the monitoring system. Based on these data, they are input into the well leakage prediction SVM support vector machine model to make on-site well leakage prediction.

[0202] Step 15: Determine the prediction accuracy based on the SVM prediction model. Based on real-time data, input it into the well leakage prediction SVM support vector machine model to make on-site well leakage prediction. Then combine it with manual experience to determine whether the prediction result is correct.

[0203] Step 16: Add real-time data to the data set. If the prediction result is correct, directly add the real-time data to the data set, that is, update the data set. If the prediction result is wrong, modify the result to be correct, and then add the real-time data to the data set, that is, update the data set.

[0204] Step 17: Update the update threshold. Based on real-time data prediction, if the prediction fails, the Delt update formula is as follows:

[0205]

[0206] Based on real-time data prediction, if the prediction is successful, the Delt update formula is as follows:

[0207]

[0208] Among them, MaxFailCnt represents the maximum number of failed predictions (can be customized, the default is 50), MaxSuccCnt represents the maximum number of successful predictions (can be customized, the default is 200, usually, MaxFailCnt <MaxSuccCnt)。

[0209] In general, assuming that the number of failures of the current model is FailCnt and the number of successes is SuccCnt, if This indicates that the model needs to be updated.

[0210] Step 18: Update the SVM model. If the SVM model update threshold Delt is less than 0, the SVM model needs to be updated, and go to step 19. Otherwise, the current model can continue to be used, and go to step 14.

[0211] Step 19: Reset all parameters. Reset the parameters related to simulated annealing, including resetting the current temperature NowTemp to MaxTemp, resetting the number of inner loop iterations to 0, etc. Go to step 1.

[0212] To summarize, steps 1 to 13 are based on the latest data set to find the optimal parameters, and then iteratively update to obtain the optimal SVM well leakage prediction model; steps 14 to 19 are based on real-time operation data, and the SVM support vector machine model for well leakage prediction is used to predict whether well leakage will occur. These two processes are independent of each other, that is, they do not affect each other. When the iterative update of the SVM well leakage prediction model is not completed, the prediction model uses the previous version of the model; when the iterative update is completed, the prediction model version update will be triggered, and the well leakage prediction will be temporarily stopped during the version update. After the update, the latest version of the model will be used.

[0213] In summary, the present invention proposes a real-time prediction method for well leakage accidents, which finds the optimal parameters of the SVM support vector machine by improving simulated annealing, and supports the rapid update of the classification model, so as to make the prediction of the well leakage prediction model more accurate and real-time. Compared with the prior art, the present invention has at least the following beneficial effects:

[0214] 1) A well leakage prediction method based on SVM support vector machine was proposed. Relying on SVM support vector machine, the intelligent level of accident warning was significantly enhanced.

[0215] 2) A method based on improved simulated annealing to search for the optimal parameters of the SVM support vector machine was proposed, which automated the network parameter adjustment process and greatly improved the accuracy of the early warning.

[0216] 3) Integrate field operation data to verify prediction results and accelerate the iterative upgrade of the SVM well leakage prediction model, thereby ensuring the real-time update and rapid prediction capabilities of the SVM well leakage prediction model.

[0217] On the other hand, Fig. 9 As shown, an embodiment of the present invention provides a real-time prediction device 900 for lost circulation accidents, which may include:

[0218] The first module 901 is used to obtain a drilling data set; the data set includes multiple sets of feature data and labeling information of whether a well leakage accident occurs in the data set;

[0219] The second module 902 is used to randomly generate key parameters in a preset interval; the key parameters include regularization coefficients and kernel parameters;

[0220] The third module 903 is used to set a preset support vector machine through key parameters, and then iteratively upgrade the support vector machine through a simulated annealing strategy based on the data set to obtain a target support vector machine;

[0221] The fourth module 904 is used to obtain real-time feature data of the drilling site, and input the real-time feature data into the target support vector machine to predict and obtain the well leakage prediction result;

[0222] The fifth module 905 is used to obtain the accuracy of the well leakage prediction result in response to the verification instruction of the target object;

[0223] The accuracy includes correctness and error; when the accuracy is error, the well leakage prediction result is corrected according to the verification instruction;

[0224] The sixth module 906 is used to associate the real-time feature data with the well leakage prediction result and add it to the data set; perform attenuation update on the preset update threshold value based on the accuracy;

[0225] The seventh module 907 is used to return to the step of obtaining real-time feature data of the drilling site when reaching the next prediction node, until the update threshold is less than or equal to 0, reset the target parameters, return to the step of randomly generating key parameters in a preset interval, and continuously update the target support vector machine; the target parameters include the update threshold.

[0226] The contents of the method embodiments of the present invention are all applicable to the device embodiments. The functions specifically implemented by the device embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0227] On the other hand, an embodiment of the present invention further provides an electronic device, the electronic device comprising a memory and a processor, the memory storing a computer program, and the processor implementing the above-mentioned hydrate stability region bottom boundary prediction method when executing the computer program. The electronic device can be any intelligent terminal including a tablet computer, a car computer, etc.

[0228] It can be understood that the contents of the above method embodiments are all applicable to the present device embodiments, the functions specifically implemented by the present device embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0229] like Fig.10 As shown, Fig.10 The hardware structure of an electronic device 1000 of another embodiment is illustrated. The electronic device 1000 includes:

[0230] The processor 1001 may be implemented by a general-purpose CPU (Central Processing Unit), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of the present invention.

[0231] The memory 1002 can be implemented in the form of a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM). The memory 1002 can store an operating system and other application programs. When the technical solution provided in the embodiment of this specification is implemented by software or firmware, the relevant program code is stored in the memory 1002, and the processor 1001 calls and executes the network node population optimization method of the embodiment of the present invention;

[0232] Input / output interface 1003, used to implement information input and output;

[0233] The communication interface 1004 is used to realize the communication interaction between the device and other devices. The communication can be realized through a wired manner (such as USB, network cable, etc.) or a wireless manner (such as mobile network, WIFI, Bluetooth, etc.);

[0234] A bus 1005 , which transmits information between various components of the device (e.g., the processor 1001 , the memory 1002 , the input / output interface 1003 , and the communication interface 1004 );

[0235] The processor 1001 , the memory 1002 , the input / output interface 1003 and the communication interface 1004 are connected to each other in communication within the device via the bus 1005 .

[0236] The electronic device embodiments described above are merely illustrative, and the units described as separate components may or may not be physically separated, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0237] The contents of the method embodiments of the present invention are all applicable to the electronic device embodiments. The functions specifically implemented by the electronic device embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0238] Another aspect of an embodiment of the present invention further provides a computer-readable storage medium, wherein the storage medium stores a program, and the program is executed by a processor to implement the above method.

[0239] It should be noted that the computer-readable medium shown in the embodiment of the present invention may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM), a flash memory, an optical fiber, a portable compact disk read-only memory (Compact Disc Read to Only Memory, CD to ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present invention, a computer-readable storage medium may be any tangible medium containing or storing a program, which may be used by or in combination with an instruction execution system, device or device. In the present invention, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer readable signal media may also be any computer readable medium other than computer readable storage media, which may send, propagate, or transmit programs for use by or in conjunction with an instruction execution system, apparatus, or device. The program code contained on the computer readable medium may be transmitted using any suitable medium, including but not limited to: wireless, wired, etc., or any suitable combination of the above.

[0240] The contents of the method embodiments of the present invention are all applicable to the computer-readable storage medium embodiments. The functions specifically implemented by the computer-readable storage medium embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0241] The embodiment of the present invention also discloses a computer program product or a computer program, which includes a computer instruction stored in a computer-readable storage medium. A processor of a computer device can read the computer instruction from the computer-readable storage medium, and the processor executes the computer instruction, so that the computer device executes the above method.

[0242] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present invention. In this regard, each box in the flow chart or block diagram can represent a module, a program segment, or a part of a code, and the above-mentioned module, program segment, or a part of a code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flow chart, and the combination of the boxes in the block diagram or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0243] It should be noted that, although several modules of the device for action execution are mentioned in the above detailed description, this division is not mandatory. In fact, according to an embodiment of the present invention, the features and functions of two or more modules or units described above can be embodied in one module or unit. On the contrary, the features and functions of one module or unit described above can be further divided into being embodied by multiple modules or units.

[0244] Through the description of the above implementation, it is easy for those skilled in the art to understand that the example implementation described here can be implemented by software, or by software combined with necessary hardware. Therefore, the technical solution according to the implementation of the present invention can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD to ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, including several instructions to enable a computing device (which can be a personal computer, a server, a touch terminal, or a network device, etc.) to execute the method according to the implementation of the present invention.

[0245] In some selectable embodiments, the function / operation mentioned in the block diagram may not occur in the order mentioned in the operation diagram. For example, depending on the function / operation involved, the two boxes shown in succession can actually be executed substantially simultaneously or the boxes can sometimes be executed in reverse order. In addition, the embodiment presented and described in the flow chart of the present invention is provided by way of example, for the purpose of providing a more comprehensive understanding of the technology. The disclosed method is not limited to the operation and logic flow presented by the present invention. Selectable embodiments are expected, wherein the order of various operations is changed and the sub-operation of a part described as a larger operation is performed independently.

[0246] In addition, although the present invention is described in the context of functional modules, it should be understood that, unless otherwise specified, one or more of the functions and / or features can be integrated into a single physical device and / or software module, or one or more functions and / or features can be implemented in separate physical devices or software modules. It is also understood that a detailed discussion of the actual implementation of each module is unnecessary for understanding the present invention. More specifically, in view of the properties, functions and internal relationships of various functional modules in the device disclosed in the present invention, the actual implementation of the module will be understood within the conventional skills of engineers. Therefore, those skilled in the art can implement the present invention set forth in the claims without excessive experimentation using ordinary techniques. It is also understood that the specific concepts disclosed are merely illustrative and are not intended to limit the scope of the present invention, which is determined by the full scope of the appended claims and their equivalents.

[0247] If the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods of each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0248] The logic and / or steps represented in the flowchart or otherwise described herein, for example, may be considered as an ordered list of executable instructions for implementing logical functions, and may be embodied in any computer-readable medium for use by an instruction execution device, apparatus or device (such as a computer-based device, a device including a processor, or other device that can fetch instructions from an instruction execution device, apparatus or device and execute the instructions), or in conjunction with such instruction execution device, apparatus or device. For purposes of this specification, "computer-readable medium" may be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution device, apparatus or device, or in conjunction with such instruction execution device, apparatus or device.

[0249] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), a fiber optic device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or, if necessary, processing in another suitable manner, and then stored in a computer memory.

[0250] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, a plurality of steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution device. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0251] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "examples", "specific examples", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.

[0252] Although the embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the claims and their equivalents.

[0253] The above is a specific description of the preferred implementation of the present invention, but the present invention is not limited to the embodiments. Those skilled in the art can make various equivalent modifications or substitutions without violating the spirit of the present invention. These equivalent modifications or substitutions are all included in the scope defined by the claims of the present invention.

Claims

1. A real-time prediction method for lost circulation accidents, characterized in that: The following steps are involved: Acquire a drilling data set; the data set includes multiple sets of feature data and labeling information of whether a well leakage accident occurs in the data set; Randomly generate key parameters in a preset interval; the key parameters include regularization coefficients and kernel parameters; The preset support vector machine is set by the key parameters, and then the support vector machine is iteratively upgraded by a simulated annealing strategy based on the data set to obtain a target support vector machine; Acquire real-time characteristic data of the drilling site, and input the real-time characteristic data into the target support vector machine for prediction to obtain a well leakage prediction result; In response to a verification instruction of the target object, obtaining the accuracy of the lost circulation prediction result; Wherein, the accuracy includes correctness and error; when the accuracy is error, the well leakage prediction result is corrected according to the verification instruction; Associating the real-time characteristic data with the well leakage prediction result and adding them to the data set; performing attenuation update on a preset update threshold based on the accuracy; When the next prediction node is reached, the step of obtaining real-time feature data of the drilling site is returned to the step until the update threshold is less than or equal to 0, the target parameters are reset, and the step of randomly generating key parameters in a preset interval is returned to the step of continuously updating the target support vector machine; the target parameters include the update threshold.

2. The real-time prediction method for lost circulation accidents according to claim 1, characterized in that: The method of setting a preset support vector machine by the key parameters, and then iteratively upgrading the support vector machine by a simulated annealing strategy based on the data set to obtain a target support vector machine comprises the following steps: The preset support vector machine is set by the key parameters, and the support vector machine is trained by the data set to obtain a support vector machine model; fitness evaluation is performed based on the training result of the data set to obtain the prediction accuracy of the support vector machine model; When the prediction accuracy is greater than the target threshold, the target threshold is updated by the prediction accuracy, the prediction accuracy is used as the historical accuracy of the next round, and the key parameter is used as the optimal parameter and the historical parameter; otherwise, based on the prediction accuracy and the historical accuracy of the previous round, the acceptance probability of the key parameter is determined in combination with the current temperature; when the acceptance probability meets the preset condition, the prediction accuracy is used as the historical accuracy of the next round, and the key parameter is used as the historical parameter; Add 1 to the number of iterations, update the historical parameters based on the preset rules, use the updated results as the key parameters, and return to execute the step of setting the preset support vector machine by the key parameters until the number of iterations reaches the number threshold; Performing attenuation processing on the current temperature based on a preset attenuation rate, setting the number of iterations to 0, returning to the step of setting the preset support vector machine by the key parameters, until the current temperature reaches a temperature threshold, and outputting the optimal parameters; Setting the support vector machine by using the optimal parameters to obtain the target support vector machine; Wherein, the target parameters include the number of iterations and the current temperature; the number of iterations is initialized and reset to 0, and the current temperature is initialized and reset to a preset maximum temperature.

3. The real-time prediction method for lost circulation accidents according to claim 2, characterized in that: The training result includes the accident prediction result of each group of the feature data in the data set; the fitness evaluation based on the training result of the data set to obtain the prediction accuracy of the vector machine model includes the following steps: Comparing the accident prediction result corresponding to each set of the feature data in the data set with the annotation information; The number of correctly predicted samples is obtained according to the comparison result, and the prediction accuracy of the vector machine model is obtained based on the ratio of the number of samples to the total number of samples in the data set.

4. The real-time prediction method for lost circulation accidents according to claim 2, characterized in that: The method of determining the acceptance probability of the key parameter based on the prediction accuracy and the historical accuracy of the previous round in combination with the current temperature includes the following steps: Obtaining an index value according to the ratio of the difference between the historical accuracy and the predicted accuracy of the previous round and the current temperature; Taking the natural constant as the base and the exponential value as the exponent, performing an exponential operation based on the base and the exponent to obtain the acceptance probability of the key parameter; Among them, the preset condition represents whether the acceptance probability is greater than the random probability; the random probability is randomly generated within a preset range.

5. The real-time prediction method for lost circulation accidents according to claim 2, characterized in that: The updating of the historical parameters based on the preset rules comprises the following steps: Performing a first update on the regularization coefficient according to a ratio of a product of a first random number and the number of iterations to the number threshold; The first update representation uses the sum of the regularization coefficient and the ratio as the regularization coefficient; Performing a second update on the kernel parameters according to a second random number; The second update representation uses the sum of the kernel parameter and the second random number as the kernel parameter.

6. The real-time prediction method for lost circulation accidents according to claim 1, characterized in that: The well leakage prediction result includes the occurrence of well leakage and the non-occurrence of well leakage; when the accuracy is wrong, the well leakage prediction result is corrected according to the verification instruction, including the following steps: When the well leakage prediction result is erroneously predicted as the sent well leakage, the well leakage prediction result is corrected to the well leakage not occurring; When the well leakage prediction result is erroneously predicted as the unsent well leakage, the well leakage prediction result is corrected to the occurred well leakage.

7. The real-time prediction method for lost circulation accidents according to claim 1, characterized in that: The attenuation updating of the preset update threshold based on the accuracy comprises the following steps: When the accuracy is correct, the difference between the update threshold and the first attenuation parameter is used as the update threshold; otherwise, the difference between the update threshold and the second attenuation parameter is used as the update threshold; The first decay parameter is determined based on the inverse of a preset maximum number of failures, and the second decay parameter is determined based on the inverse of a preset maximum number of successes.

8. A real-time prediction device for well leakage accidents, characterized in that: include: The first module is used to obtain a drilling data set; the data set includes multiple sets of feature data and labeling information of whether a well leakage accident occurs in the data set; The second module is used to randomly generate key parameters in a preset interval; the key parameters include regularization coefficients and kernel parameters; The third module is used to set a preset support vector machine through the key parameters, and then iteratively upgrade the support vector machine through a simulated annealing strategy based on the data set to obtain a target support vector machine; The fourth module is used to obtain real-time feature data of the drilling site, and input the real-time feature data into the target support vector machine to predict and obtain a well leakage prediction result; A fifth module is used to obtain the accuracy of the well leakage prediction result in response to the verification instruction of the target object; Wherein, the accuracy includes correctness and error; when the accuracy is error, the well leakage prediction result is corrected according to the verification instruction; The sixth module is used to associate the real-time characteristic data with the well leakage prediction result and add it to the data set; based on the accuracy, a preset update threshold is updated attenuated; The seventh module is used to return to the step of obtaining real-time feature data of the drilling site when reaching the next prediction node, until the update threshold is less than or equal to 0, reset the target parameters, return to the step of randomly generating key parameters in a preset interval, and continuously update the target support vector machine; the target parameters include the update threshold.

9. An electronic device, characterized in that: including a processor and a memory; The memory is used to store programs; The processor executes the program to implement the method according to any one of claims 1 to 7.

10. A computer storage medium storing a program executable by a processor, characterized in that: The program executable by the processor is used to implement the method according to any one of claims 1 to 7 when executed by the processor.

Images