Method and device for identifying drilling overflow conditions

Abstract

The present invention discloses a method and device for identifying overflow conditions in drilling, wherein the method comprises: obtaining historical drilling data; based on a wavelet transform algorithm, performing genetic algorithm training of overflow point thresholds on historical drilling data to obtain a threshold value for each characteristic data; the threshold value is used to detect mutation points of characteristic data; obtaining a variety of characteristic data of drilling from real-time logging data of drilling; performing wavelet transform processing on each characteristic data to extract high-frequency signal features of each characteristic data; and identifying overflow points of a variety of characteristic data of drilling according to the threshold value of each characteristic data and the high-frequency signal features of each characteristic data. The present invention can improve the efficiency and accuracy of identifying overflow conditions in drilling; at the same time, early prediction and warning of overflow conditions can be performed, thereby improving drilling safety.

Description

Technical Field

[0001] The invention relates to the technical field of oil drilling, and in particular to a method and a device for identifying a drilling overflow condition. Background Art

[0002] This section is intended to provide a background or context to the embodiments of the invention recited in the claims. No admission is made that the description herein is prior art by inclusion in this section.

[0003] As oil and gas exploration and development gradually move towards deep and complex formations, the risk of overflows during drilling is increasing. Oil and gas drilling experience shows that the time from overflow discovery to blowout is very short, with two-thirds of the time being within 30 minutes, and half of the time being within 10 minutes.

[0004] If overflow is not discovered in time, it may lead to well control danger, or even major accidents such as wellbore scrapping and casualties. Therefore, timely identification and early detection of overflow occurrence and giving a certain amount of warning time in advance will buy precious time for overflow treatment, thereby effectively controlling the deterioration of overflow and ensuring wellbore safety.

[0005] Traditional drilling technology identifies overflows by manually tracking characteristic parameters obtained by comprehensive logging instruments, analyzing the difference in inlet and outlet flow rates and changes in the total surface pool volume. However, due to the long depth from the wellhead to the bottom of the well, after the fluid invades the formation, it needs to return to a certain height before it can cause changes in surface parameters. As a result, this method is severely delayed in discovering overflows and is heavily dependent on the experience, responsibility and awareness of monitoring personnel.

[0006] At present, the proposed methods such as artificial neural networks and Bayesian networks still have limitations in automatically judging parameter changes and complex identification. They cannot effectively identify complex features during continuous long-term work, and cannot accurately identify overflow at an early stage. Summary of the invention

[0007] The embodiment of the present invention provides a method for identifying a drilling overflow condition, which can improve the efficiency and accuracy of identifying a drilling overflow condition; at the same time, early prediction and warning of the overflow condition can be performed, thereby improving drilling safety. The method includes:

[0008] Acquire historical drilling data; the historical drilling data is used to characterize: various characteristic data of drilling and historical data of drilling overflow conditions corresponding to the various characteristic data;

[0009] Based on the wavelet transform algorithm, the genetic algorithm training of the overflow point threshold is performed on the drilling history data to obtain the threshold of each characteristic data; the threshold is used to detect the mutation point of the characteristic data;

[0010] Obtain various characteristic data of drilling from real-time logging data of drilling;

[0011] Performing wavelet transform processing on each type of feature data to extract high-frequency signal features of each type of feature data; the wavelet transform processing includes decomposing and recombining the feature data to eliminate noise of the feature data;

[0012] According to the threshold value of each characteristic data and the high-frequency signal characteristics of each characteristic data, overflow points of various characteristic data of drilling are identified.

[0013] The embodiment of the present invention further provides a device for identifying a drilling overflow condition, which can improve the efficiency and accuracy of identifying a drilling overflow condition; at the same time, early prediction and warning of the overflow condition can be performed, thereby improving the safety of drilling. The device includes:

[0014] A drilling history data acquisition module is used to acquire drilling history data; the drilling history data is used to characterize: various characteristic data of drilling and historical data of drilling overflow conditions corresponding to the various characteristic data;

[0015] The characteristic data threshold training module is used to perform genetic algorithm training of overflow point threshold on historical drilling data based on wavelet transform algorithm to obtain the threshold of each characteristic data; the threshold is used to detect mutation points of characteristic data;

[0016] A real-time acquisition module for drilling characteristic data is used to obtain various drilling characteristic data from real-time logging data of drilling;

[0017] A wavelet transform processing module is used to perform wavelet transform processing on each type of feature data to extract high-frequency signal features of each type of feature data; the wavelet transform processing includes decomposing and recombining the feature data to eliminate noise of the feature data;

[0018] The overflow point identification module is used to identify overflow points of various characteristic data of drilling according to the threshold value of each characteristic data and the high-frequency signal characteristics of each characteristic data.

[0019] An embodiment of the present invention further provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the above-mentioned method for identifying the drilling overflow condition when executing the computer program.

[0020] An embodiment of the present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method for identifying the drilling overflow condition is implemented.

[0021] An embodiment of the present invention further provides a computer program product, which includes a computer program. When the computer program is executed by a processor, the method for identifying the drilling overflow condition is implemented.

[0022] In an embodiment of the present invention, historical drilling data is obtained; the historical drilling data is used to characterize: various characteristic data of drilling and historical data of drilling overflow conditions corresponding to the various characteristic data; based on a wavelet transform algorithm, a genetic algorithm training of overflow point threshold is performed on the historical drilling data to obtain a threshold value of each characteristic data; the threshold value is used to detect mutation points of the characteristic data; various characteristic data of drilling are obtained from real-time logging data of drilling; wavelet transform processing is performed on each characteristic data to extract high-frequency signal characteristics of each characteristic data; the wavelet transform processing includes decomposing and reorganizing the characteristic data to eliminate noise of the characteristic data; overflow points of various characteristic data of drilling are identified based on the threshold value of each characteristic data and the high-frequency signal characteristics of each characteristic data, which is different from the technical method of manually identifying overflows in the prior art. Compared with the previous case, firstly, a variety of characteristic data of drilling are obtained from the real-time logging data of drilling, and then the characteristic data threshold is determined based on the genetic algorithm to realize the identification of the overflow point. The parameter mutation can be identified by a variety of characteristic data at the initial moment of overflow, so as to detect the overflow, which can improve the efficiency and accuracy of drilling overflow condition identification; at the same time, the overflow condition can be predicted and warned in advance, and the overflow condition in the complex working conditions in oil drilling can be predicted in advance, which can timely and effectively reduce the hazards in oil drilling caused by the overflow condition, warn the drilling staff in advance, and buy precious time for further development of the overflow control, and solve the drilling safety problem caused by the serious delay in the discovery of overflow due to manual identification of overflow under the existing technology, avoid well control danger, and even serious accidents such as blowouts, thereby reducing unnecessary loss of life and property. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the prior art descriptions. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. In the drawings:

[0024] Figure 1 It is a flow chart of a method for identifying a drilling overflow condition in an embodiment of the present invention;

[0025] Figure 2 A specific example diagram of a method for identifying a drilling overflow condition in an embodiment of the present invention;

[0026] Figure 3 This is an example diagram of a process of performing wavelet transform processing in an embodiment of the present invention;

[0027] Figure 4 A schematic diagram showing an identified overflow point displayed on the original data of the outlet flow rate in an embodiment of the present invention;

[0028] Figure 5 It is a schematic diagram of a process of training a genetic algorithm for overflow point threshold value of historical drilling data in an embodiment of the present invention;

[0029] Figure 6 This is an example diagram of a process for identifying overflow points based on multiple characteristic data of drilling in an embodiment of the present invention;

[0030] Figure 7 A high-frequency signal diagram obtained after wavelet transform of pump stroke characteristic data in an embodiment of the present invention;

[0031] Figure 8 A high-frequency signal diagram obtained after wavelet transformation of all hydrocarbon characteristic data in an embodiment of the present invention;

[0032] Fig. 9 This is an example diagram of calculating the score of each individual in an initial population in an embodiment of the present invention;

[0033] Fig.10 A schematic diagram of a computer device for identifying a drilling overflow condition in an embodiment of the present invention;

[0034] Fig.11 This is a structural example diagram of a device for identifying a drilling overflow condition in an embodiment of the present invention. DETAILED DESCRIPTION

[0035] To make the purpose, technical solution and advantages of the embodiments of the present invention more clear, the embodiments of the present invention are further described in detail below in conjunction with the accompanying drawings. Here, the exemplary embodiments of the present invention and their descriptions are used to explain the present invention, but are not intended to limit the present invention.

[0036] The term "and / or" herein only describes an association relationship, indicating that three relationships may exist. For example, A and / or B may represent the following three situations: A exists alone, A and B exist at the same time, and B exists alone. In addition, the term "at least one" herein represents any combination of at least two of any one or more of a plurality of. For example, including at least one of A, B, and C may represent including any one or more elements selected from the set consisting of A, B, and C.

[0037] In the description of this specification, the terms "include", "including", "have", "contain", etc. are all open terms, which mean including but not limited to. The descriptions with reference to the terms "one embodiment", "a specific embodiment", "some embodiments", "for example", etc. mean that the specific features, structures or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures or characteristics described may be combined in a suitable manner in any one or more embodiments or examples. The order of steps involved in each embodiment is used to schematically illustrate the implementation of the present application, and the order of steps is not limited and can be appropriately adjusted as needed.

[0038] As oil and gas exploration and development gradually move towards deep and complex formations, the risk of overflows during drilling is increasing. Oil and gas drilling experience shows that the time from overflow discovery to blowout is very short, with two-thirds of the time being within 30 minutes, and half of these within 10 minutes. If overflows are not discovered in time, it may lead to well control dangers, or even major accidents such as wellbore scrapping and casualties. Therefore, timely identification and early detection of overflows and early warning of a certain amount of time will buy precious time for handling overflows, thereby effectively controlling the deterioration of overflows and ensuring wellbore safety.

[0039] Traditional drilling technology identifies overflows by manually tracking characteristic parameters obtained by comprehensive logging instruments, analyzing the difference in inlet and outlet flow rates and changes in the total surface pool volume. Due to the long depth from the wellhead to the bottom of the well, after the formation invades the fluid, it needs to return to a certain height before it can cause changes in surface parameters. This method causes a serious lag in the time it takes to detect overflows, and it is heavily dependent on the experience, responsibility and awareness of the monitoring personnel. At present, the proposed methods such as artificial neural networks and Bayesian networks still have limitations in automatically judging parameter changes and complex identification. They cannot effectively identify complex features during continuous long-term work and accurately identify overflows at an early stage.

[0040] In order to solve the above problems, an embodiment of the present invention provides a method for identifying a drilling overflow condition, which is used to identify a parameter mutation at the initial moment of overflow to detect overflow, make early predictions and warnings of overflow conditions, and warn drilling personnel in advance, so as to buy precious time for controlling the further development of overflow, avoid well control dangers, and even serious accidents such as blowouts, thereby causing unnecessary loss of life and property, and improve the efficiency and accuracy of drilling overflow condition identification; at the same time, early predictions and warnings of overflow conditions can be made, thereby improving drilling safety, see Figure 1 , the method may include:

[0041] Step 101: Acquire historical drilling data; the historical drilling data is used to characterize: various characteristic data of drilling and historical data of drilling overflow conditions corresponding to the various characteristic data;

[0042] Step 102: Based on the wavelet transform algorithm, a genetic algorithm training of overflow point thresholds is performed on the drilling history data to obtain a threshold value for each type of characteristic data; the above threshold value is used to detect mutation points of the characteristic data;

[0043] Step 103: acquiring various characteristic data of the drilling from the real-time logging data of the drilling;

[0044] Step 104: performing wavelet transform processing on each type of feature data to extract high-frequency signal features of each type of feature data; the wavelet transform processing includes decomposing and recombining the feature data to eliminate noise of the feature data;

[0045] Step 105: According to the threshold of each characteristic data and the high-frequency signal characteristics of each characteristic data, overflow points of various characteristic data of drilling are identified.

[0046] In an embodiment of the present invention, historical drilling data is obtained; the historical drilling data is used to characterize: various characteristic data of drilling and historical data of drilling overflow conditions corresponding to the various characteristic data; based on the wavelet transform algorithm, the genetic algorithm training of the overflow point threshold is performed on the historical drilling data to obtain the threshold of each characteristic data; the threshold is used to detect the mutation point of the characteristic data; various characteristic data of drilling are obtained from the real-time logging data of drilling; each characteristic data is subjected to wavelet transform processing to extract the high-frequency signal characteristics of each characteristic data; the wavelet transform processing includes decomposing and reorganizing the characteristic data to eliminate the noise of the characteristic data; the overflow point of the various characteristic data of drilling is identified according to the threshold of each characteristic data and the high-frequency signal characteristics of each characteristic data, which is different from the technical method of manually identifying overflow in the prior art. Compared with the previous case, firstly, a variety of characteristic data of drilling are obtained from the real-time logging data of drilling, and then the characteristic data threshold is determined based on the genetic algorithm to realize the identification of the overflow point. The parameter mutation can be identified by a variety of characteristic data at the initial moment of overflow, so as to detect the overflow, which can improve the efficiency and accuracy of drilling overflow condition identification; at the same time, the overflow condition can be predicted and warned in advance, and the overflow condition in the complex working conditions in oil drilling can be predicted in advance, which can timely and effectively reduce the hazards in oil drilling caused by the overflow condition, warn the drilling staff in advance, and buy precious time for further development of the overflow control, and solve the drilling safety problem caused by the serious delay in the discovery of overflow due to manual identification of overflow under the existing technology, avoid well control danger, and even serious accidents such as blowouts, thereby reducing unnecessary loss of life and property.

[0047] During specific implementation, historical drilling data is first obtained; the historical drilling data is used to represent: various characteristic data of drilling and historical data of drilling overflow conditions corresponding to the various characteristic data.

[0048] In an embodiment, obtaining various characteristic data of drilling may include: real-time obtaining various characteristic data of drilling obtained by a comprehensive logging instrument at the drilling site, such as outlet flow, vertical pressure, total hydrocarbons, pump stroke changes, drill bit depth and inlet flow, etc.; drilling overflow conditions corresponding to various characteristic data may include: drilling overflow points corresponding to different characteristic data.

[0049] In specific implementation, after obtaining the historical drilling data, the genetic algorithm of the overflow point threshold is trained on the historical drilling data based on the wavelet transform algorithm to obtain the threshold of each characteristic data; the above threshold is used to detect the mutation point of the characteristic data.

[0050] In the embodiment, based on the wavelet transform algorithm, the genetic algorithm training of the overflow point threshold is performed on the drilling history data to obtain the threshold of each characteristic data, which may include:

[0051] For each feature data:

[0052] Use random seeds to generate the initial population;

[0053] According to the fitness function of the genetic algorithm, the score of each individual in the initial population is calculated; according to the score of each individual in the initial population, individuals that meet the preset score conditions are selected from the initial population, and genetic operations are performed to obtain a new population; the above genetic operations include crossover operations, replication operations and mutation operations; the new population replaces the initial population;

[0054] Repeat the above steps to obtain a new population until the individual score reaches the maximum value or the number of cycles reaches the set genetic generation, and output the latest population:

[0055] According to the latest population output, the threshold corresponding to the feature data is determined.

[0056] In the above embodiment, the genetic algorithm can be used to obtain the optimal threshold for identifying mutations, and the relevant parameters of the genetic algorithm can be preset as follows: the number of populations is 30, the number of iterations is 50, the crossover rate of chromosomes in the population is 0.8, and the mutation rate is 0.3. In a specific above example, using the fitness function defined with the score function as the evaluation standard, the optimal overflow point threshold obtained by training can be shown in Table 1:

[0057] Table 1

[0058] Parameter name Threshold Egress traffic -0.0731314118221788 Vertical pressure -0.04382022471910113 Total hydrocarbons 0.006790425012212997 Pump stroke change -0.011675622862725943 Drill depth -0.07664875427454812

[0059] In one embodiment, the score of each individual in the initial population is calculated according to the fitness function of the genetic algorithm according to the following formula:

[0060]

[0061] Wherein, f(x) is the score of each individual in the initial population; C is a constant; x~N(0,1) indicates that x follows a standard normal distribution; index is the starting position of the overflow in the data; length is the ending position of the overflow in the data; in [index-100,index+100], x=(X-index) / 200, in [index+100,length], x=(abs(X-index)) / (length-index)+1, X is the identified overflow point. In the above embodiment, f(x) refers to the fitness calculation function according to the genetic algorithm, and the score of each individual in the initial population can be calculated by this function.

[0062] In one embodiment, the genetic algorithm training of the overflow point threshold for the drilling history data to obtain the threshold of each characteristic data may include the following steps:

[0063] Step 1: Use random seeds to initialize the population (a data set consisting of many individuals, each of which can be regarded as a solution to the optimization problem) to obtain population 1 (i.e., the initial population mentioned above);

[0064] Step 2: Use the fitness function f(x) to calculate the score of each individual. If there is an individual that meets the score condition, the algorithm ends, otherwise go to step 3;

[0065] Step 3: Select according to individual scores, discard a certain proportion of individuals, perform genetic operations on the remaining individuals, obtain a new population, such as population 2, and then jump to step 2 again;

[0066] Among them, genetic operations are divided into crossover, replication, and mutation. Each individual will randomly undergo one of these three operations or no operation. Crossover operation refers to the exchange of some parameters between two individuals according to a certain ratio and requirements. Replication operation means that the individual will generate an identical individual. Mutation operation means that some parameters of the individual are changed.

[0067] In a specific embodiment, the fitness function defined in the above genetic algorithm is the sum of the overflow position scores, which can make the position score near the overflow point high, identify the position 100 time units to the left of the overflow point, indicate incorrect identification, and make its score negative, and the position to the right of the overflow point and the overflow is correctly identified, but because it is far away from the initial overflow point, its score is positive and less than the position score of 100 time units around the overflow point, and gradually tends to 0, which is more conducive to identifying the overflow starting position and realizing early identification of overflow, such as Fig. 9 shown.

[0068] The purpose of the embodiment of the present invention is to identify mutations and detect overflows. It is expected that mutations can be detected near the initial overflow position. Therefore, in the embodiment of the present invention, points near the overflow point can have high scores; mutations after the overflow point indicate that the overflow point has been detected, but the importance of the mutations is different from that of the initial overflow expected by the embodiment of the present invention. Therefore, in the embodiment of the present invention, the position score after the area near the initial overflow is set to the score shown in the above-mentioned f(x) formula, which gradually tends to 0 backward; mutations identified in front of the overflow range indicate an identification error, and the embodiment of the present invention sets its value to -0.8. Specifically, in the embodiment of the present invention, the number of individuals in the population can be set to 30, and 100 iterations can be performed to obtain the individual with the largest fitness, obtain the chromosome therein, and decode it to obtain the optimal overflow point threshold.

[0069] In specific implementation, after the overflow point threshold genetic algorithm training is performed on the drilling history data based on the wavelet transform algorithm and the threshold of each characteristic data is obtained, various characteristic data of drilling are obtained from the real-time logging data of drilling.

[0070] In an embodiment, various characteristic data of drilling are obtained from real-time logging data of drilling, which can include: real-time acquisition of various characteristic data of drilling obtained by a comprehensive logging instrument at the drilling site, such as outlet flow, vertical pressure, total hydrocarbons, pump stroke changes, drill bit depth and inlet flow, and other characteristic data.

[0071] In the above embodiment, in order to realize the detection of mutations, the embodiment of the present invention needs to extract the high-frequency signals in the feature data and blur the signals that do not change drastically. Therefore, the embodiment of the present invention decomposes and reconstructs the original feature data through a three-level wavelet transform, and extracts the secondary high-frequency signals therein to be used as input data for the next overflow point determination.

[0072] In specific implementation, after obtaining various characteristic data of drilling from the real-time logging data of drilling, each characteristic data is subjected to wavelet transform processing to extract the high-frequency signal characteristics of each characteristic data; the above wavelet transform processing includes decomposing and reorganizing the characteristic data to eliminate the noise of the characteristic data.

[0073] In the embodiment, performing wavelet transform processing on each type of feature data to extract high-frequency signal features of each type of feature data may include:

[0074] By utilizing the wavelet multi-resolution analysis characteristics, each feature data is decomposed and reorganized at multiple scales to extract the high-frequency signal characteristics of each feature data.

[0075] In one embodiment, performing multi-scale decomposition and reorganization on each type of feature data to extract high-frequency signal features of each type of feature data may include:

[0076] For each type of feature data: perform a first-order wavelet transform on the feature data to obtain a first-order approximate signal and a first-order detail signal; the first-order detail signal is a first group of high-frequency signals;

[0077] Extract the first-order approximate signal and perform wavelet transform again to obtain the second-order approximate signal and the second-order detail signal;

[0078] The second-order detail signal is used as the high-frequency signal feature of this feature data.

[0079] In one embodiment, the wavelet transform processing is to "polish" the original signal (i.e., feature data) at different scales, i.e., convolve it with a local integrable function, so as to achieve the effect of improving the smoothness of the original signal, and detect the extreme points or zero crossings of the first-order or second-order derivatives of the processed signal.

[0080] In one embodiment, the acquired feature data can be decomposed and reorganized at multiple scales by utilizing the wavelet multi-resolution analysis characteristics to determine the location of the signal mutation. The wavelet transform is to "polish" the original signal, mainly to eliminate noise rather than edges. The polishing function satisfies the integrability This function does not require input, it only needs to be an arbitrary function that satisfies the properties of the polishing function in the R domain. The effect of such θ(t) is equivalent to a low-pass filter. According to the definition of convolutional wavelet transform, we have

[0081]

[0082]

[0083] t represents time, and the convolution operation gθ in equations (1) and (2) is s (t) is also called the polishing operator (i.e., the convolution operator that can transform the smoothness of a function). Select the smooth function θ s (t), the mutation point X(t X ,g(t x )), can be detected by wavelet transform and The maximum value of the modulus is obtained. represents the polishing function θ s (t) in the form of the i-th derivative, the smooth function θ s (t) can be an exponential function, etc.

[0084] In specific implementation, after performing wavelet transform processing on each feature data and extracting the high-frequency signal features of each feature data, overflow points of various feature data of drilling are identified according to the threshold of each feature data and the high-frequency signal features of each feature data.

[0085] In an embodiment, the multiple characteristic data of the above-mentioned drilling include: one or any combination of outlet flow characteristic data, vertical pressure characteristic data, total hydrocarbon characteristic data, pump stroke change characteristic data, drill bit depth characteristic data and inlet flow characteristic data.

[0086] In specific implementation, a method for identifying a drilling overflow condition provided by an embodiment of the present invention may further include: obtaining a feature data comparison process for overflow point identification; the feature data comparison process is used to describe a process for comparing different types of feature data of high-frequency signal features and overflow point thresholds;

[0087] Based on the threshold of each characteristic data and the high-frequency signal characteristics of each characteristic data, the overflow point identification is performed on the various characteristic data of the drilling, which may include:

[0088] The overflow point is identified for various characteristic data of the drilling according to the threshold of each characteristic data, the high-frequency signal characteristics of each characteristic data, and the characteristic data comparison process for overflow point identification.

[0089] In one embodiment, the overflow point is selected based on a flow chart obtained from expert experience (i.e., a feature data comparison process for overflow point identification), and the threshold is a standard for measuring whether a parameter data changes drastically. After substituting the threshold, the overflow point can be found based on the threshold and the expert experience flow chart.

[0090] In one embodiment, the overflow point identification is performed on the multiple characteristic data of the drilling according to the threshold of each characteristic data, the high-frequency signal characteristics of each characteristic data, and the characteristic data comparison process for the overflow point identification, which may include:

[0091] When the high-frequency signal feature of the outlet flow characteristic data is greater than or equal to the threshold value of the outlet flow characteristic data, and the high-frequency signal feature of the standing pressure characteristic data is greater than or equal to the threshold value of the standing pressure characteristic data, the current drilling position is determined as the overflow point;

[0092] When the high-frequency signal characteristics of the outlet flow characteristic data are less than the threshold of the outlet flow characteristic data, the high-frequency signal characteristics of the stand pressure characteristic data are less than the threshold of the stand pressure characteristic data, the high-frequency signal characteristics of the total hydrocarbon characteristic data are less than the threshold of the total hydrocarbon characteristic data, the high-frequency signal characteristics of the pump stroke characteristic data are less than the threshold of the pump stroke characteristic data, and the high-frequency signal characteristics of the drill bit depth characteristic data are less than the threshold of the pump stroke characteristic data, the current drilling position is determined as the overflow point.

[0093] A specific embodiment is given below to illustrate the specific application of the method of the present invention.

[0094] First, the parameters and formulas involved in this embodiment are explained as follows:

[0095] Definition 1: X is the identified mutation point;

[0096] Definition 2: x i is the data point of the i-th interval area after processing;

[0097] Definition 3: Convolution. Assuming f(x), g(x) are integrable functions on R1, then convolution

[0098] Definition 4: The fitness function f(x) is a function that outputs a score based on the input x;

[0099] Definition 5: x i ~N(0,1) indicates that the data follows a normal distribution;

[0100] Definition 6: The polishing function θ(t) is a function with local integrability properties;

[0101] Definition 6: Represents the i-th derivative form of the polishing function θ(t).

[0102] Secondly, in this embodiment, if Figure 2 The simplified flowchart shown may include the following steps:

[0103] Step 1: Real-time acquisition of parameter data obtained by a comprehensive logging instrument at the drilling site. The parameters used in the present invention are: outlet flow, vertical pressure, total hydrocarbon, pump stroke change, drill bit depth, and inlet flow.

[0104] Step 2: Figure 3 As shown, the acquired data can be decomposed and reorganized at multiple scales using the wavelet multi-resolution analysis characteristics to determine the location of the signal mutation. The wavelet transform is to "polish" the original signal, mainly to eliminate noise rather than edges. The polishing function satisfies the integrability The effect of θ(t) is equivalent to a low-pass filter. According to the definition of convolutional wavelet transform, we have

[0105]

[0106]

[0107] Where t represents time, and the convolution operation g*θ in equations (1) and (2) is s (t) is also called the polishing operator (i.e., the convolution operator that can transform the smoothness of a function). Select the smooth function θ s After θ(t), the mutation point X(t X ,g(t X )), can be detected by wavelet transform and The maximum value of the modulus is obtained; represents the i-th derivative form of the polishing function θ(t), the smoothing function θ s (t), can take an exponential function.

[0108] Step 3, extract the high-frequency signal d2 obtained after wavelet decomposition and reorganization;

[0109] Step 4: Use genetic algorithm to obtain the optimal threshold for identifying mutations. The number of populations in the genetic algorithm is 30, the number of iterations is 50, the crossover rate of chromosomes in the population is 0.8, and the mutation rate is 0.3;

[0110] For example, Figure 4 This is a schematic diagram showing the overflow point identified in an embodiment of the present invention on the original data of the outlet flow rate.

[0111] Furthermore, the brief process of the genetic algorithm in step 4 is as follows: Figure 5 As shown, the following steps may be included:

[0112] (1) Use random seeds to initialize the population (a data set consisting of many individuals, each of which can be regarded as a solution to the optimization problem) and obtain population 1;

[0113] (2) Use the fitness function f(x) to calculate the score of each individual. If there is an individual that meets the score condition, the algorithm ends, otherwise go to (3);

[0114] (3) According to the individual scores, a certain proportion of individuals are discarded, and the remaining individuals are subjected to genetic operations. The genetic operations are divided into crossover, replication, and mutation. Each individual will randomly undergo one of the three operations or no operation. The crossover operation refers to the exchange of some parameters between two individuals according to a certain ratio and requirements. The replication operation means that the individual will generate an identical individual. The mutation operation means that some parameters of the individual are changed. In this way, a new population is obtained - population 2, and then go to (2).

[0115] Using the defined fitness function with the score function as the evaluation criterion, the optimal thresholds obtained through training are shown in Table 1.

[0116] Step 5: Use the overflow identification flowchart obtained by optimal threshold and manual experience to identify the overflow point.

[0117] Furthermore, the feature data of different frequencies and different time dimensions extracted by wavelet transform in step 2 are original data;

[0118] Further, in step 3, the high-frequency signal d2 is obtained by wavelet decomposition and recombination, and the first-order wavelet transform is used to obtain the first-order approximate signal and the first-order detail signal, the first-order detail signal is the first group of high-frequency signals, on this basis, the first-order approximate signal of the first-order wavelet transform is extracted and then wavelet transform is performed to obtain the second-order approximate signal and the second-order detail signal, and so on, the second group of high-frequency signals (d2 signals) are selected for mutation detection; in step 3, the high-frequency signal d2 is obtained by wavelet decomposition and recombination for mutation detection;

[0119] Furthermore, in step 4, the high-frequency signal d2 obtained by wavelet transform is used as the input of the genetic algorithm for training parameters. The threshold is trained in combination with the overflow identification flow chart obtained by expert experience. The evaluation standard of the fitness function is the sum of the scores of all the identified overflow positions using the following scoring function. The scoring function is as follows:

[0120]

[0121] Among them, f(x) is the score of each individual in the initial population; C is a constant; x~N(0,1) means that x follows a standard normal distribution; index is the starting position of the overflow in the data; length is the end position of the overflow in the data; in [ibdex-100,index+100], x=(X-index) / 200, in [index+100,length], x=(abs(X-index)) / (length-index)+1, and X is the identified overflow point.

[0122] In the embodiment, the fitness function of the present invention is defined as the sum of overflow position scores in the genetic algorithm. The position score near the overflow point is high, and the position to the left of the overflow point 100 time units indicates an incorrect identification, and its score is set to a negative value. The position to the right of the overflow point and the overflow indicates a correct identification, but because it is far from the initial overflow point, its score is set to be positive and less than the position score of 100 time units around the overflow point, and gradually tends to 0, which is more conducive to identifying the overflow starting position and realizing the early identification of the overflow, as mentioned above. The purpose of the present invention is to identify mutations and detect overflows. The present invention hopes to detect mutations near the initial overflow position, so the present invention gives points near the overflow point a high score; mutations after the overflow point indicate that the overflow point is detected but the mutation importance of the initial overflow desired by the present invention is different, so the present invention sets the position score after the initial overflow vicinity to the score shown in the above formula, and gradually tends to 0 backward; mutations are identified in front of the overflow vicinity range, indicating an identification error, and the present invention sets its value to -0.8. The present invention sets the number of individuals in the population to 30, performs 100 iterations, obtains the individual with the largest fitness, obtains the chromosome therein, performs decoding, and obtains the optimal threshold.

[0123] Furthermore, the drilling site monitoring personnel can make a decision on the next task based on the comprehensive judgment of the detection results and field parameters in real time.

[0124] like Figure 6 As shown, according to the threshold of each characteristic data, the high-frequency signal characteristics of each characteristic data, and the characteristic data comparison process for overflow point identification, the overflow point identification of multiple characteristic data of drilling can include the following steps:

[0125] a. Input high-frequency d2 features extracted by wavelet: outlet flow, vertical pressure, total hydrocarbon, pump stroke change, drill bit depth, inlet flow; Figure 7 and Figure 8 As shown, Figure 7 A high-frequency signal diagram obtained after wavelet transform of pump stroke characteristic data in an embodiment of the present invention; Figure 8 A high-frequency signal diagram obtained after wavelet transformation of all hydrocarbon characteristic data in an embodiment of the present invention;

[0126] b. If the outlet flow rate is greater than the outlet flow rate threshold and the vertical pressure is greater than the vertical pressure threshold, go to g;

[0127] If the outlet flow rate is less than the outlet flow rate threshold and the standing pressure is less than the standing pressure threshold, go to f;

[0128] Otherwise, go to c;

[0129] c. If the total hydrocarbon is greater than the total hydrocarbon threshold, go to f;

[0130] Otherwise, switch to d;

[0131] d. If the pump stroke is greater than the pump stroke threshold, go to f;

[0132] Otherwise, switch to e;

[0133] e. If the drill depth is greater than the drill depth threshold, go to f;

[0134] Otherwise, switch to g;

[0135] f. Output is normal;

[0136] g. Output overflow.

[0137] The beneficial effect of the above technical solution in this embodiment is that: according to the results, the occurrence of overflow can be well detected, and early warning of overflow can be given, reminding drilling personnel to take remedial measures in advance, thereby reducing the possibility of further causing blowout. In addition, the method is based on wavelet mutation detection and does not rely on the experience of monitoring personnel, which can avoid the misjudgment and failure to judge the overflow due to lack of personnel experience, improper operation, lack of concentration, etc.

[0138] The present invention will be described below by means of a specific example.

[0139] Using real historical drilling data of a certain oil field, the embodiment of the present invention intercepts data more than 60 minutes before the overflow and data after the overflow occurs. There are 4663 samples in total, 3181 data before the overflow occurs, and 1428 overflow data.

[0140] Specific implementation steps based on the above data:

[0141] 1) Data processing:

[0142] In order to realize the detection of mutations, the present invention needs to extract the high-frequency signals in the signal and blur the signals with less drastic changes. Therefore, the present invention decomposes and reconstructs the original data by three-level wavelet transform, extracts the secondary high-frequency signals therein, and uses them as the input for the next overflow judgment.

[0143] 2) Genetic training threshold:

[0144] In the genetic algorithm, the present invention defines the fitness function as the sum of the overflow position scores. The position score near the overflow point is high, and the position to the left of the overflow point 100 time units is identified as an incorrect identification, and its score is set to a negative value. The position to the right of the overflow point and the overflow is correctly identified, but because it is far away from the initial overflow point, its score is set to be positive and less than the position score of 100 time units around the overflow point, and gradually tends to 0, which is more conducive to identifying the overflow starting position and realizing the early identification of the overflow, as mentioned above. The purpose of the present invention is to identify mutations and detect overflows. The present invention hopes to detect mutations near the initial overflow position, so the present invention gives points near the overflow point a high score; mutations after the overflow point indicate that the overflow point is detected but the mutation importance of the initial overflow desired by the present invention is different, so the present invention sets the position score after the initial overflow vicinity to the score shown in the above formula, and gradually tends to 0 backward; mutations are identified in front of the overflow vicinity range, indicating an identification error, and the present invention sets its value to -0.8. The present invention sets the number of individuals in the population to 30, performs 100 iterations, obtains the individual with the largest fitness, obtains the chromosome therein, performs decoding, and obtains the optimal threshold.

[0145] 3) Select overflow point:

[0146] The selection of overflow points relies on the flowchart obtained by expert experience, and the threshold is the standard for measuring whether a parameter data changes drastically. After substituting the threshold, the present invention finds the overflow point according to the threshold and the expert experience flowchart, and the identified overflow starting point position is 2621, which is 561 away from the actual overflow starting point position. Based on the range near the overflow given by the present invention, the wrong recognition point is defined as the point that is not recognized as overflow and is 100 points before the overflow starting point. The calculated error recognition rate is 4.35%.

[0147] Of course, it is understandable that the above detailed process may have other variations, and the relevant variations should all fall within the protection scope of the present invention.

[0148] In an embodiment of the present invention, historical drilling data is obtained; the historical drilling data is used to characterize: various characteristic data of drilling and historical data of drilling overflow conditions corresponding to the various characteristic data; based on the wavelet transform algorithm, the genetic algorithm training of the overflow point threshold is performed on the historical drilling data to obtain the threshold of each characteristic data; the threshold is used to detect the mutation point of the characteristic data; various characteristic data of drilling are obtained from the real-time logging data of drilling; each characteristic data is subjected to wavelet transform processing to extract the high-frequency signal characteristics of each characteristic data; the wavelet transform processing includes decomposing and reorganizing the characteristic data to eliminate the noise of the characteristic data; the overflow point of the various characteristic data of drilling is identified according to the threshold of each characteristic data and the high-frequency signal characteristics of each characteristic data, which is different from the technical method of manually identifying overflow in the prior art. Compared with the previous case, firstly, a variety of characteristic data of drilling are obtained from the real-time logging data of drilling, and then the characteristic data threshold is determined based on the genetic algorithm to realize the identification of the overflow point. The parameter mutation can be identified by a variety of characteristic data at the initial moment of overflow, so as to detect the overflow, which can improve the efficiency and accuracy of drilling overflow condition identification; at the same time, the overflow condition can be predicted and warned in advance, and the overflow condition in the complex working conditions in oil drilling can be predicted in advance, which can timely and effectively reduce the hazards in oil drilling caused by the overflow condition, warn the drilling staff in advance, and buy precious time for further development of the overflow control, and solve the drilling safety problem caused by the serious delay in the discovery of overflow due to manual identification of overflow under the existing technology, avoid well control danger, and even serious accidents such as blowouts, thereby reducing unnecessary loss of life and property.

[0149] As mentioned above, in order to accurately identify the overflow condition in advance, the embodiment of the present invention proposes a method for identifying the mutation of the oil drilling condition based on wavelet mutation detection according to the characteristics of drilling data, and identifies the mutation within a short period of time before the overflow, so as to detect the overflow before the overflow occurs. Wavelet mutation detection is to "polish" the original signal at different scales, that is, to convolve with the local integrable function, so as to achieve the effect of improving the smoothness of the original signal, and to detect the extreme value or zero crossing point of the first-order or second-order derivative of the processed signal. The high-frequency signal of the original signal will be extracted through wavelet transformation, the change of the original signal will be amplified, and then a set of optimal data will be trained through genetic algorithm. The optimal data here is the optimal threshold. The threshold is the boundary value for measuring whether a set of signal data changes dramatically. If the data value after wavelet transformation is greater than the training threshold, it is considered that the change here is drastic.

[0150] The results show that this method can better detect the occurrence of overflow, give early warning of overflow, remind drilling personnel to take remedial measures in advance, and reduce the possibility of further causing blowout. In addition, this method is based on wavelet mutation detection and does not rely on the experience of monitoring personnel. It can avoid misjudgment and failure to judge overflow due to lack of experience, improper operation, lack of concentration, etc.

[0151] The purpose of the embodiment of the present invention is to identify parameter mutations at the initial moment of overflow to detect overflow, make early predictions and warnings of overflow conditions, and warn drilling personnel in advance, so as to buy precious time for controlling the further development of overflow, avoid well control dangers, and even serious accidents such as blowouts, thereby causing unnecessary loss of life and property. It can realize the early prediction of overflow conditions in complex conditions in oil drilling, timely and effectively reduce the hazards in oil drilling caused by overflow conditions, and effectively make up for the limitations of existing technologies.

[0152] The present invention also provides a device for identifying a drilling overflow condition, as described in the following embodiments. Since the principle of the device for solving the problem is similar to the method for identifying a drilling overflow condition, the implementation of the device can refer to the implementation of the method for identifying a drilling overflow condition, and the repeated parts will not be repeated.

[0153] The embodiment of the present invention also provides a drilling overflow condition identification device, which can improve the efficiency and accuracy of drilling overflow condition identification; at the same time, early prediction and warning of overflow conditions can be performed to improve drilling safety, such as Fig.11 As shown, the device comprises:

[0154] The drilling history data acquisition module 1101 is used to acquire drilling history data; the drilling history data is used to represent: various characteristic data of drilling and historical data of drilling overflow conditions corresponding to the various characteristic data;

[0155] The characteristic data threshold training module 1102 is used to perform genetic algorithm training of overflow point thresholds on the drilling history data based on the wavelet transform algorithm to obtain the thresholds of each characteristic data; the above thresholds are used to detect mutation points of the characteristic data;

[0156] The real-time acquisition module 1103 of drilling characteristic data is used to acquire various drilling characteristic data from the real-time logging data of drilling;

[0157] The wavelet transform processing module 1104 is used to perform wavelet transform processing on each type of feature data to extract high-frequency signal features of each type of feature data; the wavelet transform processing includes decomposing and recombining the feature data to eliminate noise of the feature data;

[0158] The overflow point identification module 1105 is used to identify overflow points of various characteristic data of drilling according to the threshold value of each characteristic data and the high-frequency signal characteristics of each characteristic data.

[0159] In one embodiment, the feature data threshold training module is specifically used to:

[0160] For each feature data:

[0161] Use random seeds to generate the initial population;

[0162] According to the fitness function of the genetic algorithm, the score of each individual in the initial population is calculated; according to the score of each individual in the initial population, individuals that meet the preset score conditions are selected from the initial population, and genetic operations are performed to obtain a new population; the above genetic operations include crossover operations, replication operations and mutation operations; the new population replaces the initial population;

[0163] Repeat the above steps to obtain a new population until the individual score reaches the maximum value or the number of cycles reaches the set genetic generation, and output the latest population:

[0164] According to the latest population output, the threshold corresponding to the feature data is determined.

[0165] In one embodiment, the feature data threshold training module is specifically used to:

[0166] According to the fitness function of the genetic algorithm, the score of each individual in the initial population is calculated as follows:

[0167]

[0168] Among them, f(x) is the score of each individual in the initial population; C is a constant; x~N(0,1) means that x follows a standard normal distribution; index is the starting position of the overflow in the data; length is the end position of the overflow in the data; in [index-100,index+100], x=(X-index) / 200, in [index+100,length], x=(abs(X-index)) / (length-index)+1, and X is the identified overflow point.

[0169] In one embodiment, performing wavelet transform processing on each type of feature data to extract high-frequency signal features of each type of feature data may include:

[0170] By utilizing the wavelet multi-resolution analysis characteristics, each feature data is decomposed and reorganized at multiple scales to extract the high-frequency signal characteristics of each feature data.

[0171] In one embodiment, the wavelet transform processing module is specifically used to:

[0172] For each type of feature data: perform a first-order wavelet transform on the feature data to obtain a first-order approximate signal and a first-order detail signal; the first-order detail signal is a first group of high-frequency signals;

[0173] Extract the first-order approximate signal and perform wavelet transform again to obtain the second-order approximate signal and the second-order detail signal;

[0174] The second-order detail signal is used as the high-frequency signal feature of this feature data.

[0175] In one embodiment, the multiple characteristic data of the above-mentioned drilling include: one or any combination of outlet flow characteristic data, vertical pressure characteristic data, total hydrocarbon characteristic data, pump stroke change characteristic data, drill bit depth characteristic data and inlet flow characteristic data.

[0176] In one embodiment, the method may further include: a feature data comparison process acquisition module, which is used to:

[0177] Obtaining a feature data comparison process for overflow point identification; the feature data comparison process is used to describe the process of comparing different types of feature data with high-frequency signal features and overflow point thresholds;

[0178] Overflow point identification module, specifically used for:

[0179] The overflow point is identified for various characteristic data of the drilling according to the threshold of each characteristic data, the high-frequency signal characteristics of each characteristic data, and the characteristic data comparison process for overflow point identification.

[0180] In one embodiment, the overflow point identification module is specifically used to:

[0181] When the high-frequency signal feature of the outlet flow characteristic data is greater than or equal to the threshold value of the outlet flow characteristic data, and the high-frequency signal feature of the standing pressure characteristic data is greater than or equal to the threshold value of the standing pressure characteristic data, the current drilling position is determined as the overflow point;

[0182] When the high-frequency signal characteristics of the outlet flow characteristic data are less than the threshold of the outlet flow characteristic data, the high-frequency signal characteristics of the stand pressure characteristic data are less than the threshold of the stand pressure characteristic data, the high-frequency signal characteristics of the total hydrocarbon characteristic data are less than the threshold of the total hydrocarbon characteristic data, the high-frequency signal characteristics of the pump stroke characteristic data are less than the threshold of the pump stroke characteristic data, and the high-frequency signal characteristics of the drill bit depth characteristic data are less than the threshold of the pump stroke characteristic data, the current drilling position is determined as the overflow point.

[0183] An embodiment of the present invention provides an embodiment of a computer device for implementing all or part of the contents of the above-mentioned method for identifying drilling overflow conditions. The computer device specifically includes the following contents:

[0184] Processor, memory, communication interface and bus; wherein the processor, memory and communication interface communicate with each other through the bus; the communication interface is used to realize information transmission between related devices; the computer device can be a desktop computer, a tablet computer and a mobile terminal, etc., but the present embodiment is not limited thereto. In the present embodiment, the computer device can be implemented with reference to the embodiment of the method for realizing the identification of drilling overflow working condition and the embodiment of the device for realizing the identification of drilling overflow working condition, and the contents thereof are incorporated herein, and the repeated parts are not repeated.

[0185] Fig.10 FIG. 1 is a schematic block diagram of the system structure of the computer device 1000 according to an embodiment of the present application. Fig.10 As shown, the computer device 1000 may include a central processor 1001 and a memory 1002; the memory 1002 is coupled to the central processor 1001. It is worth noting that Fig.10 is exemplary; other types of structures may also be used to supplement or replace this structure to implement telecommunication functions or other functions.

[0186] In one embodiment, the identification function of the drilling overflow condition may be integrated into the central processor 1001. The central processor 1001 may be configured to perform the following control:

[0187] Acquire historical drilling data; the historical drilling data is used to characterize: various characteristic data of drilling and historical data of drilling overflow conditions corresponding to the various characteristic data;

[0188] Based on the wavelet transform algorithm, the genetic algorithm training of the overflow point threshold is performed on the drilling history data to obtain the threshold of each characteristic data; the threshold is used to detect the mutation point of the characteristic data;

[0189] Obtain various characteristic data of drilling from real-time logging data of drilling;

[0190] Performing wavelet transform processing on each type of feature data to extract high-frequency signal features of each type of feature data; the wavelet transform processing includes decomposing and recombining the feature data to eliminate noise of the feature data;

[0191] According to the threshold value of each characteristic data and the high-frequency signal characteristics of each characteristic data, overflow points of various characteristic data of drilling are identified.

[0192] In another embodiment, the device for identifying the drilling overflow condition can be configured separately from the central processor 1001. For example, the device for identifying the drilling overflow condition can be configured as a chip connected to the central processor 1001, and the function of identifying the drilling overflow condition can be realized through the control of the central processor.

[0193] like Fig.10 As shown, the computer device 1000 may also include: a communication module 1003, an input unit 1004, an audio processor 1005, a display 1006, and a power supply 1007. It is worth noting that the computer device 1000 does not necessarily have to include Fig.10 In addition, the computer device 1000 may also include Fig.10 For components not shown, reference may be made to the prior art.

[0194] like Fig.10 As shown, the central processor 1001 is sometimes also referred to as a controller or an operation control, and may include a microprocessor or other processor devices and / or logic devices. The central processor 1001 receives inputs and controls the operations of various components of the computer device 1000 .

[0195] The memory 1002 may be, for example, a cache, a flash memory, a hard drive, a removable medium, a volatile memory, a non-volatile memory or other suitable devices, or one or more thereof. The above-mentioned information related to the failure may be stored, and a program for executing the related information may also be stored. The central processing unit 1001 may execute the program stored in the memory 1002 to implement information storage or processing, etc.

[0196] The input unit 1004 provides input to the CPU 1001. The input unit 1004 is, for example, a key or a touch input device. The power supply 1007 is used to provide power to the computer device 1000. The display 1006 is used to display display objects such as images and text. The display may be, for example, an LCD display, but is not limited thereto.

[0197] The memory 1002 may be a solid-state memory, such as a read-only memory (ROM), a random access memory (RAM), a SIM card, etc. It may also be a memory that saves information even when the power is off, can be selectively erased, and is provided with more data, examples of which are sometimes referred to as EPROMs, etc. The memory 1002 may also be some other type of device. The memory 1002 includes a buffer memory 1021 (sometimes referred to as a buffer). The memory 1002 may include an application / function storage unit 1022, which is used to store application programs and function programs or processes for executing the operation of the computer device 1000 through the central processor 1001.

[0198] The memory 1002 may also include a data storage unit 1023 for storing data, such as contacts, digital data, pictures, sounds, and / or any other data used by the computer device. The driver storage unit 1024 of the memory 1002 may include various drivers for the computer device for communication functions and / or for executing other functions of the computer device (such as messaging applications, address book applications, etc.).

[0199] The communication module 1003 is a transmitter / receiver 1003 that sends and receives signals via the antenna 1008. The communication module (transmitter / receiver) 1003 is coupled to the central processor 1001 to provide input signals and receive output signals, which may be the same as the case of a conventional mobile communication terminal.

[0200] Based on different communication technologies, multiple communication modules 1003 may be provided in the same computer device, such as a cellular network module, a Bluetooth module and / or a wireless local area network module, etc. The communication module (transmitter / receiver) 1003 is also coupled to a speaker 1009 and a microphone 1010 via an audio processor 1005 to provide an audio output via the speaker 1009 and receive an audio input from the microphone 1010, thereby realizing a common telecommunication function. The audio processor 1005 may include any suitable buffer, decoder, amplifier, etc. In addition, the audio processor 1005 is also coupled to the central processor 1001, so that recording can be performed on the local machine through the microphone 1010, and the sound stored on the local machine can be played through the speaker 1009.

[0201] An embodiment of the present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method for identifying the drilling overflow condition is implemented.

[0202] An embodiment of the present invention further provides a computer program product, which includes a computer program. When the computer program is executed by a processor, the method for identifying the drilling overflow condition is implemented.

[0203] In an embodiment of the present invention, historical drilling data is obtained; the historical drilling data is used to characterize: various characteristic data of drilling and historical data of drilling overflow conditions corresponding to the various characteristic data; based on a wavelet transform algorithm, a genetic algorithm training of overflow point threshold is performed on the historical drilling data to obtain a threshold value of each characteristic data; the threshold value is used to detect mutation points of the characteristic data; various characteristic data of drilling are obtained from real-time logging data of drilling; wavelet transform processing is performed on each characteristic data to extract high-frequency signal characteristics of each characteristic data; the wavelet transform processing includes decomposing and reorganizing the characteristic data to eliminate noise of the characteristic data; overflow points of various characteristic data of drilling are identified based on the threshold value of each characteristic data and the high-frequency signal characteristics of each characteristic data, which is different from the technical method of manually identifying overflows in the prior art. Compared with the previous case, firstly, a variety of characteristic data of drilling are obtained from the real-time logging data of drilling, and then the characteristic data threshold is determined based on the genetic algorithm to realize the identification of the overflow point. The parameter mutation can be identified by a variety of characteristic data at the initial moment of overflow, so as to detect the overflow, which can improve the efficiency and accuracy of drilling overflow condition identification; at the same time, the overflow condition can be predicted and warned in advance, and the overflow condition in the complex working conditions in oil drilling can be predicted in advance, which can timely and effectively reduce the hazards in oil drilling caused by the overflow condition, warn the drilling staff in advance, and buy precious time for further development of the overflow control, and solve the drilling safety problem caused by the serious delay in the discovery of overflow due to manual identification of overflow under the existing technology, avoid well control danger, and even serious accidents such as blowouts, thereby reducing unnecessary loss of life and property.

[0204] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0205] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0206] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0207] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0208] The specific embodiments described above further illustrate the objectives, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific embodiment of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A method for identifying a drilling overflow condition, characterized in that: include: Acquire historical drilling data; the historical drilling data is used to characterize: various characteristic data of drilling and historical data of drilling overflow conditions corresponding to the various characteristic data; Based on the wavelet transform algorithm, the genetic algorithm training of the overflow point threshold is performed on the drilling history data to obtain the threshold of each characteristic data; the threshold is used to detect the mutation point of the characteristic data; Obtain various characteristic data of drilling from real-time logging data of drilling; Performing wavelet transform processing on each type of feature data to extract high-frequency signal features of each type of feature data; the wavelet transform processing includes decomposing and recombining the feature data to eliminate noise of the feature data; According to the threshold value of each characteristic data and the high-frequency signal characteristics of each characteristic data, overflow points of various characteristic data of drilling are identified.

2. The method according to claim 1, characterized in that Based on the wavelet transform algorithm, the genetic algorithm training of the overflow point threshold is carried out on the drilling history data to obtain the threshold of each characteristic data, including: For each feature data: Use random seeds to generate the initial population; According to the fitness function of the genetic algorithm, the score of each individual in the initial population is calculated; according to the score of each individual in the initial population, individuals that meet the preset score conditions are selected from the initial population, and genetic operations are performed to obtain a new population; the genetic operations include crossover operations, replication operations and mutation operations; the new population replaces the initial population; Repeat the above steps to obtain a new population until the individual score reaches the maximum value or the number of cycles reaches the set genetic generation, and output the latest population: According to the latest population output, the threshold corresponding to the feature data is determined.

3. The method according to claim 2, characterized in that According to the fitness function of the genetic algorithm, the score of each individual in the initial population is calculated as follows: Among them, f(x) is the score of each individual in the initial population; C is a constant; x~N(0,1) means that x follows a standard normal distribution; index is the starting position of the overflow in the data; length is the end position of the overflow in the data; in [index-100,index+100], x=(X-index) / 200, in [index+100,length], x=(abs(X-index)) / (length-index)+1, and X is the identified overflow point.

4. The method according to claim 1, characterized in that Perform wavelet transform processing on each feature data to extract the high-frequency signal features of each feature data, including: By utilizing the wavelet multi-resolution analysis characteristics, each feature data is decomposed and reorganized at multiple scales to extract the high-frequency signal characteristics of each feature data.

5. The method according to claim 4, characterized in that Perform multi-scale decomposition and reorganization on each feature data to extract the high-frequency signal features of each feature data, including: For each type of feature data: perform a first-order wavelet transform on the feature data to obtain a first-order approximate signal and a first-order detail signal; the first-order detail signal is a first group of high-frequency signals; Extract the first-order approximate signal and perform wavelet transform again to obtain the second-order approximate signal and the second-order detail signal; The second-order detail signal is used as the high-frequency signal feature of this feature data.

6. The method according to claim 1, characterized in that The multiple characteristic data of the drilling include: one or any combination of outlet flow characteristic data, standing pressure characteristic data, total hydrocarbon characteristic data, pump stroke change characteristic data, drill bit depth characteristic data and inlet flow characteristic data.

7. The method according to claim 6, characterized in that Also includes: Acquire feature data comparison process for overflow point identification; The feature data comparison process is used to describe the process of comparing different types of feature data with high-frequency signal features and overflow point thresholds; Based on the threshold of each characteristic data and the high-frequency signal characteristics of each characteristic data, the overflow point is identified for various characteristic data of the drilling, including: The overflow point is identified for various characteristic data of the drilling according to the threshold of each characteristic data, the high-frequency signal characteristics of each characteristic data, and the characteristic data comparison process for overflow point identification.

8. The method according to claim 7, characterized in that Based on the threshold of each characteristic data, the high-frequency signal characteristics of each characteristic data, and the characteristic data comparison process for overflow point identification, the overflow point identification is performed on various characteristic data of drilling, including: When the high-frequency signal feature of the outlet flow characteristic data is greater than or equal to the threshold value of the outlet flow characteristic data, and the high-frequency signal feature of the standing pressure characteristic data is greater than or equal to the threshold value of the standing pressure characteristic data, the current drilling position is determined as the overflow point; When the high-frequency signal characteristics of the outlet flow characteristic data are less than the threshold of the outlet flow characteristic data, the high-frequency signal characteristics of the stand pressure characteristic data are less than the threshold of the stand pressure characteristic data, the high-frequency signal characteristics of the total hydrocarbon characteristic data are less than the threshold of the total hydrocarbon characteristic data, the high-frequency signal characteristics of the pump stroke characteristic data are less than the threshold of the pump stroke characteristic data, and the high-frequency signal characteristics of the drill bit depth characteristic data are less than the threshold of the pump stroke characteristic data, the current drilling position is determined as the overflow point.

9. A device for identifying drilling overflow conditions, characterized in that: include: A drilling history data acquisition module is used to acquire drilling history data; the drilling history data is used to characterize: various characteristic data of drilling and historical data of drilling overflow conditions corresponding to the various characteristic data; The characteristic data threshold training module is used to perform genetic algorithm training of overflow point threshold on historical drilling data based on wavelet transform algorithm to obtain the threshold of each characteristic data; the threshold is used to detect mutation points of characteristic data; A real-time acquisition module for drilling characteristic data is used to obtain various drilling characteristic data from real-time logging data of drilling; A wavelet transform processing module is used to perform wavelet transform processing on each type of feature data to extract high-frequency signal features of each type of feature data; the wavelet transform processing includes decomposing and recombining the feature data to eliminate noise of the feature data; The overflow point identification module is used to identify overflow points of various characteristic data of drilling according to the threshold value of each characteristic data and the high-frequency signal characteristics of each characteristic data.

10. The device according to claim 9, characterized in that Feature data threshold training module, specifically used for: For each feature data: Use random seeds to generate the initial population; According to the fitness function of the genetic algorithm, the score of each individual in the initial population is calculated; according to the score of each individual in the initial population, individuals that meet the preset score conditions are selected from the initial population, and genetic operations are performed to obtain a new population; the genetic operations include crossover operations, replication operations and mutation operations; the new population replaces the initial population; Repeat the above steps to obtain a new population until the individual score reaches the maximum value or the number of cycles reaches the set genetic generation, and output the latest population: According to the latest population output, the threshold corresponding to the feature data is determined.

11. The device according to claim 10, characterized in that Feature data threshold training module, specifically used for: According to the fitness function of the genetic algorithm, the score of each individual in the initial population is calculated as follows: Among them, f(x) is the score of each individual in the initial population; C is a constant; x~N(0,1) means that x follows a standard normal distribution; index is the starting position of the overflow in the data; length is the end position of the overflow in the data; in [index-100,index+100], x=(X-index) / 200, in [index+100,length], x=(abs(X-index)) / (length-index)+1, and X is the identified overflow point.

12. The device according to claim 9, characterized in that Perform wavelet transform processing on each feature data to extract the high-frequency signal features of each feature data, including: By utilizing the wavelet multi-resolution analysis characteristics, each feature data is decomposed and reorganized at multiple scales to extract the high-frequency signal characteristics of each feature data.

13. The device according to claim 12, characterized in that Wavelet transform processing module, specifically used for: For each type of feature data: perform a first-order wavelet transform on the feature data to obtain a first-order approximate signal and a first-order detail signal; the first-order detail signal is a first group of high-frequency signals; Extract the first-order approximate signal and perform wavelet transform again to obtain the second-order approximate signal and the second-order detail signal; The second-order detail signal is used as the high-frequency signal feature of this feature data.

14. The device according to claim 9, characterized in that The multiple characteristic data of the drilling include: one or any combination of outlet flow characteristic data, standing pressure characteristic data, total hydrocarbon characteristic data, pump stroke change characteristic data, drill bit depth characteristic data and inlet flow characteristic data.

15. The device according to claim 14, characterized in that Also includes: Features Data comparison process acquisition module, used for: Acquire a feature data comparison process for overflow point identification; the feature data comparison process is used to describe the process of comparing different types of feature data with high-frequency signal features and overflow point thresholds; Overflow point identification module, specifically used for: The overflow point is identified for various characteristic data of the drilling according to the threshold of each characteristic data, the high-frequency signal characteristics of each characteristic data, and the characteristic data comparison process for overflow point identification.

16. The device according to claim 15, characterized in that Overflow point identification module, specifically used for: When the high-frequency signal feature of the outlet flow characteristic data is greater than or equal to the threshold value of the outlet flow characteristic data, and the high-frequency signal feature of the standing pressure characteristic data is greater than or equal to the threshold value of the standing pressure characteristic data, the current drilling position is determined as the overflow point; When the high-frequency signal characteristics of the outlet flow characteristic data are less than the threshold of the outlet flow characteristic data, the high-frequency signal characteristics of the stand pressure characteristic data are less than the threshold of the stand pressure characteristic data, the high-frequency signal characteristics of the total hydrocarbon characteristic data are less than the threshold of the total hydrocarbon characteristic data, the high-frequency signal characteristics of the pump stroke characteristic data are less than the threshold of the pump stroke characteristic data, and the high-frequency signal characteristics of the drill bit depth characteristic data are less than the threshold of the pump stroke characteristic data, the current drilling position is determined as the overflow point.

17. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the method according to any one of claims 1 to 8 is implemented.

18. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 8 is implemented.

19. A computer program product, characterized in that The computer program product comprises a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 8 is implemented.

Images