Real-time drilling data cleaning method and device

Abstract

The invention discloses a real-time drilling data cleaning method and device, and the method comprises the steps: obtaining drilling data at each sampling moment, and obtaining a drilling data prediction value at the current sampling moment based on an ARIMA algorithm according to the drilling data at each sampling moment before the current sampling moment; according to the drilling data at each sampling moment before the current sampling moment, obtaining a variable quantity boundary value of a drilling data predicted value at the current sampling moment; determining a confidence interval of the drilling data at the current sampling moment according to the drilling data predicted value and the variable quantity boundary value at the current sampling moment; performing comparative analysis on the drilling data at the current sampling moment and the confidence interval; and according to a comparative analysis result, cleaning the drilling data at the current sampling moment to obtain the cleaned drilling data at the current sampling moment. The method can quickly and effectively detect the abnormal value and improve the drilling data quality.

Description

Technical Field

[0001] The invention relates to the field of drilling data processing, and in particular to a real-time drilling data cleaning method and device. 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 the oil drilling industry develops towards digitalization and intelligence, the amount of data related to oil drilling is increasing. At the same time, with the development of intelligent technology, many tasks such as complex early warning monitoring or drilling speed optimization are increasingly dependent on the reliability of drilling data. However, the current drilling data is affected by sensor factors or external factors, and there are often some missing or abnormal noise data. For some real-time early warning systems or optimization systems, the impact of these noise data will have an adverse effect on the system's judgment. How to manage the real-time collected logging data, improve the quality of drilling data, and then lay the foundation for the full use of downstream algorithm capabilities is a topic worth studying in the field of oil drilling.

[0004] Drilling data is multi-dimensional time series data collected by many different types of sensors. The cleaning and anomaly detection of drilling data are essential before the data enters the downstream algorithm. However, there are still few studies on algorithms for real-time drilling data cleaning, which cannot meet the requirements of current real-time algorithms. Summary of the invention

[0005] An embodiment of the present invention provides a real-time drilling data cleaning method for achieving real-time cleaning of drilling data. The method comprises:

[0006] Acquire drilling data at each sampling time, wherein the drilling data at the current sampling time is the drilling data before cleaning, and the drilling data at each sampling time before the current sampling time includes the drilling data before and after cleaning;

[0007] Based on the ARIMA algorithm, the predicted value of the drilling data at the current sampling time is obtained according to the drilling data at each sampling time before the current sampling time;

[0008] According to the drilling data at each sampling time before the current sampling time, the change amount of the drilling data at each sampling time before the current sampling time is obtained;

[0009] According to the change amount of the drilling data at each sampling time before the current sampling time, the change amount boundary value of the drilling data prediction value at the current sampling time is obtained;

[0010] Determine the confidence interval of the drilling data at the current sampling time according to the predicted value of the drilling data at the current sampling time and the boundary value of the variation;

[0011] Compare and analyze the drilling data at the current sampling moment with the confidence interval;

[0012] According to the comparative analysis results, the drilling data at the current sampling moment is cleaned to obtain the cleaned drilling data at the current sampling moment.

[0013] The embodiment of the present invention further provides a real-time drilling data cleaning device for achieving real-time cleaning of drilling data, the device comprising:

[0014] A data acquisition module is used to acquire drilling data at each sampling time, wherein the drilling data at the current sampling time is the drilling data before cleaning, and the drilling data at each sampling time before the current sampling time includes the drilling data before and after cleaning;

[0015] A prediction module is used to obtain a predicted value of drilling data at the current sampling moment based on the drilling data at each sampling moment before the current sampling moment based on the ARIMA algorithm;

[0016] A variation calculation module, used to obtain the variation of the drilling data at each sampling time before the current sampling time according to the drilling data at each sampling time before the current sampling time;

[0017] A boundary value determination module, used to obtain a boundary value of a change in the predicted value of the drilling data at the current sampling moment according to a change in the drilling data at each sampling moment before the current sampling moment;

[0018] A confidence interval determination module is used to determine the confidence interval of the drilling data at the current sampling moment according to the predicted value of the drilling data at the current sampling moment and the boundary value of the variation;

[0019] A comparison module is used to compare and analyze the drilling data at the current sampling moment with the confidence interval;

[0020] The data cleaning module is used to clean the drilling data at the current sampling moment according to the comparative analysis results to obtain the cleaned drilling data at the current sampling moment.

[0021] An embodiment of the present invention further provides a computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the above-mentioned real-time drilling data cleaning method when executing the computer program.

[0022] 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 real-time drilling data cleaning method is implemented.

[0023] 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 real-time drilling data cleaning method is implemented.

[0024] In an embodiment of the present invention, drilling data at each sampling moment is obtained, wherein the drilling data at the current sampling moment is the drilling data before cleaning, and the drilling data at each sampling moment before the current sampling moment includes the drilling data before and after cleaning; based on the ARIMA algorithm, a predicted value of the drilling data at the current sampling moment is obtained according to the drilling data at each sampling moment before the current sampling moment; a change amount of the drilling data at each sampling moment before the current sampling moment is obtained according to the drilling data at each sampling moment before the current sampling moment; a change amount boundary value of the predicted value of the drilling data at the current sampling moment is obtained according to the change amount of the drilling data at each sampling moment before the current sampling moment; a confidence interval of the drilling data at the current sampling moment is determined according to the predicted value of the drilling data at the current sampling moment and the change amount boundary value; the drilling data at the current sampling moment is compared and analyzed with the confidence interval; according to the comparison and analysis result, the drilling data at the current sampling moment is cleaned to obtain the cleaned drilling data at the current sampling moment. In this way, based on the drilling data at each sampling moment before the current sampling moment, the predicted value of the drilling data at the current sampling moment is obtained. Combined with the upper and lower boundary constraints of the change amount, the obtained confidence interval is compared with the drilling data at the current sampling moment to realize the real-time drilling data cleaning method, which can quickly and effectively detect outliers and improve the quality of drilling data. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] 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:

[0026] Figure 1 A flow chart of a real-time drilling data cleaning method provided in an embodiment of the present invention;

[0027] Figure 2 This is an example diagram of the predicted value of drilling data at the current sampling moment provided in an embodiment of the present invention;

[0028] Figure 3 An example diagram of variation distribution and variation boundary value selection provided in an embodiment of the present invention;

[0029] Figure 4 This is a diagram showing the effect of drilling data cleaning provided in an embodiment of the present invention;

[0030] Figure 5 A schematic diagram of a velocity identification device for interlayer multiple waves provided in an embodiment of the present invention;

[0031] Figure 6 It is a structural block diagram of an electronic device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0032] 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.

[0033] 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.

[0034] 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.

[0035] The embodiment of the present invention provides a real-time drilling data cleaning method, such as Figure 1 As shown, including:

[0036] Step 101: Acquire drilling data at each sampling time, wherein the drilling data at the current sampling time is the drilling data before cleaning, and the drilling data at each sampling time before the current sampling time includes the drilling data before and after cleaning;

[0037] Step 102: Based on the ARIMA algorithm, the drilling data prediction value at the current sampling time is obtained according to the drilling data at each sampling time before the current sampling time;

[0038] Step 103: obtaining the change amount of the drilling data at each sampling time before the current sampling time according to the drilling data at each sampling time before the current sampling time;

[0039] Step 104: obtaining a change boundary value of the drilling data prediction value at the current sampling moment according to the change amount of the drilling data at each sampling moment before the current sampling moment;

[0040] Step 105: determining the confidence interval of the drilling data at the current sampling time according to the predicted value of the drilling data at the current sampling time and the boundary value of the variation;

[0041] Step 106: Compare and analyze the drilling data at the current sampling time with the confidence interval;

[0042] Step 107: According to the comparative analysis result, the drilling data at the current sampling time is cleaned to obtain the cleaned drilling data at the current sampling time.

[0043] The real-time drilling data cleaning method provided by the embodiment of the present invention is mainly divided into two stages: the prediction stage and the discrimination stage. In the prediction stage, the predicted value and the boundary value of the change amount of the drilling data are given, and then the confidence interval of the predicted value of the drilling data is determined; in the discrimination stage, it is to compare whether the drilling data at the current sampling time is within the confidence interval, and then decide whether to clean the drilling data at the current sampling time. Through the two-stage method, abnormal values ​​can be detected quickly and effectively, and a better real-time drilling data cleaning effect can be achieved.

[0044] In one embodiment, it further includes:

[0045] When the drilling data at the current sampling moment is a missing value, the predicted value of the drilling data at the current sampling moment is assigned to the missing value and determined as the drilling data after cleaning at the current sampling moment.

[0046] In one embodiment, based on the ARIMA algorithm, the drilling data prediction value at the current sampling time is obtained according to the drilling data at each sampling time before the current sampling time, including:

[0047] The predicted value of drilling data at the current sampling time is obtained according to the following formula:

[0048]

[0049] in, represents the predicted value of drilling data at the current sampling time, μ represents the offset value, i represents the sequence number of each item traversed under the order p, q, α i is the autoregression coefficient, x t-i represents the drilling data after cleaning at each sampling time before the current sampling time, ε t-i is a random interference term, βi is the moving average coefficient, p,q is the order of the ARIMA algorithm, p represents the order of the autoregressive model, and q represents the order of the moving average algorithm.

[0050] In specific implementation, the drilling data at the historical sampling time can be set as Then the data at time t and before is represented by X t .

[0051] in Represents the drilling data after cleaning at time t, which is an M-dimensional vector. represents the uncleaned drilling data at time t, represents the prediction obtained from the drilling data at the historical sampling time, where are all M-dimensional vectors.

[0052] For each dimension of data, refer to the historical data X at time t-1 and before t-1 , the predicted value is given based on the ARIMA (Autoregressive Integrated Moving Average model) algorithm.

[0053] In one embodiment, the change amount boundary value of the drilling data prediction value at the current sampling moment is obtained according to the change amount of the drilling data at each sampling moment before the current sampling moment, including:

[0054] The variation of the drilling data at each sampling time before the current sampling time is fitted to obtain the variation boundary value of the drilling data prediction value at the current sampling time.

[0055] In the specific implementation, the distribution of the drilling data change at the historical sampling time is fitted, and the set of drilling data change at the historical sampling time is defined as ΔX t ={Δx t-W+1 ,Δx t-W+2 ,…,Δx t}, where W is the window length of the drilling data variation at the historical sampling time, Δx t is the set of changes at time t. Definition K is the number of data required to calculate the change at time t. The calculation method is as follows:

[0056]

[0057] in, is the change in the kth data corresponding to the data at time t, k is the sequence number of the comparison data required to calculate the change at time t, x tis the data at time t, x t-k It is the data at time tk.

[0058] The set of drilling data changes at the historical sampling moments is fitted to obtain the mean and standard deviation of the set.

[0059]

[0060]

[0061] Among them, μ t is the mean of the set of drilling data changes at time t, σ t is the standard deviation of the set of drilling data changes at time t. W is the window length of the drilling data changes at the historical sampling time used, K is the number of data required to calculate the changes at time t, It is the change in the data at time t corresponding to the k-th data.

[0062] Predict the change boundary of the next moment. The change boundary consists of two parts: the lower boundary and upper boundary The method of obtaining it is as follows:

[0063]

[0064]

[0065] in, is the lower bound of the predicted change at the current moment, is the upper limit of the predicted change at the current moment, μ t-1 is the mean of the set of drilling data changes at the previous moment, σ t-1 is the standard deviation of the set of drilling data changes at the previous moment, and n is the standard deviation multiple used.

[0066] In one embodiment, the confidence interval of the drilling data at the current sampling time is determined according to the predicted value of the drilling data at the current sampling time and the boundary value of the variation, including:

[0067] The confidence interval of the drilling data at the current sampling time is determined by the following formula:

[0068]

[0069] in, Represents the predicted value of drilling data at the current sampling moment, Represents the lower boundary of the change in the predicted value of the drilling data at the current sampling time, Represents the upper limit of the change in the predicted value of the drilling data at the current sampling moment.

[0070] In one embodiment, the drilling data at the current sampling time is cleaned according to the comparative analysis result to obtain the cleaned drilling data at the current sampling time, including:

[0071] If the drilling data at the current sampling time is within the confidence interval, the drilling data at the current sampling time is determined as the drilling data after cleaning at the current sampling time;

[0072] If the drilling data at the current sampling time is not within the confidence interval, the boundary value of the confidence interval is determined as the drilling data after cleaning at the current sampling time.

[0073] In specific implementation, it is checked whether the drilling data at the current sampling moment is a missing value. If it is a missing value, the predicted value of the drilling data at the current sampling moment is assigned to the missing value to determine it as the drilling data after cleaning at the current sampling moment.

[0074] If the drilling data at the current sampling time is not a missing value, check whether the drilling data at the current sampling time is within the confidence interval. If not, assign the upper or lower boundary value of the confidence interval according to whether the drilling data at the current sampling time exceeds the upper boundary or exceeds the lower boundary.

[0075] As an example, take the total pool volume in drilling data cleaning.

[0076] When making predictions based on the ARIMA algorithm, the autoregressive model order p is preferably 4, and the moving average algorithm order q is preferably 3. Figure 2 As shown, 201 is the original data value, and 202 is the predicted value based on the ARIMA algorithm.

[0077] The set of drilling data changes ΔX at the historical sampling time t-1 When predicting the boundary value (upper and lower bounds) of the drilling data change at time t, the window size W is preferably 128, and the number of data K required to calculate the drilling data change at time t is preferably 2. The historical schematic diagram is as follows: Figure 3 As shown. The set of drilling data changes at the historical sampling time ΔX t-1 The distribution of is 301, and the normal distribution fitted based on the mean and standard deviation of the 301 distribution is 302. It can be seen that the set distribution of the drilling data change at the actual historical sampling time is below the corresponding Gaussian distribution curve, so the standard deviation number parameter n used to determine the change boundary value is preferably 4. By calculation, the change boundary value They are 303 and 304 respectively.

[0078] Real-time cleaning effect Figure 4As shown, 401 is the original data, 402 is the abnormal point detected in the real-time monitoring, and 403 is the data after real-time cleaning. It can be seen that the real-time drilling data cleaning method k provided in the embodiment of the present application can effectively clean the abnormal data.

[0079] The present invention also provides a real-time drilling data cleaning device, as described in the following embodiments. Since the principle of the device to solve the problem is similar to that of the real-time drilling data cleaning method, the implementation of the device can refer to the implementation of the method, and the repeated parts will not be repeated.

[0080] Figure 5 FIG. 1 is a schematic diagram of a velocity identification device for interlayer multiple waves provided in an embodiment of the present invention. Figure 5 As shown, the device comprises:

[0081] The data acquisition module 501 is used to acquire the drilling data at each sampling time, wherein the drilling data at the current sampling time is the drilling data before cleaning, and the drilling data at each sampling time before the current sampling time includes the drilling data before and after cleaning;

[0082] Prediction module 502, used to obtain the predicted value of drilling data at the current sampling time based on the drilling data at each sampling time before the current sampling time based on the ARIMA algorithm;

[0083] The variation calculation module 503 is used to obtain the variation of the drilling data at each sampling time before the current sampling time according to the drilling data at each sampling time before the current sampling time;

[0084] The boundary value determination module 504 is used to obtain the boundary value of the change amount of the drilling data prediction value at the current sampling moment according to the change amount of the drilling data at each sampling moment before the current sampling moment;

[0085] The confidence interval determination module 505 is used to determine the confidence interval of the drilling data at the current sampling time according to the predicted value of the drilling data at the current sampling time and the boundary value of the variation;

[0086] A comparison module 506 is used to compare and analyze the drilling data at the current sampling moment with the confidence interval;

[0087] The data cleaning module 507 is used to clean the drilling data at the current sampling moment according to the comparison and analysis results to obtain the cleaned drilling data at the current sampling moment.

[0088] In one embodiment, a verification module is also included, which is specifically used to:

[0089] When the drilling data at the current sampling moment is a missing value, the predicted value of the drilling data at the current sampling moment is assigned to the missing value and determined as the drilling data after cleaning at the current sampling moment.

[0090] In one embodiment, the prediction module 502 is specifically used for:

[0091] The predicted value of drilling data at the current sampling time is obtained according to the following formula:

[0092]

[0093] in, represents the predicted value of drilling data at the current sampling time, μ represents the offset value, i represents the sequence number of each item traversed under the order p, q, α i is the autoregression coefficient, x t-i represents the drilling data after cleaning at each sampling time before the current sampling time, ε t-i is a random interference term, β i is the moving average coefficient, p,q is the order of the ARIMA algorithm, p represents the order of the autoregressive model, and q represents the order of the moving average algorithm.

[0094] In one embodiment, the boundary value determination module 504 is specifically used to:

[0095] The variation of the drilling data at each sampling time before the current sampling time is fitted to obtain the variation boundary value of the drilling data prediction value at the current sampling time.

[0096] In one embodiment, the confidence interval determination module 505 is specifically used to:

[0097] The confidence interval of the drilling data at the current sampling time is determined by the following formula:

[0098]

[0099] in, Represents the predicted value of drilling data at the current sampling moment, Represents the lower boundary of the change in the predicted value of the drilling data at the current sampling time, Represents the upper boundary of the change in the predicted value of the drilling data at the current sampling moment.

[0100] In one embodiment, the data cleaning module 507 is specifically used for:

[0101] If the drilling data at the current sampling time is within the confidence interval, the drilling data at the current sampling time is determined as the drilling data after cleaning at the current sampling time;

[0102] If the drilling data at the current sampling time is not within the confidence interval, the boundary value of the confidence interval is determined as the drilling data after cleaning at the current sampling time.

[0103] Based on the above invention concept, Figure 6 As shown, the present invention also proposes a computer device 600, including a memory 610, a processor 620, and a computer program 630 stored in the memory 610 and executable on the processor 620, wherein the processor 620 implements the aforementioned real-time drilling data cleaning method when executing the computer program 930.

[0104] 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 real-time drilling data cleaning method is implemented.

[0105] 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 real-time drilling data cleaning method is implemented.

[0106] In summary, in an embodiment of the present invention, drilling data at each sampling moment is obtained, wherein the drilling data at the current sampling moment is the drilling data before cleaning, and the drilling data at each sampling moment before the current sampling moment includes the drilling data before and after cleaning; based on the ARIMA algorithm, a predicted value of the drilling data at the current sampling moment is obtained according to the drilling data at each sampling moment before the current sampling moment; a change amount of the drilling data at each sampling moment before the current sampling moment is obtained according to the drilling data at each sampling moment before the current sampling moment; a change amount boundary value of the predicted value of the drilling data at the current sampling moment is obtained according to the change amount of the drilling data at each sampling moment before the current sampling moment; a confidence interval of the drilling data at the current sampling moment is determined according to the predicted value of the drilling data at the current sampling moment and the change amount boundary value; the drilling data at the current sampling moment is compared and analyzed with the confidence interval; according to the comparison and analysis results, the drilling data at the current sampling moment is cleaned to obtain the cleaned drilling data at the current sampling moment. In this way, based on the drilling data at each sampling moment before the current sampling moment, the predicted value of the drilling data at the current sampling moment is obtained. Combined with the upper and lower boundary constraints of the change amount, the obtained confidence interval is compared with the drilling data at the current sampling moment to realize the real-time drilling data cleaning method, which can quickly and effectively detect outliers and improve the quality of drilling data.

[0107] 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.

[0108] 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 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0109] 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.

[0110] 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.

[0111] 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 real-time drilling data cleaning method, characterized in that: include: Acquire drilling data at each sampling time, wherein the drilling data at the current sampling time is the drilling data before cleaning, and the drilling data at each sampling time before the current sampling time includes the drilling data before and after cleaning; Based on the ARIMA algorithm, the predicted value of the drilling data at the current sampling time is obtained according to the drilling data at each sampling time before the current sampling time; According to the drilling data at each sampling time before the current sampling time, the change amount of the drilling data at each sampling time before the current sampling time is obtained; According to the change amount of the drilling data at each sampling time before the current sampling time, the change amount boundary value of the drilling data prediction value at the current sampling time is obtained; Determine the confidence interval of the drilling data at the current sampling time according to the predicted value of the drilling data at the current sampling time and the boundary value of the variation; Compare and analyze the drilling data at the current sampling moment with the confidence interval; According to the comparative analysis results, the drilling data at the current sampling moment is cleaned to obtain the cleaned drilling data at the current sampling moment.

2. The method according to claim 1, characterized in that Also includes: When the drilling data at the current sampling moment is a missing value, the predicted value of the drilling data at the current sampling moment is assigned to the missing value and determined as the drilling data after cleaning at the current sampling moment.

3. The method according to claim 1, characterized in that Based on the ARIMA algorithm, the drilling data prediction value at the current sampling time is obtained according to the drilling data at each sampling time before the current sampling time, including: The predicted value of drilling data at the current sampling time is obtained according to the following formula: in, represents the predicted value of drilling data at the current sampling time, μ represents the offset value, i represents the sequence number of each item traversed under the order p, q, α i is the autoregression coefficient, x t-i represents the drilling data after cleaning at each sampling time before the current sampling time, ε t-i is a random interference term, β i is the moving average coefficient, p,q is the order of the ARIMA algorithm, p represents the order of the autoregressive model, and q represents the order of the moving average algorithm.

4. The method according to claim 1, characterized in that According to the change amount of the drilling data at each sampling time before the current sampling time, the change amount boundary value of the drilling data prediction value at the current sampling time is obtained, including: The variation of the drilling data at each sampling time before the current sampling time is fitted to obtain the variation boundary value of the drilling data prediction value at the current sampling time.

5. The method according to claim 1, characterized in that According to the predicted value of the drilling data at the current sampling time and the boundary value of the variation, the confidence interval of the drilling data at the current sampling time is determined, including: The confidence interval of the drilling data at the current sampling time is determined by the following formula: in, Represents the predicted value of drilling data at the current sampling moment, Represents the lower boundary of the change in the predicted value of the drilling data at the current sampling time, Represents the upper limit of the change in the predicted value of the drilling data at the current sampling moment.

6. The method according to claim 1, characterized in that According to the comparative analysis results, the drilling data at the current sampling time is cleaned to obtain the cleaned drilling data at the current sampling time, including: If the drilling data at the current sampling time is within the confidence interval, the drilling data at the current sampling time is determined as the drilling data after cleaning at the current sampling time; If the drilling data at the current sampling time is not within the confidence interval, the boundary value of the confidence interval is determined as the drilling data after cleaning at the current sampling time.

7. A real-time drilling data cleaning device, characterized in that: include: A data acquisition module is used to acquire drilling data at each sampling time, wherein the drilling data at the current sampling time is the drilling data before cleaning, and the drilling data at each sampling time before the current sampling time includes the drilling data before and after cleaning; A prediction module is used to obtain a predicted value of drilling data at the current sampling moment based on the drilling data at each sampling moment before the current sampling moment based on the ARIMA algorithm; A variation calculation module, used to obtain the variation of the drilling data at each sampling time before the current sampling time according to the drilling data at each sampling time before the current sampling time; A boundary value determination module, used to obtain a boundary value of a change in the predicted value of the drilling data at the current sampling moment according to a change in the drilling data at each sampling moment before the current sampling moment; A confidence interval determination module is used to determine the confidence interval of the drilling data at the current sampling moment according to the predicted value of the drilling data at the current sampling moment and the boundary value of the variation; A comparison module is used to compare and analyze the drilling data at the current sampling moment with the confidence interval; The data cleaning module is used to clean the drilling data at the current sampling moment according to the comparative analysis results to obtain the cleaned drilling data at the current sampling moment.

8. The device according to claim 7, characterized in that Also includes missing validation modules for: When the drilling data at the current sampling moment is a missing value, the predicted value of the drilling data at the current sampling moment is assigned to the missing value and determined as the drilling data after cleaning at the current sampling moment.

9. The device according to claim 7, characterized in that The prediction module is specifically used for: The predicted value of drilling data at the current sampling time is obtained according to the following formula: in, represents the predicted value of drilling data at the current sampling time, μ represents the offset value, i represents the sequence number of each item traversed under the order p, q, α i is the autoregression coefficient, x t-i represents the drilling data after cleaning at each sampling time before the current sampling time, ε t-i is a random interference term, β i is the moving average coefficient, p,q is the order of the ARIMA algorithm, p represents the order of the autoregressive model, and q represents the order of the moving average algorithm.

10. The device according to claim 7, characterized in that The boundary value determination module is specifically used for: The variation of the drilling data at each sampling time before the current sampling time is fitted to obtain the variation boundary value of the drilling data prediction value at the current sampling time.

11. The device according to claim 7, characterized in that The confidence interval determination module is specifically used for: The confidence interval of the drilling data at the current sampling time is determined by the following formula: in, Represents the predicted value of drilling data at the current sampling moment, Represents the lower boundary of the change in the predicted value of the drilling data at the current sampling time, Represents the upper limit of the change in the predicted value of the drilling data at the current sampling moment.

12. The device according to claim 7, characterized in that The data cleaning module is specifically used for: If the drilling data at the current sampling time is within the confidence interval, the drilling data at the current sampling time is determined as the drilling data after cleaning at the current sampling time; If the drilling data at the current sampling time is not within the confidence interval, the boundary value of the confidence interval is determined as the drilling data after cleaning at the current sampling time.

13. 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 6 is implemented.

14. 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 6 is implemented.

15. 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 6 is implemented.

Images