Intelligent monitoring method of oil well system operation based on digital twin

Abstract

The present invention relates to the field of information retrieval technology, and specifically to an intelligent monitoring method for oil well system operation based on digital twins, including: obtaining oil well operation data of at least two dimensions of each monitoring point in the oil well; determining the similarity of the change trends of any two oil well operation data; determining the fluctuation correlation degree of any two oil well operation data, and combining the similarity of the change trends to obtain the change synchronization degree of any two oil well operation data; determining the importance of various oil well operation data based on the correlation between the change synchronization degrees of various oil well operation data and other various oil well operation data. The importance of various oil well operation data can be determined based on the importance of various oil well operation data, and then the oil well operation data with high importance can be focused on, thereby reducing the risk of losing important data and improving data processing reliability.

Description

Technical Field

[0001] The present invention relates to the field of information retrieval technology, and in particular to an intelligent monitoring method for oil well system operation based on digital twins. Background Art

[0002] With the development of digital technology, digital twin technology, by constructing multidimensional dynamic simulation models of physical objects to accurately monitor and predict the operating status of oil well systems, provides real-time decision support for intelligent oilfield system operations and management. This technology is implemented as follows: the oilfield system integrates multi-source data from the well system (including real-time data from various sensors in the well system and historical operation records), stores and compresses this data, and then uploads it to a backend center. The backend center then constructs a virtual model of the well system based on digital twin technology. This virtual model interacts with the well system in real time, continuously synchronizing changes in the well system's status. Based on this dynamic mapping relationship, digital twin technology supports real-time monitoring, trend prediction, and optimized decision-making for the well system.

[0003] Because the real-time operational data of oil well systems is large and complex, various sensors continuously collect and upload multi-dimensional parameter data during oil well operation. However, existing technologies simply upload all dimensional data directly to a backend center, or simply compress and process the data before uploading it to the backend center. They fail to identify and prioritize the most important data based on the correlations between data across different dimensions. This can result in the loss of important data, impacting the reliability of subsequent data processing based on digital twin technology. Summary of the Invention

[0004] In order to solve the technical problem that the existing processing of oil well system data may cause the loss of important data, thereby affecting the reliability of data processing, the purpose of the present invention is to provide an intelligent monitoring method for oil well system operation based on digital twins. The technical solution adopted is as follows:

[0005] The present invention provides an intelligent monitoring method for oil well system operation based on digital twins, comprising:

[0006] Obtaining oil well operation data of at least two dimensions for each monitoring point in the oil well;

[0007] Determine the similarity of the changing trends of any two oil well operating data;

[0008] Determine the degree of correlation between fluctuations of any two oil well operation data, and combine the degree of similarity of the change trends to obtain the degree of synchronization of changes in the any two oil well operation data;

[0009] The importance of various oil well operation data is determined based on the correlation between the change synchronization degree of various oil well operation data and other various oil well operation data.

[0010] In an exemplary embodiment, after obtaining the degree of synchronization of changes in any two oil well operation data, the method further includes: correcting the degree of synchronization of changes with a correction coefficient, wherein the correction coefficient is obtained from the time interval between fluctuations in any two oil well operation data.

[0011] In an exemplary embodiment, the process of obtaining the correction coefficient includes:

[0012] Determine the time when fluctuations of various oil well operation data occur, thereby obtaining a sequence of fluctuation time;

[0013] Based on the time interval between the fluctuation generation time instants at the same position in the fluctuation generation time sequence of any two oil well operation data, the time difference coefficients of each fluctuation generation time instant of any two oil well operation data are obtained;

[0014] The average value and range of the time difference coefficient generated by the fluctuation are obtained to obtain the correction coefficient, and the correction coefficient is inversely proportional to the average value and the range.

[0015] In an exemplary embodiment, the process of obtaining the fluctuation generation time includes: if the change range of the oil well operation data at two adjacent times is greater than a preset change range, then taking the latter of the two adjacent times as the fluctuation generation time.

[0016] In an exemplary embodiment, the process of obtaining the degree of similarity of the change trend includes:

[0017] Determine the overall stability of data changes of various oil well operation data;

[0018] Based on the difference between the overall stability of the data changes of any two oil well operation data and the data correlation between any two oil well operation data, the similarity of the change trends of any two oil well operation data is obtained.

[0019] In an exemplary embodiment, the process of obtaining the overall stability of data changes includes:

[0020] Obtaining a data difference between the oil well operation data at two adjacent moments in the oil well operation data, and obtaining a difference between the two adjacent data differences, to obtain a data fluctuation outlier parameter for three adjacent moments;

[0021] The data fluctuation characteristics for the three adjacent moments are obtained based on the data fluctuation outlier parameters of the three adjacent moments and the data difference of the oil well operation data at the first and last two moments of the three adjacent moments.

[0022] By integrating the data fluctuation characteristics of all three adjacent moments in the oil well operation data, the overall stability of the data changes of the oil well operation data is obtained.

[0023] In an exemplary embodiment, the process of obtaining the degree of fluctuation correlation includes:

[0024] The data fluctuation outlier parameters of the oil well operation data at three adjacent moments are integrated to obtain the overall data fluctuation parameters of the oil well operation data;

[0025] The difference characteristics of the overall fluctuation parameters of any two oil well operation data are determined and negatively correlated to obtain the degree of fluctuation correlation of the any two oil well operation data.

[0026] In an exemplary embodiment, after obtaining the degree of synchronization of changes in any two oil well operation data, the method further includes:

[0027] Comparing the degree of synchronization of various oil well operation data with other various oil well operation data with a preset change synchronization degree threshold;

[0028] A change synchronization degree that is greater than or equal to the preset change synchronization degree threshold is retained as the target change synchronization degree.

[0029] In an exemplary embodiment, the process of obtaining the importance includes:

[0030] The target change synchronization degree of the candidate oil well operation data and various reference oil well operation data are integrated to obtain a first impact index; the candidate oil well operation data is any type of oil well operation data, and the reference oil well operation data is other various oil well operation data corresponding to the target change synchronization degree of the candidate oil well operation data;

[0031] The second impact index is obtained by fusing the synchronization degree of the changes of the operating data of each two reference oil wells;

[0032] The first influencing index and the second influencing index are weightedly summed to obtain the importance of the candidate oil well operation data.

[0033] In an exemplary embodiment, after determining the importance of various oil well operation data, the method further includes:

[0034] Determine the relationship between the candidate oil well operating data and a first condition and a second condition, wherein the first condition is that the importance is greater than a preset importance threshold, and the second condition is that the overall stability of the data change is less than a preset overall stability threshold;

[0035] If the candidate oil well operation data satisfies both the first condition and the second condition, the candidate oil well operation data and its corresponding various reference oil well operation data are transmitted via at least two data transmission paths;

[0036] If the candidate oil well operating data only meets the first condition, the candidate oil well operating data is transmitted via at least two data transmission paths.

[0037] The present invention has the following beneficial effects: by using data information on two aspects, namely the similarity of the change trends of any two oil well operation data and the correlation of the fluctuations, the degree of synchronization of the changes of any two oil well operation data can be determined. The degree of synchronization of the changes characterizes the synchronization of the changes of one type of oil well operation data with the changes of the other type of oil well operation data. Thus, the degree of synchronization of the changes of each type of oil well operation data with other types of oil well operation data can be determined, and the correlation existing therein can be characterized. Finally, the importance of various types of oil well operation data can be determined based on the importance, and then the oil well operation data with high importance can be focused on, thereby reducing the risk of losing important data and improving the reliability of data processing. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] Figure 1 This is a flow chart of an intelligent monitoring method for oil well system operation based on digital twins provided by one embodiment of the present invention;

[0039] Figure 2 This is a flow chart for obtaining the degree of similarity of change trends provided by one embodiment of the present invention;

[0040] Figure 3 This is a flow chart for obtaining the overall stability of data changes provided by one embodiment of the present invention;

[0041] Figure 4 is a flow chart for obtaining the degree of fluctuation correlation provided by one embodiment of the present invention;

[0042] Figure 5 is a flow chart for obtaining a correction coefficient provided by one embodiment of the present invention;

[0043] Figure 6 This is a flowchart of obtaining the importance level provided by one embodiment of the present invention. DETAILED DESCRIPTION

[0044] To further illustrate the technical means and effects employed by the present invention to achieve its intended objectives, the following detailed description of the specific embodiments, structures, features, and effects of the present invention is provided in conjunction with the accompanying drawings and preferred embodiments. In the following description, references to "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. Furthermore, specific features, structures, or characteristics of one or more embodiments may be combined in any suitable manner.

[0045] Unless otherwise defined, all technical and scientific terms used herein have the same meanings as commonly understood by those skilled in the art to which this invention pertains. The data and information collected in this application were obtained with full consent and authorization.

[0046] This embodiment provides an intelligent monitoring method for oil well system operation based on digital twins, which is applicable to oil well systems and is used to monitor the operation of oil well systems.

[0047] In an oil well system, several monitoring points are deployed within the well. The number and specific locations of these monitoring points are determined by the implementer based on practical circumstances. Due to the complex environment within an oil well and the influence of factors such as well depth and atmospheric influences, operational data such as temperature, pressure, and hazardous gas concentrations vary significantly at different depths within the well. To ensure that the measured data accurately and comprehensively reflects the actual well conditions, in one exemplary embodiment, monitoring points are deployed at different depths within the well. Preferably, a monitoring point is deployed at equal intervals of depth, achieving equidistant placement of the monitoring points.

[0048] At any monitoring point, at least two sensors are deployed, each detecting a type of data within the oil well. The type and quantity of sensors are determined by the implementer based on the actual conditions of the oil well. In one exemplary embodiment, the sensors include: temperature sensors, pressure sensors, hydrogen sulfide concentration sensors, methane concentration sensors, and carbon dioxide concentration sensors. Each sensor corresponds to a dimension of oil well operating data. For example, a temperature sensor corresponds to temperature data at a corresponding depth within the oil well.

[0049] The sampling frequency of each sensor is set based on actual needs, for example, once per second. Furthermore, this embodiment establishes a monitoring period, which serves as the duration for monitoring the operation of the oil well system. The length of the monitoring period is set based on actual needs, for example, one day. Based on the sampling frequency, the monitoring period includes multiple sampling moments (referred to as moments). Therefore, the oil well operation data for each dimension at each monitoring point is essentially a time-sequential sequence of oil well operation data, including oil well operation data at multiple moments. Using one day as a monitoring cycle, real-time monitoring of the oil well system's operating status is achieved.

[0050] like Figure 1 As shown, the present embodiment provides an intelligent monitoring method for oil well system operation based on digital twins, including the following steps:

[0051] Step S1: obtaining oil well operation data of at least two dimensions at each monitoring point in the oil well;

[0052] Step S2: determining the similarity between the change trends of any two oil well operation data;

[0053] Step S3: determining the degree of correlation between fluctuations of any two oil well operation data, and combining the degree of similarity of the change trends to obtain the degree of synchronization of the change of any two oil well operation data;

[0054] Step S4: Determine the importance of various oil well operation data based on the correlation between the various oil well operation data and the degree of synchronization of changes in other various oil well operation data.

[0055] Each step is described in detail below with reference to the accompanying drawings.

[0056] Step S1: Obtaining oil well operation data of at least two dimensions for each monitoring point in the oil well.

[0057] Based on at least two sensors installed at each monitoring point, oil well operation data detected by various sensors is obtained. The oil well operation data detected by various sensors at each monitoring point are determined as various oil well operation data, thereby obtaining multiple oil well operation data of the oil well system. If the type and number of sensors at each monitoring point are set to be the same,

[0058] It should be understood that different types of oil well operation data may have different dimensions, such as temperature, pressure, and gas concentration. In order to facilitate subsequent data processing, various oil well operation data need to be normalized to eliminate dimensional limitations. In an exemplary embodiment, a maximum-minimum normalization method is adopted. Specifically, for any type of oil well operation data, the maximum and minimum values ​​are obtained, and then the maximum-minimum normalization method is adopted to normalize the data at each moment in the oil well operation data. As an example: for the temperature data of a certain monitoring point, the maximum and minimum values ​​in the temperature data are obtained, and then the maximum-minimum normalization method is adopted to normalize the temperature values ​​at each moment in the temperature data to obtain dimensionless time series data. All the various oil well operation data in subsequent processing are normalized oil well operation data.

[0059] Step S2: Determine the similarity between the change trends of any two oil well operation data.

[0060] For any two oil well operation data, the more similar the change trends of the two are, the stronger the correlation between them is. Therefore, the similarity of the change trends of any two oil well operation data is obtained. In an exemplary embodiment, Figure 2 As shown, a specific process of obtaining the similarity of the change trend is given as follows:

[0061] Step S2-1: Determine the overall stability of data changes of various oil well operation data.

[0062] For any type of oil well operation data, the overall stability of the data change of the oil well operation data is obtained. The overall stability of the data change represents the stability of the oil well operation data during the change process. The higher the overall stability of the data change, the more stable the change of the oil well operation data. In an exemplary embodiment, Figure 3 As shown, a specific process for obtaining the overall stability of data changes is given below:

[0063] Step S2-1-1: obtaining the data difference of the oil well operation data at two adjacent moments in the oil well operation data, and obtaining the difference between the two adjacent data differences to obtain the data fluctuation outlier parameters for three adjacent moments.

[0064] The data difference between the oil well operation data at two adjacent moments in the oil well operation data is obtained. The numerical difference is specifically the absolute value of the difference between the numerical values. The data differences between the oil well operation data at each two adjacent moments are arranged in time sequence. Then, the difference between the two adjacent data differences is obtained. The difference is specifically the absolute value of the difference between the two adjacent data differences. The obtained result is used as the data fluctuation outlier parameter for three adjacent moments. In an exemplary embodiment, the calculation method is given as follows:

[0065] ;

[0066] in, It represents the difference between the data at the i-th moment and the i+1-th moment in the oil well operation data, which is equal to , represents the value of the i-th moment in the oil well operation data, Represents the value at the i+1th moment in the oil well operation data; It represents the difference between the data at the i+1th moment and the i+2th moment in the oil well operation data, which is equal to , Represents the value at the i+2th moment in the oil well operation data; Represents the outlier parameter of data fluctuation from the i-th moment to the i+2-th moment.

[0067] According to the above process, the data fluctuation outlier parameter of each of the three adjacent moments in the oil well operation data is obtained. The larger the data fluctuation outlier parameter of the three adjacent moments, the more abnormal the data fluctuation of the three adjacent moments is, and the more obvious the data fluctuation characteristics are.

[0068] Step S2-1-2: The data fluctuation characteristics for the three adjacent moments are obtained from the data fluctuation outlier parameters at the three adjacent moments and the data difference of the oil well operation data at the first and last two moments among the three adjacent moments.

[0069] The data difference between the first and last two moments of the oil well operation data is obtained, and the data fluctuation of the three adjacent moments is characterized by the data difference between the first and last two moments. The greater the data difference between the first and last two moments, the more obvious the data fluctuation characteristics of the three adjacent moments. Accordingly, based on the data fluctuation outlier parameter of the three adjacent moments and the data difference between the first and last two moments of the oil well operation data, the data fluctuation characteristics for the three adjacent moments are obtained. In an exemplary embodiment, a specific quantification method is provided as follows:

[0070] ;

[0071] in, Represents the data fluctuation characteristics from the i-th moment to the i+2-th moment, It represents the difference between the data at the i-th moment and the i+2-th moment in the oil well operation data (specifically, the absolute value of the difference between the two), that is, the difference between the initial and final data in three consecutive moments.

[0072] Characterizes the dramatic change of the oil well operation data from the i-th moment to the i+2-th moment, and adds Used to avoid data accumulation and affect stable analysis results.

[0073] According to the above process, the data fluctuation characteristics of each of the oil well operation data at three adjacent moments are obtained.

[0074] Step S2-1-3: Fusing the data fluctuation characteristics of all three adjacent moments in the oil well operation data to obtain the overall stability of the data changes of the oil well operation data.

[0075] The average value of the data fluctuation characteristics of all three adjacent moments in the oil well operation data is calculated. This average value represents the overall data fluctuation characteristics of the oil well operation data. The larger the average value, the worse the overall stability of the data changes of the oil well operation data. Therefore, there is a negative correlation between the average value and the overall stability of the data changes of the oil well operation data. The average value is then normalized for the negative correlation, and the result obtained is the overall stability of the data changes of the oil well operation data. In an exemplary embodiment, a specific quantification method is provided as follows:

[0076] ;

[0077] in, represents the overall stability of the data changes of the oil well operation data, I represents the number of moments in the oil well operation data, Represents an exponential function with the natural constant e as its base.

[0078] According to the above process, the overall stability of data changes of various oil well operation data is obtained.

[0079] Step S2-2: Based on the difference in overall stability of data changes between any two oil well operation data and the data correlation between any two oil well operation data, the similarity of the change trends of any two oil well operation data is obtained.

[0080] Determine the difference between the overall stability of data changes of any two oil well operation data, specifically the absolute value of the difference between the overall stability of data changes of any two oil well operation data. The larger the difference, the more different the overall stability of data changes of the two oil well operation data, the more dissimilar the overall stability of data changes of the two oil well operation data, and the more dissimilar the change trends of the two oil well operation data.

[0081] The data correlation between any two oil well operation data sets is obtained. Since various oil well operation data sets are essentially oil well operation data sequences, the correlation between any two oil well operation data sequences is obtained as the data correlation between the two oil well operation data sets. In one exemplary embodiment, the DTW (Dynamic Time Warping) distance between the two oil well operation data sequences is obtained, and then the DTW distance is negatively normalized to obtain the data correlation between the two oil well operation data sets. The greater the data correlation, the more similar the changing trends of the two oil well operation data sets are.

[0082] By integrating the difference in overall stability of data changes between any two oil well operation data sets and the degree of data correlation between any two oil well operation data sets, the degree of similarity in the change trends of any two oil well operation data sets is determined. In one exemplary embodiment, the jth oil well operation data set and the j+1th oil well operation data set are used to represent any two oil well operation data sets. A specific quantitative method for quantifying the degree of similarity in the change trends of the jth oil well operation data set and the j+1th oil well operation data set is as follows:

[0083] ;

[0084] in, Indicates the similarity between the change trends of the j-th oil well operation data and the j+1-th oil well operation data, Indicates the overall stability of the data changes of the j-th oil well operation data, Indicates the overall stability of the data changes of the j+1th oil well operation data, represents the oil well operation data sequence of the jth oil well operation data, represents the oil well operation data sequence of the j+1th oil well operation data, express and DTW distance.

[0085] According to the above process, the similarity degree of the change trend of any two oil well operation data is obtained. The higher the similarity degree of the change trend, the more correlation there is between the any two oil well operation data.

[0086] Step S3: Determine the degree of correlation between fluctuations of any two oil well operation data, and combine the degree of similarity of the change trends to obtain the degree of synchronization of the change of any two oil well operation data.

[0087] For any two sets of oil well operating data, the degree of synchronization of changes in one set of oil well operating data indicates how synchronously the changes in one set of oil well operating data follow those in the other. The higher the degree of synchronization, the more synchronized the changes in the two sets of oil well operating data are, and the more correlated they are. Specifically, the degree of similarity in the changing trends of any two sets of oil well operating data reflects the degree of synchronization of the changing trends of the two sets of oil well operating data.

[0088] Then, the fluctuation correlation degree of any two oil well operation data is obtained. The fluctuation correlation degree represents the correlation degree between the fluctuation conditions of any two oil well operation data. In an exemplary embodiment, Figure 4 As shown, a specific process of obtaining the degree of fluctuation correlation is given as follows:

[0089] Step S3-1: Fusing the data fluctuation outlier parameters at three adjacent moments in the oil well operation data to obtain the overall data fluctuation parameter of the oil well operation data.

[0090] For the sake of convenience, any oil well operation data is defined as candidate oil well operation data. In step S2-1, the data fluctuation outlier parameters for three adjacent moments in the candidate oil well operation data are obtained, for example, the data fluctuation outlier parameters for the time from the i-th moment to the i+2-th moment are obtained. The data fluctuation outlier parameters for three adjacent moments in the candidate oil well operation data are integrated. Specifically, the average value of all the data fluctuation outlier parameters for three adjacent moments in the candidate oil well operation data is calculated as the overall data fluctuation parameter of the candidate oil well operation data. The calculation formula is as follows:

[0091] ;

[0092] in, It is the overall fluctuation parameter of the candidate oil well operation data.

[0093] Step S3-2: Determine the difference characteristics of the overall fluctuation parameters of any two oil well operation data and make a negative correlation to obtain the fluctuation correlation degree of any two oil well operation data.

[0094] For the jth and j+1th oil well operating data, the difference in overall data fluctuation parameters between the jth and j+1th oil well operating data is obtained, specifically the absolute value of the difference. Then, the average of the overall data fluctuation parameters of the jth and j+1th oil well operating data is obtained as the overall level of the overall data fluctuation parameters of the jth and j+1th oil well operating data.

[0095] The ratio of the difference in the overall fluctuation parameters of the j-th oil well operation data and the j+1-th oil well operation data to the average value of the overall fluctuation parameters of the j-th oil well operation data and the j+1-th oil well operation data is calculated as the difference feature between the two, which represents the proportion of the difference between the two in the overall level. The larger the difference feature, the greater the proportion of the difference between the two in the overall level, and the less correlated the fluctuations between the two are.

[0096] Then, a negative correlation is performed between the difference characteristics of the overall fluctuation parameters of the j-th oil well operation data and the j+1-th oil well operation data, and the result obtained is the fluctuation correlation degree between the j-th oil well operation data and the j+1-th oil well operation data.

[0097] In an exemplary embodiment, a specific quantitative method for the degree of correlation between the fluctuations of the j-th oil well operating data and the j+1-th oil well operating data is given as follows:

[0098] ;

[0099] in, Indicates the degree of correlation between the operating data of the jth oil well and the operating data of the j+1th oil well. is the overall fluctuation parameter of the j-th oil well operation data, is the overall fluctuation parameter of the j+1th oil well operation data, for and The average value of .

[0100] Represents the difference characteristics between the j-th oil well operation data and the j+1-th oil well operation data.

[0101] The higher the correlation between the fluctuations of the j-th oil well operation data and the j+1-th oil well operation data, the more synchronized their fluctuation changes are. The higher the synchronization, the more correlated they are.

[0102] According to the fluctuation correlation degree between the jth oil well operation data and the j+1th oil well operation data, and the similarity degree of the change trend between the jth oil well operation data and the j+1th oil well operation data, the change synchronization degree between the jth oil well operation data and the j+1th oil well operation data is obtained. In an exemplary embodiment, the fluctuation correlation degree between the jth oil well operation data and the j+1th oil well operation data is calculated. The similarity between the change trend of the j-th oil well operation data and the j+1-th oil well operation data The product of the jth oil well operation data and the j+1th oil well operation data is the degree of synchronization of the changes. .

[0103] According to the above process, all types of oil well operation data are traversed to obtain the degree of synchronization of changes between any two types of oil well operation data. The greater the degree of synchronization, the higher the data change similarity between any two types of oil well operation data.

[0104] It should be understood that in oil well system monitoring, the correlation between well operating data in different dimensions can vary significantly. For strongly correlated data (such as oil pressure, temperature, and flow), a dynamic coupling system is formed through thermodynamics and fluid dynamics mechanisms, and its changes have a clear causal chain and temporal synchronization. For example, when oil pressure increases (e.g., due to water injection), it pushes crude oil into the wellbore (increased flow), at which point friction between the fluid and the pipe wall generates heat, causing the temperature to rise. On the other hand, for weakly correlated data (such as oil content), it is only associated with other well operating data through long-term statistical trends or indirect mechanisms. Short-term fluctuations generally do not trigger linkage between multidimensional well operating data. To further obtain a more accurate degree of synchronization between any two well operating data sets, and to better distinguish between strongly and weakly correlated well operating data sets, after obtaining the degree of synchronization between any two well operating data sets, the method further includes a correction process for the degree of synchronization, using a correction coefficient as a weight for the degree of synchronization.

[0105] The correction coefficient is obtained from the time interval between any two oil well operation data fluctuations. According to the time interval between any two oil well operation data fluctuations, the correction coefficient of any two oil well operation data is obtained to correct the degree of synchronization of the change of any two oil well operation data. In an exemplary embodiment, Figure 5 As shown, a process for obtaining the correction coefficient is given as follows:

[0106] Step S3-3: Determine the time when fluctuations of various oil well operation data occur, thereby obtaining a sequence of time when fluctuations occur.

[0107] Obtain the time at which fluctuations in the candidate oil well operating data occur. The time at which fluctuations occur in the candidate oil well operating data within the monitoring period. In an exemplary embodiment, for any two adjacent moments, the amplitude of change in the oil well operating data between the two adjacent moments is obtained, specifically, the absolute value of the difference between the oil well operating data between the two adjacent moments. A preset amplitude is also set. The preset amplitude is used to determine whether the actual amplitude of change is large. The preset amplitude ranges from 0 to 1, and the specific value is set based on actual needs, such as 0.3. Furthermore, the preset amplitudes corresponding to different types of oil well operating data can be equal or different, and can be set by the implementer based on actual needs.

[0108] The variation range of the oil well operating data at two adjacent moments is compared with a preset variation range. If the variation range of the oil well operating data at two adjacent moments is greater than the preset variation range, indicating a certain fluctuation occurred between the two adjacent moments, the later of the two adjacent moments is used as the fluctuation generation time. Each moment in the candidate oil well operating data is traversed to obtain the fluctuation generation time of the candidate oil well operating data. Each fluctuation generation time is then arranged in chronological order to obtain a sequence of fluctuation generation time of the candidate oil well operating data. This method generates a sequence of fluctuation generation time of various oil well operating data.

[0109] Step S3-4: Based on the time interval between the fluctuation generation moments at the same position in the fluctuation generation moment sequence of any two oil well operation data, obtain the fluctuation generation time difference coefficients of any two oil well operation data.

[0110] For any two types of oil well operation data, the number of fluctuation generation moments contained in the fluctuation generation moment sequences of any two oil well operation data may be different. Then, only the fluctuation generation moments with the same serial number in the two fluctuation generation moment sequences are considered. For example: if the number of fluctuation generation moments in the two fluctuation generation moment sequences is 12 and 15 respectively, only the first 12 fluctuation generation moments in the two fluctuation generation moment sequences are considered, so as to ensure the acquisition of subsequent fluctuation generation time difference coefficients.

[0111] Obtain the time interval between the fluctuation generation moments at the same position (i.e., the same sequence number) in the fluctuation generation moment series of any two oil well operation data, for example: the time interval between the first fluctuation generation moment in the two fluctuation generation moment series, the time interval between the second fluctuation generation moment in the two fluctuation generation moment series, and so on, until the time interval between the last fluctuation generation moment in the two fluctuation generation moment series.

[0112] Based on the time interval, a fluctuation generation time difference coefficient is obtained. For any time interval, the time interval is normalized to obtain the fluctuation generation time difference coefficient, thereby obtaining the fluctuation generation time difference coefficient corresponding to the two types of oil well operation data. In an exemplary embodiment, the normalization method is to obtain the maximum and minimum values ​​in each time interval corresponding to the fluctuation generation time sequence of the two types of oil well operation data, and then use the maximum and minimum value normalization method to normalize each time interval to obtain the fluctuation generation time difference coefficient corresponding to each time interval.

[0113] Step S3-5: Obtain the average value and range of the time difference coefficient generated by the fluctuation to obtain the correction coefficient.

[0114] The average value of the fluctuation-generating time difference coefficients of the two types of oil well operating data is obtained to represent the overall situation of the fluctuation-generating time difference coefficients. The smaller the average value, the smaller the fluctuation time interval of the two types of oil well operating data, the more correlated the fluctuations between the two types of oil well operating data are, and the larger the correction coefficient should be. The correction coefficient is inversely proportional to the average value. Furthermore, the range of the fluctuation-generating time difference coefficients of the two types of oil well operating data is obtained to represent the range of the fluctuation-generating time difference coefficients. The smaller the range, the smaller the range of the fluctuation-generating time difference coefficients of the two types of oil well operating data, the more correlated the fluctuations between the two types of oil well operating data are, and the larger the correction coefficient should be. The correction coefficient is inversely proportional to the range. It should be understood that after the above-mentioned maximum and minimum value normalization, the range is 1.

[0115] Based on the average and range of the time difference coefficients generated by the fluctuations of the two oil well operation data, correction coefficients for the two oil well operation data are obtained. In an exemplary embodiment, a specific quantitative method for the correction coefficient is given as follows:

[0116] ;

[0117] in, represents the correction coefficient of the jth oil well operation data and the j+1th oil well operation data, The reason why the above formula does not involve the range is because the range is 1 in this implementation method.

[0118] The correction coefficients of the jth oil well operation data and the j+1th oil well operation data are The degree of synchronization with the operating data of the jth oil well and the operating data of the j+1th oil well The result of multiplication is the degree of synchronization between the jth oil well operation data and the j+1th oil well operation data after correction. .

[0119] By using the above process, the modified change synchronization degree of any two oil well operation data is obtained, and the subsequent change synchronization degree used is the modified change synchronization degree. It should be understood that as another embodiment, the change synchronization degree may not be modified.

[0120] A higher degree of corrected change synchronization indicates a higher correlation between the two well operating data. A lower degree of corrected change synchronization indicates a lower correlation between the two well operating data. To improve the reliability of subsequent data processing, these lower degrees of corrected change synchronization can be deleted, and only the higher degrees of corrected change synchronization are used in subsequent data processing.

[0121] Accordingly, after obtaining the degree of change synchronization between any two oil well operating data sets, specifically after obtaining the revised degree of change synchronization between any two oil well operating data sets, the candidate oil well operating data set is used as the analysis object. The revised degree of change synchronization between the candidate oil well operating data set and various other oil well operating data sets is obtained. A change synchronization threshold is preset. This preset change synchronization threshold is used to determine whether the revised degree of change synchronization is high. The value of this preset change synchronization threshold ranges from 0 to 1, and its specific value is set based on actual needs, such as 0.4. The revised degree of change synchronization between the candidate oil well operating data set and various other oil well operating data sets is compared with the preset change synchronization threshold. Revised degrees of change synchronization greater than or equal to the preset change synchronization threshold are obtained. The various other oil well operating data sets corresponding to these revised degrees of change synchronization have a strong correlation with the candidate oil well operating data set. The revised degrees of change synchronization greater than or equal to the preset change synchronization threshold are then defined as target degrees of change synchronization. This results in a target degree of change synchronization between the candidate oil well operating data set, and the various other oil well operating data sets corresponding to the target degree of change synchronization between the candidate oil well operating data set are defined as reference oil well operating data sets for the candidate well operating data set.

[0122] Step S4: Determine the importance of various oil well operation data based on the correlation between the various oil well operation data and the degree of synchronization of changes in other various oil well operation data.

[0123] The importance of the candidate oil well operation data is determined based on the correlation between the modified synchronization degree of the candidate oil well operation data and its respective reference oil well operation data. The stronger the correlation, the more important the candidate oil well operation data is and the higher its importance. In an exemplary embodiment, Figure 6 As shown, a process of obtaining the importance is given as follows:

[0124] Step S4-1: The target change synchronization degree of the candidate oil well operation data and the various reference oil well operation data is integrated to obtain a first impact index.

[0125] The target change synchronization degree of the candidate oil well operation data and the various reference oil well operation data of the candidate oil well operation data is integrated. Specifically, the average value is calculated to obtain the first impact index of the candidate oil well operation data. The calculation formula is as follows:

[0126] ;

[0127] in, represents the first influencing indicator of the j-th oil well operation data, represents the target change synchronization degree between the j-th oil well operating data and the k-th reference oil well operating data of the j-th oil well operating data, and K represents the number of reference oil well operating data of the j-th oil well operating data.

[0128] By adopting the above method, first influencing indicators of various oil well operation data are obtained, and the first influencing indicators represent the influence relationship between the oil well operation data and its reference oil well operation data.

[0129] Step S4-2: The synchronization degree of changes in the operating data of each two reference oil wells is integrated to obtain a second impact index.

[0130] The corrected synchronization degree of any two reference oil well operation data of the candidate oil well operation data is obtained, thereby fusing the corrected synchronization degree of every two reference oil well operation data of the candidate oil well operation data. Specifically, the average value of the corrected synchronization degree of all any two reference oil well operation data of the candidate oil well operation data is calculated, and the result obtained is the second influencing indicator of the candidate oil well operation data.

[0131] By adopting the above method, second influencing indicators of various oil well operation data are obtained, and the second influencing indicators represent the influencing relationship between the reference oil well operation data, that is, the influencing relationship between the associated oil well operation data.

[0132] Step S4-3: Perform weighted summation on the first influencing index and the second influencing index to obtain the importance of the candidate oil well operation data.

[0133] The first and second influencing indicators of the candidate oil well operation data are weighted and summed to obtain the importance of the candidate oil well operation data. Taking the j-th oil well operation data as an example, the calculation formula for the importance of the j-th oil well operation data is as follows:

[0134] ;

[0135] in, Indicates the importance of the j-th oil well operation data, Represents the second influencing indicator of the j-th oil well operation data. Represents the weight coefficient, defined as the influence coefficient, which is used to adjust the proportional relationship between the first influence index and the second influence index. The value is set according to actual needs, such as 0.6.

[0136] According to the above process, the importance of various oil well operation data is obtained. The importance represents the degree of impact that the oil well operation data can have on the oil well system as a whole. The greater the importance, the more important the oil well operation data is. When the oil well operation data of this type changes, the change of other oil well operation data in the oil well system will be more serious.

[0137] In subsequent applications, relevant measures can be taken based on the importance of various oil well operation data. For example, the more important the oil well operation data, the more attention it requires to avoid the loss of important data. In an exemplary embodiment, after determining the importance of various oil well operation data, the following specific application can be performed: two conditions are preset: a first condition and a second condition. The first condition is that the importance is greater than a preset importance threshold, and the second condition is that the overall stability of the data changes is less than a preset overall stability threshold.

[0138] Among them, the preset importance threshold is used to determine whether the importance of various oil well operation data is high, so as to facilitate the adoption of corresponding measures according to the level of importance. The specific value of the preset importance threshold is set according to actual needs, such as 0.5; the preset data change overall stability threshold is used to determine whether the overall stability of data changes of various oil well operation data is high, so as to facilitate the adoption of corresponding measures according to the level of overall stability of data changes. The specific value of the preset data change overall stability threshold is set according to actual needs, such as 0.5.

[0139] Taking the candidate oil well operation data as an example, the relationship between the candidate oil well operation data and the first condition and the second condition is determined. If the candidate oil well operation data satisfies both the first condition and the second condition, that is, the importance of the candidate oil well operation data is greater than the preset importance threshold, and the overall stability of the data change of the candidate oil well operation data is less than the preset data change overall stability threshold, it means that the importance of the candidate oil well operation data is high, and the overall stability of its data change is low, that is, the data change fluctuation is strong, then it is determined that there are certain anomalies in the candidate oil well operation data. At the same time, the various reference oil well operation data of the candidate oil well operation data also have a certain impact on the candidate oil well operation data. It is necessary to pay special attention to the candidate oil well operation data and its corresponding various reference oil well operation data. In order to avoid data loss, the candidate oil well operation data and its corresponding various reference oil well operation data are transmitted to the background center via at least two data transmission paths. Among them, at least two data transmission paths represent at least two data transmission methods, such as: wired transmission methods such as industrial Ethernet protocol and optical fiber communication, and wireless transmission methods such as 5G network. In addition, other oil well operation data except the candidate oil well operation data and the corresponding various reference oil well operation data can be transmitted after data compression.

[0140] If candidate well operating data only meets the first condition—that is, its importance is greater than a preset importance threshold, and its overall stability is greater than or equal to a preset overall stability threshold—it indicates that the candidate well operating data is highly important and its data changes are relatively stable. Therefore, only that candidate well operating data will be prioritized. To prevent data loss, the candidate well operating data will be transmitted to the backend center via at least two data transmission paths. Furthermore, other well operating data besides the candidate well operating data can be compressed for transmission.

[0141] The above judgment is performed on the importance of various oil well operation data, so as to focus on the oil well operation data with higher importance.

[0142] It should be noted that the order in which the embodiments of the present invention are described above is for illustrative purposes only and does not necessarily represent the superiority or inferiority of the embodiments. The processes depicted in the accompanying drawings do not necessarily require the specific order or sequential order shown to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0143] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on the differences from other embodiments.

Claims

1. An intelligent monitoring method for oil well system operation based on digital twins, characterized by: include: Obtaining oil well operation data of at least two dimensions for each monitoring point in the oil well; Determine the similarity of the changing trends of any two oil well operating data; The process of obtaining the degree of similarity of the change trend includes: determining the overall stability of the data change of various oil well operation data; obtaining the degree of similarity of the change trend of any two oil well operation data based on the difference between the overall stability of the data change of any two oil well operation data and the degree of data correlation between any two oil well operation data; Determine the degree of fluctuation correlation of any two oil well operation data, and combine the degree of similarity of the change trends to obtain the degree of change synchronization of the two oil well operation data; the process of obtaining the degree of fluctuation correlation includes: fusing the data fluctuation outlier parameters of the oil well operation data at three adjacent moments to obtain the overall data fluctuation parameters of the oil well operation data; determine the difference characteristics of the overall data fluctuation parameters of any two oil well operation data and make a negative correlation to obtain the degree of fluctuation correlation of the two oil well operation data; The importance of various oil well operation data is determined based on the correlation between the change synchronization degrees of various oil well operation data and other various oil well operation data; wherein, after obtaining the change synchronization degrees of any two oil well operation data, the method also includes: comparing the change synchronization degrees of various oil well operation data and other various oil well operation data with a preset change synchronization degree threshold; retaining the change synchronization degree greater than or equal to the preset change synchronization degree threshold as the target change synchronization degree; the process of obtaining the importance includes: fusing the target change synchronization degrees of the candidate oil well operation data with various reference oil well operation data to obtain a first influencing indicator; the candidate oil well operation data is any one type of oil well operation data, and the reference oil well operation data is other various oil well operation data corresponding to the target change synchronization degree of the candidate oil well operation data; fusing the change synchronization degrees of every two reference oil well operation data to obtain a second influencing indicator; performing weighted summation on the first influencing indicator and the second influencing indicator to obtain the importance of the candidate oil well operation data.

2. The method for intelligently monitoring oil well system operation based on digital twins according to claim 1 is characterized in that: After obtaining the degree of synchronization of changes in any two oil well operation data, the method further includes: correcting the degree of synchronization of changes with a correction coefficient, wherein the correction coefficient is obtained from the time interval between fluctuations in any two oil well operation data.

3. The method for intelligent monitoring of oil well system operation based on digital twins according to claim 2 is characterized in that: The process of obtaining the correction coefficient includes: Determine the time when fluctuations of various oil well operation data occur, thereby obtaining a sequence of fluctuation time; Based on the time interval between the fluctuation generation time instants at the same position in the fluctuation generation time sequence of any two oil well operation data, the time difference coefficients of each fluctuation generation time instant of any two oil well operation data are obtained; The average value and range of the time difference coefficient generated by the fluctuation are obtained to obtain the correction coefficient, and the correction coefficient is inversely proportional to the average value and the range.

4. The method for intelligently monitoring oil well system operation based on digital twins according to claim 3 is characterized in that: The process of obtaining the fluctuation generation time includes: if the change range of the oil well operation data at two adjacent times is greater than a preset change range, then taking the latter of the two adjacent times as the fluctuation generation time.

5. The method for intelligently monitoring oil well system operation based on digital twins according to claim 1 is characterized in that: The process of obtaining the overall stability of the data changes includes: Obtaining a data difference between the oil well operation data at two adjacent moments in the oil well operation data, and obtaining a difference between the two adjacent data differences to obtain a data fluctuation outlier parameter for three adjacent moments; The data fluctuation characteristics for the three adjacent moments are obtained based on the data fluctuation outlier parameters of the three adjacent moments and the data difference of the oil well operation data at the first and last two moments of the three adjacent moments. By integrating the data fluctuation characteristics of all three adjacent moments in the oil well operation data, the overall stability of the data changes of the oil well operation data is obtained.

6. The method for intelligently monitoring oil well system operation based on digital twins according to claim 1 is characterized in that: After determining the importance of various oil well operation data, the method further includes: Determine the relationship between the candidate oil well operating data and a first condition and a second condition, wherein the first condition is that the importance is greater than a preset importance threshold, and the second condition is that the overall stability of the data change is less than a preset overall stability threshold; If the candidate oil well operation data satisfies both the first condition and the second condition, the candidate oil well operation data and its corresponding various reference oil well operation data are transmitted via at least two data transmission paths; If the candidate oil well operating data only meets the first condition, the candidate oil well operating data is transmitted via at least two data transmission paths.

Images