A method and system for managing time series data of oil and gas fields

Abstract

The present invention discloses a method and system for managing time series data of oil and gas fields. The method preprocesses time series data in the production process of the oil and gas fields and identifies its timestamp to determine the corresponding target time window, and then divides dynamic well opening data and static well closing data according to the target time window, so as to realize reliable classification of the time series data in the production process of the oil and gas fields according to the time series situation, prevent the erroneous storage of redundant data, and respectively calculate the first time series characteristic value corresponding to the dynamic well opening data and the second time series characteristic value corresponding to the static well closing data, so as to merge the dynamic well opening data and the static well closing data with similar or close time series characteristics, and at the same time construct corresponding target index information for the merged target management data, so as to facilitate users to call or query related time series data, reduce server resource consumption, and improve the query and retrieval efficiency of oil and gas field production data.

Description

Technical Field

[0001] The present invention relates to the technical field of oil and gas field production data processing, in particular to an oil and gas field intermittent time series data management method and system, and a computer-readable storage medium. Background Art

[0002] In order to improve the oil production efficiency and economic benefits of oil and gas fields and reduce the burden of using pumps, the pumping control method has been more widely used. With the continuous development of Internet technology, the monitoring system of oil and gas fields has gradually realized intelligence, which is mainly reflected in the ability to monitor and manage the time series data in the production of oil and gas fields online to improve the production monitoring efficiency of oil and gas fields; however, the current monitoring system of oil and gas fields mainly uses the usual database to store and manage the time series data of oil and gas fields. Due to the large amount of time series data in oil and gas fields and the complex types involved, this type of database is easy to store some redundant data by mistake, occupying unnecessary server resources, and currently in order to improve the oil production efficiency and economic benefits of oil and gas fields and reduce the burden of using pumps, the oil and gas field inter-opening control method is more widely used on the market, and the usual database cannot classify and store the time series data in the case of oil and gas field inter-opening well, which makes it difficult for users to easily find the required inter-opening time series data from the database, so the query retrieval efficiency is low. Summary of the invention

[0003] The present invention aims to solve one of the technical problems in the related art at least to a certain extent. To this end, the present invention proposes a method and system for managing time series data of oil and gas fields, which can reduce server resource consumption and improve query retrieval efficiency.

[0004] In a first aspect, an embodiment of the present invention provides a method for managing time series data of an oil and gas field, comprising the following steps:

[0005] Step S1, continuously acquiring initial time series data in the production process of the oil and gas field, and preprocessing the initial time series data to obtain target time series data; identifying the timestamp of the target time series data, and when it is determined that there are multiple timestamps of the target time series data, determining the production time window corresponding to each timestamp according to each timestamp and the predetermined oil and gas field's intermittent production cycle;

[0006] Step S2: for each of the production time windows, determine whether the production time window is within a preset time window in the oil and gas field production process; if so, use the production time window as a target time window; otherwise, delete the production time window;

[0007] Step S3, when the target time series data is divided into at least one group of dynamic well opening data and at least one group of static well closing data according to all the target time windows, a plurality of data attributes corresponding to each group of the dynamic well opening data are respectively obtained, and each group of the static well closing data is respectively analyzed to obtain the well opening time series operation parameters corresponding to each group of the static well closing data, wherein the target time windows corresponding to any group of the dynamic well opening data and any group of the static well closing data are different;

[0008] Step S4: for each group of the dynamic well opening data, at least one data attribute is selected from the multiple data attributes as a target data attribute, and weight assignment calculation is performed on each target data attribute based on all the target data attributes to obtain weight parameters corresponding to each target data attribute; according to the target time window corresponding to the dynamic well opening data and the weight parameters corresponding to each target data attribute, a first time series feature value corresponding to the dynamic well opening data is determined;

[0009] Step S5, for each group of the static shut-in data, determining a second time series characteristic value corresponding to the static shut-in data according to the target time window corresponding to the static shut-in data and the intermittent time series operation parameter;

[0010] Step S6, in the case of configuring a plurality of different preset time series characteristic threshold intervals, traverse all the first time series characteristic values ​​and the second time series characteristic values, and when it is determined that one of the first time series characteristic values ​​and one of the second time series characteristic values ​​are both within one of the preset time series characteristic threshold intervals, merge the dynamic well opening data corresponding to the first time series characteristic value and the static well closing data corresponding to the second time series characteristic value, so as to obtain a set of target management data;

[0011] Step S7: for each group of the target management data, determine the target storage location of the target management data according to the timestamp of the target management data and the preconfigured target storage area, store the target management data according to the target storage location, and generate target index information of the target management data according to the target storage location.

[0012] Optionally, in one embodiment of the present invention, the step in step S4, performing weight assignment calculation on each of the target data attributes based on all the target data attributes to obtain weight parameters corresponding to each of the target data attributes, includes the following steps:

[0013] Step S41: for each of the target data attributes, perform specialized assignment on the target data attribute to obtain a weight value corresponding to the target data attribute;

[0014] Step S42: weighting the weight values ​​corresponding to the target data attributes using a preset weight parameter calculation formula to obtain weight parameters corresponding to the target data attributes, wherein the weight parameter calculation formula is as follows:

[0015] ;

[0016] For the The weight parameters corresponding to the target data attributes, For the The weight value corresponding to the target data attribute, For the preset The weight operation coefficient corresponding to the target data attribute, is the total number of target data attributes, .

[0017] Optionally, in one embodiment of the present invention, the step in step S4, determining the first time series characteristic value corresponding to the dynamic well opening data according to the target time window corresponding to the dynamic well opening data and the weight parameters corresponding to each of the target data attributes, comprises the following steps:

[0018] Step S43, determining a first time upper limit value and a first time lower limit value corresponding to the target time window according to the target time window corresponding to the dynamic well opening data;

[0019] Step S44: Substitute the weight parameters corresponding to each of the target data attributes, the first time upper limit value, and the first time lower limit value into a preset first time series calculation formula to calculate a first time series characteristic value corresponding to the dynamic well opening data, wherein the first time series calculation formula is as follows:

[0020] ;

[0021] is the first time series characteristic value corresponding to the dynamic well opening data, is the first time upper limit value, is the lower limit of the first time.

[0022] Optionally, in one embodiment of the present invention, when the intermittent time series operation parameters include oil well static pressure parameters, shut-in riser pressure parameters and well killing fluid injection parameters, the steps in step S5, determining the second time series characteristic value corresponding to the static shut-in data according to the target time window corresponding to the static shut-in data and the intermittent time series operation parameters, include the following steps:

[0023] Step S51, determining a second time upper limit value and a second time lower limit value corresponding to the target time window according to the target time window corresponding to the static shut-in data;

[0024] Step S52: Substitute the second time upper limit value, the second time lower limit value, the oil well static pressure parameter, the shut-in riser pressure parameter and the well killing fluid injection parameter into a preconfigured time series feature evaluation model, and calculate the second time series feature value corresponding to the static shut-in data through the second time series calculation formula in the time series feature evaluation model.

[0025] Optionally, in one embodiment of the present invention, the second timing calculation formula is as follows:

[0026] ;

[0027] in, is the second time series characteristic value corresponding to the static shut-in data, is the second time upper limit value, is the lower limit of the second time, is the oil well static pressure parameter, is the shut-in riser pressure parameter, is the well killing fluid injection parameter, is a first preset conversion factor corresponding to the shut-in riser pressure parameter, is a second preset conversion factor corresponding to the well killing fluid injection parameter.

[0028] Optionally, in one embodiment of the present invention, the step in step S7, determining the target storage location of the target management data according to the timestamp of the target management data in combination with a preconfigured target storage area, comprises the following steps:

[0029] Step S71, dividing the pre-configured target storage area into a plurality of storage areas according to a preset time interval, and constructing corresponding storage area information for each of the storage areas;

[0030] Step S72, generating corresponding time identification information according to the timestamp of the target management data, and comparing the time identification information with each storage area information one by one;

[0031] Step S73: When the retrieved time identification information matches one of the storage area information, determine one of the storage areas as the target storage location of the target management data.

[0032] Optionally, in one embodiment of the present invention, the step in step S1, preprocessing the initial time series data to obtain target time series data, includes the following steps:

[0033] Step S11, performing abnormal data detection on the initial time series data to obtain an abnormal data detection result; deleting the abnormal data in the initial time series data according to the abnormal data detection result to obtain first time series data;

[0034] Step S12: denoise, clean and compress the first time series data in sequence to obtain target time series data.

[0035] In a second aspect, an embodiment of the present invention provides an oil and gas field time series data management system, including:

[0036] at least one processor;

[0037] at least one memory for storing at least one program;

[0038] When at least one of the programs is executed by at least one of the processors, the method for managing the intermittent time series data of an oil and gas field as described in the first aspect is implemented.

[0039] In a third aspect, an embodiment of the present invention provides a computer-readable storage medium storing a program executable by a processor, wherein the program executable by the processor is used to implement the method for managing the intermittent time series data of an oil and gas field as described in the first aspect when executed by the processor.

[0040] The present invention proposes a method and system for managing time series data of oil and gas fields, which pre-processes time series data in the production process of oil and gas fields and identifies its timestamp to determine the corresponding target time window, and then divides dynamic well opening data and static well closing data according to the target time window, so as to realize reliable classification of time series data in the production process of oil and gas fields according to the time series situation, prevent the erroneous storage of redundant data, and respectively calculate the first time series characteristic value corresponding to the dynamic well opening data and the second time series characteristic value corresponding to the static well closing data, so as to merge the dynamic well opening data and the static well closing data with similar or close time series characteristics based on the comparison results between different preset time series characteristic threshold intervals and the first time series characteristic value and the second time series characteristic value, and at the same time construct corresponding target index information for the merged target management data, so as to facilitate users to call or query related time series data; therefore, in the production process of oil and gas fields, by analyzing, managing and storing the time series data of oil and gas fields, it is possible to reduce server resource consumption and further improve the query and retrieval efficiency of oil and gas field production data. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Figure 1It is a flow chart of an oil and gas field intermittent time series data management method provided by one embodiment of the present invention;

[0042] Figure 2 yes Figure 1 A partial flow chart of the step “preprocessing the initial time series data to obtain the target time series data” in step S1 of FIG.

[0043] Figure 3 yes Figure 1 A partial flow chart of the step S4 in step "performing weight assignment calculations on each target data attribute based on all target data attributes to obtain weight parameters corresponding to each target data attribute";

[0044] Figure 4 yes Figure 1 A partial flow chart of the step S4 in step “determining the first time series characteristic value corresponding to the dynamic well opening data according to the target time window corresponding to the dynamic well opening data and the weight parameters corresponding to each target data attribute”;

[0045] Figure 5 yes Figure 1 A partial flow chart of the step S5 in step "determining the second time series characteristic value corresponding to the static shut-in data according to the target time window corresponding to the static shut-in data and the interval time series operation parameter";

[0046] Figure 6 yes Figure 1 A partial flow chart of the step S7 of “determining a target storage location of the target management data according to the timestamp of the target management data in combination with the preconfigured target storage area”;

[0047] Figure 7 It is a structural schematic diagram of an oil and gas field time series data management system provided by one embodiment of the present invention. DETAILED DESCRIPTION

[0048] like Figure 1 As shown, an embodiment of the present invention provides an intermittent time series data management method for an oil and gas field, which may include but is not limited to steps S1 to S7, wherein the time series data is data arranged in chronological order, usually representing a certain metric or event that changes over time; each data point in the time series data usually depends on one or more previous historical data points, and each data point has a timestamp to mark the time when the data was collected, ensuring that the data is arranged in chronological order.

[0049] Step S1, continuously acquiring initial time series data in the production process of the oil and gas field, and preprocessing the initial time series data to obtain target time series data; identifying the timestamp of the target time series data, and when it is determined that there are multiple timestamps of the target time series data, determining the production time window corresponding to each timestamp according to each timestamp and the predetermined intermittent production cycle of the oil and gas field, wherein the frequency or period of continuously acquiring the initial time series data can be set according to the actual application scenario, and there is no restriction here, for example, selecting 3 consecutive days, a week, half a month or a month as the duration for acquiring the initial time series data, etc., and further, within the specific duration, any suitable sampling time can be selected according to the specific scenario, for example, within 3 consecutive days, 09:00-18:00 is selected every day to sample the initial time series data, etc., and there is no restriction here;

[0050] Step S2: for each production time window, determine whether the production time window is within a preset time window in the oil and gas field production process; if so, use the production time window as a target time window; otherwise, delete the production time window;

[0051] Step S3, when the target time series data is divided into at least one group of dynamic well opening data and at least one group of static well closing data according to all target time windows, a plurality of data attributes corresponding to each group of dynamic well opening data are respectively obtained, and each group of static well closing data is respectively analyzed to obtain the time series operation parameters corresponding to each group of static well closing data, wherein the target time windows corresponding to any group of dynamic well opening data and any group of static well closing data are different, which means that the timestamps corresponding to the dynamic well opening data and the static well closing data must be different, which reflects that the two will not overlap at any time node in the time production cycle of the oil and gas field;

[0052] Step S4, for each group of dynamic well opening data, at least one data attribute is obtained from multiple data attributes as the target data attribute, and weight assignment calculation is performed on each target data attribute based on all target data attributes to obtain weight parameters corresponding to each target data attribute; according to the target time window corresponding to the dynamic well opening data and the weight parameters corresponding to each target data attribute, the first time series feature value corresponding to the dynamic well opening data is determined, wherein the specific manner of obtaining at least one data attribute as the target data attribute from multiple data attributes can be multiple, for example, when multiple data attributes can include but are not limited to timestamps, cycles, indicators, metrics, identifiers, and data, etc., a random selection manner is adopted for screening, or, when a timestamp is selected as one of the target data attributes, the remaining two data attributes are arbitrarily selected as the remaining target data attributes. Preferably, in this case, indicators and metrics are selected as the remaining target data attributes, etc., which are not limited here;

[0053] Step S5: for each set of static shut-in data, determine a second time series characteristic value corresponding to the static shut-in data according to a target time window and an interval time series operation parameter corresponding to the static shut-in data;

[0054] Step S6, in the case of configuring multiple different preset time series feature threshold intervals, traverse all first time series feature values ​​and second time series feature values, and when it is determined that one of the first time series feature values ​​and one of the second time series feature values ​​are both within one of the preset time series feature threshold intervals, merge the dynamic well opening data corresponding to the first time series feature value and the static well closing data corresponding to the second time series feature value, so as to obtain a set of target management data, wherein the specific ranges of the multiple different preset time series feature threshold intervals are not limited, and can be set exclusively according to the particularity of the actual application scenario, which is not limited here; it should be noted that as long as it is determined that one of the first time series feature values ​​and one of the second time series feature values ​​are both within one of the preset time series feature threshold intervals, a merge is performed, and so on, and multiple sets of target management data may be obtained in the end;

[0055] Step S7: for each group of target management data, determine the target storage location of the target management data according to the timestamp of the target management data and the preconfigured target storage area, store the target management data according to the target storage location, and generate target index information of the target management data according to the target storage location.

[0056] In this step, the time series data in the oil and gas field production process is preprocessed and its timestamp is identified to determine the corresponding target time window, and then the dynamic well opening data and the static well closing data are divided according to the target time window, so as to realize the reliable classification of the time series data in the oil and gas field production process according to the opening situation, prevent the erroneous storage of redundant data, and respectively calculate the first time series characteristic value corresponding to the dynamic well opening data and the second time series characteristic value corresponding to the static well closing data, so as to merge the dynamic well opening data and the static well closing data with similar or close time series characteristics based on the comparison results between different preset time series characteristic threshold intervals and the first time series characteristic value and the second time series characteristic value, and at the same time, construct the corresponding target index information for the merged target management data, so as to facilitate the user to call or query the relevant opening time series data; therefore, in the oil and gas field production process, by analyzing, managing and storing the opening time series data of the oil and gas field, the server resource consumption can be reduced, and the query and retrieval efficiency of the oil and gas field production data can be further improved.

[0057] It can be understood that, since the merged target management data is a combination of dynamic well opening data and static well shut-in data with similar or close timing characteristics, the merged target management data has a relatively integrated timing characteristic, which indicates that the corresponding dynamic well opening data and static well shut-in data at this time have good timing adaptability. Since the timestamps corresponding to the dynamic well opening data and the static well shut-in data are known, it is equivalent to providing inspiration for the inter-well opening control method of oil and gas fields, that is, it prompts that the dynamic well opening data and static well shut-in data at the timestamp corresponding to such a combination are relatively better, so as to instruct users or background control systems how to better and more effectively perform inter-well opening control of oil and gas fields.

[0058] like Figure 2 As shown, in one embodiment of the present invention, the steps in step S1, preprocessing the initial time series data to obtain the target time series data, may include but are not limited to the following steps:

[0059] Step S11, performing abnormal data detection on the initial time series data to obtain an abnormal data detection result; deleting the abnormal data in the initial time series data according to the abnormal data detection result to obtain first time series data;

[0060] Step S12: denoise, clean and compress the first time series data in sequence to obtain target time series data.

[0061] In this step, abnormal data detection is mainly performed on whether the data is missing, whether the data is associated, and whether the data has abnormal values. Accordingly, abnormal data can be but is not limited to missing data, null value data, and abnormal data. By denoising, cleaning, and compressing the first time series data, unnecessary redundant components in the first time series data can be removed to obtain target time series data with higher data accuracy. The range of data compression can be set accordingly according to the actual application scenario, and is not limited here. Noise reduction, cleaning, and compression are one of the commonly used technical means in this field. To avoid redundancy, they will not be elaborated here.

[0062] In one embodiment, in step S1, when it is determined that there are multiple timestamps of the target time series data, it means that the target time series data is sampled in different sampling intervals. For example, if multiple timestamps are located at different time nodes within 1 day, they may include but are not limited to 09:00-12:00, 14:00-18:00 and 19:00-22:00, etc.; there are multiple specific ways to determine the production time window corresponding to each timestamp according to each timestamp and the predetermined open production cycle of the oil and gas field, among which the open production cycle of the oil and gas field reflects the open control method of the oil and gas field. For example, if the intermittent production cycle is 1 day, it means that the oil and gas field produces every 1 day. The intermittent production cycle of the oil and gas field can be set accordingly according to the actual application scenario; when determining each timestamp and the intermittent production cycle, it can be but not limited to judging whether the specific timestamp overlaps with the intermittent production cycle. If there is an overlap, the overlapping part is used as the production time window corresponding to the specific timestamp, otherwise the production time window of the specific timestamp is considered to be empty. Alternatively, technical personnel in this field can select a corresponding method to determine the production time window corresponding to each timestamp according to the specific application scenario, etc., which is not limited here.

[0063] In one embodiment, the specific method of determining whether the production time window is within the preset time window in the oil and gas field production process in step S2 may be multiple, such as determining whether the production time window is completely included in the preset time window. If so, the production time window is used as a target time window, otherwise the production time window is deleted. Alternatively, determining whether the production time window is included in the corresponding preset time window, where the corresponding preset time window is not necessarily the actually configured preset time window, but may be a derived preset time window, such as determining that the production time window is 14:00-18:00 on the first day. , and the actual configured preset time window is 10:00-19:30 on the second day. It can be seen that the production time window is not within the actual configured preset time window. However, considering that the intermittent production cycle is 2 days, that is, the first day and the second day can be regarded as equivalent in the intermittent production cycle, so 10:00-19:30 on the second day can be regarded as 10:00-19:30 on the first day, that is, as a derived preset time window, then it can be determined that the production time window is included in the corresponding preset time window, then the production time window is used as a target time window, otherwise the production time window is deleted.

[0064] In one embodiment, in step S3, when the target time series data is divided into at least one group of dynamic well opening data and at least one group of static well closing data according to all target time windows, it means that the target time series data at this time can be divided into at least one group of dynamic well opening data and at least one group of static well closing data. Specifically, taking two target time windows as an example, one is 10:00-19:30 on the first day, and the other is 14:00-18:00 on the second day. If the sampling times corresponding to the target time series data are 15:00-17:30 on the first day, 15:00-17:30 on the second day, and 19:00-21:30 on the second day, and the oil and gas field has an open production cycle of 1 day, it can be determined that: when the first day is the state of the oil and gas field being opened, 15:00-17:30 on the first day is within 10:00-19:30 on the first day (one of the target time windows), then in the first day, The target time series data collected from 15:00 to 17:30 on the 1st day is a set of dynamic well opening data. Correspondingly, the 2nd day is the status of oil and gas field shutdown work. 15:00 to 17:30 on the 2nd day is within 14:00-18:00 (another target time window) on the 2nd day, and the target time series data collected from 15:00 to 17:30 on the 2nd day is a set of static well closing data. However, 19:00 to 21:30 on the 2nd day is not within any target time window. Therefore, the target time series data collected from 19:00 to 21:30 on the 2nd day is not used as a basis for division. By analogy, all dynamic well opening data and / or static well closing data that should be divided can be determined in this way; it can be understood that the type of data obtained by division is not limited, and may be separate dynamic well opening data or static well closing data, or may include both dynamic well opening data and static well closing data.

[0065] In one embodiment, the multiple data attributes corresponding to each group of dynamic well opening data in step S3 may be of multiple types, which need to be determined according to the specific application scenario. Generally speaking, they may include but are not limited to timestamps, cycles, indicators, metrics, identifiers, and data, etc. Different data attributes reflect different characteristics of dynamic well opening data, among which metrics represent the attribution of data, indicators represent specified measurement parameters collected, such as drilling fluid parameters of oil wells, etc., cycles represent the collection cycle of dynamic well opening data, identifiers represent the recognition degree of dynamic well opening data, and data represent the data content of dynamic well opening data. It should be noted that different groups of dynamic well opening data may have different metrics and indicators.

[0066] In one embodiment, the specific implementation method of the step in step S3, respectively parsing each group of static shut-in data to obtain the intermittent time series operation parameters corresponding to each group of static shut-in data, can be multiple, and is not limited here. For example, when a group of static shut-in data includes the liquid level change data of the oil well within the timestamp corresponding to the group of static shut-in data, that is, the liquid level data of the oil well at the beginning stage and the liquid level data of the oil well at the end stage, then the difference between the two liquid level data is obtained, and the well killing fluid injection parameter corresponding to the static shut-in data (that is, a kind of intermittent time series operation parameter) can be obtained, or when a group of static shut-in data includes the pressure change data of the oil well within the timestamp corresponding to the group of static shut-in data, that is, the pressure position parameter of the oil well at the beginning stage and the pressure position parameter of the oil well at the end stage, then the difference between the two is obtained, and the oil well static pressure parameter corresponding to the static shut-in data (that is, another kind of intermittent time series operation parameter) can be obtained. By analogy, the corresponding intermittent time series operation parameter can be determined in the manner shown above, which is not repeated here.

[0067] like Figure 3 As shown, in one embodiment of the present invention, the steps in step S4, based on all target data attributes, weight assignment calculation is performed on each target data attribute to obtain weight parameters corresponding to each target data attribute, which may include but is not limited to the following steps:

[0068] Step S41: for each target data attribute, perform specialized assignment on the target data attribute to obtain a weight value corresponding to the target data attribute;

[0069] Step S42: weight values ​​corresponding to each target data attribute are calculated by using a preset weight parameter calculation formula to obtain weight parameters corresponding to each target data attribute, wherein the weight parameter calculation formula is as follows:

[0070] ;

[0071] For the The weight parameter corresponding to the target data attribute, For the The weight value corresponding to the target data attribute, For the preset The weight operation coefficient corresponding to the target data attribute, is the total number of target data attributes (also the total number of weight parameters corresponding to the target data attributes), , The specific value of can be set according to different target data attributes and is not limited here.

[0072] In this step, specialized assignments are made to the target data attributes to achieve corresponding weight distinctions for each target data attribute, thereby reflecting the weight differences of different target data attributes, and then the weight values ​​corresponding to each target data attribute are assigned weights through a preset weight parameter calculation formula, so that weight parameters corresponding to each target data attribute with high data accuracy and relatively small errors can be obtained. There are many ways to perform specialized assignments on the target data attributes. For example, the total value of the assignments is first set to a fixed value, which can be set to 1, and each weight value corresponding to the target data attribute is set to 0~1, and then random assignment or arithmetic increasing assignment is used for assignment. For example, arithmetic increasing assignment means that the weight value corresponding to the next target data attribute is increased by a fixed difference compared to the previous one, and there is no restriction here.

[0073] like Figure 4 As shown, in one embodiment of the present invention, the steps in step S4, according to the target time window corresponding to the dynamic well opening data and the weight parameters corresponding to each target data attribute, determine the first time series characteristic value corresponding to the dynamic well opening data, which may include but is not limited to the following steps:

[0074] Step S43, determining a first time upper limit value and a first time lower limit value corresponding to the target time window according to the target time window corresponding to the dynamic well opening data;

[0075] Step S44, substituting the weight parameter, the first time upper limit value and the first time lower limit value corresponding to each target data attribute into a preset first time series calculation formula, and calculating and obtaining the first time series characteristic value corresponding to the dynamic well opening data;

[0076] Specifically, the first timing calculation formula is as follows:

[0077] ;

[0078] in, is the first time series characteristic value corresponding to the dynamic well opening data, is the first time upper limit, It is the first time lower limit.

[0079] In this step, the first time upper limit value and the first time lower limit value corresponding to the target time window are determined to obtain the relative size of the target time window corresponding to the dynamic well opening data, and then the weight parameters, the first time upper limit value and the first time lower limit value corresponding to each target data attribute are substituted into the preset first time series calculation formula, so as to calculate the reliable first time series characteristic value corresponding to the dynamic well opening data, so as to reduce the calculation error, wherein the first time upper limit value and the first time lower limit value corresponding to the target time window can be determined intuitively and effectively according to the target time window, but is not limited to, for example, one of the target time windows is 10:00-19:30 on the first day, then the first time upper limit value is 19:30 on the first day, and the second time upper limit value is 10:00 on the first day, and the second time upper limit value is 10:00 on the first day, and the method of determining the second time upper limit value and the second time lower limit value corresponding to the target time window in the following embodiment can be carried out in this way, which will not be repeated later.

[0080] like Figure 5 As shown, in one embodiment of the present invention, when the intermittent time series operation parameters include the oil well static pressure parameter, the shut-in riser pressure parameter and the well killing fluid injection parameter, the steps in step S5, according to the target time window corresponding to the static shut-in data and the intermittent time series operation parameters, determine the second time series characteristic value corresponding to the static shut-in data, which may include but is not limited to the following steps:

[0081] Step S51, determining a second time upper limit value and a second time lower limit value corresponding to the target time window according to the target time window corresponding to the static shut-in data;

[0082] Step S52: Substitute the second time upper limit value, the second time lower limit value, the oil well static pressure parameter, the shut-in riser pressure parameter and the well killing fluid injection parameter into the preconfigured time series feature evaluation model, and calculate the second time series feature value corresponding to the static shut-in data through the second time series calculation formula in the time series feature evaluation model.

[0083] In this step, the second time upper limit value and the second time lower limit value corresponding to the target time window are determined to obtain the relative size of the target time window corresponding to the static shut-in data, and then the second time upper limit value, the second time lower limit value, the oil well static pressure parameter, the shut-in riser pressure parameter and the well-killing fluid injection parameter are substituted into the preconfigured time series feature evaluation model. The second time series calculation formula in the time series feature evaluation model can be used to calculate the second time series characteristic value corresponding to the static shut-in data, so as to reduce the calculation error.

[0084] In one embodiment, there may be multiple types of time series feature evaluation models, and those skilled in the art may select one according to the actual application scenario. For example, it may be, but is not limited to, a convolutional neural network, and there is no specific restriction on the way of training the convolutional neural network. For example: first, the second time upper limit value, the second time lower limit value, the oil well static pressure parameter, the shut-in riser pressure parameter and the wellbore injection parameter recorded in the historical production process are normalized, and then all the normalized input data are input into the input layer of the convolutional neural network, and finally the quantized value of the trained second time series feature value is output through the output layer of the convolutional neural network. After multiple cycles of the above training operation, the convolutional neural network training is finally completed, and the preconfigured time series feature evaluation model is obtained.

[0085] In one embodiment, the calculation process of the timing feature evaluation model is not described in detail, and is specifically summarized as the second timing calculation formula in the timing feature evaluation model, as shown below:

[0086] ;

[0087] in, is the second time series characteristic value corresponding to the static shut-in data, is the second time upper limit value, is the second time lower limit, is the well static pressure parameter, is the shut-in riser pressure parameter, is the injection parameter of the well killing fluid, is a first preset conversion factor corresponding to the shut-in riser pressure parameter, is the second preset conversion factor corresponding to the well killing fluid injection parameter. It should be noted that, , The specific value of can be set according to different shut-in riser pressure parameters and well-killing fluid injection parameters, and is not limited here.

[0088] like Figure 6 As shown, in one embodiment of the present invention, the steps in step S7, determining the target storage location of the target management data according to the timestamp of the target management data combined with the preconfigured target storage area, may include but is not limited to the following steps:

[0089] Step S71, dividing the pre-configured target storage area into a plurality of storage areas according to a preset time interval, and constructing corresponding storage area information for each storage area respectively;

[0090] Step S72: Generate corresponding time identification information according to the time stamp of the target management data, and compare the time identification information with each storage area information one by one;

[0091] Step S73: When the retrieved time identification information matches one of the storage area information, one of the storage areas is determined as the target storage location of the target management data.

[0092] In this step, the preconfigured target storage area is first divided into multiple storage areas according to preset time intervals, so as to achieve accurate division of the target storage area, and the multiple storage areas obtained by division correspond to different target management data, respectively, and then the corresponding time identification information is generated according to the timestamp of the target management data, that is, the timestamp of the target management data is used for special identification, and the time identification information is compared with each storage area information one by one to find the storage area information matching the time identification information. If the retrieved time identification information matches one of the storage area information, it means that the storage area information is suitable for the timestamp configuration of the target management data, and therefore the storage area can be determined as the target storage location of the target management data.

[0093] It should be noted that the time identification information can be but is not limited to matching with multiple storage area information. When there are multiple storage area information matching the time identification information, a storage area corresponding to one storage area information can be selected at will as the target storage location of the target management data; the specific value of the preset time interval can be set accordingly according to the actual application scenario, and is not limited here.

[0094] Figure 7 FIG. 1 is a schematic diagram of a structure of an oil and gas field time series data management system 1000 provided by an embodiment of the present invention. Figure 7 As shown, the oil and gas field time series data management system 1000 includes a memory 1100 and a processor 1200. The number of the memory 1100 and the processor 1200 can be one or more. Figure 7 In the embodiment, a memory 1100 and a processor 1200 are taken as an example; the memory 1100 and the processor 1200 in the device may be connected via a bus or other means. Figure 7 The example of connecting through bus is taken in the following.

[0095] The memory 1100 is a computer-readable storage medium that can be used to store software programs, computer executable programs and modules, such as program instructions / modules corresponding to the oil and gas field time series data management method provided in any embodiment of the present invention. The processor 1200 implements the above-mentioned oil and gas field time series data management method by running the software programs, instructions and modules stored in the memory 1100.

[0096] The memory 1100 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system and an application required for at least one function. In addition, the memory 1100 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other non-volatile solid-state storage device. In some instances, the memory 1100 may further include a memory remotely arranged relative to the processor 1200, and these remote memories may be connected to the device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0097] An embodiment of the present invention further provides a computer-readable storage medium storing computer-executable instructions for executing the method for managing time series data of an oil and gas field as provided in any embodiment of the present invention.

[0098] An embodiment of the present invention also provides a computer program product, including a computer program or computer instructions, wherein the computer program or computer instructions are stored in a computer-readable storage medium, a processor of a computer device reads the computer program or computer instructions from the computer-readable storage medium, and the processor executes the computer program or computer instructions, so that the computer device executes the method for managing intermittent time series data of oil and gas fields provided in any embodiment of the present invention.

[0099] Those skilled in the art will appreciate that all or some of the steps in the methods disclosed above, and the functional modules / units in the systems and devices may be implemented as software, firmware, hardware, or a suitable combination thereof.

[0100] In hardware implementation, the division between the functional modules / units mentioned in the above description does not necessarily correspond to the division of physical components; for example, a physical component may have multiple functions, or a function or step may be performed by several physical components in cooperation. Some or all physical components may be implemented as software executed by a processor, such as a central processing unit, a digital signal processor, or a microprocessor, or implemented as hardware, or implemented as an integrated circuit, such as an application-specific integrated circuit. Such software may be distributed on a computer-readable medium, which may include a computer storage medium (or non-transitory medium) and a communication medium (or transient medium). As is well known to those of ordinary skill in the art, the term computer storage medium includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storing information (such as computer-readable instructions, data structures, program modules, or other data). Computer storage media include, but are not limited to, RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital versatile disk (DVD) or other optical disk storage, magnetic cassettes, magnetic tapes, disk storage or other magnetic storage devices, or any other medium that can be used to store desired information and can be accessed by a computer. Furthermore, it is well known to those skilled in the art that communication media typically embodies computer readable instructions, data structures, program modules, or other data in a modulated data signal such as a carrier wave or other transport mechanism, and may include any information delivery media.

[0101] The terms "component", "module", "system", etc. used in this specification are used to represent computer-related entities, hardware, firmware, a combination of hardware and software, software, or software in execution. For example, a component can be, but is not limited to, a process running on a processor, a processor, an object, an executable file, an execution thread, a program, or a computer. By way of illustration, both applications running on a computing device and a computing device can be components. One or more components may reside in a process or an execution thread, and a component may be located on a computer or distributed between two or more computers. In addition, these components may be executed from various computer-readable media having various data structures stored thereon. Components may communicate, for example, through local or remote processes based on signals having one or more data packets (e.g., data from two components interacting with another component between a local system, a distributed system, or a network, such as the Internet interacting with other systems through signals).

Claims

1. A method for managing time series data of an oil and gas field, characterized in that: The steps include: Step S1, continuously acquiring initial time series data in the production process of the oil and gas field, and preprocessing the initial time series data to obtain target time series data; identifying the timestamp of the target time series data, and when it is determined that there are multiple timestamps of the target time series data, determining the production time window corresponding to each timestamp according to each timestamp and the predetermined oil and gas field's intermittent production cycle; Step S2: for each of the production time windows, determine whether the production time window is within a preset time window in the production process of the oil and gas field; if so, use the production time window as a target time window; otherwise, delete the production time window; Step S3, when the target time series data is divided into at least one group of dynamic well opening data and at least one group of static well closing data according to all the target time windows, a plurality of data attributes corresponding to each group of the dynamic well opening data are respectively obtained, and each group of the static well closing data is respectively analyzed to obtain the well opening time series operation parameters corresponding to each group of the static well closing data, wherein the target time windows corresponding to any group of the dynamic well opening data and any group of the static well closing data are different; Step S4: for each group of the dynamic well opening data, at least one data attribute is selected from the multiple data attributes as a target data attribute, and weight assignment calculation is performed on each target data attribute based on all the target data attributes to obtain weight parameters corresponding to each target data attribute; according to the target time window corresponding to the dynamic well opening data and the weight parameters corresponding to each target data attribute, a first time series feature value corresponding to the dynamic well opening data is determined; Step S5, for each group of the static shut-in data, determining a second time series characteristic value corresponding to the static shut-in data according to the target time window corresponding to the static shut-in data and the intermittent time series operation parameter; Step S6, in the case of configuring a plurality of different preset time series characteristic threshold intervals, traverse all the first time series characteristic values ​​and the second time series characteristic values, and when it is determined that one of the first time series characteristic values ​​and one of the second time series characteristic values ​​are both within one of the preset time series characteristic threshold intervals, merge the dynamic well opening data corresponding to the first time series characteristic value and the static well closing data corresponding to the second time series characteristic value, so as to obtain a set of target management data; Step S7: for each group of the target management data, determine the target storage location of the target management data according to the timestamp of the target management data and the preconfigured target storage area, store the target management data according to the target storage location, and generate target index information of the target management data according to the target storage location.

2. The method for managing time series data of an oil and gas field according to claim 1, characterized in that: The step in step S4, performing weight assignment calculation on each of the target data attributes based on all the target data attributes to obtain weight parameters corresponding to each of the target data attributes, includes the following steps: Step S41: for each of the target data attributes, perform specialized assignment on the target data attribute to obtain a weight value corresponding to the target data attribute; Step S42: weighting the weight values ​​corresponding to the target data attributes using a preset weight parameter calculation formula to obtain weight parameters corresponding to the target data attributes, wherein the weight parameter calculation formula is as follows: ； For the The weight parameters corresponding to the target data attributes, For the The weight value corresponding to the target data attribute, For the preset The weight operation coefficient corresponding to the target data attribute, is the total number of target data attributes, .

3. The method for managing time series data of an oil and gas field according to claim 2, characterized in that: The step in step S4, determining the first time series characteristic value corresponding to the dynamic well opening data according to the target time window corresponding to the dynamic well opening data and the weight parameters corresponding to each of the target data attributes, includes the following steps: Step S43, determining a first time upper limit value and a first time lower limit value corresponding to the target time window according to the target time window corresponding to the dynamic well opening data; Step S44: Substitute the weight parameters corresponding to each of the target data attributes, the first time upper limit value, and the first time lower limit value into a preset first time series calculation formula to calculate a first time series characteristic value corresponding to the dynamic well opening data, wherein the first time series calculation formula is as follows: ； is the first time series characteristic value corresponding to the dynamic well opening data, is the first time upper limit value, is the lower limit of the first time.

4. The method for managing time series data of an oil and gas field according to claim 1, characterized in that: When the intermittent time series operation parameters include oil well static pressure parameters, shut-in riser pressure parameters and well killing fluid injection parameters, the steps in step S5, according to the target time window corresponding to the static shut-in data and the intermittent time series operation parameters, determine the second time series characteristic value corresponding to the static shut-in data, including the following steps: Step S51, determining a second time upper limit value and a second time lower limit value corresponding to the target time window according to the target time window corresponding to the static shut-in data; Step S52: Substitute the second time upper limit value, the second time lower limit value, the oil well static pressure parameter, the shut-in riser pressure parameter and the well killing fluid injection parameter into a preconfigured time series feature evaluation model, and calculate the second time series feature value corresponding to the static shut-in data through the second time series calculation formula in the time series feature evaluation model.

5. The method for managing time series data of an oil and gas field according to claim 4, characterized in that: The second timing calculation formula is as follows: ； in, is the second time series characteristic value corresponding to the static shut-in data, is the second time upper limit value, is the lower limit of the second time, is the oil well static pressure parameter, is the shut-in riser pressure parameter, is the well killing fluid injection parameter, is a first preset conversion factor corresponding to the shut-in riser pressure parameter, is a second preset conversion factor corresponding to the well killing fluid injection parameter.

6. The method for managing time series data of an oil and gas field according to claim 1, characterized in that: The step in step S7, determining the target storage location of the target management data according to the timestamp of the target management data combined with the pre-configured target storage area, includes the following steps: Step S71, dividing the pre-configured target storage area into a plurality of storage areas according to a preset time interval, and constructing corresponding storage area information for each of the storage areas; Step S72, generating corresponding time identification information according to the timestamp of the target management data, and comparing the time identification information with each storage area information one by one; Step S73: When the retrieved time identification information matches one of the storage area information, determine one of the storage areas as the target storage location of the target management data.

7. The method for managing time series data of an oil and gas field according to claim 1, characterized in that: The step in step S1, preprocessing the initial time series data to obtain target time series data, includes the following steps: Step S11, performing abnormal data detection on the initial time series data to obtain an abnormal data detection result; deleting the abnormal data in the initial time series data according to the abnormal data detection result to obtain first time series data; Step S12: denoise, clean and compress the first time series data in sequence to obtain target time series data.

8. An oil and gas field time series data management system, characterized in that: include: at least one processor; at least one memory for storing at least one program; When at least one of the programs is executed by at least one of the processors, the method for managing the intermittent time series data of an oil and gas field as described in any one of claims 1 to 7 is implemented.

9. A computer-readable storage medium, characterized in that: A processor-executable program is stored therein, and when the processor-executable program is executed by the processor, it is used to implement the method for managing the intermittent time series data of an oil and gas field as described in any one of claims 1 to 7.

Images