Water injection well blockage grade evaluation method, device, equipment and medium

Abstract

The invention relates to the field of oilfield development, and discloses a water injection well blockage level evaluation method, device and equipment and a medium, and the target operation time period of a water injection well is determined, and the target operation time period comprises a to-be-predicted time step and corresponding first N time steps. According to the target parameter time sequence data of the water injection well in the target operation time period, whether the water injection well has the blocking risk in the to-be-predicted time step or not is judged. If it is determined that the blocking risk exists, the operation data of the water injection well in the to-be-predicted time step are preprocessed, and the processed operation data are obtained. And respectively inputting the processed operation data into a trained first blockage level prediction model and a trained second blockage level prediction model to carry out blockage level prediction so as to obtain first prediction data and second prediction data. And based on the first prediction data and the second prediction data, determining a target blockage level of the water injection well in the to-be-predicted time step. The method can achieve the intelligent evaluation of the blocking level of the water injection well, and can effectively improve the evaluation efficiency.

Description

Technical Field

[0001] The invention relates to the field of oil field development, and in particular to a method, a device, equipment and a medium for evaluating the blockage level of a water injection well. Background Art

[0002] Water injection wells play an important role in oil field development. They can replenish formation energy, increase reservoir pressure, and thus improve oil field recovery.

[0003] During the oil field production process, as time goes by, water injection wells will gradually become clogged, resulting in a decrease in water injection efficiency and affecting the oil field production benefits.

[0004] The relevant technology mainly relies on manual experience to evaluate the blockage of water injection wells, and the evaluation efficiency is low. Summary of the invention

[0005] The present invention provides a method, device, equipment and medium for evaluating the blockage level of water injection wells, which are used to solve the defect that the related technology mainly relies on manual experience to evaluate the blockage situation of water injection wells and has low evaluation efficiency, realize intelligent evaluation of the blockage situation of water injection wells, and improve evaluation efficiency.

[0006] In a first aspect, the present invention provides a method for evaluating the blockage level of a water injection well, comprising:

[0007] Determine a target operation period of the water injection well according to the time step to be predicted; wherein the target operation period includes the time step to be predicted and the corresponding first N time steps, where N is an integer not less than 1;

[0008] According to the target parameter time series data of the water injection well in the target operation period, it is determined whether the water injection well has a blockage risk at the time step to be predicted;

[0009] Determining that the water injection well has a risk of blockage at the time step to be predicted, preprocessing the operation data of the water injection well at the time step to be predicted to obtain processed operation data;

[0010] inputting the processed operation data into the trained first congestion level prediction model and the second congestion level prediction model respectively to perform congestion level prediction, thereby obtaining first prediction data output by the first congestion level prediction model and second prediction data output by the second congestion level prediction model;

[0011] Based on the first prediction data and the second prediction data, a target blockage level of the water injection well at the time step to be predicted is determined.

[0012] Optionally, judging whether the water injection well has a blockage risk at the time step to be predicted based on the target parameter time series data of the water injection well in the target operation period includes:

[0013] Acquire time series data of apparent water absorption index of the water injection well in the target operation period;

[0014] Performing a stationarity test on the apparent water absorption index time series data to determine whether the water injection well has a risk of blockage at the time step to be predicted;

[0015] If it is determined that the apparent water absorption index time series data is not stable, it is determined that the water injection well has a risk of blockage at the time step to be predicted;

[0016] If it is determined that the apparent water absorption index time series data is stationary, it is determined that the water injection well has no blockage risk at the time step to be predicted.

[0017] Optionally, preprocessing the operation data of the water injection well at the time step to be predicted to obtain processed operation data includes:

[0018] Acquire multi-type parameter values ​​of the water injection well at the time step to be predicted, wherein the multi-type parameter values ​​include parameter values ​​of multiple parameters;

[0019] For any parameter value of the parameter, normalize the parameter value of the parameter to obtain a normalized parameter value of the parameter;

[0020] The normalized parameter values ​​of all the parameters are arranged according to the set parameter arrangement order to obtain a corresponding parameter value sequence, and the parameter value sequence is used as the processed running data.

[0021] Optionally, the multi-type parameter values ​​include at least two of the corrected pump pressure, oil pressure, daily water injection volume, injection rate and / or apparent water absorption index.

[0022] Optionally, the first prediction data and the second prediction data include prediction probabilities corresponding to M set congestion levels, where M is an integer greater than 1;

[0023] The step of determining the target blockage level of the water injection well at the time step to be predicted based on the first prediction data and the second prediction data comprises:

[0024] For any set congestion level, adding the predicted probability corresponding to the congestion level in the first prediction data and the predicted probability corresponding to the congestion level in the second prediction data to obtain a final probability corresponding to the congestion level;

[0025] A maximum probability is determined among the final probabilities corresponding to each of the congestion levels, and the congestion level corresponding to the maximum probability is determined as the target congestion level.

[0026] Optionally, after determining the target blockage level of the water injection well at the time step to be predicted based on the first prediction data and the second prediction data, the method further includes:

[0027] Acquire a set measure correspondence relationship, where the measure correspondence relationship is a correspondence relationship between a plurality of the congestion levels and a plurality of congestion handling measures;

[0028] Determining the corresponding congestion handling measure in the measure correspondence according to the target congestion level;

[0029] The determined blockage treatment measures are output to recommend technicians to use the blockage treatment measures to treat the water injection well.

[0030] Optionally, the first congestion level prediction model is a random forest classification model, and the second congestion level prediction model is a support vector machine classification model.

[0031] In a second aspect, the present invention provides a water injection well blockage level assessment device, comprising:

[0032] A first determining unit is used to determine a target operation period of the water injection well according to the time step to be predicted; wherein the target operation period includes the time step to be predicted and the corresponding first N time steps, where N is an integer not less than 1;

[0033] A judgment unit, configured to judge whether the water injection well has a blockage risk at the time step to be predicted according to the target parameter time series data of the water injection well in the target operation period;

[0034] A preprocessing unit, used for determining that the water injection well has a risk of blockage at the time step to be predicted, and then preprocessing the operation data of the water injection well at the time step to be predicted to obtain processed operation data;

[0035] A prediction unit, configured to input the processed operation data into the trained first congestion level prediction model and the trained second congestion level prediction model, respectively, to perform congestion level prediction, and obtain first prediction data output by the first congestion level prediction model and second prediction data output by the second congestion level prediction model;

[0036] The second determination unit is used to determine the target blockage level of the water injection well at the time step to be predicted based on the first prediction data and the second prediction data.

[0037] In a third aspect, the present invention provides a computer device, comprising: a memory and a processor, the memory and the processor being communicatively connected to each other, the memory storing computer instructions, and the processor executing the method for assessing the blockage level of an injection well according to the first aspect or any corresponding embodiment thereof by executing the computer instructions.

[0038] In a fourth aspect, the present invention provides a computer-readable storage medium having computer instructions stored thereon, the computer instructions being used to enable a computer to execute the method for assessing the blockage level of an injection well according to the first aspect or any corresponding embodiment thereof.

[0039] The method, device, equipment and medium for evaluating the blockage level of water injection wells provided by the present invention can determine the target operation period of the water injection well according to the time step to be predicted; wherein the target operation period includes the time step to be predicted and the corresponding first N time steps, and N is an integer not less than 1. According to the target parameter time series data of the water injection well in the target operation period, it is judged whether the water injection well has a blockage risk at the time step to be predicted. If it is determined that the water injection well has a blockage risk at the time step to be predicted, the operation data of the water injection well at the time step to be predicted is preprocessed to obtain the processed operation data. The processed operation data is respectively input into the trained first blockage level prediction model and the second blockage level prediction model to predict the blockage level, and the first prediction data output by the first blockage level prediction model and the second prediction data output by the second blockage level prediction model are obtained. Based on the first prediction data and the second prediction data, the target blockage level of the water injection well at the time step to be predicted is determined. The present invention can realize the intelligent evaluation of the blockage level of the water injection well, and can effectively improve the evaluation efficiency of the blockage level of the water injection well. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0041] Figure 1 A flow chart of a method for evaluating the blockage level of a water injection well provided in an embodiment of the present invention;

[0042] Figure 2 A flow chart of another method for evaluating the blockage level of a water injection well provided by an embodiment of the present invention;

[0043] Figure 3 A schematic diagram of the structure of a water injection well blockage level assessment device provided by an embodiment of the present invention;

[0044] Figure 4 A schematic diagram of the structure of a computer device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0045] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0046] Combine the following Figure 1-Figure 2 The method for evaluating the blockage level of a water injection well of the present invention is described.

[0047] like Figure 1 As shown, this embodiment proposes a first method for evaluating the blockage level of a water injection well, which may include the following steps:

[0048] S101. Determine a target operation period of the water injection well according to the time step to be predicted; wherein the target operation period includes the time step to be predicted and the corresponding first N time steps, where N is an integer not less than 1.

[0049] The time step to be predicted is a time step for which the water injection well blockage level prediction is required, such as the latest time step in the oil field production process. It should be noted that the time step can be a time point of a specific duration, such as half a day, a day or a week.

[0050] Specifically, the first N time steps are N time steps before the time step to be predicted and adjacent to the time step to be predicted.

[0051] The target operating time period may be a time period consisting of the time step to be predicted and the previous N time steps.

[0052] S102. Determine whether there is a blockage risk for the water injection well at the time step to be predicted based on the target parameter time series data of the water injection well within the target operation period.

[0053] The target parameter time series data may be parameter value time series data of a set physical parameter of the water injection well in a target operation period, and the target parameter time series data includes the parameter value of the set physical parameter at each time step in the target operation period.

[0054] Optionally, step S102 may include:

[0055] Obtaining time series data of apparent water absorption index of water injection wells within a target operation period;

[0056] The stability test of the apparent water absorption index time series data is carried out to determine whether there is a blockage risk in the injection well at the time step to be predicted;

[0057] If it is determined that the apparent water absorption index time series data is not stable, it is determined that the injection well has a blockage risk at the time step to be predicted;

[0058] If it is determined that the apparent water absorption index time series data is stationary, it is determined that there is no risk of blockage in the injection well at the time step to be predicted.

[0059] The apparent water absorption index time series data may include the apparent water absorption index of each time step in the target operating period.

[0060] Specifically, in this embodiment, an Augmented Dickey-Fuller (ADF) test can be performed on the apparent water absorption index time series data. If the ADF result is less than the statistical values ​​of the three levels of 1%, 5%, and 10% at the same time, it can be determined that the apparent water absorption index time series data has stationarity, and at this time it can be determined that the injection well does not have a risk of blockage at the time step to be predicted, and the execution of step S103 can be prohibited. Otherwise, it can be determined that the apparent water absorption index time series data does not have stationarity, and at this time it can be determined that the injection well has a risk of blockage at the time step to be predicted.

[0061] S103: If it is determined that the water injection well has a blockage risk at the time step to be predicted, the operation data of the water injection well at the time step to be predicted is preprocessed to obtain processed operation data.

[0062] Specifically, in this embodiment, when it is determined that the water injection well has a risk of blockage at the time step to be predicted, the operation data of the water injection well at the time step to be predicted can be preprocessed to obtain corresponding processed operation data.

[0063] Optionally, step S103 may include:

[0064] Obtaining multi-type parameter values ​​of the water injection well at the time step to be predicted, wherein the multi-type parameter values ​​include parameter values ​​of multiple parameters;

[0065] For a parameter value of any parameter, the parameter value of the parameter is normalized to obtain a normalized parameter value of the parameter;

[0066] The normalized parameter values ​​of all parameters are arranged according to the set parameter arrangement order to obtain the corresponding parameter value sequence, and the parameter value sequence is used as the processed running data.

[0067] Optionally, the above-mentioned multi-type parameter values ​​include at least two of the corrected pump pressure, oil pressure, daily water injection volume, injection rate and / or apparent water absorption index.

[0068] Among them, the corrected daily water injection volume = daily water injection volume × 24 / production time.

[0069] Among them, injection rate = corrected daily water injection volume / injection volume.

[0070] Among them, apparent water absorption index = corrected daily water injection volume / oil pressure.

[0071] Specifically, in this embodiment, for the parameter value of any parameter, the maximum parameter value and the minimum parameter value of the parameter can be statistically calculated based on the historical parameter values ​​of the parameter, and the parameter value of the parameter can be normalized based on the maximum parameter value and the minimum parameter value to obtain the normalized parameter value of the parameter.

[0072] S104: Input the processed operating data into the trained first congestion level prediction model and the second congestion level prediction model respectively to perform congestion level prediction, and obtain first prediction data output by the first congestion level prediction model and second prediction data output by the second congestion level prediction model.

[0073] Optionally, the first congestion level prediction model is a random forest classification model, and the second congestion level prediction model is a support vector machine classification model.

[0074] Specifically, this embodiment can input the processed operating data into the trained first blockage level prediction model and the second blockage level prediction model respectively, so that the first blockage level prediction model and the second blockage level prediction model predict the blockage level of the injection well at the predicted time step based on the processed operating data, and obtain the first prediction data output by the first blockage level prediction model, and obtain the second prediction data output by the second blockage level prediction model.

[0075] S105. Determine a target blockage level of the water injection well at a time step to be predicted based on the first prediction data and the second prediction data.

[0076] Specifically, this embodiment can determine the blockage level of the water injection well at the time step to be predicted, that is, the target blockage level, according to the first prediction data and the second prediction data.

[0077] Optionally, the first prediction data and the second prediction data include prediction probabilities corresponding to M set congestion levels, where M is an integer greater than 1. In this case, step S105 may include:

[0078] For any set congestion level, the predicted probability corresponding to the congestion level in the first prediction data is added to the predicted probability corresponding to the congestion level in the second prediction data to obtain a final probability corresponding to the congestion level;

[0079] The maximum probability is determined among the final probabilities corresponding to each congestion level, and the congestion level corresponding to the maximum probability is determined as the target congestion level.

[0080] In this embodiment, the technicians can pre-set M blockage levels, such as no abnormality, slight blockage, medium blockage and severe blockage.

[0081] Specifically, in this embodiment, for any congestion level, a first prediction probability corresponding to the congestion level can be determined in the first prediction data, and a second prediction probability corresponding to the congestion level can be determined in the second prediction data. Then, the sum of the first prediction probability and the second prediction probability is calculated, and the sum is determined to be the final probability corresponding to the congestion level.

[0082] It can be understood that, in this embodiment, the final probability corresponding to each congestion level can be determined separately.

[0083] Specifically, this embodiment may determine the maximum probability among the final probabilities corresponding to each congestion level, determine the congestion level corresponding to the maximum probability, and determine the congestion level corresponding to the maximum probability as the target congestion level.

[0084] The method for evaluating the blockage level of water injection wells proposed in this embodiment can determine the target operation period of the water injection well according to the time step to be predicted; wherein the target operation period includes the time step to be predicted and the corresponding first N time steps, and N is an integer not less than 1. According to the target parameter time series data of the water injection well in the target operation period, it is judged whether the water injection well has a blockage risk at the time step to be predicted. If it is determined that the water injection well has a blockage risk at the time step to be predicted, the operation data of the water injection well at the time step to be predicted is preprocessed to obtain the processed operation data. The processed operation data is respectively input into the trained first blockage level prediction model and the second blockage level prediction model to predict the blockage level, and the first prediction data output by the first blockage level prediction model and the second prediction data output by the second blockage level prediction model are obtained. Based on the first prediction data and the second prediction data, the target blockage level of the water injection well at the time step to be predicted is determined. This embodiment can realize the intelligent evaluation of the blockage level of water injection wells, and can effectively improve the evaluation efficiency of the blockage level of water injection wells.

[0085] based on Figure 1 This embodiment proposes a second method for evaluating the blockage level of water injection wells. After step S105, the method may further include:

[0086] Acquire a set measure correspondence relationship, where the measure correspondence relationship is a correspondence relationship between multiple congestion levels and multiple congestion processing measures;

[0087] Determine corresponding congestion treatment measures in the measure correspondence relationship according to the target congestion level;

[0088] The determined blockage treatment measures are output to recommend technicians to use the blockage treatment measures to treat the water injection wells.

[0089] The blockage treatment measures may be pre-set measures for treating water injection wells that are blocked and have a specific blockage level.

[0090] Specifically, the measure correspondence may be a one-to-one correspondence between a plurality of congestion levels and a plurality of congestion handling measures.

[0091] Specifically, this embodiment can search for a blockage treatment measure corresponding to the target blockage level among the multiple blockage treatment measures included in the measure correspondence relationship. Afterwards, this embodiment can output the blockage treatment measure to show it to the technician, prompting the technician to treat the water injection well based on the blockage treatment measure to alleviate or solve the blockage problem of the water injection well.

[0092] The water injection well blockage level assessment method proposed in this embodiment can determine the blockage treatment measures corresponding to the target blockage level, prompting technical personnel to adopt the blockage treatment measures to treat the water injection wells, alleviate or solve the blockage problem of the water injection wells, and improve the water injection efficiency of the water injection wells and the production benefits of the oil field.

[0093] In the related art, the evaluation of the blockage degree of water injection wells mainly relies on manual experience, which has problems such as low evaluation efficiency, poor accuracy and lack of real-time performance. The water injection well blockage level evaluation method of this embodiment can timely and accurately evaluate the blockage level of water injection wells and improve the evaluation efficiency, which is of great significance for ensuring oilfield production safety and improving development efficiency.

[0094] based on Figure 1 ,like Figure 2 As shown, this embodiment proposes a third method for evaluating the blockage level of water injection wells. In this method, this embodiment can train a blockage assessment model to obtain a trained blockage level prediction model, and then perform blockage level prediction based on the blockage level prediction model. Specifically, the method may include the following steps:

[0095] S1. Collecting water injection well production data. Specifically, this embodiment can collect water injection well historical dynamic data, including production time, production duration, oil pressure, pump pressure, daily injection volume, daily water injection volume and well measures data, and perform sample annotation of water injection well blockage level based on expert experience to construct a water injection well blockage level sample set, where the water injection well blockage level can include three levels: no abnormality, slight blockage, and severe blockage, represented by 0, 1 and 2 respectively. After collecting the water injection well historical dynamic data, the following data is further calculated, and the pump pressure, oil pressure, corrected daily water injection volume, injection rate and apparent water absorption index are used as sample features.

[0096] S2. Perform data preprocessing, including removing stable segments, normalization, and downsampling.

[0097] In the process of identifying and eliminating stable segments, this embodiment can segment the visual water absorption index time series with a sliding window of 60 days, and use ADF stability test for each segment. If the ADF result is less than the statistical values ​​of the three levels of 1%, 5% and 10% at the same time, it means that the curve is stable. The dynamic data corresponding to this part of the curve is eliminated and directly diagnosed as no abnormality, and does not participate in model training and prediction.

[0098] In the normalization process, this embodiment may normalize the data using a min-max method, wherein the maximum value may be the 95th percentile of the data, and the minimum value may be the 5th percentile of the data.

[0099] In the downsampling process, this embodiment may use a neighbor downsampling method to downsample the data to ensure a balance in the number of samples corresponding to the three labels of no abnormality, slight congestion, and severe congestion.

[0100] S3. Construct a random forest model and a support vector machine (SVM) model, and perform model integration. The integrated model is constructed by integrating the random forest classification algorithm with the support vector machine classification algorithm. The number of random forest decision trees is set to 100, and the kernel function used in the support vector machine is set to the radial basis function. The sum of the prediction probabilities of the two models under different labels is used as the final prediction probability of the integrated model, and the label with the highest prediction probability is used as the final classification result.

[0101] S4. Input the data pre-processed in step S2 into the integrated model constructed in step S3 for training, obtain a first congestion level prediction model and a second congestion level prediction model, and output the models.

[0102] S5. Preprocess the collected new dynamic data to obtain processed data, input the processed data into a trained blockage assessment model, i.e., a water injection well blockage grade prediction model, to predict the blockage degree, output the prediction result, i.e., the water injection well blockage degree classification result, and recommend measures.

[0103] In practical applications, the blockage level calculated by this embodiment is highly consistent with the blockage level obtained through expert experience and historical well measure data annotation, and the overall accuracy rate reaches 87.7%.

[0104] It should be noted that this embodiment aims to accurately and efficiently determine the blockage status of water injection wells, guide subsequent maintenance and management, and thus improve the efficiency of oil field development. This embodiment can use historical blockage data to construct a sample set, process and annotate the data set, use an integrated model composed of random forest and support vector machine algorithms, and through parameter optimization and model testing and evaluation, realize blockage degree classification alarm, push evaluation results and measures. Compared with related technologies, this embodiment can evaluate the blockage degree based on dynamic production data with high accuracy, and the evaluation process can be automated and real-time, shortening the evaluation cycle, improving work efficiency, and timely discovering potential safety hazards to ensure the safe operation of water injection wells.

[0105] This embodiment can adopt an integrated model composed of random forest and support vector machine algorithms, and through parameter optimization and model testing and evaluation, implement congestion degree classification alarm, push evaluation results and measure suggestions.

[0106] The method for assessing the blockage level of injection wells proposed in this embodiment can determine the blockage level of injection wells efficiently and accurately based on the dynamic data of injection wells by adopting machine learning methods, avoid the inefficiency and uncertainty of related technologies, provide support for timely unblocking measures, and accurately and efficiently calculate the blockage degree of injection wells, thereby greatly shortening the assessment cycle and improving work efficiency; at the same time, it improves the timeliness of injection well blockage assessment, avoids problems such as pressure anomalies and equipment damage that may be caused by injection well blockage, and reduces safety risks.

[0107] like Figure 3 As shown, this embodiment provides a water injection well blockage level assessment device, which may include:

[0108] The first determining unit 301 is used to determine the target operation period of the water injection well according to the time step to be predicted; wherein the target operation period includes the time step to be predicted and the corresponding first N time steps, where N is an integer not less than 1;

[0109] A judgment unit 302 is used to judge whether there is a blockage risk of the water injection well at a time step to be predicted based on the target parameter time series data of the water injection well in the target operation period;

[0110] The preprocessing unit 303 is used to determine that there is a risk of blockage in the water injection well at the time step to be predicted, and then preprocess the operation data of the water injection well at the time step to be predicted to obtain processed operation data;

[0111] The prediction unit 304 is used to input the processed operation data into the trained first congestion level prediction model and the second congestion level prediction model respectively to perform congestion level prediction, and obtain the first prediction data output by the first congestion level prediction model and the second prediction data output by the second congestion level prediction model;

[0112] The second determination unit 305 is used to determine the target blockage level of the water injection well at the time step to be predicted based on the first prediction data and the second prediction data.

[0113] It should be noted that the processing of the first determination unit 301, the judgment unit 302, the preprocessing unit 303, the prediction unit 304 and the second determination unit 305 and the beneficial effects thereof can be respectively referred to in Figure 1 Steps S101 to S105 in the above are not described in detail.

[0114] Optionally, the determining unit 302 is further configured to:

[0115] Obtaining time series data of apparent water absorption index of water injection wells within a target operation period;

[0116] The stability test of the apparent water absorption index time series data is carried out to determine whether there is a blockage risk in the injection well at the time step to be predicted;

[0117] If it is determined that the apparent water absorption index time series data is not stable, it is determined that the injection well has a blockage risk at the time step to be predicted;

[0118] If it is determined that the apparent water absorption index time series data is stationary, it is determined that there is no risk of blockage in the injection well at the time step to be predicted.

[0119] Optionally, the preprocessing unit 303 is further configured to:

[0120] Obtaining multi-type parameter values ​​of the water injection well at the time step to be predicted, wherein the multi-type parameter values ​​include parameter values ​​of multiple parameters;

[0121] For a parameter value of any parameter, the parameter value of the parameter is normalized to obtain a normalized parameter value of the parameter;

[0122] The normalized parameter values ​​of all parameters are arranged according to the set parameter arrangement order to obtain the corresponding parameter value sequence, and the parameter value sequence is used as the processed running data.

[0123] Optionally, the multi-type parameter values ​​include at least two of the corrected pump pressure, oil pressure, daily water injection volume, injection rate and / or apparent water absorption index.

[0124] Optionally, the first prediction data and the second prediction data include prediction probabilities corresponding to M set congestion levels, where M is an integer greater than 1;

[0125] The second determining unit 305 is further configured to:

[0126] For any set congestion level, the predicted probability corresponding to the congestion level in the first prediction data is added to the predicted probability corresponding to the congestion level in the second prediction data to obtain a final probability corresponding to the congestion level;

[0127] The maximum probability is determined among the final probabilities corresponding to each congestion level, and the congestion level corresponding to the maximum probability is determined as the target congestion level.

[0128] Optionally, the above device further includes a measure recommendation unit, which is used to:

[0129] After determining the target blockage level of the water injection well at the time step to be predicted based on the first prediction data and the second prediction data, the set measure correspondence relationship is obtained, where the measure correspondence relationship is a correspondence relationship between multiple blockage levels and multiple blockage treatment measures;

[0130] Determine corresponding congestion treatment measures in the measure correspondence relationship according to the target congestion level;

[0131] The determined blockage treatment measures are output to recommend technicians to use the blockage treatment measures to treat the water injection wells.

[0132] Optionally, the first congestion level prediction model is a random forest classification model, and the second congestion level prediction model is a support vector machine classification model.

[0133] The water injection well blockage level assessment device proposed in this embodiment can determine the target operation time period of the water injection well according to the time step to be predicted; wherein the target operation time period includes the time step to be predicted and the corresponding first N time steps, and N is an integer not less than 1. According to the target parameter time series data of the water injection well in the target operation time period, it is judged whether the water injection well has a blockage risk at the time step to be predicted. If it is determined that the water injection well has a blockage risk at the time step to be predicted, the operation data of the water injection well at the time step to be predicted is preprocessed to obtain the processed operation data. The processed operation data is respectively input into the trained first blockage level prediction model and the second blockage level prediction model to predict the blockage level, and the first prediction data output by the first blockage level prediction model and the second prediction data output by the second blockage level prediction model are obtained. Based on the first prediction data and the second prediction data, the target blockage level of the water injection well at the time step to be predicted is determined. This embodiment can realize the intelligent evaluation of the blockage level of the water injection well, and can effectively improve the evaluation efficiency of the blockage level of the water injection well.

[0134] The water injection well blockage level assessment device in this embodiment is presented in the form of a functional unit, where the unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and memory that executes one or more software or fixed programs, and / or other devices that can provide the above functions.

[0135] The embodiment of the present invention also provides a computer device having the above Figure 3 The device for evaluating the blockage level of a water injection well is shown.

[0136] See also Figure 4 , a schematic diagram of the structure of a computer device provided by an optional embodiment of the present invention, the computer device includes: one or more processors 10, a memory 20, and interfaces for connecting various components, including high-speed interfaces and low-speed interfaces. The various components are connected to each other using different buses for communication, and can be installed on a common motherboard or installed in other ways as needed. The processor can process instructions executed in the computer device, including instructions stored in or on the memory to display graphical information of the GUI on an external input / output device (such as a display device coupled to the interface). In some optional embodiments, if necessary, multiple processors and / or multiple buses can be used together with multiple memories and multiple memories. Similarly, multiple computer devices can be connected, and each device provides part of the necessary operations (for example, as a server array, a group of blade servers, or a multi-processor system). Figure 4 A processor 10 is taken as an example.

[0137] The processor 10 may be a central processing unit, a network processor or a combination thereof. The processor 10 may further include a hardware chip. The hardware chip may be a dedicated integrated circuit, a programmable logic device or a combination thereof. The programmable logic device may be a complex programmable logic device, a field programmable gate array, a general purpose array logic or any combination thereof.

[0138] The memory 20 stores instructions executable by at least one processor 10, so that at least one processor 10 executes the method shown in the above embodiment.

[0139] The memory 20 may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function. The data storage area may store data created according to the use of the computer device, etc. In addition, the memory 20 may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage devices. In some optional embodiments, the memory 20 may optionally include a memory remotely arranged relative to the processor 10, and these remote memories may be connected to the computer 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.

[0140] The memory 20 may include a volatile memory, such as a random access memory. The memory may also include a non-volatile memory, such as a flash memory, a hard disk or a solid state drive. The memory 20 may also include a combination of the above-mentioned types of memory.

[0141] The computer device further comprises a communication interface 30 for the computer device to communicate with other devices or a communication network.

[0142] The embodiment of the present invention also provides a computer-readable storage medium. The method according to the embodiment of the present invention can be implemented in hardware, firmware, or can be implemented as a computer code that can be recorded in a storage medium, or can be implemented as a computer code that is originally stored in a remote storage medium or a non-temporary machine-readable storage medium and will be stored in a local storage medium through a network download, so that the method described herein can be stored in such software processing on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only storage memory, a random access memory, a flash memory, a hard disk or a solid-state hard disk, etc.; further, the storage medium can also include a combination of the above types of memories. It can be understood that a computer, a processor, a microprocessor controller, or programmable hardware includes a storage component that can store or receive software or computer code. When the software or computer code is accessed and executed by a computer, a processor, or hardware, the method shown in the above embodiment is implemented.

[0143] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for evaluating the blockage level of a water injection well, characterized in that: include: Determine a target operation period of the water injection well according to the time step to be predicted; wherein the target operation period includes the time step to be predicted and the corresponding first N time steps, where N is an integer not less than 1; According to the target parameter time series data of the water injection well in the target operation period, it is determined whether the water injection well has a blockage risk at the time step to be predicted; Determining that the water injection well has a risk of blockage at the time step to be predicted, preprocessing the operation data of the water injection well at the time step to be predicted to obtain processed operation data; inputting the processed operation data into the trained first congestion level prediction model and the second congestion level prediction model respectively to perform congestion level prediction, thereby obtaining first prediction data output by the first congestion level prediction model and second prediction data output by the second congestion level prediction model; Based on the first prediction data and the second prediction data, a target blockage level of the water injection well at the time step to be predicted is determined.

2. The method according to claim 1, characterized in that: The determining, based on the target parameter time series data of the water injection well in the target operation period, whether the water injection well has a blockage risk at the time step to be predicted includes: Acquire time series data of apparent water absorption index of the water injection well in the target operation period; Performing a stationarity test on the apparent water absorption index time series data to determine whether the water injection well has a risk of blockage at the time step to be predicted; If it is determined that the apparent water absorption index time series data is not stable, it is determined that the water injection well has a risk of blockage at the time step to be predicted; If it is determined that the apparent water absorption index time series data is stationary, it is determined that the water injection well has no blockage risk at the time step to be predicted.

3. The method according to claim 1, characterized in that: The preprocessing of the operation data of the water injection well at the time step to be predicted to obtain the processed operation data includes: Acquire multi-type parameter values ​​of the water injection well at the time step to be predicted, wherein the multi-type parameter values ​​include parameter values ​​of multiple parameters; For any parameter value of the parameter, normalize the parameter value of the parameter to obtain a normalized parameter value of the parameter; The normalized parameter values ​​of all the parameters are arranged according to the set parameter arrangement order to obtain a corresponding parameter value sequence, and the parameter value sequence is used as the processed running data.

4. The method according to claim 3, characterized in that The multi-type parameter values ​​include at least two of the corrected pump pressure, oil pressure, daily water injection volume, injection rate and / or apparent water absorption index.

5. The method according to claim 1, characterized in that The first prediction data and the second prediction data include prediction probabilities corresponding to M set congestion levels, where M is an integer greater than 1; The step of determining the target blockage level of the water injection well at the time step to be predicted based on the first prediction data and the second prediction data comprises: For any set congestion level, adding the predicted probability corresponding to the congestion level in the first prediction data and the predicted probability corresponding to the congestion level in the second prediction data to obtain a final probability corresponding to the congestion level; A maximum probability is determined among the final probabilities corresponding to each of the congestion levels, and the congestion level corresponding to the maximum probability is determined as the target congestion level.

6. The method according to claim 1, characterized in that After determining the target blockage level of the water injection well at the time step to be predicted based on the first prediction data and the second prediction data, the method further includes: Acquire a set measure correspondence relationship, where the measure correspondence relationship is a correspondence relationship between a plurality of the congestion levels and a plurality of congestion handling measures; Determining the corresponding congestion handling measure in the measure correspondence according to the target congestion level; The determined blockage treatment measures are output to recommend technicians to use the blockage treatment measures to treat the water injection well.

7. The method according to any one of claims 1 to 6, characterized in that The first congestion level prediction model is a random forest classification model, and the second congestion level prediction model is a support vector machine classification model.

8. A device for evaluating the blockage level of a water injection well, characterized in that: include: A first determining unit is used to determine a target operation period of the water injection well according to the time step to be predicted; wherein the target operation period includes the time step to be predicted and the corresponding first N time steps, where N is an integer not less than 1; A judgment unit, configured to judge whether the water injection well has a blockage risk at the time step to be predicted according to the target parameter time series data of the water injection well in the target operation period; A preprocessing unit, used for determining that the water injection well has a risk of blockage at the time step to be predicted, and then preprocessing the operation data of the water injection well at the time step to be predicted to obtain processed operation data; A prediction unit, configured to input the processed operation data into the trained first congestion level prediction model and the trained second congestion level prediction model, respectively, to perform congestion level prediction, and obtain first prediction data output by the first congestion level prediction model and second prediction data output by the second congestion level prediction model; The second determination unit is used to determine the target blockage level of the water injection well at the time step to be predicted based on the first prediction data and the second prediction data.

9. A computer device, characterized in that: include: A memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the water injection well blockage level assessment method according to any one of claims 1 to 7 by executing the computer instructions.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a computer to execute the water injection well blockage level assessment method according to any one of claims 1 to 7.

Images