Linkage control method for filling mother liquor into well water

Abstract

The invention relates to the technical field of resource collection, in particular to an injection well water and mother liquor topdressing linkage control method. The method comprises the following steps: acquiring a first sequence and a second sequence of measured clear water flow and predicted clear water flow corresponding to a first monitoring period; performing similarity analysis on the sequence trend of the first sequence and the sequence trend of the second sequence to obtain a prediction confidence value indicating the reliability degree of a prediction algorithm; performing adaptive correction on a first parameter value of a key parameter of the prediction algorithm according to the prediction confidence value to obtain a second parameter value; and regulating and controlling the clear water flow in the second monitoring period by using the prediction algorithm in the second monitoring period based on the second parameter value. According to the invention, the flow of the clear water can be accurately controlled by combining the real-time flow of the mother liquor based on the proportion requirement of the injection liquid formed by the clear water and the mother liquor, so that the actual injection ratio of the injection liquid formed by the clear water and the mother liquor is highly close to the ideal proportion.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of resource collection, and in particular to an injection well water and mother liquor linkage control method. BACKGROUND

[0002] For an oilfield entering a high water cut period, a polymer flooding technology is usually used to promote oil production. The specific process is as follows: a polymer mother liquor meeting the concentration requirement is prepared at a preparation station, is delivered to each injection station by an external delivery pump, and then a proportion of the mother liquor and water is prepared according to the injection concentration and injection amount requirement of each well to perform single-well polymer injection in a development block. In actual production, the injection amount of the mother liquor and clean water of each polymer injection well is different, and therefore, in the mixing process of the single-well mother liquor and clean water, the flow of each is controlled by an actuator.

[0003] When the mother liquor flow is determined, in order to enable the injection liquid formed by the mother liquor and the clean water to maintain a preset proportion, the clean water flow needs to be controlled accurately to match the determined mother liquor flow. Although a prediction algorithm is used in the prior art to regulate the clean water flow to suppress control disturbances generated by various interferences, it is found in application that the control accuracy of the clean water flow of the prediction algorithm is still insufficient. SUMMARY

[0004] The present application aims to provide an injection well water and mother liquor linkage control method to solve the technical problem of low control accuracy of the clean water flow in the prior art.

[0005] In a first aspect, an embodiment of the present application provides an injection well water and mother liquor linkage control method, which comprises the following steps:

[0006] obtaining a first sequence and a second sequence, wherein the first sequence is used to indicate a measured data sequence of the clean water flow in a first monitoring period, and the second sequence is used to indicate a predicted data sequence of the clean water flow in the first monitoring period;

[0007] performing similarity analysis on the sequence trend of the first sequence and the sequence trend of the second sequence to obtain a prediction confidence value, wherein the prediction confidence value is used to indicate the reliability of a prediction algorithm corresponding to the second sequence in the first monitoring period;

[0008] performing adaptive correction on a first parameter value of a key parameter of the prediction algorithm according to the prediction confidence value to obtain a second parameter value, wherein the prediction weight of algorithm input data corresponding to the prediction algorithm and its time interval are in a negative correlation relationship, the time interval is used to indicate the time difference between the data acquisition time of the algorithm input data and the current time, and the key parameter is used to indicate the change rate of the prediction weight;

[0009] Based on the second parameter value, the predicted algorithm is used to predict the clear water flow in a second monitoring period to obtain a clear water flow prediction result, and the clear water flow in the second monitoring period is regulated according to the clear water flow prediction result, the second monitoring period being a next monitoring period of the first monitoring period.

[0010] In some embodiments, the step of performing similarity analysis on the sequence trend of the first sequence and the sequence trend of the second sequence to obtain a prediction confidence value comprises:

[0011] performing trend analysis on the first sequence to obtain a third sequence, and performing trend analysis on the second sequence to obtain a fourth sequence;

[0012] performing element-by-element difference analysis on the third sequence and the fourth sequence to obtain a local difference coefficient;

[0013] performing sequence difference analysis on the third sequence and the fourth sequence to obtain a global difference coefficient;

[0014] obtaining a prediction confidence value according to the local difference coefficient and the global difference coefficient.

[0015] In some embodiments, the step of performing element-by-element difference analysis on the third sequence and the fourth sequence to obtain a local difference coefficient comprises:

[0016] In the third sequence, the difference between each sequence element and the element at the corresponding sequence position in the fourth sequence is analyzed to obtain a plurality of element difference values, wherein the plurality of element difference values correspond one-to-one to the plurality of sequence elements included in the third sequence;

[0017] The plurality of element difference values are respectively normalized to obtain a plurality of element difference normalized values;

[0018] The average of the plurality of element difference normalized values is calculated to obtain the local difference coefficient.

[0019] In some embodiments, the step of performing sequence difference analysis on the third sequence and the fourth sequence to obtain a global difference coefficient comprises:

[0020] The third sequence and the fourth sequence are subjected to nonlinear alignment processing to obtain a sequence deviation;

[0021] The sequence deviation is normalized based on the length of the third sequence to obtain the global difference coefficient.

[0022] In some embodiments, the local difference coefficient and the prediction confidence value are in a negative correlation relationship, and the global difference coefficient and the prediction confidence value are in a negative correlation relationship.

[0023] In some embodiments, the step of obtaining the predicted confidence value based on the local difference coefficient and the global difference coefficient includes:

[0024] The local difference coefficient is numerically transformed to obtain a local similarity coefficient, and the global difference coefficient is numerically transformed to obtain a global similarity coefficient, wherein the local similarity coefficient and the local difference coefficient are negatively correlated, and the global similarity coefficient and the global difference coefficient are negatively correlated.

[0025] The predicted confidence value is obtained by weighting the local similarity coefficient and the global similarity coefficient, wherein the calculation weight of the global similarity coefficient is greater than the calculation weight of the local similarity coefficient.

[0026] In some embodiments, the prediction algorithm is an exponential moving average algorithm, and the key parameter is the smoothing factor of the exponential moving average algorithm.

[0027] In some embodiments, the step of adaptively correcting the first parameter value of the key parameter of the prediction algorithm based on the prediction confidence value to obtain the second parameter value includes:

[0028] The concentration deviation value of the injection solution is obtained during the first monitoring period, wherein the injection solution is formed by mixing water and mother liquor, and the concentration deviation value is used to indicate the degree of deviation between the measured concentration of the injection solution and the ideal ratio during the first monitoring period.

[0029] Based on the predicted confidence value and the concentration deviation value, the first parameter value of the key parameter of the prediction algorithm is adaptively corrected to obtain the second parameter value.

[0030] In some embodiments, the step of obtaining the concentration deviation value of the injected solution within a first monitoring period includes:

[0031] Obtain multiple measured concentrations of the injected fluid during the first monitoring period;

[0032] Calculate the absolute difference between each measured concentration and the ideal ratio to obtain multiple concentration difference values;

[0033] The multiple concentration difference values ​​were normalized to obtain multiple normalized concentration difference values.

[0034] The average value of multiple concentration difference normalization values ​​is determined as the concentration deviation value of the injected liquid in the first monitoring period.

[0035] In some embodiments, the step of adaptively correcting the first parameter value of the key parameter of the prediction algorithm based on the predicted confidence value and the concentration deviation value to obtain the second parameter value includes:

[0036] Based on the predicted confidence value and the concentration deviation value, a parameter correction coefficient is determined, wherein the predicted confidence value and the parameter correction coefficient are negatively correlated, and the concentration deviation value and the parameter correction coefficient are positively correlated;

[0037] The parameter correction value is obtained by multiplying the parameter correction coefficient by the parameter fluctuation value corresponding to the key parameter, wherein the parameter fluctuation value is the difference between the rated maximum parameter value and the rated minimum parameter value of the key parameter.

[0038] The sum of the first parameter value and the parameter correction value is determined as the second parameter value, and the first parameter value is the rated minimum parameter value of the key parameter.

[0039] Secondly, another embodiment of the present invention provides a linkage control system for injection well water chasing mother fluid, the system comprising:

[0040] The data acquisition module is used to acquire a first sequence and a second sequence, wherein the first sequence is used to indicate the measured data sequence of clean water flow within the first monitoring period, and the second sequence is used to indicate the predicted data sequence of clean water flow within the first monitoring period.

[0041] The data analysis module is used to perform similarity analysis on the sequence trend of the first sequence and the sequence trend of the second sequence to obtain a prediction confidence value, wherein the prediction confidence value is used to indicate the reliability of the prediction algorithm corresponding to the second sequence in the first monitoring period;

[0042] The data correction module is used to adaptively correct the first parameter value of the key parameter of the prediction algorithm according to the prediction confidence value to obtain the second parameter value. The prediction weight of the algorithm input data corresponding to the prediction algorithm is negatively correlated with its time interval. The time interval is used to indicate the time difference between the data acquisition time of the algorithm input data and the current time. The key parameter is used to indicate the rate of change of the prediction weight.

[0043] The prediction module is used to predict the clean water flow rate using the prediction algorithm within the second monitoring period based on the second parameter value, obtain the clean water flow rate prediction result, and regulate the clean water flow rate within the second monitoring period according to the clean water flow rate prediction result. The second monitoring period is the next monitoring period after the first monitoring period.

[0044] Thirdly, in another embodiment of the present invention, an electronic device is provided, including a processor, a memory, and a computer program stored in the memory and executable on the processor, wherein the computer program, when executed by the processor, implements the steps of the method described in the first aspect.

[0045] Fourthly, in another embodiment of the present invention, a computer-readable storage medium is provided, on which a computer program is stored, which, when executed by a processor, implements the steps of the method described in the first aspect.

[0046] The present invention has the following beneficial effects:

[0047] By analyzing the similarity of data trends between measured and predicted clean water flow rates within the same monitoring period, the reliability of the prediction algorithm used in the corresponding monitoring period is quantified. Based on this, the parameter values ​​of key parameters of the prediction algorithm are corrected to guide the prediction algorithm to better complete the clean water flow rate prediction work in the next monitoring period. This allows for better control of the clean water flow rate based on the required ratio of clean water and mother liquor to the injection liquid, combined with the real-time flow rate of the mother liquor, so that the actual injection ratio of the clean water and mother liquor is highly close to the ideal ratio. Attached Figure Description

[0048] To more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0049] Figure 1 This is a schematic flowchart of a method for linkage control of injected well water chasing mother fluid provided in an embodiment of the present invention;

[0050] Figure 2 This is a schematic diagram of a dual closed-loop ratio control system provided in an embodiment of the present invention;

[0051] Figure 3 This is a schematic diagram of the structure of an injection well water chasing mother fluid linkage control system provided in an embodiment of the present invention;

[0052] Figure 4 This is a schematic diagram of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0053] To further illustrate the technical means and effects adopted by the present invention to achieve its intended purpose, the following, in conjunction with the accompanying drawings and preferred embodiments, details the specific implementation, structure, features, and effects of the injection well water chasing mother fluid linkage control method proposed according to the present invention. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. Furthermore, specific features, structures, or characteristics in one or more embodiments can be combined in any suitable form.

[0054] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains.

[0055] The specific scheme of the injection well water chasing mother fluid linkage control method provided by the present invention will be described in detail below with reference to the accompanying drawings.

[0056] In one embodiment, the present invention provides a method for coordinated control of injected well water following the mother fluid, such as... Figure 1 As shown, the method includes:

[0057] Step S1: Obtain the first sequence and the second sequence.

[0058] The first sequence is used to indicate the measured data sequence of clean water flow rate within the first monitoring period, and the second sequence is used to indicate the predicted data sequence of clean water flow rate within the first monitoring period.

[0059] It should be understood that the first sequence and the second sequence mentioned above correspond to the same injection well. That is, the first sequence specifically indicates the measured data sequence of the clear water flow rate of the target injection well within the first monitoring period, and the second sequence specifically indicates the predicted data sequence of the clear water flow rate of the target injection well within the first monitoring period. The target injection well can be understood as any injection well using polymer flooding technology.

[0060] The first sequence can be obtained by an electromagnetic flowmeter (with a sampling frequency that meets the Nyquist condition) installed in the clean water pipeline of the target injection well. It should be noted that the clean water flow data collected by the electromagnetic flowmeter will be arranged in an orderly manner according to time sequence, and after mean filtering, it will be divided into time domains according to the corresponding monitoring period to form several measured data sequences. The aforementioned first sequence is one of the several measured data sequences.

[0061] It should also be noted that the number of sequence elements included in the first sequence is the same as the number of sequence elements included in the second sequence, and there is a corresponding relationship, that is, any sequence element in the second sequence can be regarded as the predicted value of the sequence element at the corresponding position in the first sequence.

[0062] In this invention, the monitoring cycle length can be adaptively adjusted according to the actual working conditions. In this invention, the monitoring cycle length is set to 1 minute based on experience.

[0063] The second sequence mentioned above was obtained by processing the measured data sequence of the clear water flow rate in the third monitoring period using a prediction algorithm. The third monitoring period is the monitoring period preceding the first monitoring period.

[0064] Step S2: Perform a similarity analysis on the sequence trend of the first sequence and the sequence trend of the second sequence to obtain the prediction confidence value.

[0065] The prediction confidence value is used to indicate the reliability of the prediction algorithm corresponding to the second sequence during the first monitoring period.

[0066] In this context, the sequence trend can be understood as the information obtained from trend analysis of the corresponding data sequence.

[0067] In actual working conditions, noise (such as air bubbles in pipes) is inevitably mixed in during data acquisition. Since noise has a strong impact on the numerical values ​​of the sequence elements of the first and second sequences, direct analysis of the first and second sequences is severely affected by noise. However, sequence trends aim to extract the dominant change patterns of each sequence element in the corresponding data sequence, which can better suppress the numerical interference caused by noise. Based on this, similarity analysis of the first and second sequences can make the predicted confidence values ​​obtained from the analysis more accurate and reliable.

[0068] Specifically, the step of performing a similarity analysis between the sequence trends of the first sequence and the second sequence to obtain the prediction confidence value includes:

[0069] A third sequence is obtained by performing trend analysis on the first sequence, and a fourth sequence is obtained by performing trend analysis on the second sequence;

[0070] Element-by-element difference analysis was performed on the third sequence and the fourth sequence to obtain local difference coefficients;

[0071] Sequence difference analysis was performed on the third sequence and the fourth sequence to obtain the global difference coefficient;

[0072] The prediction confidence value is obtained based on the local difference coefficient and the global difference coefficient.

[0073] In this invention, the HP (Hodrick Prescott Filter) algorithm is used to complete the above trend analysis operation. However, it should be understood that other trend analysis algorithms can also be used to complete the above trend analysis operation in the application.

[0074] The third sequence contains the same number of sequence elements as the fourth sequence.

[0075] In the above settings, by combining element-wise difference analysis with sequence difference analysis, the difference between measured data and predicted data is comprehensively evaluated by using the individual dimension corresponding to the sequence element and the overall dimension corresponding to the sequence, which makes the determined prediction confidence value more accurate and reliable.

[0076] The aforementioned local difference coefficient is used to indicate the degree of difference between the third and fourth sequences in the individual dimensions corresponding to the sequence elements.

[0077] The global difference coefficient mentioned above is used to indicate the degree of difference between the third and fourth sequences in the overall dimension corresponding to the sequences.

[0078] Specifically, the local difference coefficient is negatively correlated with the prediction confidence value. That is, the greater the difference between the third sequence and the fourth sequence in the individual dimension corresponding to the sequence elements, the more significant the difference between the measured data and the predicted data in the first monitoring period. This indicates that the prediction effect of the prediction algorithm in the first monitoring period is worse, which means that the reliability of the prediction algorithm in the first monitoring period is lower.

[0079] Similarly, the global difference coefficient is negatively correlated with the prediction confidence value. That is, the greater the difference between the third sequence and the fourth sequence in the overall dimension corresponding to the sequence, the more significant the difference between the measured data and the predicted data in the first monitoring period. This indicates that the prediction effect of the prediction algorithm in the first monitoring period is worse, and that the reliability of the prediction algorithm in the first monitoring period is lower.

[0080] Further, the step of performing element-by-element difference analysis on the third sequence and the fourth sequence to obtain local difference coefficients includes:

[0081] In the third sequence, the difference between each sequence element and its corresponding sequence position in the fourth sequence is analyzed to obtain multiple element difference values, wherein the multiple element difference values ​​correspond one-to-one with the multiple sequence elements included in the third sequence;

[0082] The difference values ​​of the multiple elements are normalized to obtain the normalized difference values ​​of the multiple elements.

[0083] The average of the normalized differences of the multiple elements is calculated to obtain the local difference coefficient.

[0084] In this invention, the absolute difference between each sequence element in the third sequence and its corresponding element in the fourth sequence is defined as the element difference value.

[0085] For example, the element difference value corresponding to the i-th sequence element in the third sequence It can be represented as:

[0086]

[0087] in, This represents the i-th sequence element in the third sequence. This represents the i-th sequence element in the fourth sequence.

[0088] In this invention, normalization is intended to map the numerical values ​​of data to the 0-1 range, so as to facilitate the merging of data obtained by different methods, and to retain the characteristics of the data obtained by each method while eliminating the dimensional differences between different data.

[0089] In one example, the ratio of the element difference value to the difference reference value can be determined as the corresponding element difference normalization value, where the difference reference value is the difference between the maximum value and the minimum value in the third sequence.

[0090] Further, the step of performing sequence difference analysis on the third sequence and the fourth sequence to obtain the global difference coefficient includes:

[0091] The third sequence and the fourth sequence are non-linearly aligned to obtain the sequence deviation;

[0092] The sequence deviation is normalized based on the length of the third sequence to obtain the global difference coefficient.

[0093] In the above setup, a non-linear alignment process is used to compare the alignment difficulty between the third and fourth sequences from the perspective of the entire sequence, thereby quantifying the overall sequence deviation between the third and fourth sequences.

[0094] In one example, the non-linear alignment between the third and fourth sequences can be achieved using the Dynamic Time Warping (DTW) algorithm. In this example, the sequence deviation is the DTW distance between the third and fourth sequences.

[0095] For example, the global difference coefficient It can be represented as:

[0096]

[0097] in, This represents the DTW distance between the third and fourth sequences. Indicates the third sequence, Indicates the fourth sequence, This represents the total number of sequence elements included in the third sequence (i.e., the length of the third sequence). This represents the maximum value in the third sequence. This represents the minimum value in the third sequence. This is a constant parameter to prevent the result from being meaningless if the denominator is 0. The default value range is [0.001, 1], and the value in this example is 0.01.

[0098] In this example, based on the above settings, while retaining the characteristics of the DTW distance used to quantify the overall sequence difference between the third and fourth sequences, the influence of the DTW distance caused by the fluctuation of sequence length and sequence amplitude is eliminated to adapt to the normalization measures of the local difference coefficient in the calculation process, thereby eliminating the numerical deviation between the local difference coefficient and the global difference coefficient when summarizing, making the obtained prediction confidence value more accurate and reliable.

[0099] Furthermore, the step of obtaining the prediction confidence value based on the local difference coefficient and the global difference coefficient includes:

[0100] The local difference coefficient is numerically transformed to obtain a local similarity coefficient, and the global difference coefficient is numerically transformed to obtain a global similarity coefficient, wherein the local similarity coefficient and the local difference coefficient are negatively correlated, and the global similarity coefficient and the global difference coefficient are negatively correlated.

[0101] The predicted confidence value is obtained by weighting the local similarity coefficient and the global similarity coefficient, wherein the calculation weight of the global similarity coefficient is greater than the calculation weight of the local similarity coefficient.

[0102] For example, the global similarity coefficient It can be represented as:

[0103]

[0104] Local similarity coefficient It can be represented as:

[0105]

[0106] Predicted confidence value It can be represented as:

[0107]

[0108] in, Represents the local difference coefficient. This represents the local difference sensitivity factor (used to control the conversion rate between the local difference coefficient and the local similarity coefficient). This represents the global difference sensitivity factor (used to control the conversion rate between the global difference coefficient and the global similarity coefficient). This represents an exponential function with base e. The weights used to calculate the global similarity coefficient are... The weights used to calculate the local similarity coefficient are... and Both are integers and their sum is 1.

[0109] In the above settings, the calculation weight of the global similarity coefficient is set to be greater than that of the local similarity coefficient. This is to adapt to the situation in the sequence difference assessment process where the difference in the overall dimension of the sequence is more important (compared to the difference in the individual elements of the sequence). This ensures that the calculation of the predicted confidence value can take more into account the similarity between the overall sequences, which makes the calculated predicted confidence value more accurate and reliable.

[0110] Step S3: Adaptively adjust the first parameter value of the key parameter of the prediction algorithm according to the prediction confidence value to obtain the second parameter value.

[0111] The prediction weights of the algorithm input data corresponding to the prediction algorithm are negatively correlated with their time interval. The time interval is used to indicate the time difference between the data acquisition time of the algorithm input data and the current time. The key parameter is used to indicate the rate of change of the prediction weights.

[0112] Specifically, the prediction algorithm in this invention is the exponential moving average (EMA) algorithm, and the key parameter is the smoothing factor of the exponential moving average algorithm.

[0113] It should be noted that the data smoothing function of the exponential moving average algorithm is specifically used for prediction in this invention. By obtaining the measured flow rate of clean water in the previous monitoring period, the exponential moving average algorithm is used to smooth the data to obtain predictive data for guiding the control of clean water flow rate in the next monitoring period.

[0114] The step of adaptively correcting the first parameter value of the key parameter of the prediction algorithm based on the prediction confidence value to obtain the second parameter value includes:

[0115] The concentration deviation value of the injection solution is obtained during the first monitoring period, wherein the injection solution is formed by mixing water and mother liquor, and the concentration deviation value is used to indicate the degree of deviation between the measured concentration of the injection solution and the ideal ratio during the first monitoring period.

[0116] Based on the predicted confidence value and the concentration deviation value, the first parameter value of the key parameter of the prediction algorithm is adaptively corrected to obtain the second parameter value.

[0117] In this invention, in addition to analyzing the predictive reliability of the prediction algorithm, the actual injection ratio (reflected by measured concentration) of the injection liquid obtained by mixing clean water and mother liquor is further analyzed to determine the degree of deviation between the actual injection ratio and the ideal ratio. Based on the actual application requirements (to make the actual injection ratio of the injection liquid approach the ideal ratio in the long term), corresponding realistic constraints are introduced to ensure the accuracy and practicality of the corrected second parameter value.

[0118] The ideal ratio can be understood as the concentration of the injection fluid to be injected into the target injection well in order to achieve the goal of the target injection well having an oil production efficiency exceeding a preset efficiency threshold (or having the highest oil production efficiency).

[0119] Specifically, the steps for obtaining the concentration deviation value of the injected solution during the first monitoring period include:

[0120] Obtain multiple measured concentrations of the injected fluid during the first monitoring period;

[0121] Calculate the absolute difference between each measured concentration and the ideal ratio to obtain multiple concentration difference values;

[0122] The multiple concentration difference values ​​were normalized to obtain multiple normalized concentration difference values.

[0123] The average value of multiple concentration difference normalization values ​​is determined as the concentration deviation value of the injected liquid in the first monitoring period.

[0124] The above-mentioned measured concentrations correspond one-to-one with multiple monitoring times within the first monitoring cycle. The measured concentrations are specifically the concentration data collected by the concentration detection sensor (located in the injection liquid transport pipeline) at the corresponding monitoring time.

[0125] In one example, the ratio of the concentration difference value to the concentration deviation reference value can be determined as the corresponding concentration difference normalization value. In this example, the concentration deviation reference value is used to indicate the maximum deviation between the measured concentration of the injected solution and the ideal ratio. It can be set based on experience or determined based on the maximum absolute difference between the measured concentration of the injected solution and the ideal ratio detected in historical situations.

[0126] Specifically, the step of adaptively correcting the first parameter value of the key parameter of the prediction algorithm based on the predicted confidence value and the concentration deviation value to obtain the second parameter value includes:

[0127] Based on the predicted confidence value and the concentration deviation value, a parameter correction coefficient is determined, wherein the predicted confidence value and the parameter correction coefficient are negatively correlated, and the concentration deviation value and the parameter correction coefficient are positively correlated;

[0128] The parameter correction value is obtained by multiplying the parameter correction coefficient by the parameter fluctuation value corresponding to the key parameter, wherein the parameter fluctuation value is the difference between the rated maximum parameter value and the rated minimum parameter value of the key parameter.

[0129] The sum of the first parameter value and the parameter correction value is determined as the second parameter value, and the first parameter value is the rated minimum parameter value of the key parameter.

[0130] A higher prediction confidence value indicates that the prediction algorithm is more reliable in the first monitoring period, which means that the change in clean water flow is relatively gentle. Therefore, a smaller smoothing factor is needed to ensure the smooth processing of the prediction algorithm so that a more accurate clean water flow prediction can be maintained in the next monitoring period (i.e., the second monitoring period).

[0131] The higher the concentration deviation value, the worse the concentration control effect of the injected liquid is in the first monitoring period (e.g., the mother liquor pump speed adjustment causes fluctuations in the mother liquor flow rate, while the clean water flow rate is lagging behind in tracking the fluctuations in the mother liquor). When a relatively significant concentration deviation has been detected, it is more necessary to use a larger smoothing factor to improve the prediction algorithm's ability to track the actual flow rate changes so as to reduce the concentration deviation in the next monitoring period (i.e., the second monitoring period).

[0132] For example, parameter correction coefficient It can be represented as:

[0133]

[0134] in, This indicates the concentration deviation value.

[0135] The second parameter value can be Represented as:

[0136]

[0137] in, This represents the minimum nominal value of a key parameter. This represents the rated maximum value of the key parameter. This represents the sensitivity factor (used to adjust the degree of influence of the parameter correction coefficient on the value of the second parameter). It is a positive number.

[0138] The aforementioned minimum limit parameter value can be understood as the minimum parameter value that the key parameter can be set to. Similarly, the maximum limit parameter value can be understood as the maximum parameter value that the key parameter can be set to.

[0139] Step S4: Based on the second parameter value, use the prediction algorithm to predict the clean water flow rate in the second monitoring period, obtain the clean water flow rate prediction result, and adjust the clean water flow rate in the second monitoring period according to the clean water flow rate prediction result.

[0140] The second monitoring cycle is the next monitoring cycle following the first monitoring cycle.

[0141] The above-mentioned clear water flow prediction results include at least the predicted data sequence of clear water flow in the second monitoring period. In this case, regulating the clear water flow in the second monitoring period based on the clear water flow prediction results should be understood as: based on the predicted data sequence of clear water flow in the second monitoring period, managing the opening degree of the clear water valve in the second monitoring period.

[0142] It should be noted that the method described in this invention (for clean water flow control) is applied to a dual closed-loop ratio control system, and the corresponding schematic diagram of this system can be seen as follows. Figure 2 As shown, the mother liquor controller, mother liquor actuator, and mother liquor flow meter constitute the mother liquor control loop, and the clean water controller, clean water actuator, and clean water flow meter constitute the clean water control loop. The ratio is used as a ratio meter.

[0143] Among them, the mother liquor control circuit is the main control circuit, and the clean water control circuit is the slave control circuit.

[0144] In a dual-loop ratio control system, each component interacts with other components through I / O modules (including but not limited to digital modules, analog modules, and serial communication modules).

[0145] In the dual closed-loop ratio control system, the input quantities of mother liquor and clean water (theoretical values, set based on actual working conditions) are input. Through the controller's calculation, the set flow rate of mother liquor can be obtained (based on which the output of mother liquor is controlled). Based on the average feedback flow rate of mother liquor (actual flow rate of mother liquor) and the mixing ratio, the set flow rate of clean water is calculated (based on which the output of clean water is controlled).

[0146] In practical applications, when the mother liquor control loop experiences fluctuations in feedback flow due to external interference, the mother liquor actuator will implement closed-loop control of the mother liquor flow rate. Simultaneously, the set flow rate of clean water that matches the mix ratio will be calculated based on the mix ratio and the mother liquor feedback flow rate, and the clean water loop will be controlled accordingly. Through the combined action of the mother liquor loop and the clean water loop, polymer injection in a single well will proceed according to the mix ratio requirements.

[0147] It should be noted that in the above closed-loop control process, when the flow rate of the clean water loop fluctuates due to external disturbances, the closed-loop adjustment will be performed by the PID control of the clean water actuator itself (to make the actual flow rate of clean water as close as possible to the set flow rate of clean water), which will not affect the mother liquor control loop. The processing flow of the clean water actuator for closed-loop adjustment can be found in the relevant description of the aforementioned method embodiments, and will not be repeated here to avoid repetition.

[0148] In summary, when applying the method described in this invention for the linkage control of water-following mother liquor, after determining the actual injection flow rate of the mother liquor, the ideal flow rate of clean water can be determined accordingly based on the ideal ratio. The value of the smoothing factor is dynamically adjusted according to the change in clean water control noise to fully suppress noise interference in the clean water flow control process, ensuring the control accuracy and timeliness of the clean water flow rate, so that the actual injection flow rate of clean water matches the actual injection flow rate of the mother liquor. This keeps the deviation between the actual injection ratio and the ideal ratio of the injected fluid at a low level for a long time, ensuring that the injection concentration of the injected fluid during the high water cut period is consistently qualified, contributing to the efficient, green, and intelligent exploitation of oilfields, and ultimately improving the exploitation efficiency of the corresponding oilfields.

[0149] Taking 216 wells in four injection stations across four blocks (West 2 of Xing 10, West 1 of Xing 11, and West 1 of Xing 11) in Daqing Oilfield as an example, the application of the injection well water-mother fluid linkage control method revealed that before the linkage control was implemented, the mother fluid actuator was already at 100%, but the mother fluid feedback value (actual mother fluid flow rate) still did not reach the set value, while the clean water feedback value was basically consistent with the clean water set value. This resulted in a significant deviation between the actual injection ratio and the ideal ratio. After the linkage control was implemented, the clean water set flow rate was automatically lowered based on the ratio and the average mother fluid feedback flow rate. As the clean water feedback flow rate decreased, the mother fluid feedback flow rate increased accordingly, and the injection ratio (actual injection concentration) gradually approached the ratio (ideal injection concentration) and remained stable over a long period. After the linkage control stabilized, compared to before implementation, the clean water feedback flow rate decreased, the mother fluid feedback flow rate increased, and the difference between the injection ratio and the ratio was less than 3%, meeting the ratio requirements.

[0150] In another embodiment, the present invention provides an injection well water chasing mother fluid linkage control system 300, such as... Figure 3 As shown, the system 300 includes:

[0151] The data acquisition module 301 is used to acquire a first sequence and a second sequence, wherein the first sequence is used to indicate the measured data sequence of clean water flow within the first monitoring period, and the second sequence is used to indicate the predicted data sequence of clean water flow within the first monitoring period.

[0152] The data analysis module 302 is used to perform similarity analysis on the sequence trend of the first sequence and the sequence trend of the second sequence to obtain a prediction confidence value, wherein the prediction confidence value is used to indicate the reliability of the prediction algorithm corresponding to the second sequence in the first monitoring period;

[0153] Data correction module 303 is used to adaptively correct the first parameter value of the key parameter of the prediction algorithm according to the prediction confidence value to obtain the second parameter value. The prediction weight of the algorithm input data corresponding to the prediction algorithm is negatively correlated with its time interval. The time interval is used to indicate the time difference between the data acquisition time of the algorithm input data and the current time. The key parameter is used to indicate the rate of change of the prediction weight.

[0154] The prediction module 304 is used to predict the clear water flow rate using the prediction algorithm within the second monitoring period based on the second parameter value, obtain the clear water flow rate prediction result, and regulate the clear water flow rate within the second monitoring period according to the clear water flow rate prediction result, wherein the second monitoring period is the next monitoring period after the first monitoring period.

[0155] It should be noted that the system provided in the above embodiments is only an example of the division of the above functional modules. In practical applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the computer equipment can be divided into different functional modules to complete all or part of the functions described above. In addition, the injection well water chasing mother liquid linkage control system and the injection well water chasing mother liquid linkage control method embodiment provided in the above embodiments belong to the same concept, and the specific implementation process can be found in the method embodiment, which will not be repeated here.

[0156] This invention also provides an electronic device. Please refer to [link to relevant documentation]. Figure 4 The electronic device may include a processor 401, a memory 402, and a program 4021 stored in the memory 402 and executable on the processor 401.

[0157] When program 4021 is executed by processor 401, it can achieve the following: Figure 1 Any steps in the corresponding method embodiments and the achievement of the same beneficial effects will not be repeated here.

[0158] Those skilled in the art will understand that all or part of the steps of the methods described in the above embodiments can be implemented by hardware related to program instructions, and the program can be stored in a readable medium.

[0159] This invention also provides a readable storage medium storing a computer program, which, when executed by a processor, can perform the above-described functions. Figure 1 Any step in the corresponding method embodiment can achieve the same technical effect, and will not be repeated here to avoid repetition.

[0160] The computer-readable storage medium of this invention can be any combination of one or more computer-readable media. The computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. For example, a computer-readable storage medium can be an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of computer-readable storage media (a non-exhaustive list) include: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this document, a computer-readable storage medium can be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0161] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media may also be any computer-readable medium other than computer-readable storage media, capable of sending, propagating, or transmitting programs for use by or in connection with an instruction execution system, apparatus, or device.

[0162] The program code contained on the storage medium can be transmitted using any suitable medium, including but not limited to wireless, wire, optical fiber, RF, etc., or any suitable combination thereof.

[0163] Computer program code for performing the operations of this invention can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as conventional procedural programming languages ​​such as "C" or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or terminal. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0164] This invention also provides a computer program product that, when run on a computer, causes the computer to perform the aforementioned steps to achieve the injection well water chasing mother fluid linkage control method provided in the above embodiments.

[0165] It should be noted that the order of the above embodiments of the present invention is merely for descriptive purposes and does not represent the superiority or inferiority of the embodiments. The processes depicted in the accompanying drawings do not necessarily require a specific or sequential order to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0166] The various embodiments in this specification are described in a progressive manner. The same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on describing the differences from other embodiments.

Claims

1. A method for injection well water mother liquor linkage control, characterized in that, The method comprises: obtaining a first sequence and a second sequence, wherein the first sequence is used to indicate a measured data sequence of clean water flow in a first monitoring period, and the second sequence is used to indicate a predicted data sequence of clean water flow in the first monitoring period; performing similarity analysis on sequence trends of the first sequence and the second sequence to obtain a prediction confidence value, wherein the prediction confidence value is used to indicate a reliability degree of a prediction algorithm corresponding to the second sequence in the first monitoring period; performing adaptive correction on a first parameter value of a key parameter of the prediction algorithm according to the prediction confidence value to obtain a second parameter value, wherein a prediction weight of algorithm input data corresponding to the prediction algorithm is in a negative correlation relationship with a time interval thereof, the time interval is used to indicate a time difference between a data acquisition time of the algorithm input data and a current time, and the key parameter is used to indicate a change rate of the prediction weight; performing clean water flow prediction in a second monitoring period based on the second parameter value using the prediction algorithm to obtain a clean water flow prediction result, and performing regulation and control on the clean water flow in the second monitoring period according to the clean water flow prediction result, the second monitoring period being a next monitoring period of the first monitoring period.

2. The injection well water tracer mother liquor linkage control method of claim 1, wherein, The step of performing similarity analysis on sequence trends of the first sequence and the second sequence to obtain a prediction confidence value comprises: performing trend analysis on the first sequence to obtain a third sequence, and performing trend analysis on the second sequence to obtain a fourth sequence; performing element-by-element difference analysis on the third sequence and the fourth sequence to obtain a local difference coefficient; performing sequence difference analysis on the third sequence and the fourth sequence to obtain a global difference coefficient; obtaining the prediction confidence value according to the local difference coefficient and the global difference coefficient.

3. The injection well water tracer mother liquor linkage control method of claim 2, wherein, The step of performing element-by-element difference analysis on the third sequence and the fourth sequence to obtain a local difference coefficient comprises: in the third sequence, analyzing a difference between each sequence element and an element at a corresponding sequence position thereof in the fourth sequence to obtain a plurality of element difference values, wherein the plurality of element difference values one-to-one correspond to a plurality of sequence elements included in the third sequence; performing normalization processing on the plurality of element difference values respectively to obtain a plurality of element difference normalized values; calculating an average value of the plurality of element difference normalized values to obtain the local difference coefficient.

4. The injection well water tracer mother liquor linkage control method of claim 2, wherein, The step of performing sequence difference analysis on the third sequence and the fourth sequence to obtain a global difference coefficient comprises: performing nonlinear alignment processing on the third sequence and the fourth sequence to obtain a sequence deviation; performing normalization processing on the sequence deviation based on a length of the third sequence to obtain the global difference coefficient.

5. The injection well water tracer mother liquor linkage control method of claim 2, wherein, The local difference coefficient is in a negative correlation relationship with the prediction confidence value, and the global difference coefficient is in a negative correlation relationship with the prediction confidence value.

6. The injection well water tracer mother liquor linkage control method of claim 5, wherein, The step of obtaining the prediction confidence value according to the local difference coefficient and the global difference coefficient comprises: The local difference coefficient is converted into a local similarity coefficient, and the global difference coefficient is converted into a global similarity coefficient, wherein the local similarity coefficient is negatively correlated with the local difference coefficient, and the global similarity coefficient is negatively correlated with the global difference coefficient. The local similarity coefficient and the global similarity coefficient are weighted to obtain the prediction confidence value, wherein the calculation weight of the global similarity coefficient is greater than the calculation weight of the local similarity coefficient.

7. The injection well water tracer mother liquor linkage control method of claim 1, wherein, The prediction algorithm is an exponential moving average algorithm, and the key parameter is a smoothing factor of the exponential moving average algorithm.

8. The injection well water tracer mother liquor linkage control method of claim 7, wherein, The step of adaptively correcting a first parameter value of a key parameter of the prediction algorithm according to the prediction confidence value to obtain a second parameter value comprises: obtaining a concentration deviation value of the injection liquid in the first monitoring period, wherein the injection liquid is formed by mixing water and a mother liquid, and the concentration deviation value is used to indicate the deviation degree between the measured concentration and the ideal ratio of the injection liquid in the first monitoring period; adaptively correcting the first parameter value of the key parameter of the prediction algorithm according to the prediction confidence value and the concentration deviation value to obtain the second parameter value.

9. The injection well water tracer mother liquor linkage control method of claim 8, wherein, The step of obtaining the concentration deviation value of the injection liquid in the first monitoring period comprises: obtaining a plurality of measured concentrations of the injection liquid in the first monitoring period; calculating the absolute difference value between each measured concentration and the ideal ratio to obtain a plurality of concentration difference values; normalizing the plurality of concentration difference values respectively to obtain a plurality of concentration difference normalized values; determining the average value of the plurality of concentration difference normalized values as the concentration deviation value of the injection liquid in the first monitoring period.

10. The injection well water follow-up solution linkage control method according to claim 9, characterized by, The step of adaptively correcting the first parameter value of the key parameter of the prediction algorithm according to the prediction confidence value and the concentration deviation value to obtain the second parameter value comprises: determining a parameter correction coefficient according to the prediction confidence value and the concentration deviation value, wherein the prediction confidence value is negatively correlated with the parameter correction coefficient, and the concentration deviation value is positively correlated with the parameter correction coefficient; calculating the product of the parameter correction coefficient and a parameter fluctuation value corresponding to the key parameter to obtain a parameter correction value, wherein the parameter fluctuation value is the difference between a rated maximum parameter value and a rated minimum parameter value of the key parameter; determining the sum of the first parameter value and the parameter correction value as the second parameter value, wherein the first parameter value is the rated minimum parameter value of the key parameter.

Images