Sealing grade judgment system and method for transmission unit of stratum isolation valve

Abstract

The invention provides a system and method for judging the sealing grade of a transmission unit of a stratum isolation valve, and the method comprises the steps: obtaining an original data set of an underground sealing state, and carrying out the preprocessing of the original data set; constructing a time sequence weighted regression model based on historical data, evaluating the current sealing grade, training the time sequence weighted regression model by using the training set, constructing a dynamic regression model in combination with the current sealing grade, the corresponding sealing grade of the previous moment and the change of the environment variable, and generating a predicted sealing grade of the next moment; according to the predicted changes of the sealing grade and the environment variable at the next moment, through a controllable deformation mechanism, the sealing adjustment deformation amount of the equipment is generated, and the sealing system is dynamically adjusted; and according to the difference between the sealing grade at the next moment and the current sealing grade, generating an optimized sliding sleeve adjustment demand by combining the change of the environment variable and the sealing adjustment deformation of the equipment.

Description

Technical Field

[0001] The present invention belongs to the downhole field, and particularly relates to a sealing level determination system and method for a formation isolation valve drive unit. Background Art

[0002] In the drilling, cementing, and completion operations of oil and gas fields, the formation isolation valve is an important tool for isolating different formation pressures, controlling fluid flow, and optimizing subsequent stimulation operations. Currently, formation isolation valves usually use packers, cementing sleeves, ball setting, etc. to achieve sealing and fluid control. However, as oil and gas field development advances towards deeper, higher temperature and pressure environments, and complex formations, existing formation isolation valves still have many technical problems in terms of sealing stability, sealing level assessment, and construction reliability.

[0003] Firstly, most existing packers use fixed-shaped elastic sealing structures, such as rubber sealing elements. In the high-temperature and high-pressure downhole environment, rubber materials are prone to a decrease in sealing ability due to aging, mechanical fatigue, uneven thermal expansion, etc.

[0004] In addition, the wellbore often has characteristics such as irregular shape, microfractures, and pores. Traditional fixed sealing structures cannot fully adapt, and it is easy to form micro-leakage channels, resulting in the failure of the packer seal.

[0005] Secondly, the sealing structure of the cementing sleeve is prone to being affected by long-term annulus pressure changes after cementing. The sealing elements of the sleeve may fail due to stress relaxation, material creep, etc., affecting the safety of downhole operations.

[0006] In the prior art, the determination of the sealing level usually relies on post-cementing pressure tests or fluid leakage tests, but this method can only provide static measurement results and cannot real-time monitor the sealing state during actual production, making it difficult to detect micro-leakage or sealing performance degradation in a timely manner, thereby increasing the risk and cost of subsequent operations.

[0007] In addition, during the cementing process, the sealing structure of the cementing sleeve may be abnormal due to the influence of the complex downhole pressure environment. Cement slurry may flow back along the micro-channels, resulting in a decrease in cementing quality and further affecting the sealing effect of the formation isolation valve. Existing cementing sleeves usually rely on improving mechanical precision or increasing the thickness of the sealing material to reduce the risk of cement backflow, but these measures cannot fundamentally solve problems such as poor sealing adaptability, difficulty in real-time determination of the sealing level, and cement backflow. In addition, during the cementing construction process, the slip switch tool and the slip sleeve usually adopt an interference fit structure, and jamming may occur during the switching operation, resulting in the tool being unable to be recovered smoothly or the sleeve being unable to be switched normally, affecting the entire construction process.

[0008] Therefore, there are still significant technical challenges in the existing formation isolation valves in terms of long-term sealing stability, real-time assessment of the sealing state, optimization of the cementing sleeve sealing structure, and reliability of the sleeve switching. There is an urgent need for a technical solution that can dynamically adapt to the complex downhole environment, improve the sealing level, and achieve intelligent assessment of the sealing state to enhance the sealing reliability and construction safety of the formation isolation valve. Summary of the Invention

[0009] The object of the present invention is to propose a sealing level determination system and method for the drive unit of a formation isolation valve. By introducing a controllable deformation sealing structure and a multi-modal intelligent sealing monitoring system, active optimization and real-time assessment of the sealing state of the formation isolation valve are realized.

[0010] To solve the above technical problems, an embodiment of the present invention provides a method for determining the sealing level of the drive unit of a formation isolation valve. The method includes:

[0011] Obtain the original data set of the downhole sealing state, preprocess the original data set, and divide the preprocessed data set into a training set and a validation set using the time period division method;

[0012] Build a time series weighted regression model based on historical data, evaluate the current sealing level, train the time series weighted regression model using the training set, and build a dynamic regression model by combining the current sealing level, the corresponding previous sealing level, and the changes in environmental variables to generate the predicted sealing level at the next moment;

[0013] According to the predicted sealing level at the next moment and the changes in environmental variables, generate the sealing adjustment deformation amount of the device through a controllable deformation mechanism, and dynamically adjust the sealing system;

[0014] According to the difference between the sealing level at the next moment and the current sealing level, combined with the changes in environmental variables and the sealing adjustment deformation amount of the device, generate the optimized sleeve adjustment requirements to maintain the sealing stability; the sleeve adjustment requirements include: the position of the sleeve and the sealing pressure.

[0015] As a preferred solution, the original data set includes: sensor data, position data, and dynamic sensing data; the preprocessing of the original data set includes: detecting outliers by calculating the local density difference between data points and their neighbor points; for the missing values at a certain moment, estimating and filling the values according to the data of the previous and next points by linear interpolation; normalization processing and standardization processing; weighted smoothing processing.

[0016] As a preferred solution, the time series weighted regression model is expressed as:

[0017]

[0018] Wherein, is the sealing level of the device at time ; is the feature output by the th sensor at time ; is the feature output by the th environmental variable at time ; and are regression coefficients to be learned, used to quantify the influence of different sensors and environmental variables on the sealing level; is the dynamic correction term coefficient, used to adjust the influence of changes in sensor data on the sealing level evaluation; is the weighting factor, indicating the influence degree of different sensors on the sealing level; represents the change amount between the th sensor at time and ;

[0019] Wherein, the training set is used to optimize the regression coefficients , and the weighting factor , and minimize the error between the predicted sealing level and the actual observed value; the least squares method is used as the loss function to train the time series weighted regression model;

[0020] The time series weighted regression model is evaluated on the validation set to test its accuracy and generalization ability.

[0021] As a preferred solution, the dynamic regression model is constructed as follows:

[0022] Obtain the sealing level of the device at time ;

[0023] Respectively weight the error between the sealing level of the device at time and the sealing level of the device at time , the influence of sensor data on the trend, and the change amount of environmental variables;

[0024] According to the sealing level of the device at time and the weighted output, obtain the predicted sealing level at the next moment.

[0025] As a preferred solution, the controllable deformation mechanism is used to generate the sealing adjustment deformation amount of the device, which is realized by the following formula:

[0026]

[0027] Wherein, represents the time The local controllable deformation amount; is a system constant representing the deformation amount under the reference state of the device; is the th sensor reading at time , which is used to reflect the current working state of the device; is the th environmental variable reading at time , which is used to describe the impact of the environment on the device; is an adjustment coefficient representing the degree of influence of the change in the sealing level on the deformation amount; is the change amount of the sealing level at the current moment , which reflects the increase or decrease of the sealing level.

[0028] As a preferred solution, dynamically adjusting the sealing system includes:

[0029] Calculating the local controllable deformation amount of each local component through a dynamic regression model according to the sensor data and environmental variables of the device, combined with the change amount of the sealing level;

[0030] Adjusting each local sealing component using an accurate control system; wherein, the adjustment amplitude is determined by the local controllable deformation amount, and the local controllable deformation amount is the telescopic amount of the local sealing strip or the displacement amount of the sealing cover;

[0031] After each adjustment, collect a new sealing level value through the sensor, input it into the time series weighted regression model again, update the sealing level prediction in real time, and continue to adjust the sealing system according to the change.

[0032] As a preferred solution, the accurate control system includes a servo drive device.

[0033] As a preferred solution, the optimized adjustment requirement of the slip sleeve is optimized based on the sealing adjustment deformation amount of the device, and at the same time, based on the constraint regularization of the sealing deformation amount, a penalty is imposed on the deformation amount exceeding a certain threshold, and finally the slip sleeve adjustment amount is obtained.

[0034] As a preferred solution, according to the slip sleeve adjustment amount, adjusting the position and sealing pressure of the slip sleeve through a control system includes:

[0035] Performing precise displacement adjustment through the servo drive system according to the slip sleeve adjustment amount to ensure that the slip sleeve position is within the optimized range;

[0036] At the same time, dynamically adjusting the sealing pressure of the slip sleeve according to the adjustment amount;

[0037] After each adjustment, the new sealing state is fed back in real time through the sensor, and the new adjustment requirement is calculated for iterative optimization.

[0038] Based on the above embodiments, another embodiment of the present invention provides a sealing level determination system for a formation isolation valve drive unit, which is characterized in that the system includes:

[0039] A data set acquisition module, configured to obtain an original data set of the downhole sealing state, preprocess the original data set, and divide the preprocessed data set into a training set and a validation set by using a time period division method;

[0040] A sealing level determination and prediction module, configured to construct a time series weighted regression model based on historical data, evaluate the current sealing level, train the time series weighted regression model using the training set, combine the current sealing level, the corresponding previous sealing level, and changes in environmental variables to construct a dynamic regression model, and generate a predicted next moment sealing level;

[0041] A sealing adjustment module, configured to generate a sealing adjustment deformation amount of the device through a controllable deformation mechanism according to the predicted next moment sealing level and changes in environmental variables, and dynamically adjust the sealing system;

[0042] A sealing optimization module, configured to generate an optimized sliding sleeve adjustment requirement according to the difference between the next moment sealing level and the current sealing level, combine changes in environmental variables and the sealing adjustment deformation amount of the device, and maintain the stability of the seal; the sliding sleeve adjustment requirement includes: the position of the sliding sleeve and the sealing pressure

[0043] The beneficial technical effects of the present invention are at least as follows:

[0044] First of all, the present invention adopts a locally controllable deformation sealing structure, integrating a shape memory alloy sealing ring and a hydraulic fine-tuning unit at the sealing parts of the packer and the cementing sliding sleeve, enabling the sealing element to actively adjust the sealing state according to changes in the downhole environment. The shape memory alloy sealing ring can deform with changes in temperature and pressure, making the sealing structure closely fit the wellbore wall. Even if the wellbore wall is irregular, it can still form an efficient seal. At the same time, the hydraulic fine-tuning unit can actively adjust the sealing pressure during seal degradation, extending the seal life.

[0045] Secondly, the present invention integrates a multi-modal seal monitoring system. By arranging fiber Bragg grating sensors and ultrasonic seal detection devices at the sealing parts, the sealing state is monitored in real time, and the sealing level is determined in combination with an artificial intelligence analysis model. The fiber Bragg grating sensors can monitor the stress state and deformation of the packer, while the ultrasonic seal detection system can identify the contact integrity of the sealing surface and accurately judge whether there are micro-leakage channels. The artificial intelligence analysis model automatically classifies the sealing level based on the seal monitoring data and triggers a seal optimization strategy when the seal state deteriorates, improving the reliability of the seal.

[0046] In addition, the present invention optimizes the sealing structure of the cementing sliding sleeve and adopts a hydraulic locking mechanism to make the sliding sleeve enter an irreversible sealing state after closing, thereby preventing cement backflow and improving the cementing quality. At the same time, the present invention improves the structure of the sliding sleeve switching tool and adopts an adaptive sliding sealing mechanism to reduce the frictional resistance during the switching process, reduce the risk of jamming, and improve the construction success rate. Through the adaptive sealing structure and intelligent sealing determination method of the present invention, the long-term sealing stability of the formation isolation valve can be effectively improved, the sealing level can be evaluated in real time, the sealing effect of the cementing sliding sleeve can be optimized, and the safety of the sliding sleeve operation can be improved, which is applicable to the oil and gas field development operations of deep wells, high-temperature and high-pressure wells, and complex formation wells. Description of the Drawings

[0047] The present invention will be further described with reference to the accompanying drawings. However, the embodiments in the drawings do not constitute any limitation to the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained according to the following drawings.

[0048] Figure 1 It is a flowchart of a method for determining the sealing level of a drive unit of a formation isolation valve according to the present invention. Detailed Embodiments

[0049] To make the objectives, technical solutions, and advantages of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application. Apparently, the described embodiments are some, but not all, of the embodiments of the present application. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present application without creative efforts shall fall within the scope of protection of the present application.

[0050] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those of ordinary skill in the technical field to which this application belongs; the terms used herein are only for the purpose of describing specific embodiments and are not intended to limit this application; the terms "including" and "having" and any variations thereof in the specification and claims of this application and the above description of the drawings are intended to cover non-exclusive inclusion.

[0051] In the description of the embodiments of this application, technical terms such as "first" and "second" are only used to distinguish different objects and cannot be understood as indicating or implying relative importance or implicitly indicating the quantity, specific order, or primary-secondary relationship of the indicated technical features. In the description of the embodiments of this application, "a plurality" means two or more unless otherwise specifically defined.

[0052] Reference to "embodiment" in this application means that the specific features, structures, or characteristics described in connection with the embodiment can be included in at least one embodiment of this application. The phrase appears at various positions in the specification and does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment mutually exclusive with other embodiments. Those skilled in the art will explicitly and implicitly understand that the embodiments described herein can be combined with other embodiments.

[0053] In the description of the embodiments of this application, the term "and / or" is merely a description of the association relationship of associated objects, indicating that three relationships can exist. For example, A and / or B can represent three situations: A exists alone, A and B exist simultaneously, and B exists alone. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship.

[0054] In the description of the embodiments of this application, the term "plurality" refers to more than two (including two). Similarly, "multiple groups" refers to more than two groups (including two groups), and "multiple pieces" refers to more than two pieces (including two pieces).

[0055] In the description of the embodiments of this application, unless otherwise clearly specified and limited, technical terms such as "installation", "connection", "connection", "fixation", etc. should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or integrated; it can also be a mechanical connection or an electrical connection; it can be directly connected or indirectly connected through an intermediate medium, and it can be the communication inside two components or the interaction relationship between two components. For those of ordinary skill in the art, the specific meanings of the above terms in the embodiments of this application can be understood according to specific situations.

[0056] Embodiment 1

[0057] As Figure 1 shown, a method for determining the sealing level of a formation isolation valve drive unit provided by an embodiment of the present invention includes the following steps:

[0058] S1. Obtain the original data set of the downhole sealing state, preprocess the original data set, and divide the preprocessed data set into a training set and a validation set by using a time period division method.

[0059] Specifically, the input of this step is the original data set from various hardware sensors , and these data are mainly composed of the following types of information:

[0060] Sensor data: Environmental sensor data such as temperature, humidity, and pressure.

[0061] Position data: Real-time position data provided by GPS or other positioning devices.

[0062] Dynamic sensing data: For example, data captured by accelerometers, gyroscopes, etc. for device movement.

[0063] Since this data often comes from different sensors and has inconsistent formats, there are many problems in directly using the original data for subsequent analysis, such as noise, missing data, dimensional inconsistency, etc. Therefore, a series of preprocessing steps are required in the present invention to improve the data quality.

[0064] Preferably, to improve the accuracy of the data, the present invention needs to remove outliers from the data and handle missing values. For different data characteristics, the present invention uses the following two methods:

[0065] Outlier detection: Detect outliers in the data based on the Local Outlier Factor (LOF) algorithm. This method identifies outliers by calculating the local density difference between a data point and its neighbor points. Formula:

[0066]

[0067] Where, is the current data point, is the data point of k nearest neighbor points. is the inverse of the local density of point , that is , is and the distance between.

[0068] Missing value filling: For missing data, the present invention uses linear interpolation to fill it. Specifically, for the missing value at a certain moment, the present invention estimates and fills the value by linear interpolation based on the data of the two adjacent points. Interpolation formula:

[0069]

[0070] Where, is the estimated value of the missing data, and are the actual data of the two time points before and after the missing point respectively.

[0071] Preferably, the next step of data preprocessing is to perform normalization and standardization. Normalization is to process data with different dimensions and ranges so that they are on the same scale to avoid the unbalanced impact of different dimensions on model learning.

[0072] Min - Max Normalization: To ensure that all features are within the same range, the present invention normalizes the value of each feature into the interval [0, 1]. This method is applicable when the data does not contain obvious outliers. Formula:

[0073]

[0074] where, is the normalized feature value, and are respectively the minimum and maximum values of the feature .

[0075] Standardization: For features with large differences and more suitable for the assumption of a standard normal distribution, the present invention adopts standardization to make the mean of the data 0 and the variance 1. The specific formula is as follows:

[0076]

[0077] where, is the standardized feature value, and are respectively the mean and standard deviation of the feature .

[0078] Preferably, considering that the sensor data in the present invention often has temporal dependence and real - time requirements, the present invention designs an improved "temporal weighted moving average filter". This filter combines a weighted time window and local time trend analysis to remove short - term fluctuations and retain long - term trends.

[0079]

[0080] where, is the smoothed data point. is the weighting coefficient, is the original data at the th moment. is the trend estimate based on the time series, usually obtained through a simple linear regression model. is the adjustment coefficient, used to balance the influence of the local time trend and the smoothing window. Through this weighted smoothing process, the present invention can remove the noise in the temporal data and retain the long - term trend and important information of the data.

[0081] After completing data cleaning, standardization, and temporal smoothing processing, the present invention divides the data set into a training set and a validation set. To avoid future data leakage, the present invention adopts a division method based on time periods.

[0082]

[0083] where, is the end of the training set time period, is the total time length of the data set.

[0084] In this step, by combining innovative time series weighted smoothing processing and weighted normalization methods, the noise in the data is effectively removed, and the important trend information is retained. These preprocessing methods provide high-quality data input for subsequent model training, and ensure the stability and generalization ability of the model. Through a reasonable data partitioning method, the present invention ensures that there is no future data leakage problem between the training set and the validation set, thereby improving the accuracy and robustness of the model.

[0085] S2. Construct a time series weighted regression model based on historical data, evaluate the current sealing level, and use the training set to train the time series weighted regression model. Combine the current sealing level, the corresponding previous sealing level, and the changes in environmental variables to construct a dynamic regression model, and generate the predicted next moment sealing level.

[0086] Specifically, the purpose of the evaluation model is to train a regression model through existing historical data, so as to predict the sealing level of the current device . In order to improve the accuracy of the model, the present invention needs to capture the relationship between the sealing level and environmental changes based on historical time series data. Previously, the present invention has divided the data into a training set and a validation set. Therefore, the present invention will use these data to train the model and evaluate its performance.

[0087] Preferably, the definition of the time series weighted regression model is:

[0088] Assume that the sealing level of the device is determined by the weighted combination of historical sensor data and environmental variables. On this basis, an improved time series weighted regression model is proposed, which includes a sensor change term and an environmental variable change term.

[0089]

[0090] Among them, is the sealing level of the device at time ; is the feature output by the th sensor at time ; is the feature output by the th environmental variable at time ; and are regression coefficients to be learned, used to quantify the influence of different sensors and environmental variables on the sealing level; is the dynamic correction term coefficient, used to adjust the influence of the change in sensor data on the sealing level evaluation; is a weighting factor, indicating the influence degree of different sensors on the sealing level; represents the th sensor at time and the change amount between.

[0091] Use the training set to optimize the regression coefficients , and the weighting factor , to minimize the error between the predicted sealing level and the actual observed value. The present invention adopts the least squares method (LeastSquares) as the loss function to train the model. The training process is as follows:

[0092]

[0093] wherein, is the sealing level predicted by the model.

[0094] By minimizing the loss function , the present invention obtains a trained regression model, which can be evaluated on the validation set to test the accuracy and generalization ability of the model.

[0095] After completing the sealing level evaluation, the present invention continues with trend prediction to make a judgment on the future equipment sealing state. In trend prediction, the present invention uses historical sealing level data and environmental variable changes to establish a dynamic regression model.

[0096] Preferably, the dynamic regression model:

[0097] Based on the current sealing level and the sealing level at the previous moment , as well as the changes in environmental variables, establish a model for predicting the future sealing level. This model reflects the trend of the equipment sealing level changing over time by dynamically adjusting the coefficients:

[0098]

[0099] wherein, is the predicted sealing level at the next moment; is the sealing level at the current moment; is the sealing level at the previous moment; is the time series smoothing coefficient, controlling the influence of the current sealing level change; is the weighted correction coefficient of the sensor data for the trend change; is the weighted coefficient of the sensor data for the trend; represents the th sensor's change amount; is the trend correction coefficient for environmental variable changes; is the change amount of the

[0100] S3. According to the predicted next moment's sealing level and the changes in environmental variables, through the controllable deformation mechanism, generate the sealing adjustment deformation amount of the device and dynamically adjust the sealing system.

[0101] Specifically, based on the sealing level prediction model, the self-adaptive sealing adjustment step of local controllable deformation is mainly used to dynamically adjust the sealing system according to the changes of the device in the actual working environment. The goal of this step is to achieve local sealing performance optimization through the controllable deformation mechanism based on the predicted sealing level and the current device state information. The input comes from the output of step 2, that is, the predicted sealing level and the changes in environmental variables . These data will be combined with the current actual state information of the device and used for sealing adjustment.

[0102] : The sealing level at the next moment obtained through the trend prediction model.

[0103] : The change amount of the environmental variable at time , which reflects the influence of environmental factors on the operating state of the device.

[0104] The key to this step is to use the local controllable deformation mechanism to adjust the sealing state of the device in real time according to the sealing level prediction and the changes in environmental variables. This adjustment process is achieved by controlling some local components of the device (such as sealing strips, sealing covers, etc.). Assuming that the deformation amount of each local component is related to the change in the sealing level and the change in environmental factors, the present invention designs a dynamic control model based on regression coefficient adjustment. This model adjusts the deformation amount through a weighting factor, enabling the device to adapt to different environmental conditions and sealing requirements.

[0105] Based on the local controllable deformation model, the sealing adjustment deformation amount of the device can be expressed by the following formula:

[0106]

[0107] Among them, is the local controllable deformation amount representing time , which is the core goal of the adjustment of the device sealing system, with the unit of length (such as millimeters). is the system constant, representing the deformation amount under the reference state of the device. is the th sensor at time The reading is used to reflect the current working state of the device. is the reading of the th environmental variable at time is the adjustment coefficient, indicating the degree of influence of the change in the sealing level on the deformation amount. is the change amount of the sealing level indicating the current moment, , reflecting the increase or decrease of the sealing level. Specific implementation

[0108] Input acquisition: According to the sensor data of the device and environmental variables , combined with the change amount of the sealing level output in step 2 , calculate the deformation amount of each local component through a dynamic regression model .

[0109] Deformation control: Use an accurate control system (such as a servo drive device) to adjust each local sealing component. The adjustment amplitude is determined by , and this deformation amount can be subdivided into the expansion and contraction amount of the local sealing strip or the displacement amount of the sealing cover.

[0110] Feedback mechanism: After each adjustment, collect the new sealing level value through the sensor, and input it into the trend prediction model again to update the sealing level prediction in real time and continue to adjust the sealing system according to the change.

[0111] The output of this step is the adjusted sealing level , which represents the sealing state of the device after local controllable deformation adjustment under the current environment and operating state. The new sealing level prediction result will be used as the input for the next prediction to continuously optimize the sealing performance of the device. The core of this step is to dynamically adjust the local sealing components of the device so that they can adapt to the changes in working conditions and the environment, thereby maintaining the long-term stable operation and efficient sealing of the device.

[0112] S4. According to the difference between the sealing level at the next moment and the current sealing level, combined with the change of the environmental variable and the sealing adjustment deformation amount of the device, generate an optimized sliding sleeve adjustment requirement to maintain the sealing stability; the sliding sleeve adjustment requirement includes: the position of the sliding sleeve and the sealing pressure.

[0113] Specifically, in this step, the present invention focuses on the adaptive adjustment of the sliding sleeve sealing system to avoid the influence of cement backflow on the oil and gas well equipment. In step 3, the present invention has obtained the sealing level prediction value according to the multi-sensor feedback information , and determines the current sealing state of the device. Based on these results, the present invention needs to further optimize the sealing effect of the sliding sleeve by adjusting the displacement and sealing pressure of the sliding sleeve to maintain the stability of the seal.

[0114] Input: Sealing level prediction result : The sealing level value predicted by Step 3, used to indicate the sealing requirement of the device.

[0115] Current sealing state : The state of the current sealing system of the device, from the sealing detection results of the previous step. Environmental state change amount : The influence amount of the current working environment of the device (such as temperature, pressure, vibration, etc.) on the sealing system. Local deformation amount of the sliding sleeve : The local deformation data of the sliding sleeve from the previous step, used to calculate the change in sealing performance.

[0116] Operation:

[0117] The goal of this step is to optimize the position and pressure of the sliding sleeve by designing an adaptive adjustment model based on the aforementioned inputs, so as to improve the sealing performance and prevent the occurrence of cement backflow.

[0118] The present invention proposes a dynamic feedback adjustment model, the core of which is to calculate the adjustment requirement of the sliding sleeve according to the difference between the predicted sealing level value and the current state, combined with the change of environmental variables. At the same time, when calculating the adjustment amount, the present invention introduces an adaptive regularization term to limit over-adjustment and avoid equipment damage caused by rapid changes.

[0119] Basic formula for sliding sleeve adjustment:

[0120] First, by comparing the predicted sealing level with the current sealing state , the error of the sealing system is obtained, and then the adjustment requirement of the sliding sleeve is calculated.

[0121] The present invention introduces a new adjustment function , which not only considers the sealing level error, but also takes into account the environmental variable change amount and the local deformation amount to improve the adaptive ability. The adjustment formula is as follows:

[0122]

[0123] Among them, is the adjustment amount of the sliding sleeve, indicating the displacement amount (unit: millimeter) that the sliding sleeve should move. is an adaptive adjustment coefficient, which is dynamically updated based on the device status and historical data, and reflects the influence of the seal level error on the sliding sleeve adjustment. is the current device seal status, which is the output from the previous step. is the predicted value of the seal level (the output of step 3). is the environmental feedback adjustment coefficient, which describes the environmental variable 's influence on the sliding sleeve adjustment. is each environmental factor 's influence coefficient on the sliding sleeve adjustment, which is obtained by training based on experimental or simulation data. is the local deformation feedback coefficient, which reflects the local deformation amount 's influence on the sliding sleeve adjustment amount. is the local seal deformation amount data of the aforementioned step.

[0124] To prevent equipment damage caused by excessive adjustment, the present invention introduces a regularization term in the adjustment model. This term can constrain the sliding sleeve adjustment amount, so that excessive adjustment amounts are punished, thereby maintaining the stability of the equipment operation. The present invention proposes a constraint regularization based on the seal deformation amount, and this regularization term punishes the deformation amount exceeding a certain threshold. Its form is:

[0125]

[0126] Among them, is the regularization term, which represents the penalty term for excessive adjustment, and the unit is the square of the adjustment amount. is the regularization coefficient, which controls the intensity of the penalty term. is the absolute value of the sliding sleeve adjustment amount. The final adjustment amount is given by the following formula:

[0127]

[0128] Furthermore, according to the finally calculated sliding sleeve adjustment amount , the position and seal pressure of the sliding sleeve are adjusted through the control system. The specific steps include:

[0129] Sliding sleeve position adjustment: According to , precise displacement adjustment is carried out through the servo drive system to ensure that the sliding sleeve position is within the optimized range.

[0130] Seal pressure optimization: At the same time, according to the adjustment amount, the seal pressure of the sliding sleeve is dynamically adjusted. The adjustment formula for the seal pressure is:

[0131]

[0132] Among them, is the adjusted sealing pressure. is the initial sealing pressure. is the adjustment coefficient related to the sliding sleeve material and working environment, obtained based on experimental data.

[0133] Through the above method, the adjustment of the sliding sleeve can not only ensure the sealing effect but also effectively avoid cement backflow.

[0134] The specific implementation steps of this step are as follows:

[0135] Collect real-time environmental data: Collect environmental change data of the device through sensors , and combine with the predicted sealing level value output in step 3 .

[0136] Calculate the sliding sleeve adjustment requirement: Use the formula to calculate the preliminary sliding sleeve adjustment amount , and optimize it in combination with environmental changes and local deformation amounts.

[0137] Introduce regularization constraints: Regularize the sliding sleeve adjustment amount through the formula to limit the possible negative impacts of excessive adjustment on the device.

[0138] Execute the adjustment: Input the final adjustment amount into the servo control system to precisely adjust the position and sealing pressure of the sliding sleeve.

[0139] Real-time feedback and optimization: After each adjustment, the new sealing state is feedback in real time through sensors, and the new adjustment requirement is calculated to provide data support for the next adjustment.

[0140] Unless otherwise specifically stated, the relative steps, numerical expressions, and numerical values of the components and steps set forth in these embodiments do not limit the scope of the present application.

[0141] If the described functions are implemented in the form of software function units and sold or used as independent products, they can be stored in a non-volatile computer-readable storage medium executable by a processor. Based on this understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art or part of this technical solution can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the system described in various embodiments of the present application. The foregoing storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), magnetic disks, or optical discs that can store program codes.

[0142] In the description of the present application, it should be noted that the orientation or positional relationship indicated by terms such as "upper" and "lower" is based on the orientation or positional relationship shown in the drawings, or the orientation or positional relationship in which the inventive product is customarily placed during use. It is only for the convenience of describing the present application and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be construed as a limitation to the present application.

[0143] In the description of the present application, it should also be noted that unless otherwise clearly specified and defined, the terms "arranged", "installed", "connected" and "coupled" should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be directly connected or indirectly connected through an intermediate medium, and it can be the communication inside two elements. For those of ordinary skill in the art, the specific meanings of the above terms in the present application can be understood according to specific circumstances.

[0144] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements on some or all of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for determining the sealing level of a formation isolation valve transmission unit, characterized in that: The method comprises: Obtaining the original data set of the underground sealing status, preprocessing the original data set, and dividing the preprocessed data set into a training set and a verification set using a time period division method; A time series weighted regression model is constructed based on historical data to evaluate the current sealing level, and the time series weighted regression model is trained using a training set, and a dynamic regression model is constructed by combining the current sealing level, the corresponding sealing level at the previous moment, and changes in environmental variables to generate a predicted sealing level at the next moment; According to the predicted changes in the sealing level and environmental variables at the next moment, the sealing adjustment deformation of the equipment is generated through a controllable deformation mechanism, and the sealing system is adjusted dynamically; According to the difference between the sealing level at the next moment and the current sealing level, combined with the changes in environmental variables and the sealing adjustment deformation of the equipment, an optimized sleeve adjustment requirement is generated to maintain the stability of the seal; the sleeve adjustment requirement includes: the position of the sleeve and the sealing pressure.

2. A method for determining the sealing level of a formation isolation valve transmission unit according to claim 1, characterized in that: The original data set includes: sensor data, position data and dynamic sensor data; the preprocessing of the original data set includes: outlier detection by calculating the local density difference between the data point and its neighboring points; for the missing value at a certain moment, estimating the filling value according to the data of the previous and next two points through linear interpolation; normalization and standardization; weighted smoothing.

3. A method for determining the sealing level of a formation isolation valve transmission unit according to claim 1, characterized in that: The time series weighted regression model is expressed as: in, For the device at time Sealing level; For the The sensor at the time Output characteristics; For the environment variables at time Output characteristics; and are the regression coefficients to be learned, which are used to quantify the impact of different sensor and environmental variables on the sealing level; It is the dynamic correction coefficient, which is used to adjust the impact of changes in sensor data on the sealing level assessment; is a weighting factor, which indicates the influence of different sensors on the sealing level; Indicates The sensor at the time and The amount of change between Among them, the regression coefficient of the training set is used , and weighting factor , minimize the error between the predicted sealing level and the actual observed value; use the least square method as the loss function to train the time series weighted regression model; Evaluation is performed on the validation set to test the accuracy and generalization ability of the time series weighted regression model.

4. A method for determining the sealing level of a formation isolation valve transmission unit according to claim 3, characterized in that: The dynamic regression model is constructed as follows: Get the device at time Sealing level; The equipment is The sealing level and equipment at all times The error of the sealing level, the influence of sensor data on the trend, and the change of environmental variables are weighted respectively; According to the device at the time The sealing level and the weighted output are used to obtain the predicted sealing level at the next moment.

5. A method for determining the sealing level of a formation isolation valve transmission unit according to claim 1, characterized in that: The controllable deformation mechanism is used to generate the sealing adjustment deformation of the device, which is achieved by the following formula: in, Indicates time The local controllable deformation; is a system constant, which indicates the deformation of the equipment under the reference state; For the The sensor at the time The reading is used to reflect the current working status of the equipment; For the environment variables at time Readings to describe the impact of the environment on the device; is the adjustment coefficient, which indicates the influence of the change of sealing grade on the deformation; To indicate the change in sealing level at the current moment, , reflecting the improvement or reduction of sealing level.

6. A method for determining the sealing level of a formation isolation valve transmission unit according to claim 5, characterized in that: The dynamic adjustment of the sealing system includes: Based on the sensor data and environmental variables of the equipment, combined with the change in sealing level, the local controllable deformation of each local component is calculated through a dynamic regression model; Using a precise control system to adjust each local sealing component; wherein the amplitude of the adjustment is determined by the local controllable deformation amount, which is the expansion and contraction amount of the local sealing strip or the displacement amount of the sealing cover; After each adjustment, the new sealing level value is collected by the sensor and input into the time series weighted regression model again to update the sealing level prediction in real time and continue to adjust the sealing system according to the changes.

7. A method for determining the sealing level of a formation isolation valve transmission unit according to claim 6, characterized in that: The precise control system includes a servo drive.

8. A method for determining the sealing level of a formation isolation valve transmission unit according to claim 5, characterized in that: The optimized sleeve adjustment requirement is optimized based on the seal adjustment deformation of the equipment, and based on the constraint regularization of the seal deformation, a penalty is imposed on the deformation exceeding a certain threshold, and finally the sleeve adjustment amount is obtained.

9. A method for determining the sealing level of a formation isolation valve transmission unit according to claim 8, characterized in that: According to the adjustment amount of the sleeve, the position of the sleeve and the sealing pressure are adjusted through the control system, including: According to the adjustment amount of the sleeve, the servo drive system performs precise displacement adjustment to ensure that the position of the sleeve is within the optimized range; At the same time, the sealing pressure of the sleeve is dynamically adjusted according to the adjustment amount; After each adjustment, the new sealing status is fed back in real time through the sensor, and the new adjustment requirements are calculated for iterative optimization.

10. A sealing level determination system for a formation isolation valve transmission unit, characterized in that: The system comprises: The data set acquisition module is used to obtain the original data set of the underground sealing status, and pre-process the original data set, and divide the pre-processed data set into a training set and a verification set by using a time period division method; The sealing level determination and prediction module is used to construct a time series weighted regression model based on historical data, evaluate the current sealing level, and use the training set to train the time series weighted regression model, and construct a dynamic regression model based on the current sealing level, the corresponding sealing level at the previous moment, and the changes in environmental variables to generate a predicted sealing level at the next moment; The sealing adjustment module is used to generate the sealing adjustment deformation of the equipment through a controllable deformation mechanism according to the predicted changes in the sealing level and environmental variables at the next moment, and dynamically adjust the sealing system; The sealing optimization module is used to generate optimized sleeve adjustment requirements to maintain the stability of the seal based on the difference between the sealing level at the next moment and the current sealing level, combined with changes in environmental variables and the sealing adjustment deformation of the equipment; the sleeve adjustment requirements include: the position of the sleeve and the sealing pressure.

Images