A real-time scheduling control method for well-blasting production based on time distance

Abstract

The invention relates to the technical field of well gun control, and discloses a real-time scheduling control method for well gun excitation production based on time distance, comprising the following steps: step one: obtaining positioning data of all well guns in an excitation target area, planning schemes of all well guns and historical data after explosion, and classifying and forming a positioning data set, a scheme data set and a historical data set; step two: analyzing the distance between each well gun, generating a distance data group, and obtaining a first time distance rule; step three: analyzing the delay time when the planning scheme is detonated and the propagation time after detonation, generating a corresponding time data group, obtaining a second time distance rule, and achieving flexible planning and high production efficiency; step four: setting a monitoring period of fixed time, analyzing the energy fluctuation trend during multiple monitoring periods, generating a corresponding amplitude index and energy propagation speed, training and generating a time distance model, and obtaining a third time distance rule, and achieving high safety of autonomous scheduling control.

Description

Technical Field

[0001] The invention relates to the technical field of well gun control, and in particular to a real-time scheduling control method for well gun excitation production based on time distance. Background Art

[0002] The well gun used in oil field production is a device used to increase the production of oil and gas wells. By generating high-pressure gas or liquid in the well, oil and gas are driven to flow from underground to the surface. Well guns usually consist of a main engine and an auxiliary engine, which work together to generate the required pressure. The main engine is responsible for generating high-pressure gas or liquid, while the auxiliary engine is used to control and regulate these pressures. When the well gun is started, the main engine first generates high-pressure gas or liquid, which is then transported to the auxiliary engine for further pressure regulation. Finally, the regulated pressure gas or liquid is transported to the oil and gas well through a pipeline, thereby driving the oil and gas from underground to the surface. The use of well guns can significantly increase the production of oil and gas wells because it can effectively drive oil and gas from deep underground to the surface.

[0003] At present, traditional well and gun production scheduling and control methods require a long time to respond to production needs, resulting in delays in production plans and reduced production efficiency. They lack sufficient flexibility and adaptability. In addition, they lack autonomous scheduling and control capabilities. Once the pressure in the well is too high, blowout accidents are likely to occur. Summary of the invention

[0004] In view of the shortcomings of the prior art, the present invention provides a real-time scheduling and control method for well and gun excitation production based on time distance, which has the advantages of flexible planning, high production efficiency, and high safety of autonomous scheduling and control. It solves the problems of poor flexibility and low efficiency of traditional well and gun production scheduling and control methods, and lack of autonomous scheduling and control capabilities.

[0005] To achieve the above object, the present invention provides the following technical solution: a real-time scheduling control method for well-gun excitation production based on time distance, comprising the following steps:

[0006] Step 1: Connect the central control console and the sensor device through the network to obtain the positioning data of all wells and guns in the target area, the planning schemes of all wells and guns, and the historical data after the explosion, and classify them into positioning data sets, plan data sets, and historical data sets;

[0007] Step 2: Set a fixed critical distance , and combined with the positioning data set, analyze the distance between each well and gun to generate the corresponding distance data set , we get the first time distance rule of well gun;

[0008] Step 3: Based on the historical data set, analyze the delay time of the planning scheme when it is detonated and the propagation time after detonation to generate the corresponding duration data set , we get the second time distance rule of well gun;

[0009] Step 4: Set a fixed monitoring period , and combined with the program data set and historical data set to analyze multiple monitoring cycles The energy fluctuation trend during the period generates the corresponding amplitude index and energy propagation speed , train the generative temporal distance model , and we get the third time distance rule for well guns.

[0010] Preferably, in step 1, the expression for locating the data set is , to Indicates the first to The positioning data of each well gun, the positioning data is the GPS coordinates, Indicates the oil well number where a single well gun is located.

[0011] Preferably, in step 1, the expression of the solution data set is , to Indicates the first to A planning scheme, including the explosion sequence and explosion method, Indicates the oil well number corresponding to a single planning scheme.

[0012] Preferably, in step 1, the expression of the historical data set is , to Indicates the first to The historical data after the explosion of each planning scheme includes the command time, explosion time, wellhead time and wellhead waveform. Indicates the oil well number corresponding to a single planning scheme.

[0013] Preferably, in step 2, the distance data set The calculation formula is as follows:

[0014] ;

[0015] In the formula, represents the distance data set, Indicates the location of the dataset The location data of each well gun, Indicates the location of the dataset The location data of each well gun, Indicates the difference in GPS coordinates between two wells and guns, Indicates simultaneous calculation The difference in GPS coordinates between the wells and guns is the distance data set.

[0016] Preferably, in step 2, according to the distance data set , construct the distance-time diagram, and then analyze the first time distance rule of well gun. If the distance data group The difference in GPS coordinates between any two wells and guns exceeds the critical distance , then two well guns are allowed to be detonated simultaneously. If the distance data set The difference in GPS coordinates between any two wells and guns does not exceed the critical distance , then a waiting interval needs to be set between the explosion times of the two well guns, and the duration of the waiting interval is greater than or equal to 60s.

[0017] Preferably, in step 3, the duration data group The calculation process is as follows:

[0018] Extract the historical data set The historical data after the explosion of the planning scheme, and the The instruction time of each planning scheme is marked as , will The explosion time of the planning scheme is marked as , will The wellhead time of each planning scheme is marked as ;

[0019] ;

[0020] In the formula, Represents a duration data group, The time difference between the time when the explosion energy reaches the wellhead and the time when the well gun is detonated is the propagation time. It indicates the time difference between the well gun detonation time and the command time, that is, the delay time. The time data group includes the detonation time. The delay time and detonation time of each planning scheme The length of time it takes to spread a plan.

[0021] Preferably, in step three, according to the duration data group , set a unified time interval, the sum of the maximum delay time and the maximum propagation time is the unified time interval, and the second time distance rule of well guns requires that all well guns be detonated in sequence according to a unified time interval.

[0022] Preferably, in step 4, the amplitude index and energy propagation speed The calculation process is as follows:

[0023] According to the monitoring cycle Divide the first time slot into the second time slot, the first time slot corresponds to The first well gun detonated in the planning scheme, the second time slot corresponds to The second well gun to be detonated in the plan;

[0024] According to the historical data set, the historical data of the well gun in the first time slot is extracted, and the wellhead waveform of the well gun in the first time slot is marked as ;

[0025] according to , the monitoring cycle The amplitude during the period is marked as , to Indicates monitoring cycle During the period from the first to the The amplitude at each time point;

[0026] ;

[0027] ;

[0028] In the formula, represents the amplitude index, The sum of the amplitudes of the wellhead waveforms in the first time slot divided by the time point is the average amplitude. , Indicates monitoring cycle During the period The amplitude at each time point, It means that according to the variance formula, the variance value obtained is the amplitude index of the well shot in the first time slot;

[0029] ;

[0030] In the formula, represents the energy propagation speed, Indicates The oil well depth corresponding to each planning scheme is It represents the energy propagation speed obtained by dividing the oil well depth by the propagation time.

[0031] Preferably, in step 4, the time distance model The training process is as follows:

[0032] According to the scheme data set, divided Planning schemes are the training set, divided into The planning schemes are used as the test set, and then the distance data set , Monitoring cycle and energy propagation speed As a hyperparameter;

[0033] The training set and the duration data group corresponding to the training set and amplitude index Substitute into the time distance model Perform fitting training and then substitute the test set into the trained time distance model , generate the corresponding delay time, propagation time and wellhead waveform. If the generated delay time and propagation time are consistent with the time data set corresponding to the test set The generated wellhead waveform is consistent with the amplitude index of the test set. Consistent, indicating a time distance model The accuracy of the time distance model is high. The generated scheduling strategy is the third time distance rule of well gun. If the generated delay time and propagation time are consistent with the time data set corresponding to the test set Inconsistency or amplitude index of generated wellhead waveform and test set corresponding Inconsistency, indicating a time distance model The accuracy is low, and the fitting training continues until the generated delay time, propagation time, wellhead waveform and test set time data set is and amplitude index Consistent.

[0034] Compared with the prior art, the present invention provides a real-time scheduling control method for well-gun excitation production based on time distance, which has the following beneficial effects:

[0035] 1. The present invention connects the central control console and the sensor device through the network to obtain the positioning data of all wells and guns in the target area, the planning schemes of all wells and guns, and the historical data after the explosion, and classifies them into positioning data sets, plan data sets, and historical data sets, and sets a fixed value critical distance. , and combined with the positioning data set, analyze the distance between each well and gun to generate the corresponding distance data set , which helps to accurately adjust the scheduling strategy in the future, according to the distance data group , construct a distance-time graph, analyze and obtain the first time distance rule of wells and guns, which is suitable for application scenarios with a small number of wells and guns involved in the explosion. According to the historical data set, analyze the delay time of the planned detonation and the propagation time after detonation, and generate the corresponding time data set , which helps to enhance the system's time prediction capability. , set a unified time interval, the sum of the maximum delay time and the maximum propagation time is the unified time interval, the second time distance rule of wells and guns requires that all wells and guns be detonated in sequence at a unified time interval, the unified time interval ensures the stability of the explosion process, and avoids the interference of aftershocks on subsequent explosion tasks. When there are a large number of wells and guns involved in the explosion, the distance is equal and the planning scheme corresponding to each well and gun is the same, it is suitable to implement the second time distance rule, which has flexible planning and high production efficiency.

[0036] 2. The present invention sets a fixed-length monitoring cycle , and combined with the program data set and historical data set to analyze multiple monitoring cycles The energy fluctuation trend during the period generates the corresponding amplitude index and energy propagation speed , in-depth analysis of the energy fluctuation trend of well guns in each time slot under different planning schemes helps to avoid the heavy gun effect and aftershock interference, and captures the timing information between different planning schemes through fitting training and learning, and trains and generates time distance models , to achieve autonomous scheduling control capabilities, if the generated delay duration, propagation duration and the duration data set corresponding to the test set The generated wellhead waveform is consistent with the amplitude index of the test set. Consistent, indicating a time distance model The accuracy of the time distance model is high. The generated scheduling strategy is the third time distance rule of well guns, and the autonomous scheduling control has high safety. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] Figure 1 It is a step diagram of the method of the present invention. DETAILED DESCRIPTION

[0038] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0039] Since the traditional well-gun production scheduling control method takes a long time to respond to production needs, it leads to delays in production planning and reduced production efficiency. It lacks sufficient flexibility and adaptability. In addition, it lacks autonomous scheduling control capabilities. Once the pressure in the well is too high, a blowout accident is likely to occur. Therefore, a real-time scheduling control method for well-gun production based on time distance is provided. Please refer to Figure 1 , the method comprises the following steps:

[0040] Step 1: Connect the central control console and the sensor device through the network to obtain the positioning data of all wells and guns in the target area, the planning schemes of all wells and guns, and the historical data after the explosion, and classify them into positioning data sets, plan data sets, and historical data sets;

[0041] The expression for locating the data set is , to Indicates the first to The positioning data of each well gun, the positioning data is the GPS coordinates, Indicates the oil well number where a single well gun is located. The positioning accuracy of GPS coordinates can be as low as centimeters. The best positioning accuracy is helpful for subsequent accurate prediction of detonation strategies.

[0042] The expression of the scenario data set is , to Indicates the first to A planning scheme, including the explosion sequence and explosion method, Indicates the oil well number corresponding to a single planning scheme. Different oil wells have different depths and cross-sectional areas, and the corresponding planning schemes are also different. In actual use, a single well shot corresponds to multiple excitation points, and the setting depth of each excitation point is also different;

[0043] The expression of the historical data set is , to Indicates the first to The historical data after the explosion of each planning scheme includes the command time, explosion time, wellhead time and wellhead waveform. Indicates the oil well number corresponding to a single planning scheme, and monitors the sensor data after the explosion of the planning scheme in real time, which is helpful for the subsequent rapid analysis of the time distance rules corresponding to different planning schemes;

[0044] Step 2: Set a fixed critical distance , and combined with the positioning data set, analyze the distance between each well and gun to generate the corresponding distance data set , and its calculation formula is as follows:

[0045] ;

[0046] In the formula, represents the distance data set, Indicates the location of the dataset The location data of each well gun, Indicates the location of the dataset The location data of each well gun, Indicates the difference in GPS coordinates between two wells and guns, Indicates simultaneous calculation The GPS coordinate difference between each well and gun is the distance data group. In-depth analysis of the positioning distance between each well and gun will help to accurately adjust the scheduling strategy in the future.

[0047] According to the distance data set , construct the distance-time diagram, and then analyze the first time distance rule of well gun. If the distance data group The difference in GPS coordinates between any two wells and guns exceeds the critical distance , then two well guns are allowed to be detonated simultaneously. If the distance data set The difference in GPS coordinates between any two wells and guns does not exceed the critical distance , then a waiting interval needs to be set between the explosion times of the two wells and guns, and the waiting interval is greater than or equal to 60s. When the number of wells and guns involved in the explosion is small, the first time distance rule is suitable for implementation;

[0048] Step 3: Based on the historical data set, analyze the delay time of the planning scheme when it is detonated and the propagation time after detonation to generate the corresponding duration data set , the calculation process is as follows:

[0049] Extract the historical data set The historical data after the explosion of the planning scheme, and the The instruction time of each planning scheme is marked as , will The explosion time of the planning scheme is marked as , will The wellhead time of each planning scheme is marked as ;

[0050] ;

[0051] In the formula, Represents a duration data group, The time difference between the time when the explosion energy reaches the wellhead and the time when the well gun is detonated is the propagation time. It indicates the time difference between the well gun detonation time and the command time, that is, the delay time. The time data group includes the detonation time. The delay time and detonation time of each planning scheme The propagation time after each planning scheme and in-depth analysis of monitoring data at different stages will help enhance the system's time prediction capabilities;

[0052] According to the duration data group , set a unified time interval, the sum of the maximum delay time and the maximum propagation time is the unified time interval, the second time distance rule of wells and guns requires all wells and guns to be detonated in sequence at a unified time interval, the unified time interval ensures the stability of the explosion process, and avoids the interference of aftershocks on subsequent explosion tasks. When there are a large number of wells and guns involved in the explosion, the distance is equal and the planning schemes corresponding to each well and gun are the same, it is suitable to implement the second time distance rule, which has flexible planning and high production efficiency;

[0053] Step 4: Set a fixed monitoring period , and combined with the program data set and historical data set to analyze multiple monitoring cycles The energy fluctuation trend during the period generates the corresponding amplitude index and energy propagation speed , the calculation process is as follows:

[0054] According to the monitoring cycle Divide the first time slot into the second time slot, the first time slot corresponds to The first well gun detonated in the planning scheme, the second time slot corresponds to The second well gun to be detonated in the plan;

[0055] According to the historical data set, the historical data of the well gun in the first time slot is extracted, and the wellhead waveform of the well gun in the first time slot is marked as ;

[0056] according to , the monitoring cycle The amplitude during the period is marked as , to Indicates monitoring cycle During the period from the first to the The amplitude at each time point;

[0057] ;

[0058] ;

[0059] In the formula, represents the amplitude index, The sum of the amplitudes of the wellhead waveforms in the first time slot divided by the time point is the average amplitude. , Indicates monitoring cycle During the period The amplitude at each time point, It means that according to the variance formula, the variance value obtained is the amplitude index of the well shot in the first time slot;

[0060] ;

[0061] In the formula, represents the energy propagation speed, Indicates The oil well depth corresponding to each planning scheme is The energy propagation speed is obtained by dividing the oil well depth by the propagation time. In-depth analysis of the energy fluctuation trend of the well gun in each time slot under different planning schemes helps to avoid the heavy gun effect and aftershock interference, so as to formulate the optimal scheduling strategy;

[0062] Training a Generative Temporal Distance Model , we get the third time distance rule of well gun, and its time distance model The training process is as follows:

[0063] According to the scheme data set, divided Planning schemes are the training set, divided into The planning schemes are used as the test set, and then the distance data set , Monitoring cycle and energy propagation speed As a hyperparameter;

[0064] The training set and the duration data group corresponding to the training set and amplitude index Substitute into the time distance model Perform fitting training and then substitute the test set into the trained time distance model , generate the corresponding delay time, propagation time and wellhead waveform, specifically, the time distance model It is a recurrent neural network that captures the timing information between different planning schemes through fitting training and learning, and realizes autonomous scheduling control capability. If the generated delay duration and propagation duration are consistent with the duration data set corresponding to the test set The generated wellhead waveform is consistent with the amplitude index of the test set. Consistent, indicating a time distance model The accuracy of the time distance model is high. The generated scheduling strategy is the third time distance rule of well guns, and the autonomous scheduling control is highly secure. If the generated delay time and propagation time are consistent with the time data set corresponding to the test set, Inconsistency or amplitude index of generated wellhead waveform and test set corresponding Inconsistency, indicating a time distance model The accuracy is low, and the fitting training continues until the generated delay time, propagation time, wellhead waveform and test set time data set is and amplitude index Consistent.

[0065] Example 1

[0066] In this experiment, an oil well at a depth of 500 meters was selected as the experimental object. The oil well was set with an excitation point at a depth of 500 meters, and a detonation command was issued at 10:00:00. After testing, the explosion time of the well gun was 10:00:10, and the time when the explosion energy reached the wellhead was 10:01:00. The duration data group The calculation formula is as follows:

[0067] ;

[0068] In the formula, Represents a duration data group, 50s represents the time difference between the time when the explosion energy reaches the wellhead and the time when the well gun is detonated, that is, the propagation duration, and 10s represents the time difference between the well gun detonation time and the instruction time, that is, the delay duration.

[0069] Example 2

[0070] In this experiment, an oil well at a depth of 1000 meters was selected as the experimental object. The oil well was set with excitation points at depths of 1000 meters and 500 meters respectively. The 1000-meter excitation point was detonated first, and the 500-meter excitation point was detonated second. After testing, within 5 seconds, the amplitudes of the wellhead waveforms were 1cm / s, 2cm / s, 2cm / s, 5cm / s and 5cm / s respectively, and the amplitude index The calculation formula is as follows:

[0071] ;

[0072] ;

[0073] In the formula, represents the amplitude index, The sum of the amplitudes of the wellhead waveform at the 1000-meter excitation point in the first time slot divided by the time point gives an average amplitude of 3 cm / s. According to the variance formula, the variance value of 2.8 is the amplitude index of the 1000-meter excitation point in the first time slot.

[0074] While the embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that many changes, modifications, substitutions and variations can be made to the embodiments without departing from the principles and spirit of the invention.

Claims

1. A real-time scheduling control method for well and gun production based on time distance, characterized in that: The following steps are involved: Step 1: Connect the central control console and the sensor device through the network to obtain the positioning data of all wells and guns in the target area, the planning schemes of all wells and guns, and the historical data after the explosion, and classify them into positioning data sets, plan data sets, and historical data sets; Step 2: Set a fixed critical distance , and combined with the positioning data set, analyze the distance between each well and gun to generate the corresponding distance data set , get the first time distance rule of well gun; in the step 2, according to the distance data group , construct the distance-time diagram, and then analyze the first time distance rule of well gun. If the distance data group The difference in GPS coordinates between any two wells and guns exceeds the critical distance , then two well guns are allowed to be detonated simultaneously. If the distance data set The difference in GPS coordinates between any two wells and guns does not exceed the critical distance , then a waiting interval needs to be set between the explosion times of the two well guns, and the waiting interval should be greater than or equal to 60s; Step 3: Based on the historical data set, analyze the delay time of the planning scheme when it is detonated and the propagation time after detonation to generate the corresponding duration data set , and obtain the second time distance rule of well gun; in the step three, according to the time length data group , set a unified time interval, the sum of the maximum delay time and the maximum propagation time is the unified time interval, and the second time distance rule of well guns requires that all well guns be detonated in sequence according to the unified time interval; Step 4: Set a fixed monitoring period , and combined with the program data set and historical data set to analyze multiple monitoring cycles The energy fluctuation trend during the period generates the corresponding amplitude index and energy propagation speed , train the generative temporal distance model , we get the third time distance rule for well guns; Among them, set a fixed-duration monitoring cycle , and combined with the program data set and historical data set to analyze multiple monitoring cycles The energy fluctuation trend during the period generates the corresponding amplitude index and energy propagation speed , the calculation process is as follows: According to the monitoring cycle Divide the first time slot into the second time slot, the first time slot corresponds to The first well gun detonated in the planning scheme, the second time slot corresponds to The second well gun to be detonated in the plan; According to the historical data set, the historical data of the well gun in the first time slot is extracted, and the wellhead waveform of the well gun in the first time slot is marked as ; according to , the monitoring cycle The amplitude during the period is marked as , to Indicates monitoring cycle During the period from the first to the The amplitude at each time point; ； ； In the formula, represents the amplitude index, The sum of the amplitudes of the wellhead waveforms in the first time slot divided by the time point is the average amplitude. , Indicates monitoring cycle During the period The amplitude at each time point, It means that according to the variance formula, the variance value obtained is the amplitude index of the well shot in the first time slot; ； In the formula, represents the energy propagation speed, Indicates The oil well depth corresponding to each planning scheme is The energy propagation speed is obtained by dividing the oil well depth by the propagation time. In-depth analysis of the energy fluctuation trend of the well gun in each time slot under different planning schemes helps to avoid the heavy gun effect and aftershock interference, so as to formulate the optimal scheduling strategy; Training a Generative Temporal Distance Model , we get the third time distance rule of well gun, and its time distance model The training process is as follows: According to the scheme data set, divided Planning schemes are the training set, divided into The planning schemes are used as the test set, and then the distance data set , Monitoring cycle and energy propagation speed As a hyperparameter; The training set and the duration data group corresponding to the training set and amplitude index Substitute into the time distance model Perform fitting training and then substitute the test set into the trained time distance model , generate the corresponding delay time, propagation time and wellhead waveform, specifically, the time distance model It is a recurrent neural network that captures the timing information between different planning schemes through fitting training and learning, and realizes autonomous scheduling control capabilities. If the generated delay duration and propagation duration are consistent with the duration data set corresponding to the test set The generated wellhead waveform is consistent with the amplitude index of the test set. Consistent, indicating a time distance model The accuracy of the time distance model is high. The generated scheduling strategy is the third time distance rule of well guns, and the autonomous scheduling control is highly secure. If the generated delay time and propagation time are consistent with the time data set corresponding to the test set, Inconsistency or amplitude index of generated wellhead waveform and test set corresponding Inconsistency, indicating a time distance model The accuracy is low, and the fitting training continues until the generated delay time, propagation time, wellhead waveform and test set time data set is and amplitude index Consistent.

2. The real-time scheduling control method for well and gun production based on time distance according to claim 1 is characterized by: In step 1, the expression for locating the data set is: , to Indicates the first to The positioning data of each well gun, the positioning data is the GPS coordinates, Indicates the oil well number where a single well gun is located.

3. The real-time scheduling control method for well and gun production based on time distance according to claim 2 is characterized by: In step 1, the expression of the solution data set is: , to Indicates the first to A planning scheme, including the explosion sequence and explosion method, Indicates the oil well number corresponding to a single planning scheme.

4. The real-time scheduling control method for well and gun production based on time distance according to claim 3 is characterized by: In step 1, the expression of the historical data set is: , to Indicates the first to The historical data after the explosion of each planning scheme includes the command time, explosion time, wellhead time and wellhead waveform. Indicates the oil well number corresponding to a single planning scheme.

5. The real-time scheduling control method for well and gun production based on time distance according to claim 1 is characterized by: In step 3, the duration data group The calculation process is as follows: Extract the historical data set The historical data after the explosion of the planning scheme, and the The instruction time of each planning scheme is marked as , will The explosion time of the planning scheme is marked as , will The wellhead time of each planning scheme is marked as .

Images