CN116816327A

CN116816327A - Oil well connectivity detection method, device, electronic equipment and medium

Info

Publication number: CN116816327A
Application number: CN202210257889.6A
Authority: CN
Inventors: 郭肖; 艾爽; 庞伟; 范杰
Original assignee: China Petroleum and Chemical Corp; Sinopec Petroleum Engineering Technology Research Institute Co Ltd
Current assignee: China Petroleum and Chemical Corp; Sinopec Petroleum Engineering Technology Research Institute Co Ltd
Priority date: 2022-03-16
Filing date: 2022-03-16
Publication date: 2023-09-29

Abstract

The disclosure relates to the technical field of petroleum engineering well completion, and provides a method, a device, electronic equipment and a medium for detecting oil well connectivity. The method comprises the following steps: acquiring adjacent oil production data of an adjacent well in a first preset time period; setting the oil production data of the monitoring well in a first preset time period to be zero to obtain zero oil production data so as to simulate the monitoring well to execute well closing; leading adjacent oil production data and zero oil production data into a trained target prediction model, and predicting target bottom hole pressure data of a monitoring well in a first preset time period; based on the target bottom hole pressure data, it is determined whether the monitoring well and the adjacent well are in communication. According to the embodiment of the disclosure, through the steps, the detection accuracy can be improved, and the test period is greatly shortened.

Description

Oil well connectivity detection method, device, electronic equipment and medium

Technical Field

The disclosure relates to the technical field of petroleum engineering well completion, in particular to a method, a device, electronic equipment and a medium for detecting oil well connectivity.

Background

The well connectivity information is widely used for oil field development design, yield prediction, well dynamic evaluation, water/gas injection management and encryption well planning. The following technical schemes are often adopted in the prior art to detect the connectivity of the oil well:

And (5) tracer test. Tracer tests are effective and practical for studying connectivity between injection and production wells because the design of injection strategies depends on reservoir connectivity. In addition, tracer tests are also used to diagnose fracture connectivity to estimate fracture volumes between fractured well groups. However, the primary flow path detected from the production stage through the tracer test may change as tracer injection and production may cause redistribution of the interwell pressure field. When there are no fractures, the tracer recovery may be low, and it is difficult to distinguish between open permeable fields and closed geological formations by the tracer test, so the accuracy of the tracer test is low.

And (5) interference testing. With the development of permanent downhole pressure gauges (PDG), pressure measurement functions have been enhanced to continuously monitor downhole pressure changes over a long period of time. This advancement has made possible another method of quantitatively determining the degree of communication between wells: long-term interference testing. The method is typically applied to two wells, where the source well controls the flow and sends a specific signal to the monitoring well. The duration of a conventional interference test is on the order of days when there is no hydraulic connectivity. Therefore, the test period of the interference test is excessively long.

Therefore, the technical problems of low test accuracy and overlong test period exist in the prior art.

Disclosure of Invention

In view of the above, the embodiments of the present disclosure provide a method, an apparatus, an electronic device, and a medium for detecting connectivity of an oil well, so as to solve the technical problems of low test accuracy and too long test period in the prior art.

In a first aspect of an embodiment of the present disclosure, there is provided a method for detecting connectivity of an oil well, including:

acquiring adjacent oil production data of an adjacent well in a first preset time period;

setting the oil production data of the monitoring well in a first preset time period to be zero to obtain zero oil production data so as to simulate the monitoring well to execute well closing;

leading adjacent oil production data and zero oil production data into a trained target prediction model, and predicting target bottom hole pressure data of a monitoring well in a first preset time period;

based on the target bottom hole pressure data, it is determined whether the monitoring well and the adjacent well are in communication.

In some embodiments, determining whether the monitoring well and the adjacent well are in communication based on the target bottom hole pressure data comprises:

when the target bottom hole pressure data continues to decrease, it is determined that the monitoring well communicates with an adjacent well.

In some embodiments, determining whether the monitoring well and the adjacent well are in communication based on the target bottom hole pressure data further comprises:

And when the change amplitude of the target bottom hole pressure data is smaller than a preset change threshold value, determining that the monitoring well and the pair are not communicated.

In some embodiments, the target prediction model is an LSTM deep learning network model.

In some embodiments, the training step of the target prediction model comprises:

respectively acquiring oil production data of a monitoring well and an adjacent well in a second preset time period, and original bottom hole pressure data of the monitoring well in the second preset time period;

leading the oil production data of the monitoring well and the adjacent well in a second preset time period into a preset original prediction model to generate predicted bottom hole pressure data in the second preset time period;

generating a training result based on the predicted bottom hole pressure data, the original bottom hole pressure data and a preset loss calculation function;

when the training result indicates failure, the original predictive model is retrained.

In some embodiments, the training step of the target prediction model further comprises:

when the training result indicates success, the original prediction model of the current training is determined as the target prediction model.

In some embodiments, the loss calculation function may be one of:

square loss function, absolute loss function, or Huber loss function.

In a second aspect of the embodiments of the present disclosure, there is provided an oil well connectivity detection apparatus, including:

the acquisition module is configured to acquire adjacent oil production data of adjacent wells in a first preset time period;

the zeroing module is configured to zeroe the oil production data of the monitoring well in the first preset time period so as to simulate well closing; setting the oil production data of the monitoring well in the first preset time period to be zero to obtain zero-set oil production data so as to simulate the monitoring well to execute well closing;

a generation module configured to import the adjacent production data and the zeroed production data into a trained target prediction model to predict target bottom hole pressure data of the monitoring well for the first preset time period;

a determination module configured to determine whether the monitoring well and the adjacent well are in communication based on the target bottom hole pressure data.

In some embodiments, the loss calculation function is one of:

square loss function, absolute loss function, or Huber loss function.

In a third aspect of the disclosed embodiments, there is provided an electronic device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, the steps implemented by the processor when executing the computer program comprising:

In some embodiments, the loss calculation function is one of:

square loss function, absolute loss function, or Huber loss function.

In a fourth aspect of the disclosed embodiments, there is provided a computer-readable storage medium storing a computer program which, when executed by a processor, performs steps comprising:

In some embodiments, the loss calculation function is one of:

square loss function, absolute loss function, or Huber loss function.

Advantageous effects

Compared with the prior art, the beneficial effects of the embodiment of the disclosure at least comprise: compared with the prior art, the embodiment of the disclosure has the beneficial effects that: the adjacent oil production data and the zero oil production data are imported into the target prediction model to generate target bottom hole pressure data of the monitoring well in a first preset time period, and whether the monitoring well is communicated with the adjacent well or not is judged, so that the detection accuracy can be improved, and the test period is greatly shortened.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure, the drawings that are required for the embodiments or the description of the prior art will be briefly introduced below, and it is obvious that the drawings in the following description are only the embodiments, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.

FIG. 1 is a schematic diagram of one scenario of a well connectivity detection method provided in accordance with an embodiment of the present disclosure;

FIG. 2 is a flow chart of an embodiment two of a method for well connectivity detection provided in accordance with an embodiment of the present disclosure;

FIG. 3a is a schematic diagram of an oil production curve of a monitoring well and an adjacent well in an oil well connectivity detection method according to an embodiment of the present disclosure;

FIG. 3b is a graphical representation of target bottom hole pressure data in a method for well connectivity detection according to an embodiment of the present disclosure;

FIG. 3c is another graphical representation of target bottom hole pressure data in a method of well connectivity detection provided in accordance with an embodiment of the present disclosure;

FIG. 4 is a flow chart of embodiment three of another method of well connectivity detection provided in accordance with embodiments of the present disclosure;

FIG. 5 is a simplified schematic structural diagram of an oil well connectivity detection device provided in accordance with an embodiment of the present disclosure;

fig. 6 is a schematic diagram of an electronic device provided according to an embodiment of the present disclosure.

Detailed Description

Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While certain embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete. It should be understood that the drawings and embodiments of the present disclosure are for illustration purposes only and are not intended to limit the scope of the present disclosure.

It should be further noted that, for convenience of description, only a portion relevant to the present disclosure is shown in the drawings. Embodiments of the present disclosure and features of embodiments may be combined with each other without conflict.

It should be noted that the terms "first," "second," and the like in this disclosure are merely used to distinguish between different systems, devices, modules, or units and are not intended to limit the order or interdependence of functions performed by such systems, devices, modules, or units.

It should be noted that references to "one", "a plurality" and "a plurality" in this disclosure are intended to be illustrative rather than limiting, and those of ordinary skill in the art will appreciate that "one or more" is intended to be understood as "one or more" unless the context clearly indicates otherwise.

The names of messages or information interacted between the various devices in the embodiments of the present disclosure are for illustrative purposes only and are not intended to limit the scope of such messages or information.

The present disclosure will be described in detail below with reference to the accompanying drawings in conjunction with embodiments.

Embodiment one:

fig. 1 is a schematic diagram of an application scenario of an oil well connectivity detection method according to a first embodiment of the present disclosure.

In the application scenario of fig. 1, first, the computing device 101 may acquire adjacent production data 102 for adjacent wells for a first preset period of time.

Next, the computing device 101 may set the oil production data of the monitoring well for the first preset time period to zero, resulting in the zeroed oil production data 103 to simulate the monitoring well performing a shut-in.

Again, the computing device 101 may import adjacent production data 102 and zeroed production data 103 into a trained target prediction model 104 to predict target bottom hole pressure data 105 for the monitoring well for a first preset period of time.

Finally, the computing device 101 may determine 106 whether the monitoring well is in communication with an adjacent well based on the target bottom hole pressure data 105.

The computing device 101 may be hardware or software. When the computing device is hardware, the computing device may be implemented as a distributed cluster formed by a plurality of servers or terminal devices, or may be implemented as a single server or a single terminal device. When the computing device is embodied as software, it may be installed in the hardware devices listed above. It may be implemented as a plurality of software or software modules, for example, for providing distributed services, or as a single software or software module. The present invention is not particularly limited herein.

It should be understood that the number of computing devices in fig. 1 is merely illustrative. There may be any number of computing devices, as desired for an implementation.

Embodiment two:

with continued reference to fig. 2, a flow 200 of a second embodiment of a well connectivity detection method according to the present disclosure is shown. The method may be performed by the computing device 101 in fig. 1. The method for detecting the connectivity of the oil well comprises the following steps:

step 201, acquiring adjacent oil production data of adjacent wells in a first preset time period.

In some alternative implementations, the execution entity of the well connectivity detection method (e.g., computing device 101 shown in fig. 1) may connect the target device via a wired connection or a wireless connection, and then obtain the adjacent production data of the adjacent wells for the first preset period of time. The first preset time period may refer to a preset time interval for selecting adjacent oil production data. The time period may be in days. The adjacent production data may refer to production data of adjacent wells for the first predetermined period of time. The data acquisition interval of adjacent oil production data can be in common units of seconds, minutes, hours, days and the like, and the oil production data can be in units of tons (abbreviated as t). As an example, reference may be made to fig. 3a, wherein SHB1-6H may refer to a graphical representation of the neighboring oil production data, the first preset time period may be 0 to 800 days in fig. 3a, the data acquisition interval of the neighboring oil production data may be 1 time/day, and the neighboring oil production data is in tons.

It should be noted that the wireless connection may include, but is not limited to, 3G/4G/5G connection, wiFi connection, bluetooth connection, wiMAX connection, zigbee connection, UWB (ultra wideband) connection, and other now known or later developed wireless connection.

Step 202, setting the oil production data of the monitoring well in the first preset time period to be zero, and obtaining the zero oil production data so as to simulate the monitoring well to execute well shut-in.

In some optional implementations, the executing body may set the oil production data of the monitoring well in the first preset period to zero, so as to obtain the zero oil production data, so as to simulate the monitoring well to execute the well shut-in.

When the connectivity of the monitoring well and the adjacent well is detected, the oil production data of the monitoring well in the first preset time period can be set to be 0, and the monitoring well is simulated to perform well closing, namely oil production is stopped. The data acquisition interval for monitoring the oil production data can be in common units of seconds, minutes, hours, days and the like, and the oil production data can be in units of tons (abbreviated as t). As an example, reference may be made to fig. 3a, wherein SHB1-10H may refer to a graphical representation of the monitored oil production data, the first preset time period may be 0 to 800 days in fig. 3a, the data acquisition interval of the monitored oil production data may be 1 time per day, and the monitored oil production data is in tons.

Step 203, importing adjacent oil production data and zero oil production data into a trained target prediction model to predict target bottom hole pressure data of the monitoring well in a first preset time period.

In some alternative implementations, the execution body may import adjacent production data and zeroed production data into a trained target prediction model to predict target bottom hole pressure data of the monitoring well for a first predetermined period of time. The target prediction model may refer to trained downhole pressure data that may be predicted for a monitored well based on the oil production data for the monitored well and the oil production data for an adjacent well. And importing the adjacent oil production data and the zero oil production data into a trained target prediction model, and checking predicted bottom hole pressure data of the monitoring well.

The target prediction model may be any machine learning model that implements regression, and is not particularly limited herein.

In some preferred implementations, the target predictive model is an LSTM (Long Short-Term Memory network) deep learning network model.

Step 204, based on the target bottom hole pressure data, it is determined whether the monitoring well and the adjacent well are in communication.

In some alternative implementations, the executive may determine whether the monitored well and the adjacent well are in communication based on the target bottom hole pressure data.

Because the bottom hole pressure data of the monitoring well is obtained by the combined action and prediction of the oil production data of the monitoring well and the oil production data of the adjacent well, if the monitoring well is communicated with the adjacent well, the oil level of the monitoring well is lowered when the oil level of the adjacent well is lowered due to the communication effect although the oil production data of the monitoring well is zero, and the bottom hole pressure data of the monitoring well is lowered. Otherwise, if the monitoring well is not communicated with the adjacent well, the oil production data of the monitoring well is zero, the oil level of the monitoring well is not changed no matter how the oil level of the adjacent well is changed, and the bottom hole pressure data of the monitoring well is not changed correspondingly.

In some preferred implementations, the monitoring well is determined to be in communication with an adjacent well as the target bottom hole pressure data continues to decrease.

Referring to FIG. 3b, the bottom hole pressure data is plotted as SHB1-10H, and since SHB1-10H is gradually decreasing, it is possible to determine that the monitoring well is communicating with the adjacent well.

In other preferred implementations, the monitoring well and pair discontinuity are determined when the target bottom hole pressure data variation amplitude is less than a preset variation threshold.

Due to the incomplete accuracy of the predictions, the target bottom hole pressure data may not be accurately maintained. A change threshold may thus be set, and when the magnitude of the change is less than the change threshold, it may be determined that the monitoring well and the adjacent well are not in communication. The change threshold may be 1, 0.1, 0.03, or the like, and is set as needed, without being particularly limited thereto.

In still other preferred implementations, the monitoring well and pair discontinuity is determined when the target bottom hole pressure data change amplitude is zero.

Referring to FIG. 3c, the bottom hole pressure data is shown as a curve of SHB1-10H, and since the variation amplitude of SHB1-10H is zero, i.e. remains unchanged, it can be determined that the monitoring well and the adjacent well are not in communication.

The beneficial effects of one of the implementation manners of the above embodiments of the disclosure include at least: compared with the prior art, the embodiment of the disclosure has the beneficial effects that: the adjacent oil production data and the zero oil production data are imported into the target prediction model to generate target bottom hole pressure data of the monitoring well in a first preset time period, and whether the monitoring well is communicated with the adjacent well or not is judged, so that the detection accuracy can be improved, and the test period is greatly shortened.

Embodiment III:

with continued reference to fig. 4, a flow 400 of a third embodiment of a well connectivity detection method according to the present disclosure is shown, which may be performed by the computing device 101 of fig. 1. The oil well connectivity detection method comprises the following steps:

step 401, acquiring oil production data of the monitoring well and the adjacent well in a second preset time period, and original bottom hole pressure data of the monitoring well in the second preset time period respectively.

In some alternative implementations, the executing entity may obtain the oil production data of the monitoring well and the adjacent well during the second preset time period, and the raw bottom hole pressure data of the monitoring well during the second preset time period, respectively.

The second preset time period may refer to a time interval for acquiring actual data while the monitoring well and the neighboring well are operating properly. Normal operation may refer to monitoring of the well and adjacent well both performing production operations, and also may obtain corresponding production data. The raw bottom hole pressure data may refer to bottom hole pressure data of the monitoring well over a second preset period of time.

Step 402, importing the oil production data of the monitoring well and the adjacent well in the second preset time period into a preset original prediction model to generate predicted bottom hole pressure data in the second preset time period.

In some optional implementations, the executing body may import the oil production data of the monitoring well and the adjacent well in the second preset time period into a preset original prediction model to generate predicted bottom hole pressure data in the second preset time period. Specifically, the prediction is performed, the oil production data of the monitored well and the oil production data of the adjacent well can be respectively used as 2 input parameters to be imported into the original prediction model, and the output parameters of the original prediction model are predicted bottom hole pressure data in a second preset time period. The predicted bottom hole pressure data may refer to bottom hole pressure data of the monitored well for a second predetermined period of time as predicted by the raw predictive model.

Step 403, generating training results based on the predicted bottom hole pressure data, the raw bottom hole pressure data and a preset loss calculation function.

In some alternative implementations, the executing entity may generate the training result based on the predicted bottom hole pressure data, the raw bottom hole pressure data, and a predetermined loss calculation function by:

In the first step, the execution body may generate the deviation data based on the predicted bottom hole pressure data, the raw bottom hole pressure data, and a predetermined loss calculation function. The loss calculation function is a common function of the prediction model and is used to represent the degree of deviation of the predicted value and the control value, that is, the deviation data.

And secondly, the execution main body can compare the deviation data with a preset deviation threshold value to generate a training result.

The deviation threshold may refer to a preset limit value for defining a deviation data range. When the deviation data is not smaller than the preset deviation threshold value, the deviation degree is larger, and the model needs to be trained continuously. And when the deviation data is smaller than a preset deviation threshold value, the model training is completed, wherein the requirement is met.

It should be noted that the loss function of the original prediction model (or the target prediction model) may be a square loss function, an absolute loss function, or a regression loss function commonly used as a Huber loss function. Since the square loss function, the absolute loss function, or the Huber loss function are all the prior art, the details are not repeated here. In addition, other existing or future discovered loss functions that can be used for regression problems, in addition to the regression loss functions described above, are within the scope of the present disclosure.

Step 404, when the training result indicates success, determining the original prediction model of the current training as the target prediction model.

In some alternative implementations, when the training result indicates success, the executing entity may determine the original prediction model of the current training as the target prediction model.

In other alternative implementations, when the training result indicates failure, the executing entity may re-execute steps 402 to 403 to re-train the original prediction model.

At step 405, adjacent production data for adjacent wells for a first predetermined period of time is obtained.

In addition, the first preset time may be the same as or different from the second preset time.

In some preferred implementations, the first preset time is the same as the second preset time described above.

When the first preset time is the same as the second preset time, the change of the downhole pressure data of the monitoring well can be accurately predicted.

And step 406, setting the oil production data of the monitoring well in the first preset time period to be zero, and obtaining the zero-set oil production data so as to simulate the monitoring well to execute well shut-in.

Step 407, importing adjacent oil production data and zero oil production data into a trained target prediction model to predict target bottom hole pressure data of the monitoring well in a first preset time period.

In some preferred implementations, the target prediction model is an LSTM deep learning network model.

Step 408, based on the target bottom hole pressure data, it is determined whether the monitoring well and the adjacent well are in communication.

The beneficial effects of one of the above embodiments of the present disclosure include at least: compared with the prior art, the embodiment of the disclosure has the beneficial effects that: the adjacent oil production data and the zero oil production data are imported into the target prediction model to generate target bottom hole pressure data of the monitoring well in a first preset time period, and whether the monitoring well is communicated with the adjacent well or not is judged, so that the detection accuracy can be improved, and the test period is greatly shortened.

Any combination of the above optional technical solutions may be adopted to form an optional embodiment of the present application, which is not described herein.

Embodiment four:

the following are device embodiments of the present disclosure that may be used to perform method embodiments of the present disclosure. For details not disclosed in the embodiments of the apparatus of the present disclosure, please refer to the embodiments of the method of the present disclosure.

With further reference to fig. 4, as an implementation of the method described above for each of the above figures, the present disclosure provides an embodiment of an oil well connectivity detection apparatus, which corresponds to the embodiment described above for fig. 2.

As shown in fig. 5, the oil well connectivity detection apparatus 500 of the present embodiment includes:

an acquisition module 501 configured to acquire adjacent production data for adjacent wells over a first preset period of time.

A zeroing module 502 configured to zeroe production data of the monitoring well during the first preset time period to simulate well shut-in; setting the oil production data of the monitoring well in the first preset time period to be zero, and obtaining zero-set oil production data so as to simulate the monitoring well to execute well closing.

A generating module 503 configured to import the adjacent oil production data and the zeroed oil production data into a trained target prediction model to predict target bottom hole pressure data of the monitoring well for the first preset time period.

A determination module 504 is configured to determine whether the monitoring well and the adjacent well are in communication based on the target bottom hole pressure data.

In some preferred implementations, determining whether the monitoring well and the adjacent well are in communication based on the target bottom hole pressure data includes:

In some preferred implementations, the training step of the target prediction model includes:

and respectively acquiring oil production data of the monitoring well and the adjacent well in a second preset time period, and original bottom hole pressure data of the monitoring well in the second preset time period.

In some preferred implementations, the executing entity may obtain the oil production data of the monitoring well and the adjacent well during the second preset time period, and the raw bottom hole pressure data of the monitoring well during the second preset time period, respectively.

And importing the oil production data of the monitoring well and the adjacent well in the second preset time period into a preset original prediction model to generate predicted bottom hole pressure data in the second preset time period.

And generating a training result based on the predicted bottom hole pressure data, the original bottom hole pressure data and a preset loss calculation function.

In some alternative implementations, when the training result indicates failure, the executing body may re-execute the steps to train to retrain the original prediction model.

In some preferred implementations, the training step of the target prediction model further comprises:

In some preferred implementations, the loss calculation function may be one of:

square loss function, absolute loss function, or Huber loss function.

It will be appreciated that the modules described in the apparatus 500 correspond to the various steps in the method described with reference to fig. 2. Thus, the operations, features and resulting benefits described above with respect to the method are equally applicable to the apparatus 500 and the modules contained therein, and are not described in detail herein.

Fifth embodiment:

as shown in fig. 6, the electronic device 600 may include a processing means (e.g., a central processing unit, a graphics processor, etc.) 601, which may perform various appropriate actions and processes according to a program stored in a Read Only Memory (ROM) 602 or a program loaded from a storage means 608 into a Random Access Memory (RAM) 603. In the RAM 603, various programs and data required for the operation of the electronic apparatus 600 are also stored. The processing device 601, the ROM 602, and the RAM 603 are connected to each other through a bus 604. An input/output (I/O) interface 605 is also connected to bus 604.

In general, the following devices may be connected to the I/O interface 605: input devices 606 including, for example, a touch screen, touchpad, keyboard, mouse, camera, microphone, accelerometer, gyroscope, and the like; an output device 607 including, for example, a Liquid Crystal Display (LCD), a speaker, a vibrator, and the like; storage 608 including, for example, magnetic tape, hard disk, etc.; and a communication device 609. The communication means 609 may allow the electronic device 600 to communicate with other devices wirelessly or by wire to exchange data. While fig. 6 shows an electronic device 600 having various means, it is to be understood that not all of the illustrated means are required to be implemented or provided. More or fewer devices may be implemented or provided instead. Each block shown in fig. 6 may represent one device or a plurality of devices as needed.

In particular, according to the present embodiment, the process described above with reference to the flowcharts may be implemented as a computer software program. For example, the present embodiment includes a computer program product comprising a computer program embodied on a computer readable medium, the computer program containing program code for performing the method shown in the flowchart. In the present embodiment, the computer program can be downloaded and installed from a network through the communication means 609, or installed from the storage means 608, or installed from the ROM 602. When the computer program is executed by the processing means 601, the following steps may be performed:

And acquiring adjacent oil production data of the adjacent wells in a first preset time period.

Setting the oil production data of the monitoring well in the first preset time period to zero so as to simulate well closing; setting the oil production data of the monitoring well in the first preset time period to be zero, and obtaining zero-set oil production data so as to simulate the monitoring well to execute well closing.

And importing the adjacent oil production data and the zero oil production data into a trained target prediction model to predict target bottom hole pressure data of the monitoring well in the first preset time period.

And judging whether the monitoring well and the adjacent well are communicated or not based on the target bottom hole pressure data.

In some preferred implementations, the loss calculation function may be one of:

square loss function, absolute loss function, or Huber loss function.

It should be noted that, in this embodiment, the computer readable medium may be a computer readable signal medium or a computer readable storage medium, or any combination of the two. The computer readable storage medium can be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. More specific examples of the computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In this embodiment, a computer-readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In the present embodiment, however, the computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, with the computer-readable program code embodied therein. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination of the foregoing. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: electrical wires, fiber optic cables, RF (radio frequency), and the like, or any suitable combination of the foregoing.

In some implementations, the clients, servers may communicate using any currently known or future developed network protocol, such as HTTP (HyperText Transfer Protocol ), and may be interconnected with any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), the internet (e.g., the internet), and peer-to-peer networks (e.g., ad hoc peer-to-peer networks), as well as any currently known or future developed networks.

The computer readable medium may be embodied in the apparatus; or may exist alone without being incorporated into the electronic device. The computer readable medium carries one or more programs which, when executed by the electronic device, cause the electronic device to perform the steps of:

In some preferred implementations, the loss calculation function may be one of:

square loss function, absolute loss function, or Huber loss function.

The computer program code for carrying out operations of the present embodiments may be written in one or more programming languages, including an object oriented programming language such as Java, smalltalk, C ++ and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computer (for example, through the Internet using an Internet service provider).

The flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.

The modules described in the present embodiment may be implemented by software or hardware. The described modules may also be provided in a processor, for example, as:

The device comprises an acquisition module, a zero setting module, a generation module and a judgment module. For example, the acquisition module may also be described as a "module that acquires neighboring production data".

The functions described above herein may be performed, at least in part, by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: a Field Programmable Gate Array (FPGA), an Application Specific Integrated Circuit (ASIC), an Application Specific Standard Product (ASSP), a system on a chip (SOC), a Complex Programmable Logic Device (CPLD), and the like.

The foregoing description is only of the preferred embodiments of the present disclosure and description of the principles of the technology being employed. It will be appreciated by those skilled in the art that the scope of the invention in the embodiments of the present disclosure is not limited to the specific combination of the above technical features, but encompasses other technical features formed by any combination of the above technical features or their equivalents without departing from the spirit of the invention. Such as the above-described features, are mutually substituted with (but not limited to) the features having similar functions disclosed in the embodiments of the present disclosure.

Claims

1. A method for detecting connectivity of an oil well, comprising:

setting the oil production data of the monitoring well in the first preset time period to be zero to obtain zero-set oil production data so as to simulate the monitoring well to execute well closing;

leading the adjacent oil production data and the zero oil production data into a trained target prediction model, and predicting target bottom hole pressure data of the monitoring well in the first preset time period;

2. The method of claim 1, wherein the determining whether the monitoring well and the adjacent well are in communication based on the target bottom hole pressure data comprises:

and determining that the monitoring well is communicated with the adjacent well when the target bottom hole pressure data continuously decreases.

3. The method according to claim 2, wherein the method further comprises:

and when the change amplitude of the target bottom hole pressure data is smaller than a preset change threshold value, determining that the monitoring well and the adjacent well are not communicated.

4. The method of claim 1, wherein the target prediction model is an LSTM deep learning network model.

5. The method of claim 1, wherein the training of the target predictive model comprises:

respectively acquiring oil production data of the monitoring well and the adjacent well in a second preset time period and original bottom hole pressure data of the monitoring well in the second preset time period;

importing the oil production data of the monitoring well and the adjacent well in a second preset time period into a preset original prediction model to generate predicted bottom hole pressure data in the second preset time period;

and retraining the original prediction model when the training result indicates failure.

6. The method of claim 5, wherein the method further comprises:

and when the training result shows success, determining the original prediction model which is trained at present as the target prediction model.

7. The method of claim 5, wherein the loss calculation function is one of:

square loss function, absolute loss function, or Huber loss function.

8. An oil well connectivity detection apparatus, comprising:

9. An electronic device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that the processor implements the steps of the method according to any of claims 1 to 7 when the computer program is executed.

10. A computer readable storage medium storing a computer program, characterized in that the computer program when executed by a processor implements the steps of the method according to any one of claims 1 to 7.