Method and system for regulating and controlling rheological property parameters of drilling fluid and storage medium

Abstract

The invention belongs to the technical field of oil drilling, and discloses a drilling fluid rheological property parameter regulation and control method and system and a storage medium, and the method comprises the steps: generating an initial regulation and control instruction based on a comparison result of a historical monitoring data set stored in cloud storage equipment and test information data of a test mud tank; training the neural network model based on the historical monitoring data set and the initial regulation and control instruction, and constructing a test mud tank regulation and control model; acquiring multiple groups of real-time monitoring data of the test mud tank, solving the test mud tank adjustment model by adopting a multi-objective optimization algorithm, and generating an optimal regulation and control instruction for adjusting rheological property parameters of the drilling fluid in the mud tank; and the optimal regulation and control instruction is applied to the control valve to regulate the rheological property of the drilling fluid. Under the condition that human intervention is not needed, automatic regulation and control can be accurately carried out on the rheological property of the drilling fluid, the drilling efficiency is improved, and the drilling risk is reduced.

Description

Technical Field

[0001] This invention belongs to the field of petroleum drilling technology, and specifically relates to a method, system and storage medium for controlling drilling fluid rheological performance parameters. Background Technology

[0002] In oil drilling, the rheological properties of drilling fluid are crucial for successful drilling. However, existing drilling fluid measurements are time-consuming and exhibit significant lag, making it difficult to use multi-source data from the drilling process for feedback adjustment of the drilling fluid. This can easily lead to problems such as wellbore instability and salt intrusion. Furthermore, traditional methods for controlling the rheological properties of drilling fluids mainly rely on manual experience and field tests, lacking systematicity and real-time capabilities, and are insufficient to meet the complex and ever-changing geological environments and drilling requirements. Summary of the Invention

[0003] To address the shortcomings of existing technologies, this invention discloses a method, system, and storage medium for controlling the rheological properties of drilling fluids.

[0004] This invention is achieved through the following technical solution:

[0005] Firstly, a method for controlling drilling fluid rheological properties includes:

[0006] Based on the comparison results between the historical monitoring dataset stored in the cloud storage device and the test information data of the test mud tank, an initial control command is generated;

[0007] The neural network model was trained based on historical monitoring datasets and initial control commands to construct an experimental mud tank control model.

[0008] Multiple sets of real-time monitoring data of the test mud tank were acquired, and a multi-objective optimization algorithm was used to solve the control model of the test mud tank to generate the optimal control command for adjusting the rheological performance parameters of the drilling fluid in the mud tank.

[0009] The optimal control command is applied to the control valve to adjust the rheological properties of the drilling fluid.

[0010] In some embodiments, the test information data includes test mud tank monitoring data and standard range data for each monitoring item.

[0011] In some embodiments, the historical monitoring dataset and the corresponding initial control instructions are divided into a training dataset and a test dataset in an 8:2 ratio using a random partitioning method.

[0012] In some embodiments, the training dataset is used to train a neural network model;

[0013] The test dataset is used to test and validate the neural network model.

[0014] In some embodiments, the neural network model is trained with the goal of maximizing the improvement of the rheological performance parameters of the drilling fluid in the test mud tank while minimizing the control cost, thereby obtaining a test mud tank control model.

[0015] In some embodiments, the equilibrium constraints that the experimental mud tank control model needs to satisfy include: the drilling fluid's own internal liquid level, density, pH value, and temperature.

[0016] In some embodiments, multiple sets of real-time monitoring data are collected by data acquisition devices installed in multiple sub-regions of the test mud tank.

[0017] In some embodiments, the real-time monitoring data includes: drilling fluid density, pH value, temperature, apparent viscosity, plastic viscosity, dynamic shear force, and bottom hole pressure collected in real time from the logging room.

[0018] Secondly, a drilling fluid rheological performance parameter control system includes:

[0019] The module includes an initial instruction generation module, a control model construction module, a control instruction solving module, and a control instruction sending module.

[0020] The initial instruction generation module is used to generate initial control instructions based on the comparison results between the historical monitoring dataset stored in the cloud storage device and the test information data of the test mud tank.

[0021] The control model construction module is used to train the neural network model based on the historical monitoring dataset and the initial control command, with the goal of maximizing the improvement of the parameters of the drilling fluid rheological properties of the test mud tank and minimizing the control cost, so as to obtain the test mud tank control model.

[0022] The control command solving module is used to solve the test mud tank control model using a multi-objective optimization algorithm based on multiple sets of real-time monitoring data, so as to obtain the optimal control command for adjusting the rheological performance parameters of the drilling fluid in the mud tank.

[0023] The control command sending module is used to send the optimal control command to the corresponding control valve, and to control the start and stop of the control valve according to the optimal control command, so as to adjust the rheological performance parameters of the drilling fluid in the test mud tank to the standard range.

[0024] Thirdly, a computer-readable storage medium is characterized in that it stores one or more programs that, when executed, can implement the method described in the claims.

[0025] Compared with the prior art, the present invention has the following advantages:

[0026] 1. Historical data charts can be displayed on the client side, enabling 24-hour online monitoring and data collection, reducing the workload for workers and enhancing practicality;

[0027] 2. The multi-objective optimization algorithm used in this invention obtains the optimal control command, which has the advantages of speed and efficiency in controlling drilling fluid performance;

[0028] 3. It can automatically control the rheological properties of drilling fluid relatively accurately without human intervention, thereby improving drilling efficiency and reducing drilling risks.

[0029] Other features and advantages of the invention will be set forth in the description which follows, and will be apparent in part from the description, or may be learned by practicing this information. The objects and other advantages of the invention may be realized and obtained by means of the structures pointed out in the description, claims and drawings. Attached Figure Description

[0030] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0031] Figure 1 This is a schematic diagram of a drilling fluid rheological property parameter control method disclosed in this embodiment;

[0032] Figure 2 This is a schematic diagram of the optimal control command solution process disclosed in this embodiment;

[0033] Figure 3 This is a schematic diagram of a drilling fluid rheological performance parameter control system disclosed in this embodiment.

[0034] Figure 4 This is a schematic diagram of an electronic device structure disclosed in this embodiment. Detailed Implementation

[0035] The accompanying drawings are for illustrative purposes only and should not be construed as limiting this patent. To better illustrate this embodiment, some components in the drawings may be omitted, enlarged, or reduced, and do not represent the actual dimensions of the product. It is understandable to those skilled in the art that some well-known structures and their descriptions may be omitted in the drawings. The positional relationships described in the drawings are for illustrative purposes only and should not be construed as limiting this patent.

[0036] like Figure 1 The method for controlling the rheological properties of drilling fluid, as shown, includes the following steps:

[0037] S1. Based on the comparison results between the historical monitoring dataset stored in the cloud storage device and the test information data of the test mud tank, generate the initial control command.

[0038] Specifically, the experimental information data includes data on the monitoring items of the experimental mud tank and standard range data for each monitoring item. The standard range for each monitoring item refers to the standard value range of each parameter under different working conditions. For example, density will be different at different stages of drilling operations, but the error range will not exceed ±0.01. If the true value of density at a certain period is 1.4, then its standard range is 1.39 to 1.41. The historical monitoring dataset and the corresponding initial control command are used to train the dataset and test the dataset in an 8:2 ratio using a random partitioning method.

[0039] S2. Based on historical monitoring datasets and initial control commands, train the neural network model to construct the experimental mud tank control model.

[0040] Specifically, the training dataset is used to train the corresponding neural network model, and then the neural network model is tested and verified using the test dataset.

[0041] Furthermore, with the optimization objective of improving the rheological properties of the drilling fluid in the test mud tank to a predetermined standard range and minimizing the control cost, the neural network model is optimized to obtain the test mud tank control model. During the construction of the test mud tank control model, the equilibrium conditions of the drilling fluid itself in the tank, such as liquid level, density, pH value, and temperature, need to be met to ensure the stability and effectiveness of the control process.

[0042] S3. Acquire multiple sets of real-time monitoring data from the test mud tank, and use a multi-objective optimization algorithm to solve the mud tank adjustment model to generate the optimal control command for adjusting the rheological performance parameters of the drilling fluid in the mud tank.

[0043] Specifically, multiple sets of real-time monitoring data are collected using data acquisition devices installed in various sub-areas of the test mud tank. These real-time monitoring data include: drilling fluid density, pH value, temperature, apparent viscosity, plastic viscosity, dynamic shear force, and bottom hole pressure collected in real-time from the logging room. Furthermore, using a multi-objective optimization algorithm, based on the collected real-time monitoring data, the test mud tank control model is solved to generate optimal control commands for the rheological performance parameters of the drilling fluid within the test mud tank.

[0044] Furthermore, the process for obtaining the optimal control command is as follows: Figure 2 As shown, it includes the following steps:

[0045] S31. Preprocess the real-time monitoring data, calculate the positive difference between the maximum and minimum values, and determine whether the positive difference exceeds a preset threshold. If it exceeds the threshold, it indicates that the performance of the drilling fluid has changed seriously. Immediately issue an alarm to remind the staff to check the equipment operation and drilling safety precautions. If it does not exceed the threshold, retain all data for subsequent processing.

[0046] S32. Calculate the average value of the real-time monitoring data after preprocessing of each project, and input the calculation results into the test mud tank control model;

[0047] S33. Solve the problem using a multi-objective optimization algorithm to generate the optimal control command.

[0048] The generated optimal control command is sent to the corresponding control valve, and the start and stop of the control valve are adjusted according to the optimal control command to stabilize the rheological performance parameters of the drilling fluid in the test mud tank within the standard range.

[0049] S4. Monitor and control the results, and upload the data to the cloud for further analysis.

[0050] After the control is completed, the data of the drilling fluid rheological performance parameters monitored in real time and the corresponding optimal control instructions are uploaded to the cloud storage device, and the charts of the on-site monitoring data are displayed on the client for further analysis.

[0051] In some embodiments, such as Figure 3 The drilling fluid rheological performance parameter control system shown includes: an initial command generation module, a control model construction module, a control command solving module, and a control command sending module.

[0052] Specifically, the initial instruction generation module is used to generate initial control instructions based on the comparison results between the historical monitoring dataset stored in the cloud storage device and the test information. The test information includes the test mud tank monitoring items and the standard range of each monitoring item.

[0053] The control model construction module is used to optimize and train the neural network model based on the historical monitoring dataset and initial control instructions, with the goal of maximizing the improvement of the parameters of the drilling fluid rheological properties in the test mud tank and minimizing the control cost, so as to obtain the test mud tank control model.

[0054] The control command solving module is used to solve the mud tank control model based on multiple sets of real-time monitoring data using a multi-objective optimization algorithm to obtain the optimal control command for adjusting the rheological performance parameters of the drilling fluid in the mud tank.

[0055] The control command sending module is used to send the optimal control command to the corresponding control valve, and to control the start and stop of the control valve according to the optimal control command, so as to adjust the rheological performance parameters of the drilling fluid in the test mud tank to the standard range.

[0056] like Figure 4 As shown, embodiments of this disclosure also provide an electronic device, including a processor, a communication interface, a memory, and a communication bus. The processor, communication interface, and memory communicate with each other via the communication bus.

[0057] The memory is a computer-readable storage medium used to store one or more programs.

[0058] The processor is configured to execute a program stored in a computer-readable storage medium.

[0059] The computer-readable storage medium may be included in the device / apparatus described in the above embodiments; or it may exist independently and not assembled into the device / apparatus. In summary, this invention can use 5G wireless communication technology to send the monitoring data collected by the data acquisition device and the corresponding optimal control instructions to the cloud storage device, and display historical data charts on the client side, making the experimental process more intuitive, realizing 24-hour online monitoring and data acquisition, reducing the labor intensity of workers, and enhancing practicality. This invention can automatically control the rheological properties of drilling fluids relatively accurately without human intervention, and is particularly suitable for controlling the rheological properties of drilling fluids in "digital oilfields".

[0060] Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for controlling the rheological properties of drilling fluid, characterized in that, include: Based on the comparison results between the historical monitoring dataset stored in the cloud storage device and the test information data of the test mud tank, an initial control command is generated; The neural network model was trained based on historical monitoring datasets and initial control commands to construct an experimental mud tank control model. Multiple sets of real-time monitoring data of the test mud tank were acquired, and a multi-objective optimization algorithm was used to solve the control model of the test mud tank to generate the optimal control command for adjusting the rheological performance parameters of the drilling fluid in the mud tank. The optimal control command is applied to the control valve to adjust the rheological properties of the drilling fluid.

2. The method for controlling drilling fluid rheological properties according to claim 1, characterized in that, The test information data includes data on the test mud tank monitoring items and the standard range data for each monitoring item.

3. The method for controlling drilling fluid rheological properties according to claim 1, characterized in that, The historical monitoring dataset and the corresponding initial control instructions were divided into a training dataset and a test dataset in an 8:2 ratio using a random partitioning method.

4. The method for controlling drilling fluid rheological properties according to claim 3, characterized in that, The training dataset is used to train a neural network model; The test dataset is used to test and validate the neural network model.

5. The method for controlling drilling fluid rheological properties according to claim 1, characterized in that, The neural network model was trained with the goal of maximizing the improvement of the rheological performance parameters of the drilling fluid in the test mud tank while minimizing the control cost, thus obtaining the test mud tank control model.

6. The method for controlling drilling fluid rheological properties according to claim 1, characterized in that, The experimental mud tank control model needs to meet the following equilibrium constraints: the drilling fluid's own internal liquid level, density, pH value, and temperature.

7. The method for controlling drilling fluid rheological properties according to claim 1, characterized in that, Multiple sets of real-time monitoring data were collected using data acquisition devices installed in several sub-areas of the test mud tank.

8. The method for controlling drilling fluid rheological properties according to claim 1, characterized in that, The real-time monitoring data includes: drilling fluid density, pH value, temperature, apparent viscosity, plastic viscosity, dynamic shear force, and bottom hole pressure collected in real time from the logging room.

9. A drilling fluid rheological performance parameter control system, characterized in that, include: The module includes an initial instruction generation module, a control model construction module, a control instruction solving module, and a control instruction sending module. The initial instruction generation module is used to generate initial control instructions based on the comparison results between the historical monitoring dataset stored in the cloud storage device and the test information data of the test mud tank. The control model construction module is used to train the neural network model based on the historical monitoring dataset and the initial control command, with the goal of maximizing the improvement of the parameters of the drilling fluid rheological properties of the test mud tank and minimizing the control cost, so as to obtain the test mud tank control model. The control command solving module is used to solve the test mud tank control model using a multi-objective optimization algorithm based on multiple sets of real-time monitoring data, so as to obtain the optimal control command for adjusting the rheological performance parameters of the drilling fluid in the mud tank. The control command sending module is used to send the optimal control command to the corresponding control valve, and to control the start and stop of the control valve according to the optimal control command, so as to adjust the rheological performance parameters of the drilling fluid in the test mud tank to the standard range.

10. A computer-readable storage medium, characterized in that, The storage contains one or more programs that, when executed, can implement the method described in any one of claims 1-8.

Images