Adaptive control method and device for reservoir isolation valve combined with reservoir distribution scenario

Abstract

The present invention discloses an adaptive control method and device for reservoir isolation valves in combination with reservoir distribution scenarios, and relates to the technical field of isolation valves. The method includes: acquiring reservoir scenario environmental data streams through sensor network monitoring; constructing a three-dimensional model of reservoir distribution; performing reservoir parameter analysis and flow simulation to obtain reservoir spatial distribution characteristics and reservoir flow trends, perform multi-dimensional risk assessment, and determine a reservoir risk area parameter set; obtain a reservoir isolation valve control strategy; perform adaptive control analysis on a reservoir risk area parameter set based on the reservoir isolation valve control strategy to obtain isolation valve coordination control parameters, and adaptive feedback control of a target reservoir isolation valve through isolation valve coordination control parameters. The method solves the technical problem in the prior art that reservoir isolation valves cannot achieve precise control for complex reservoir distribution scenarios, resulting in low reservoir exploitation efficiency, and achieves the technical effect of improving exploitation efficiency by adaptively adjusting the isolation valve control strategy.

Description

Technical Field

[0001] The present invention relates to the technical field of isolation valves, and in particular to a method and device for adaptively controlling an oil reservoir isolation valve in combination with an oil reservoir distribution scenario. Background Art

[0002] With the continuous development of oil and gas field exploitation technology, the scenarios faced by oil reservoir exploitation are becoming more and more complex, especially in an environment where multiple factors such as multi-layer reservoir structure, different geological conditions, pressure, temperature, etc. are intertwined. The flow trend of reservoir fluid is difficult to predict, and the risks that may be encountered during the exploitation process also increase accordingly. In traditional reservoir isolation valve control methods, it is often impossible to accurately control according to the actual distribution of the reservoir, which makes it difficult for the isolation valve to adapt to the complex reservoir environment, and there are problems such as inaccurate isolation and fluid loss of control, which seriously affects the efficiency and safety of oil and gas field exploitation. The current market demand for technology that can dynamically adjust and accurately control isolation valves is becoming more and more urgent to cope with the changing reservoir distribution scenarios and ensure the safety and efficiency of the reservoir exploitation process. Summary of the invention

[0003] The present application provides an adaptive control method and device for a reservoir isolation valve in combination with a reservoir distribution scenario, which solves the technical problem in the prior art that the reservoir isolation valve cannot achieve precise control for complex reservoir distribution scenarios, resulting in low reservoir exploitation efficiency.

[0004] In view of the above problems, the present application provides a method and device for adaptively controlling a reservoir isolation valve in combination with a reservoir distribution scenario.

[0005] In a first aspect of the present application, a method for adaptively controlling a reservoir isolation valve in combination with a reservoir distribution scenario is provided, the method comprising:

[0006] A sensor network is deployed in the target reservoir distribution scenario area, wherein the sensor network integration includes pressure sensors, temperature sensors, and flow sensors, and the sensor network is used to monitor and obtain the reservoir scenario environment data stream; the drilling exploration signal stream is collected and obtained, and reservoir simulation modeling is performed based on the reservoir scenario environment data stream and the drilling exploration signal stream to construct a three-dimensional reservoir distribution model; reservoir parameter analysis and flow simulation are performed based on the three-dimensional reservoir distribution model to obtain reservoir spatial distribution characteristics and reservoir flow trends, and multi-dimensional risk assessment is performed on the reservoir spatial distribution characteristics and reservoir flow trends to determine the reservoir risk area parameter set; a reservoir isolation valve control strategy library is constructed, and the structural characteristic information of the target reservoir isolation valve and the reservoir exploitation target are matched with the reservoir isolation valve control strategy library to obtain the reservoir isolation valve control strategy; based on the reservoir isolation valve control strategy, the reservoir risk area parameter set is adaptively controlled and analyzed to obtain the isolation valve coordination control parameters, and the target reservoir isolation valve is adaptively feedback controlled through the isolation valve coordination control parameters.

[0007] A second aspect of the present application provides an adaptive control device for a reservoir isolation valve in combination with a reservoir distribution scenario, the device comprising:

[0008] A data acquisition module, which is used to deploy a sensor network in the target reservoir distribution scenario area, wherein the sensor network integration includes pressure sensors, temperature sensors, and flow sensors, and the sensor network is used to monitor and obtain the reservoir scenario environment data stream; a simulation modeling module, which is used to collect and obtain the drilling exploration signal stream, and perform reservoir simulation modeling based on the reservoir scenario environment data stream and the drilling exploration signal stream to construct a three-dimensional reservoir distribution model; a simulation analysis module, which is used to perform reservoir parameter analysis and flow simulation based on the three-dimensional reservoir distribution model to obtain the spatial distribution characteristics and reservoir flow trend, perform multi-dimensional risk assessment on the spatial distribution characteristics of the reservoir and the reservoir flow trend, and determine the reservoir risk area parameter set; a matching module, the matching module is used to build a reservoir isolation valve control strategy library, match the reservoir isolation valve control strategy library according to the structural characteristic information of the target reservoir isolation valve and the reservoir production target, and obtain the reservoir isolation valve control strategy; a control module, the control module is used to perform adaptive control analysis on the reservoir risk area parameter set based on the reservoir isolation valve control strategy, obtain the isolation valve coordination control parameters, and perform adaptive feedback control on the target reservoir isolation valve through the isolation valve coordination control parameters.

[0009] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0010] First, a sensor network is deployed in the target reservoir distribution scenario area, where the sensor network integration includes pressure sensors, temperature sensors, and flow sensors, and the sensor network is used to monitor and obtain the reservoir scenario environment data stream. Then, the drilling exploration signal stream is collected and acquired, and reservoir simulation modeling is performed based on the reservoir scenario environment data stream and the drilling exploration signal stream to build a three-dimensional reservoir distribution model. Then, reservoir parameter analysis and flow simulation are performed based on the three-dimensional reservoir distribution model to obtain the reservoir spatial distribution characteristics and reservoir flow trends, and multi-dimensional risk assessment is performed on the reservoir spatial distribution characteristics and reservoir flow trends to determine the reservoir risk area parameter set. Next, a reservoir isolation valve control strategy library is constructed, and the structural characteristic information of the target reservoir isolation valve and the reservoir exploitation target are matched with the reservoir isolation valve control strategy library to obtain the reservoir isolation valve control strategy. Finally, based on the reservoir isolation valve control strategy, an adaptive control analysis is performed on the reservoir risk area parameter set to obtain the isolation valve coordination control parameters, and the isolation valve coordination control parameters are used to perform adaptive feedback control on the target reservoir isolation valve. The invention solves the technical problem that the reservoir isolation valve in the prior art cannot realize precise control for complex reservoir distribution scenarios, resulting in low reservoir extraction efficiency. By adaptively adjusting the isolation valve control strategy, the technical effect of improving extraction efficiency is achieved. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0012] Figure 1 A schematic flow chart of a method for adaptively controlling a reservoir isolation valve in combination with a reservoir distribution scenario provided in an embodiment of the present application;

[0013] Figure 2 A schematic diagram of the structure of an adaptive control device for a reservoir isolation valve in combination with a reservoir distribution scenario provided in an embodiment of the present application.

[0014] Explanation of the reference numerals: data acquisition module 11 , simulation modeling module 12 , simulation analysis module 13 , matching module 14 , control module 15 . DETAILED DESCRIPTION

[0015] The present application solves the technical problem in the prior art that reservoir isolation valves cannot achieve precise control for complex reservoir distribution scenarios, resulting in low reservoir exploitation efficiency, by providing an adaptive control method and device for reservoir isolation valves combined with reservoir distribution scenarios.

[0016] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0017] It should be noted that the terms "including" and "having" are intended to cover non-exclusive inclusions. For example, a process, method, system, product or server that includes a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or modules that are not explicitly listed or are inherent to these processes, methods, products or devices.

[0018] Embodiment 1, as Figure 1 As shown, the present application provides an adaptive control method for reservoir isolation valves in combination with reservoir distribution scenarios, wherein the method includes:

[0019] A sensor network is deployed in the target reservoir distribution scenario area, wherein the sensor network integration includes pressure sensors, temperature sensors, and flow sensors, and the reservoir scenario environment data stream is monitored and acquired through the sensor network.

[0020] In the target reservoir distribution scenario area, a sensor network is deployed to fully cover the key areas of the reservoir. The sensor network integrates a variety of sensor devices, including pressure sensors, temperature sensors and flow sensors, which are used to monitor the environmental conditions of the reservoir in real time; the pressure sensor is used to monitor the pressure changes in the reservoir, the temperature sensor is used to detect the temperature changes in various areas of the reservoir, and the flow sensor is responsible for monitoring the flow rate of oil and gas fluids in the reservoir; the environmental conditions of the reservoir are monitored in real time through the sensor network to obtain the reservoir scenario environmental data stream, which contains parameters such as pressure, temperature, and flow in the reservoir area.

[0021] The drilling exploration signal stream is acquired, and reservoir simulation modeling is performed based on the reservoir scene environment data stream and the drilling exploration signal stream to construct a three-dimensional reservoir distribution model.

[0022] While acquiring the reservoir scene environment data stream, the drilling exploration signal stream is collected. The drilling exploration signal usually includes geological information, rock characteristics, fluid composition and other data generated during the drilling process. By combining the reservoir scene environment data stream with the drilling exploration signal stream and using simulation modeling technology, an accurate three-dimensional reservoir distribution model can be constructed. The three-dimensional reservoir distribution model reflects the geographical characteristics of the reservoir and the fluid flow state.

[0023] Furthermore, the construction of the three-dimensional reservoir distribution model includes:

[0024] The drilling exploration signal stream is decomposed and denoised by using the ensemble empirical mode decomposition technology to obtain a usable drilling exploration signal stream; the noise characteristic analysis is performed on the reservoir scene environment data stream to obtain data noise characteristic information, and a data filter is designed based on the data noise characteristic information; the reservoir scene environment data stream is filtered and preprocessed based on the data filter to obtain a usable reservoir scene environment data stream; the usable drilling exploration signal stream and the usable reservoir scene environment data stream are associated with parameter extraction and modeling to obtain a reservoir structure model, a reservoir deposition model and a reservoir dynamic model; the reservoir structure model, the reservoir deposition model and the reservoir dynamic model are integrated and tuned to build the three-dimensional reservoir distribution model.

[0025] Specifically, the acquired drilling exploration signal stream is decomposed and denoised using the ensemble empirical mode decomposition technique. The ensemble empirical mode decomposition technique can effectively extract the effective components in the signal and remove the background noise, thereby obtaining a usable drilling exploration signal stream. The noise characteristic analysis of the reservoir scene environmental data stream is performed to identify and quantify the noise characteristics in the data, such as random noise, periodic noise, etc. Based on the obtained data noise characteristic information, a data filter suitable for the noise characteristic is designed. The data filter is used to eliminate or reduce the noise in the environmental data stream to ensure the accuracy and availability of the data. The designed data filter is used to perform filtering preprocessing on the reservoir scene environmental data stream to obtain to the cleaned available reservoir scenario environment data stream; extract key parameters related to reservoir structure, reservoir deposition and reservoir dynamics, including formation pressure, temperature, permeability, porosity, fluid saturation, etc. from the available drilling exploration signal stream and the available reservoir scenario environment data stream; based on the extracted associated parameters, establish a reservoir structure model, a reservoir deposition model and a reservoir dynamic model, which respectively reflect the geological structure, sedimentary characteristics and fluid dynamic behavior of the reservoir; integrate and optimize the constructed reservoir structure model, reservoir deposition model and reservoir dynamic model, and through the synergistic effect of multiple models and comprehensively consider the influence of different factors, finally construct a complete three-dimensional reservoir distribution model.

[0026] Furthermore, obtaining the available drilling exploration signal stream includes:

[0027] The drilling exploration signal stream is decomposed and averaged by ensemble empirical mode decomposition technology to obtain IMF signal components; effective signal selection and filter design are performed based on the frequency characteristics and energy distribution of the IMF signal components to determine a signal low-pass filter; the drilling exploration signal stream is subjected to noise reduction and square wave shaping by a signal low-pass filter to obtain a denoised drilling exploration signal stream; the denoised drilling exploration signal stream is subjected to noise reduction effect evaluation and signal noise reduction optimization to obtain the available drilling exploration signal stream.

[0028] Specifically, the ensemble empirical mode decomposition technology adds tiny white noise to the drilling exploration signal stream multiple times, performs empirical mode decomposition on the signal after each noise addition, and then performs ensemble average of all decomposed intrinsic mode functions (IMFs) to obtain IMF signal components; the frequency characteristics and energy distribution of the IMF signal components are analyzed, and by identifying which IMF components contain effective signals related to drilling exploration (such as formation response, fluid characteristics, etc.), as well as the frequency range and energy intensity of these signals, a basis for subsequent filter design can be provided; based on the analysis results of the IMF signal components, a suitable A low-pass filter is used to filter out high-frequency noise and retain the main signal components; the designed low-pass filter is used to perform noise reduction processing on the drilling exploration signal stream. After removing the noise, square wave shaping processing is required to enhance the clarity and readability of the signal; the noise reduction effect of the drilling exploration signal stream after noise reduction processing is evaluated, and relevant indicators (such as signal-to-noise ratio, mean square error, etc.) are used to quantify the noise reduction effect; according to the results of the noise reduction effect evaluation, the noise reduction processing process is optimized, including adjusting the filter parameters, improving the noise reduction algorithm, adding additional signal processing technology, etc., to further improve the signal quality, and finally obtain a usable drilling exploration signal stream.

[0029] Reservoir parameter analysis and flow simulation are performed based on the three-dimensional reservoir distribution model to obtain reservoir spatial distribution characteristics and reservoir flow trends, and multi-dimensional risk assessment is performed on the reservoir spatial distribution characteristics and reservoir flow trends to determine a reservoir risk area parameter set.

[0030] Utilize various data in the three-dimensional reservoir distribution model to analyze reservoir parameters, evaluate the physical and chemical characteristics of the reservoir through numerical simulation, and obtain key parameters such as permeability, porosity and saturation; use flow simulation software to model the flow trend of fluids inside the reservoir, including calculating the flow path, flow velocity and pressure changes of the fluid under different conditions, so as to fully understand the dynamic behavior within the reservoir; extract the spatial distribution characteristics of the reservoir by analyzing the simulation results, and identify the fluid distribution and reserve characteristics in different areas of the reservoir; evaluate the flow trend of the reservoir fluid and obtain the reservoir flow trend based on the results of flow simulation; conduct multi-dimensional risk assessment based on the extracted spatial distribution characteristics and flow trends of the reservoir, involving the analysis of potential risk factors (such as fluid loss of control, formation collapse, etc.), and assessing their impact on mining safety and efficiency; determine the parameter set of reservoir risk areas through risk assessment.

[0031] Furthermore, the determination of the reservoir risk area parameter set includes:

[0032] The three-dimensional reservoir distribution model is divided into reservoir areas according to the reservoir spatial distribution characteristics and reservoir flow trends to obtain a reservoir distribution block set; reservoir risk factor information is obtained, and the reservoir risk factor information includes reservoir geological risk, reservoir engineering risk and reservoir environmental safety risk; based on the reservoir risk factor information, a multi-dimensional assessment is performed on the reservoir spatial distribution characteristics and reservoir flow trends to obtain a reservoir area risk parameter set; based on the reservoir area risk parameter set, the reservoir distribution block set is risk classified and identified to determine the reservoir risk area parameter set.

[0033] Specifically, the three-dimensional reservoir distribution model is regionally divided into blocks according to the spatial distribution characteristics and flow trends of the reservoir. By dividing the reservoir into multiple blocks, a set of reservoir distribution blocks is obtained. Each block has relatively consistent geological characteristics and fluid flow trends, so as to more accurately analyze and manage the characteristics and risks of each area; collect reservoir risk factor information, which includes reservoir geological risks (including reservoir heterogeneity, fault and fracture development, rock mechanical properties, etc.), reservoir engineering risks (risks involved in engineering operations such as drilling, completion, water injection, and oil production), and reservoir environmental safety risks (the impact of reservoir development on the surrounding environment, such as groundwater pollution, soil erosion, ecological damage, etc.) ; Combine the collected reservoir risk factor information with the spatial distribution characteristics and flow trends of the reservoir to conduct a multi-dimensional risk assessment. Quantitative and qualitative analysis methods can be used to identify the potential impact of different risk factors on reservoir exploitation, determine the risk level of each area, and then obtain a set of reservoir regional risk parameters. The reservoir regional risk parameter set may include risk probability, risk impact degree, risk level, etc., which are used to quantitatively represent the risk status of different areas of the reservoir; Based on the reservoir regional risk parameter set, the reservoir distribution block set is risk-classified and identified, each block is classified according to its risk level, and high-risk areas, low-risk areas, etc. are clearly identified; Combined with the risk classification results, a reservoir risk area parameter set is formed.

[0034] A reservoir isolation valve control strategy library is constructed, and the structure characteristic information of the target reservoir isolation valve and the reservoir production target are matched with the reservoir isolation valve control strategy library to obtain the reservoir isolation valve control strategy.

[0035] Collect the structural characteristics of the target reservoir isolation valve, including its material, size, operating mechanism, response time, etc.; determine the reservoir exploitation target, including production volume, production speed, recovery rate, safety requirements, etc.; according to the reservoir exploitation target and the structural characteristics of the reservoir isolation valve, analyze the control tasks that the isolation valve needs to perform during the exploitation process, such as flow regulation, pressure control, emergency closure, etc., and design corresponding control strategies for each control task; integrate the designed and verified effective control strategies into a unified strategy library to obtain the reservoir isolation valve control strategy library, which contains a variety of control strategies, covering different operating conditions and expected results, in order to cope with various changes in the reservoir exploitation process. During the exploitation process, according to the real-time monitoring data (such as pressure, temperature and flow) and the reservoir characteristics, the control strategy that best matches the structural characteristics and exploitation target of the target reservoir isolation valve is selected. Through matching, the reservoir isolation valve control strategy suitable for specific reservoir conditions is finally obtained.

[0036] Furthermore, the obtaining of the reservoir isolation valve control strategy includes:

[0037] Based on the structural characteristic information of the target reservoir isolation valve and the reservoir production target, similarity calculation is performed with the reservoir isolation valve control strategy library to obtain a control strategy similarity set; the reservoir isolation valve control strategy library is arranged in descending order according to the control strategy similarity set to obtain an isolation valve control strategy sequence set; strategy matching optimization is performed based on the isolation valve control strategy sequence set to obtain a matching isolation valve control strategy; deviation analysis and strategy optimization are performed on the matching isolation valve control strategy based on the control strategy similarity set to obtain the reservoir isolation valve control strategy.

[0038] Specifically, based on the structural characteristic information and production objectives of the target reservoir isolation valve, similarity calculation is performed with each strategy in the control strategy library, and algorithms (such as cosine similarity, Euclidean distance, etc.) are used to quantify the similarity between each strategy and the target characteristics to form a control strategy similarity set; according to the calculated control strategy similarity set, the reservoir isolation valve control strategy library is sorted in descending order to obtain an isolation valve control strategy sequence set; in the isolation valve control strategy sequence set, strategy matching optimization is performed to select the control strategy with the greatest similarity as the matching isolation valve control strategy; for the selected matching isolation valve control strategy, deviation analysis is performed based on the control strategy similarity set to identify possible minor deviations between the selected strategy and the target requirements, and according to the results of the deviation analysis, necessary optimization is performed on the matching isolation valve control strategy, including fine-tuning of control parameters, adding additional monitoring or protection mechanisms, or optimizing the strategy execution process; after deviation analysis and strategy optimization, the final reservoir isolation valve control strategy is obtained.

[0039] Based on the reservoir isolation valve control strategy, an adaptive control analysis is performed on the reservoir risk area parameter set to obtain isolation valve coordination control parameters, and adaptive feedback control is performed on the target reservoir isolation valve through the isolation valve coordination control parameters.

[0040] The reservoir isolation valve control strategy is used to perform adaptive control analysis on the reservoir risk area parameter set, and the isolation valve coordinated control parameters are obtained. Subsequently, the isolation valve of the target reservoir is adaptively feedback controlled through the isolation valve coordinated control parameters to ensure the recovery efficiency and safety of the reservoir.

[0041] Furthermore, obtaining the isolation valve coordinated control parameters includes:

[0042] According to the reservoir isolation valve control strategy, an adaptive learning network architecture is selected; a reservoir isolation valve control parameter set is collected and acquired, and the reservoir isolation valve control parameter set is classified into strategy control factor categories according to the reservoir isolation valve control strategy to obtain an isolation valve control factor parameter set; the isolation valve control factor parameter set is branch trained and optimized using the adaptive learning network architecture to determine an isolation valve control adaptive network; an adaptive control analysis is performed on the reservoir risk area parameter set based on the isolation valve control adaptive network to output the isolation valve coordination control parameters.

[0043] Specifically, according to the characteristics of the reservoir isolation valve control strategy, a suitable adaptive learning network architecture (such as deep neural network, recursive neural network, etc.) is selected. The architecture should have the ability to process complex data relationships and real-time learning to support dynamic adjustment of control parameters; the control parameter set of the reservoir isolation valve is collected, including various operating states, environmental conditions, system responses and other information, and the reservoir isolation valve control parameter set is classified according to the reservoir isolation valve control strategy, and the main control factors affecting the isolation valve performance are identified, so as to obtain the isolation valve control factor parameter set, such as switch state, opening control, rotation speed and torque, etc.; for each isolation valve control factor parameter set, the selected adaptive learning network architecture is used for branch training and optimization, that is, a network branch is established for each control factor, and each branch focuses on learning and optimizing the control strategy related to the factor; through training, the network can identify the relationship between each parameter and the control effect, thereby enhancing the prediction ability and adaptability of the model; based on the trained isolation valve control adaptive network, the reservoir risk area parameter set is adaptively controlled and analyzed to obtain the isolation valve coordinated control parameters.

[0044] Further, the determining of the isolation valve control adaptive network includes:

[0045] The adaptive learning network architecture is used to perform branch training and fusion on the isolation valve control factor parameter set to obtain an initial isolation valve control fusion network; the initial isolation valve control fusion network is verified and evaluated to obtain network performance parameters, and a network optimizer is selected based on the network performance parameters; a network loss function is constructed based on the adaptive network fusion optimization target; the network loss function is minimized based on the network optimizer, and the initial isolation valve control fusion network is iteratively optimized based on the solution results to determine the isolation valve control adaptive network.

[0046] Specifically, an adaptive learning network architecture is used to perform independent branch training on each isolation valve control factor parameter set, and each branch network focuses on learning and optimizing the feature representation and control strategy related to its corresponding control factor; after the branch training is completed, an appropriate fusion strategy (such as weighted average) is used to fuse the outputs of each branch network to obtain an initial isolation valve control fusion network; the initial isolation valve control fusion network is verified and evaluated to evaluate the network's performance in prediction and control, and obtain relevant network performance parameters (such as accuracy, loss value, etc.); based on the obtained network performance parameters, a comprehensive analysis of the network performance is performed. Identify which aspects of the network perform well and which aspects have deficiencies; select a suitable network optimizer (such as stochastic gradient descent, momentum optimizer, etc.) based on the results of network performance analysis and the characteristics of the network optimizer; construct a corresponding network loss function based on the adaptive network fusion optimization goal. The loss function is used to quantify the gap between the network prediction results and the actual control effect to guide the network optimization process; use the selected network optimizer to minimize the constructed network loss function, and continuously adjust the network parameters through the back propagation algorithm to reduce the value of the loss function, thereby improving the prediction ability of the model; according to the solution results, iteratively optimize the parameters of the initial isolation valve control fusion network, continuously improve the network performance, and finally determine the isolation valve control adaptive network.

[0047] In summary, the embodiments of the present application have at least the following technical effects:

[0048] First, a sensor network is deployed in the target reservoir distribution scenario area, where the sensor network integration includes pressure sensors, temperature sensors, and flow sensors, and the sensor network is used to monitor and obtain the reservoir scenario environment data stream. Then, the drilling exploration signal stream is collected and acquired, and reservoir simulation modeling is performed based on the reservoir scenario environment data stream and the drilling exploration signal stream to build a three-dimensional reservoir distribution model. Then, reservoir parameter analysis and flow simulation are performed based on the three-dimensional reservoir distribution model to obtain the reservoir spatial distribution characteristics and reservoir flow trends, and multi-dimensional risk assessment is performed on the reservoir spatial distribution characteristics and reservoir flow trends to determine the reservoir risk area parameter set. Next, a reservoir isolation valve control strategy library is constructed, and the structural characteristic information of the target reservoir isolation valve and the reservoir exploitation target are matched with the reservoir isolation valve control strategy library to obtain the reservoir isolation valve control strategy. Finally, based on the reservoir isolation valve control strategy, an adaptive control analysis is performed on the reservoir risk area parameter set to obtain the isolation valve coordination control parameters, and the isolation valve coordination control parameters are used to perform adaptive feedback control on the target reservoir isolation valve. The invention solves the technical problem that the reservoir isolation valve in the prior art cannot realize precise control for complex reservoir distribution scenarios, resulting in low reservoir extraction efficiency. By adaptively adjusting the isolation valve control strategy, the technical effect of improving extraction efficiency is achieved.

[0049] Embodiment 2 is based on the same inventive concept as the adaptive control method of reservoir isolation valve combined with reservoir distribution scenario in the above embodiment. Figure 2 As shown, the present application provides an adaptive control device for a reservoir isolation valve in combination with a reservoir distribution scenario, wherein the device comprises:

[0050] A data acquisition module 11, the data acquisition module 11 is used to deploy a sensor network in the target reservoir distribution scenario area, wherein the sensor network integration includes pressure sensors, temperature sensors, flow sensors, and the reservoir scenario environment data stream is monitored and acquired through the sensor network; a simulation modeling module 12, the simulation modeling module 12 is used to acquire a drilling exploration signal stream, perform reservoir simulation modeling based on the reservoir scenario environment data stream and the drilling exploration signal stream, and construct a three-dimensional reservoir distribution model; a simulation analysis module 13, the simulation analysis module 13 is used to perform reservoir parameter analysis and flow simulation based on the three-dimensional reservoir distribution model, and obtain the reservoir spatial distribution characteristics and Reservoir flow trend, perform multi-dimensional risk assessment on the spatial distribution characteristics of the reservoir and the reservoir flow trend, and determine the reservoir risk area parameter set; a matching module 14, the matching module 14 is used to build a reservoir isolation valve control strategy library, match the reservoir isolation valve control strategy library according to the structural characteristic information of the target reservoir isolation valve and the reservoir production target, and obtain the reservoir isolation valve control strategy; a control module 15, the control module 15 is used to perform adaptive control analysis on the reservoir risk area parameter set based on the reservoir isolation valve control strategy, obtain the isolation valve coordination control parameters, and perform adaptive feedback control on the target reservoir isolation valve through the isolation valve coordination control parameters.

[0051] Furthermore, the simulation modeling module 12 is used to perform the following method:

[0052] The drilling exploration signal stream is decomposed and denoised by using the ensemble empirical mode decomposition technology to obtain a usable drilling exploration signal stream; the noise characteristic analysis is performed on the reservoir scene environment data stream to obtain data noise characteristic information, and a data filter is designed based on the data noise characteristic information; the reservoir scene environment data stream is filtered and preprocessed based on the data filter to obtain a usable reservoir scene environment data stream; the usable drilling exploration signal stream and the usable reservoir scene environment data stream are associated with parameter extraction and modeling to obtain a reservoir structure model, a reservoir deposition model and a reservoir dynamic model; the reservoir structure model, the reservoir deposition model and the reservoir dynamic model are integrated and tuned to build the three-dimensional reservoir distribution model.

[0053] Furthermore, the simulation modeling module 12 is used to perform the following method:

[0054] The drilling exploration signal stream is decomposed and averaged by ensemble empirical mode decomposition technology to obtain IMF signal components; effective signal selection and filter design are performed based on the frequency characteristics and energy distribution of the IMF signal components to determine a signal low-pass filter; the drilling exploration signal stream is subjected to noise reduction and square wave shaping by a signal low-pass filter to obtain a denoised drilling exploration signal stream; the denoised drilling exploration signal stream is subjected to noise reduction effect evaluation and signal noise reduction optimization to obtain the available drilling exploration signal stream.

[0055] Furthermore, the simulation analysis module 13 is used to perform the following method:

[0056] The three-dimensional reservoir distribution model is divided into reservoir areas according to the reservoir spatial distribution characteristics and reservoir flow trends to obtain a reservoir distribution block set; reservoir risk factor information is obtained, and the reservoir risk factor information includes reservoir geological risk, reservoir engineering risk and reservoir environmental safety risk; based on the reservoir risk factor information, a multi-dimensional assessment is performed on the reservoir spatial distribution characteristics and reservoir flow trends to obtain a reservoir area risk parameter set; based on the reservoir area risk parameter set, the reservoir distribution block set is risk classified and identified to determine the reservoir risk area parameter set.

[0057] Furthermore, the matching module 14 is used to perform the following method:

[0058] Based on the structural characteristic information of the target reservoir isolation valve and the reservoir production target, similarity calculation is performed with the reservoir isolation valve control strategy library to obtain a control strategy similarity set; the reservoir isolation valve control strategy library is arranged in descending order according to the control strategy similarity set to obtain an isolation valve control strategy sequence set; strategy matching optimization is performed based on the isolation valve control strategy sequence set to obtain a matching isolation valve control strategy; deviation analysis and strategy optimization are performed on the matching isolation valve control strategy based on the control strategy similarity set to obtain the reservoir isolation valve control strategy.

[0059] Furthermore, the control module 15 is used to execute the following method:

[0060] According to the reservoir isolation valve control strategy, an adaptive learning network architecture is selected; a reservoir isolation valve control parameter set is collected and acquired, and the reservoir isolation valve control parameter set is classified into strategy control factor categories according to the reservoir isolation valve control strategy to obtain an isolation valve control factor parameter set; the isolation valve control factor parameter set is branch trained and optimized using the adaptive learning network architecture to determine an isolation valve control adaptive network; an adaptive control analysis is performed on the reservoir risk area parameter set based on the isolation valve control adaptive network to output the isolation valve coordination control parameters.

[0061] Furthermore, the control module 15 is used to execute the following method:

[0062] The adaptive learning network architecture is used to perform branch training and fusion on the isolation valve control factor parameter set to obtain an initial isolation valve control fusion network; the initial isolation valve control fusion network is verified and evaluated to obtain network performance parameters, and a network optimizer is selected based on the network performance parameters; a network loss function is constructed based on the adaptive network fusion optimization target; the network loss function is minimized based on the network optimizer, and the initial isolation valve control fusion network is iteratively optimized based on the solution results to determine the isolation valve control adaptive network.

[0063] It should be noted that the above-mentioned sequence of the embodiments of the present application is only for description and does not represent the advantages and disadvantages of the embodiments. And the above-mentioned specific embodiments of this specification are described. The processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0064] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application shall be included in the protection scope of the present application.

[0065] This specification and drawings are merely exemplary illustrations of the present application and are deemed to cover any and all modifications, variations, combinations or equivalents within the scope of the present application. Obviously, a person skilled in the art may make various modifications and variations to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalents, the present application intends to include these modifications and variations.

Claims

1. An adaptive control method for reservoir isolation valves in combination with reservoir distribution scenarios, characterized in that: The method comprises: Deploy a sensor network in the target reservoir distribution scenario area, wherein the sensor network integration includes pressure sensors, temperature sensors, and flow sensors, and monitors and obtains reservoir scenario environment data streams through the sensor network; Acquire the drilling exploration signal stream, perform reservoir simulation modeling based on the reservoir scene environment data stream and the drilling exploration signal stream, and construct a three-dimensional reservoir distribution model; Performing reservoir parameter analysis and flow simulation based on the three-dimensional reservoir distribution model to obtain reservoir spatial distribution characteristics and reservoir flow trends, performing multi-dimensional risk assessment on the reservoir spatial distribution characteristics and reservoir flow trends, and determining a reservoir risk area parameter set; Constructing a reservoir isolation valve control strategy library, matching the target reservoir isolation valve's structural characteristic information and the reservoir production target with the reservoir isolation valve control strategy library to obtain the reservoir isolation valve control strategy; Based on the reservoir isolation valve control strategy, an adaptive control analysis is performed on the reservoir risk area parameter set to obtain isolation valve coordination control parameters, and adaptive feedback control is performed on the target reservoir isolation valve through the isolation valve coordination control parameters.

2. The method for adaptively controlling reservoir isolation valves in combination with reservoir distribution scenarios according to claim 1, characterized in that: The construction of the three-dimensional reservoir distribution model comprises: Using ensemble empirical mode decomposition technology to decompose and reduce noise on the drilling exploration signal stream to obtain a usable drilling exploration signal stream; Performing noise characteristic analysis on the reservoir scene environment data stream to obtain data noise characteristic information, and designing a data filter based on the data noise characteristic information; Performing filtering preprocessing on the reservoir scene environment data stream based on the data filter to obtain a usable reservoir scene environment data stream; Performing correlation parameter extraction modeling on the available drilling exploration signal stream and the available reservoir scene environment data stream to obtain a reservoir structural model, a reservoir deposition model and a reservoir dynamic model; The reservoir structure model, reservoir sedimentation model and reservoir dynamic model are integrated and optimized to build the three-dimensional reservoir distribution model.

3. The method for adaptively controlling reservoir isolation valves in combination with reservoir distribution scenarios according to claim 2, characterized in that: The method of obtaining the available drilling exploration signal stream comprises: Using ensemble empirical mode decomposition technology to decompose and ensemble average the drilling exploration signal stream to obtain IMF signal components; Perform effective signal selection and filter design based on the frequency characteristics and energy distribution of the IMF signal components, and determine a signal low-pass filter; Using a signal low-pass filter to perform noise reduction and square wave shaping on the drilling exploration signal stream to obtain a denoised drilling exploration signal stream; The denoising drilling exploration signal stream is subjected to denoising effect evaluation and signal denoising optimization to obtain the usable drilling exploration signal stream.

4. The method for adaptively controlling reservoir isolation valves in combination with reservoir distribution scenarios according to claim 1, characterized in that: The step of determining a set of reservoir risk area parameters includes: Divide the three-dimensional reservoir distribution model into reservoir areas according to the reservoir spatial distribution characteristics and reservoir flow trends to obtain a reservoir distribution block set; Acquiring reservoir risk factor information, wherein the reservoir risk factor information includes reservoir geological risk, reservoir engineering risk, and reservoir environmental safety risk; Based on the reservoir risk factor information, a multi-dimensional evaluation is performed on the reservoir spatial distribution characteristics and reservoir flow trend to obtain a reservoir regional risk parameter set; The reservoir distribution block set is risk classified and identified based on the reservoir area risk parameter set to determine the reservoir risk area parameter set.

5. The method for adaptively controlling reservoir isolation valves in combination with reservoir distribution scenarios according to claim 1, characterized in that: The obtaining of the reservoir isolation valve control strategy comprises: Based on the structural characteristic information of the target reservoir isolation valve and the reservoir production target, similarity calculation is performed with the reservoir isolation valve control strategy library to obtain a control strategy similarity set; Arranging the reservoir isolation valve control strategy library in descending order according to the control strategy similarity set to obtain an isolation valve control strategy sequence set; Performing strategy matching optimization based on the isolation valve control strategy sequence set to obtain a matching isolation valve control strategy; Based on the control strategy similarity set, deviation analysis and strategy optimization are performed on the matching isolation valve control strategy to obtain the reservoir isolation valve control strategy.

6. The method for adaptively controlling reservoir isolation valves in combination with reservoir distribution scenarios according to claim 1, characterized in that: The obtaining of the isolation valve coordinated control parameters comprises: selecting an adaptive learning network architecture according to the reservoir isolation valve control strategy; Acquire a reservoir isolation valve control parameter set, classify the reservoir isolation valve control parameter set by strategy control factors according to the reservoir isolation valve control strategy, and obtain an isolation valve control factor parameter set; Using the adaptive learning network architecture, branch training optimization is performed on the isolation valve control factor parameter set to determine an isolation valve control adaptive network; Based on the isolation valve control adaptive network, an adaptive control analysis is performed on the reservoir risk area parameter set, and the isolation valve coordinated control parameters are output.

7. The method for adaptively controlling reservoir isolation valves in combination with reservoir distribution scenarios according to claim 6, characterized in that: The determining isolation valve control adaptive network comprises: Using the adaptive learning network architecture, branch training and fusion are performed on the isolation valve control factor parameter set to obtain an initial isolation valve control fusion network; Verifying and evaluating the initial isolation valve control fusion network to obtain network performance parameters, and selecting and obtaining a network optimizer based on the network performance parameters; Construct a network loss function based on the adaptive network fusion optimization goal; The network loss function is minimized based on the network optimizer, and the initial isolation valve control fusion network is iteratively optimized according to the solution result to determine the isolation valve control adaptive network.

8. An adaptive control device for reservoir isolation valves in combination with reservoir distribution scenarios, characterized in that: The device for implementing the method for adaptively controlling a reservoir isolation valve in combination with a reservoir distribution scenario according to any one of claims 1 to 7 comprises: A data acquisition module, wherein the data acquisition module is used to deploy a sensor network in the target reservoir distribution scene area, wherein the sensor network integration includes a pressure sensor, a temperature sensor, and a flow sensor, and the reservoir scene environment data flow is monitored and acquired through the sensor network; A simulation modeling module, the simulation modeling module is used to collect and acquire the drilling exploration signal stream, perform reservoir simulation modeling based on the reservoir scene environment data stream and the drilling exploration signal stream, and construct a three-dimensional model of reservoir distribution; A simulation analysis module, which is used to perform reservoir parameter analysis and flow simulation based on the three-dimensional reservoir distribution model, obtain reservoir spatial distribution characteristics and reservoir flow trends, perform multi-dimensional risk assessment on the reservoir spatial distribution characteristics and reservoir flow trends, and determine a reservoir risk area parameter set; A matching module, wherein the matching module is used to construct a reservoir isolation valve control strategy library, and to match the reservoir isolation valve control strategy library with the structural characteristic information of the target reservoir isolation valve and the reservoir production target to obtain the reservoir isolation valve control strategy; A control module, the control module is used to perform adaptive control analysis on the reservoir risk area parameter set based on the reservoir isolation valve control strategy, obtain isolation valve coordination control parameters, and perform adaptive feedback control on the target reservoir isolation valve through the isolation valve coordination control parameters.

Images