A method, device and medium for enhancing production of an offshore oil reservoir based on a neural network

Abstract

The embodiments of this specification disclose a method, device, and medium for increasing the production of an offshore oil reservoir based on a neural network, including: obtaining current offshore oil reservoir parameters; if the oil production per unit time of the offshore oil reservoir in the current offshore oil reservoir parameters is lower than the preset unit oil production; inputting the production pressure difference, injection pressure difference, oil reservoir exploitation ratio in the current offshore oil reservoir parameters, and the preset unit oil production into a pre-trained production adjustment model to obtain a pressure difference adjustment plan, where the production adjustment model is a multi-layer perceptron neural network model including multiple fully connected layers, and the pressure difference adjustment plan includes adjusting the production pressure difference and / or injection pressure difference, and the production pressure difference adjustment value and / or injection pressure difference adjustment value; adjusting the production pressure difference and / or injection pressure difference of the offshore oil reservoir in the current offshore oil reservoir parameters according to the pressure difference adjustment plan to increase the oil production per unit time of the current offshore oil reservoir.

Description

Technical Field

[0001] This specification relates to the field of computer technology, and in particular to a method, device, and medium for increasing production of marine oil reservoirs based on neural networks. Background Art

[0002] Marine oil reservoirs refer to strata containing recoverable petroleum resources located at the bottom of the ocean or beneath the ocean. Due to the particularities of the marine geological environment, the exploitation of marine oil reservoirs is more complex and difficult than that of terrestrial oil fields.

[0003] During offshore oil reservoir development, controlling production differential pressure and water injection differential pressure is often challenging. Production differential pressure refers to the difference between the reservoir's internal pressure and the wellhead pressure, while water injection differential pressure refers to the difference between the pressure of the injected water and the reservoir's internal pressure. By adjusting these differential pressures, oil production can be effectively controlled.

[0004] However, the current offshore oil reservoir exploitation technology cannot effectively control the production pressure difference and water injection pressure difference, resulting in the oil production per unit time failing to meet expectations. Summary of the Invention

[0005] One or more embodiments of this specification provide a method, device, and medium for increasing the production of marine oil reservoirs based on a neural network, which are used to solve the technical problems raised by the background technology.

[0006] One or more embodiments of this specification adopt the following technical solutions:

[0007] One or more embodiments of this specification provide a method for increasing production of marine oil reservoirs based on a neural network, comprising:

[0008] During the exploitation of an offshore oil reservoir, current offshore oil reservoir parameters are obtained, including the production pressure difference, water injection pressure difference, oil reservoir exploitation ratio, and oil production per unit time of the offshore oil reservoir;

[0009] If the oil production per unit time of the marine oil reservoir in the current marine oil reservoir parameters is lower than the preset unit oil production;

[0010] Inputting the production differential pressure, water injection differential pressure, and oil reservoir production ratio of the marine oil reservoir, as well as the preset unit oil production, of the current marine oil reservoir parameters into a pre-trained production adjustment model to obtain a pressure differential adjustment scheme, wherein the production adjustment model is a multi-layer perceptron neural network model including a plurality of fully connected layers, and the pressure differential adjustment scheme includes adjusting the production differential pressure and / or the water injection differential pressure, as well as a production differential pressure adjustment value and / or a water injection differential pressure adjustment value;

[0011] Adjust the production pressure difference and / or injection pressure difference of the marine reservoir in the current marine reservoir parameters according to the pressure difference adjustment plan to increase the oil production per unit time of the current marine reservoir.

[0012] It should be noted that the embodiments of this specification have the following beneficial effects through the above content:

[0013] Increase oil production: By analyzing and adjusting the current marine reservoir parameters, this method can effectively control and adjust the production pressure difference and injection pressure difference. Through the pressure difference adjustment plan obtained from the pre-trained neural network model, the production pressure difference and injection pressure difference of the marine reservoir can be accurately adjusted. By reasonably adjusting the production pressure difference and injection pressure difference, the pressure distribution of the reservoir can be improved, the fluidity of the oil in the reservoir can be increased, and thus the oil production per unit time can be effectively increased.

[0014] Improve recovery efficiency: By effectively controlling and adjusting the production pressure difference and injection pressure difference, the oil production capacity in the reservoir can be increased, the fluidity of the oil in the reservoir can be enhanced, and the oil in the reservoir can be promoted to move towards the wellhead. This will help improve the recovery efficiency of the reservoir, that is, the ratio between the total amount of oil obtained from the reservoir and the total amount of recoverable oil.

[0015] Improve economic benefits: By increasing the oil production per unit time and recovery efficiency, the oil production and production efficiency of the oilfield can be significantly increased, thus bringing more oil output. This will improve the economic benefits of the oilfield and increase the income and profits of oil companies.

[0016] Fast response and precise adjustment: This method uses a pre-trained neural network model to calculate the pressure difference adjustment plan, which has the characteristics of fast response and precise adjustment. By inputting the current marine reservoir parameters, a pressure difference adjustment plan suitable for actual conditions can be quickly obtained, and the production pressure difference and injection pressure difference can be precisely adjusted. This will improve the flexibility and response ability of the reservoir exploitation process.

[0017] Furthermore, the current marine reservoir parameters in the embodiments of this specification also include marine geological characteristics;

[0018] Inputting the production pressure difference, injection pressure difference, and reservoir exploitation ratio of the marine reservoir in the current marine reservoir parameters, as well as the preset unit oil production, into the pre-trained production adjustment model to obtain a pressure difference adjustment plan, includes:

[0019] Input the production pressure difference, injection pressure difference, reservoir exploitation ratio, and marine geological characteristics of the marine reservoir in the current marine reservoir parameters, as well as the preset unit oil production, into the production adjustment model to obtain a pressure difference adjustment plan.

[0020] It should be noted that the embodiments of this specification have the following beneficial effects through the above content:

[0021] Optimize resource utilization: Considering the influence of marine geological characteristics on reservoir exploitation, reservoir resources can be utilized more reasonably to avoid waste of resources.

[0022] Furthermore, the marine geological characteristics in the embodiments of this specification include geological structure, lithological characteristics, and sedimentary characteristics.

[0023] Furthermore, the current marine reservoir parameters in the embodiments of this specification further include marine reservoir characteristics;

[0024] Before adjusting the production pressure difference and / or injection pressure difference of the marine reservoir in the current marine reservoir parameters according to the pressure difference adjustment plan, the method further includes:

[0025] Input the production pressure difference, injection pressure difference, and marine reservoir characteristics of the marine reservoir in the current marine reservoir parameters into a pressure difference optimization model to obtain a pressure difference optimization plan. The pressure difference optimization model is an optimization model based on big data analysis. The pressure difference optimization plan includes optimized production pressure difference and / or injection pressure difference, and production pressure difference optimization value and / or injection pressure difference optimization value;

[0026] Compare the error between the pressure difference optimization plan and the pressure difference adjustment plan;

[0027] If the error is less than a preset threshold, execute the adjustment of the production pressure difference and / or injection pressure difference of the marine reservoir in the current marine reservoir parameters according to the pressure difference adjustment plan.

[0028] It should be noted that through the above content, the embodiments of this specification have the following beneficial effects:

[0029] Reduce error: By comparing the error between the pressure difference optimization plan and the pressure difference adjustment plan, the accuracy and feasibility of the production adjustment model can be evaluated and verified. If the error is less than the preset threshold, it indicates that the result of the production adjustment model is relatively reliable, and the adjustment plan can be executed.

[0030] Furthermore, the marine reservoir characteristics in the embodiments of this specification include the permeability and porosity of the marine reservoir.

[0031] Furthermore, in the embodiments of this specification, before adjusting the production pressure difference and / or injection pressure difference of the marine reservoir in the current marine reservoir parameters according to the pressure difference adjustment plan, the method further includes:

[0032] Determine the final production pressure difference and / or final injection pressure difference according to the production pressure difference adjustment value and / or injection pressure difference adjustment value;

[0033] Determine whether the final production pressure difference and / or the final injection pressure difference exceed the pre-set maximum production pressure difference and / or the maximum injection pressure difference;

[0034] If not, adjust the production pressure difference and / or the injection pressure difference of the marine reservoir in the current marine reservoir parameters according to the pressure difference adjustment plan.

[0035] It should be noted that the embodiments of this specification have the following beneficial effects through the above content:

[0036] First, by determining the final production pressure difference and / or the final injection pressure difference according to the production pressure difference adjustment value and / or the injection pressure difference adjustment value, it can be ensured that the adjusted pressure difference value is reasonable, avoiding the adverse effects of too large or too small pressure differences on the reservoir.

[0037] Second, by judging whether the final production pressure difference and / or the final injection pressure difference exceed the pre-set maximum production pressure difference and / or the maximum injection pressure difference, it can be ensured that the adjusted pressure difference value will not exceed the range that the reservoir can withstand, thus protecting the reservoir from damage.

[0038] Finally, if the final production pressure difference and / or the final injection pressure difference do not exceed the pre-set maximum pressure difference value, then the production pressure difference and / or the injection pressure difference of the marine reservoir in the current marine reservoir parameters can be adjusted according to the pressure difference adjustment plan. This can effectively improve the development efficiency of the reservoir, increase the production of the reservoir, and thus improve the economic benefits.

[0039] Furthermore, in the embodiments of this specification, before determining whether the final production pressure difference and / or the final injection pressure difference exceed the pre-set maximum production pressure difference and / or the maximum injection pressure difference, the method further includes:

[0040] Obtain the maximum production pressure difference and the maximum injection pressure difference that the marine reservoir can withstand according to the permeability and porosity of the marine reservoir formation in the marine reservoir characteristics, and the geological structure, lithological characteristics and sedimentary characteristics in the marine geological characteristics.

[0041] It should be noted that the embodiments of this specification have the following beneficial effects through the above content:

[0042] Improved safety: By pre-setting the maximum production pressure difference and the maximum injection pressure difference, it can effectively prevent reservoir damage or safety accidents caused by excessive pressure. Understanding and complying with the maximum bearing pressure of the reservoir helps to maintain the stability and production safety of the reservoir.

[0043] Reservoir protection: Based on factors such as the permeability, porosity, geological structure, lithological characteristics, and sedimentary characteristics of the reservoir, the bearing capacity of the reservoir can be more accurately judged, thereby avoiding reservoir fractures, pollution, or other forms of damage caused by overpressure production.

[0044] Enhanced oil recovery: Reasonable production pressure differences and injection pressure differences contribute to increasing the oil recovery rate in the reservoir. By precisely controlling the pressure, the production strategy can be optimized to enable more crude oil to be effectively produced.

[0045] Prolonging reservoir life: By scientifically managing the reservoir pressure, the decline rate of the reservoir can be slowed down, and the production cycle of the reservoir can be extended, thereby maximizing economic benefits.

[0046] Furthermore, in the embodiments of this specification, if the final production pressure difference and / or the final injection pressure difference exceed the preset maximum production pressure difference and / or the maximum injection pressure difference, the method further includes:

[0047] Determine the adjusted production pressure difference and / or injection pressure difference according to the pressure difference adjustment plan;

[0048] Adjust the production pressure difference and / or injection pressure difference of the marine reservoir in the current marine reservoir parameters according to the maximum production pressure difference and / or the maximum injection pressure difference.

[0049] It should be noted that the embodiments of this specification have the following beneficial effects through the above content:

[0050] Protecting reservoir stability: By determining the adjustment value of the pressure difference according to the pressure difference adjustment plan and adjusting the pressure difference of the current reservoir according to the limit of the maximum pressure difference, it is possible to avoid adverse effects on the stability of the reservoir caused by excessive or too low pressure, thereby protecting the production capacity and long-term sustainable exploitation of the reservoir.

[0051] Reducing the risk of reservoir damage: Timely adjusting the production pressure difference and injection pressure difference to keep them within an appropriate range can avoid the risk of reservoir damage caused by excessive or too low pressure differences, such as reservoir fractures and pore collapses.

[0052] An oil production enhancement device for a marine reservoir based on a neural network provided by one or more embodiments of this specification includes:

[0053] At least one processor; and,

[0054] A memory communicatively connected to the at least one processor; wherein,

[0055] The memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to:

[0056] When exploiting an offshore oil reservoir, obtain the current offshore oil reservoir parameters, where the current offshore oil reservoir parameters include the production pressure difference, injection pressure difference, oil reservoir exploitation ratio, and oil production per unit time of the offshore oil reservoir;

[0057] If the oil production per unit time of the offshore oil reservoir in the current offshore oil reservoir parameters is lower than the preset oil production per unit;

[0058] Input the production pressure difference, injection pressure difference, and oil reservoir exploitation ratio of the offshore oil reservoir in the current offshore oil reservoir parameters, as well as the preset oil production per unit, into a pre-trained production adjustment model to obtain a pressure difference adjustment plan. The production adjustment model is a multi-layer perceptron neural network model including multiple fully connected layers. The pressure difference adjustment plan includes adjusting the production pressure difference and / or injection pressure difference, as well as the production pressure difference adjustment value and / or injection pressure difference adjustment value;

[0059] Adjust the production pressure difference and / or injection pressure difference of the offshore oil reservoir in the current offshore oil reservoir parameters according to the pressure difference adjustment plan to increase the oil production per unit time of the current offshore oil reservoir.

[0060] A non-volatile computer storage medium provided by one or more embodiments of this specification stores computer-executable instructions, and when the computer-executable instructions are executed by a computer, they can achieve:

[0061] When exploiting an offshore oil reservoir, obtain the current offshore oil reservoir parameters, where the current offshore oil reservoir parameters include the production pressure difference, injection pressure difference, oil reservoir exploitation ratio, and oil production per unit time of the offshore oil reservoir;

[0062] If the oil production per unit time of the offshore oil reservoir in the current offshore oil reservoir parameters is lower than the preset oil production per unit;

[0063] Input the production pressure difference, injection pressure difference, and oil reservoir exploitation ratio of the offshore oil reservoir in the current offshore oil reservoir parameters, as well as the preset oil production per unit, into a pre-trained production adjustment model to obtain a pressure difference adjustment plan. The production adjustment model is a multi-layer perceptron neural network model including multiple fully connected layers. The pressure difference adjustment plan includes adjusting the production pressure difference and / or injection pressure difference, as well as the production pressure difference adjustment value and / or injection pressure difference adjustment value;

[0064] Adjust the production pressure difference and / or injection pressure difference of the offshore oil reservoir in the current offshore oil reservoir parameters according to the pressure difference adjustment plan to increase the oil production per unit time of the current offshore oil reservoir.

[0065] The above at least one technical solution adopted by the embodiments of this specification can achieve the following beneficial effects:

[0066] Increasing oil production: By analyzing and adjusting the current parameters of the offshore oil reservoir, this method can effectively control and adjust the production pressure difference and injection pressure difference. Through the pressure difference adjustment scheme obtained according to the pre-trained neural network model, the production pressure difference and injection pressure difference of the offshore oil reservoir can be accurately adjusted. By reasonably adjusting the production pressure difference and injection pressure difference, the pressure distribution of the oil reservoir can be improved, the fluidity of the oil in the oil reservoir can be enhanced, and thus the oil production per unit time can be effectively increased.

[0067] Increasing oil recovery rate: By effectively controlling and adjusting the production pressure difference and injection pressure difference, the oil production capacity in the oil reservoir can be increased, the fluidity of the oil in the oil reservoir can be enhanced, and the oil in the oil reservoir can be promoted to move towards the wellhead. This will help increase the oil recovery rate of the oil reservoir, that is, the ratio between the total amount of oil obtained from the oil reservoir and the total amount of recoverable oil.

[0068] Increasing economic benefits: By increasing the oil production per unit time and the oil recovery rate, the production and production efficiency of the oilfield can be significantly increased, resulting in more oil output. This will improve the economic benefits of the oilfield and increase the income and profits of oil companies.

[0069] Quick response and precise adjustment: This method uses a pre-trained neural network model to calculate the pressure difference adjustment scheme, which features quick response and precise adjustment. By inputting the current parameters of the offshore oil reservoir, a pressure difference adjustment scheme suitable for the actual conditions can be quickly obtained, and the production pressure difference and injection pressure difference can be precisely adjusted. This will improve the flexibility and response ability of the oil reservoir exploitation process. Description of the Drawings

[0070] To more clearly illustrate the technical solutions in the embodiments of this specification or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments recorded in this specification. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings. In the drawings:

[0071] Figure 1 It is a schematic flowchart of a method for increasing production of an offshore oil reservoir based on a neural network provided by one or more embodiments of this specification;

[0072] Figure 2 It is a schematic structural diagram of a device for increasing production of an offshore oil reservoir based on a neural network provided by one or more embodiments of this specification. Detailed Embodiments

[0073] The embodiments of this specification provide a method, a device, and a medium for increasing production of an offshore oil reservoir based on a neural network.

[0074] To enable those skilled in the art to better understand the technical solutions in this specification, the following will clearly and completely describe the technical solutions in the embodiments of this specification in conjunction with the accompanying drawings in the embodiments of this specification. Obviously, the described embodiments are only a part of the embodiments of this specification, rather than all the embodiments. Based on the embodiments of this specification, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the scope of protection of this specification.

[0075] Figure 1 It is a schematic flowchart of a method for enhancing oil production in an offshore oil reservoir based on a neural network provided for one or more embodiments of this specification. This process can be executed by an oil production increase system. Some input parameters or intermediate results in the process allow manual intervention and adjustment to help improve accuracy.

[0076] The method flow steps of the embodiments of this specification are as follows:

[0077] S102. During the exploitation of the offshore oil reservoir, obtain the current offshore oil reservoir parameters, where the current offshore oil reservoir parameters include the production pressure difference, injection pressure difference, oil reservoir exploitation ratio, and oil production per unit time of the offshore oil reservoir.

[0078] In the embodiments of this specification, for the above content, the following specific implementation schemes can be adopted:

[0079] Data collection and monitoring: Establish a data acquisition module. The acquisition module can include various sensors, monitoring devices, etc., for real-time acquisition of the current offshore oil reservoir parameters, such as production pressure difference, injection pressure difference, oil reservoir exploitation ratio, and oil production per unit time.

[0080] Data analysis and processing: Analyze and process the collected data. Data processing tools and algorithms can be used to extract useful information and features to form an accurate description of the current offshore oil reservoir parameters.

[0081] Parameter monitoring and control: According to the obtained current offshore oil reservoir parameters, establish a monitoring module to monitor the production pressure difference, injection pressure difference, oil reservoir exploitation ratio, and oil production per unit time in real time.

[0082] S104. If the oil production per unit time of the offshore oil reservoir in the current offshore oil reservoir parameters is lower than the preset unit oil production.

[0083] In the embodiments of this specification, the preset unit oil production can be adjusted according to the actual situation.

[0084] S106. Input the production pressure difference, injection pressure difference, reservoir exploitation ratio of the current marine reservoir parameters, and the preset unit oil production into a pre-trained production adjustment model to obtain a pressure difference adjustment plan. The production adjustment model is a multi-layer perceptron neural network model including multiple fully connected layers. The pressure difference adjustment plan includes adjusting the production pressure difference and / or injection pressure difference, and the production pressure difference adjustment value and / or injection pressure difference adjustment value.

[0085] In the embodiments of this specification, for the above content, the following specific implementation solutions can be adopted:

[0086] Data preparation and preprocessing: Sort out and prepare the required current marine reservoir parameter data, including production pressure difference, injection pressure difference, reservoir exploitation ratio, and preset unit oil production. Perform preprocessing on the data, such as normalization, outlier removal, etc.

[0087] Construct a neural network model: Construct a neural network model for production adjustment. This may involve selecting a suitable neural network structure, determining input variables and output variables, setting a suitable loss function, etc. The input variables can be the production pressure difference, injection pressure difference, and reservoir exploitation ratio of the marine reservoir in the marine reservoir parameters, and the preset unit oil production. The output variable can be the pressure difference adjustment plan, and the loss function can be the mean absolute error.

[0088] Model training and verification: Use historical data to train and verify the constructed neural network model. This involves dividing the data set into a training set and a verification set, and iteratively training the model through the backpropagation algorithm to optimize the weights and biases of the model to minimize the loss function.

[0089] Model testing and evaluation: Use an independent test data set to test and evaluate the trained model. Calculate indicators such as the accuracy, recall rate, and root mean square error of the model to evaluate the performance and reliability of the model.

[0090] Input parameters and generate a pressure difference adjustment plan: Input the current marine reservoir parameters, including production pressure difference, injection pressure difference, reservoir exploitation ratio, and preset unit oil production, into the trained neural network model. The model can predict the required pressure difference adjustment plan according to the input parameters, including the values of adjusting the production pressure difference and / or injection pressure difference, and the production pressure difference adjustment value and / or injection pressure difference adjustment value.

[0091] It should be noted that the pressure difference adjustment plan includes adjusting the production pressure difference, adjusting the injection pressure difference, and adjusting both the production pressure difference and the injection pressure difference.

[0092] Adjust the production pressure difference:

[0093] 1. Analyze factors such as reservoir productivity, oil-water distribution, and degree of utilization to evaluate the reasonableness of the current production pressure difference.

[0094] 2. Determine the adjustment direction and amplitude of the production pressure differential according to the production adjustment model, in combination with the actual working conditions and production requirements.

[0095] 3. Gradually increase or decrease the production pressure differential according to the adjustment direction, observe the response of the production volume, and make further adjustments based on the results.

[0096] 4. During the adjustment process, pay attention to balancing the reservoir pressure and avoid reservoir damage or reserve loss caused by overexploitation.

[0097] Adjust the injection pressure differential:

[0098] 1. Analyze factors such as the geographical location, injection water quality, and seepage characteristics between the injection well and the production well, and evaluate the reasonableness of the current injection pressure differential.

[0099] 2. Determine the adjustment direction and amplitude of the injection pressure differential according to the production adjustment model, in combination with the actual working conditions and production increase requirements.

[0100] 3. Gradually increase or decrease the injection pressure differential according to the adjustment direction, observe the response of the production volume, and make further adjustments based on the results.

[0101] 4. During the adjustment process, pay attention to controlling the injection volume and adjusting the injection pressure to avoid poor oil production or unsatisfactory water flooding effect caused by over-injection.

[0102] Adjust the production pressure differential adjustment value and the injection pressure differential adjustment value:

[0103] 1. Combine the production adjustment model, production data, and injection data, and determine the optimal combination of the production pressure differential adjustment value and the injection pressure differential adjustment value through sensitivity analysis and optimization algorithms.

[0104] 2. On the premise of considering production conditions, geological characteristics, and engineering and technical limitations, determine the appropriate pressure differential adjustment value to achieve the preset unit oil production.

[0105] 3. Gradually adjust the production pressure differential adjustment value and the injection pressure differential adjustment value according to the adjustment plan, and evaluate and adjust according to the actual production volume change.

[0106] It should be noted that the multi-layer perceptron (MLP, Multilayer Perceptron) neural network model is a common feedforward neural network, which consists of multiple neurons and forms a multi-layer structure by connecting these neurons. Each neuron receives the input from the neurons in the previous layer, processes it through an activation function, and then passes the output to the neurons in the next layer. The production pressure differential, injection pressure differential, and reservoir exploitation ratio can be used as inputs, and the pressure differential adjustment plan can be obtained through the calculation of the hidden layer.

[0107] Further, the current marine reservoir parameters in the embodiments of this specification further include marine geological characteristics; inputting the production pressure difference, injection pressure difference, and reservoir exploitation ratio of the marine reservoir in the current marine reservoir parameters, as well as the preset unit oil production, into a pre-trained production adjustment model to obtain a pressure difference adjustment plan. It is possible to input the production pressure difference, injection pressure difference, reservoir exploitation ratio, and marine geological characteristics of the marine reservoir in the current marine reservoir parameters, as well as the preset unit oil production, into the production adjustment model to obtain a pressure difference adjustment plan.

[0108] It should be noted that through the above content, the embodiments of this specification have the following beneficial effects:

[0109] Optimize resource utilization: Considering the impact of marine geological characteristics on reservoir exploitation, reservoir resources can be utilized more reasonably, avoiding waste of resources.

[0110] Further, the marine geological characteristics in the embodiments of this specification include geological structure, lithological characteristics, and sedimentary characteristics.

[0111] It should be noted that collect and analyze data on marine geological structures, including geological structure characteristics such as faults, folds, and tectonic blocks. Obtain relevant data through means such as seismic exploration and geological exploration. Evaluate its impact on reservoir production according to the type and distribution of geological structures. The study of lithological characteristics can reveal the physical properties, porosity, permeability, etc. of rocks, providing a basis for reservoir production analysis. The analysis of sedimentary characteristics helps to reveal the properties, thickness, pore structure, etc. of sedimentary layers, providing a basis for reservoir production analysis.

[0112] Further, the current marine reservoir parameters in the embodiments of this specification further include marine reservoir characteristics;

[0113] Before adjusting the production pressure difference and / or injection pressure difference of the marine reservoir in the current marine reservoir parameters according to the pressure difference adjustment plan, the production pressure difference, injection pressure difference, and marine reservoir characteristics of the marine reservoir in the current marine reservoir parameters can be input into a pressure difference optimization model to obtain a pressure difference optimization plan. The pressure difference optimization model is an optimization model based on big data analysis. The pressure difference optimization plan includes optimized production pressure difference and / or injection pressure difference, as well as production pressure difference optimization value and / or injection pressure difference optimization value; compare the error between the pressure difference optimization plan and the pressure difference adjustment plan; if the error is less than a preset threshold, execute the adjustment of the production pressure difference and / or injection pressure difference of the marine reservoir in the current marine reservoir parameters according to the pressure difference adjustment plan; if the error is not less than the preset threshold, it indicates that the above pressure difference adjustment plan is not accurate and a new pressure difference adjustment plan needs to be determined.

[0114] It should be noted that regarding the above content, the following specific implementation solutions can be adopted:

[0115] Data collection and preprocessing: Collect the required marine reservoir parameter data, including production pressure differential, injection pressure differential, and marine reservoir characteristics. Preprocess the collected data, including cleaning, removing outliers, and handling missing values, etc., to ensure the accuracy and integrity of the data.

[0116] Establishment of pressure differential optimization model: Machine learning, data mining and other methods can be used to train a model to learn the relationship between pressure differential and production, and obtain an optimization model.

[0117] Input parameters and calculate: Input the production pressure differential, injection pressure differential, and marine reservoir characteristics in the current marine reservoir parameters into the pressure differential optimization model for calculation and analysis. The optimization model will obtain an optimal pressure differential optimization plan based on the combination of these parameters.

[0118] Obtain the pressure differential optimization plan: According to the calculation results of the pressure differential optimization model, obtain the pressure differential optimization plan. This plan includes the numerical values of the optimized production pressure differential and / or injection pressure differential, as well as the corresponding optimized values.

[0119] It should be noted that the embodiments of this specification have the following beneficial effects through the above content:

[0120] Reduce errors: By comparing the errors between the pressure differential optimization plan and the pressure differential adjustment plan, the accuracy and feasibility of the production adjustment model can be evaluated and verified. If the error is less than the preset threshold, it indicates that the results of the production adjustment model are relatively reliable, and the adjustment plan can be executed.

[0121] Furthermore, the marine reservoir characteristics in the embodiments of this specification include the permeability and porosity of the marine reservoir.

[0122] Permeability is an indicator of the water permeability of rocks or sediments, which determines the mobility of fluids in the reservoir. Higher permeability usually means better fluid mobility and higher production capacity. In the pressure differential optimization plan, the production pressure differential and / or injection pressure differential are adjusted to improve production efficiency. If the reservoir permeability is high and the fluid mobility in the reservoir is good, then during the pressure differential adjustment process, the production pressure differential and / or injection pressure differential can be appropriately increased to increase production. For reservoirs with low permeability, since the fluid moves slowly in the reservoir, excessive pressure differential may lead to large energy losses and reservoir damage. Therefore, in the pressure differential optimization plan, it is necessary to balance the adjustment range of the production pressure differential and / or injection pressure differential according to the specific reservoir characteristics and engineering limitations to avoid adverse effects on the reservoir.

[0123] Porosity is the ratio of the pore volume to the total volume in reservoir rocks, reflecting the ability of the reservoir to store fluids. Higher porosity means a higher fluid storage capacity. In the differential pressure optimization scheme, the production rate is optimized by adjusting the production differential pressure and / or the injection differential pressure. Reservoirs with higher porosity usually have a larger fluid storage capacity, and the oil-water flow and production efficiency can be increased by reasonably adjusting the differential pressure to increase the production rate. However, if the porosity is low, the fluid storage capacity of the reservoir is small, and it may be challenging to increase the production rate by adjusting the differential pressure. In this case, it may be necessary to comprehensively consider other production enhancement measures, such as artificially increasing permeability and increasing injection pressure, to optimize the relationship between the differential pressure and the production rate.

[0124] S108. Adjust the production differential pressure and / or the injection differential pressure of the marine reservoir in the current marine reservoir parameters according to the differential pressure adjustment scheme to increase the oil production per unit time of the current marine reservoir.

[0125] Furthermore, in the embodiments of this specification, before adjusting the production differential pressure and / or the injection differential pressure of the marine reservoir in the current marine reservoir parameters according to the differential pressure adjustment scheme, the final production differential pressure and / or the final injection differential pressure can be determined according to the production differential pressure adjustment value and / or the injection differential pressure adjustment value; determine whether the final production differential pressure and / or the final injection differential pressure exceeds the preset maximum production differential pressure and / or the maximum injection differential pressure; if not, then execute the adjustment of the production differential pressure and / or the injection differential pressure of the marine reservoir in the current marine reservoir parameters according to the differential pressure adjustment scheme; if so, then there is no need to execute the adjustment of the production differential pressure and / or the injection differential pressure of the marine reservoir in the current marine reservoir parameters according to the differential pressure adjustment scheme.

[0126] It should be noted that the embodiments of this specification have the following beneficial effects through the above content:

[0127] First of all, by determining the final production differential pressure and / or the final injection differential pressure according to the production differential pressure adjustment value and / or the injection differential pressure adjustment value, it can be ensured that the adjusted differential pressure value is reasonable, avoiding adverse effects on the reservoir caused by too large or too small differential pressure.

[0128] Secondly, by determining whether the final production differential pressure and / or the final injection differential pressure exceeds the preset maximum production differential pressure and / or the maximum injection differential pressure, it can be ensured that the adjusted differential pressure value does not exceed the range that the reservoir can withstand, thus protecting the reservoir from damage.

[0129] Finally, if the final production pressure differential and / or the final injection pressure differential do not exceed the preset maximum pressure differential value, then the production pressure differential and / or the injection pressure differential of the offshore reservoir in the current offshore reservoir parameters can be adjusted according to the pressure differential adjustment plan. This can effectively improve the development efficiency of the reservoir, increase the production of the reservoir, and thus improve the economic benefits.

[0130] Further, in the embodiments of this specification, before determining whether the final production pressure differential and / or the final injection pressure differential exceed the preset maximum production pressure differential and / or the maximum injection pressure differential, based on the permeability and porosity of the offshore reservoir in the offshore reservoir characteristics, as well as the geological structure, lithological characteristics, and sedimentary characteristics in the offshore geological characteristics, the maximum production pressure differential and the maximum injection pressure differential that the offshore reservoir can withstand are obtained.

[0131] It should be noted that regarding the above content, the following specific implementation solutions can be adopted:

[0132] Analysis of the permeability and porosity of the offshore reservoir: Collect and organize the relevant data on the permeability and porosity of the offshore reservoir. Then, conduct statistical analysis and evaluation on the data to obtain the average permeability and porosity of the offshore reservoir. Using these data, key parameters such as the permeability and porosity of the offshore reservoir can be calculated.

[0133] Analysis of offshore geological characteristics: By collecting and organizing the relevant data on the geological structure, lithological characteristics, and sedimentary characteristics of the offshore reservoir, analyze and evaluate the geological characteristics of the offshore reservoir. Based on the geological characteristics, the physical and chemical properties of the rock and the distribution and combination of the rock layers can be understood.

[0134] Calculation of the maximum production pressure differential and the maximum injection pressure differential: Combine the permeability and porosity of the offshore reservoir and the geological structure, lithological characteristics, and sedimentary characteristics of the offshore geological characteristics to calculate the maximum production pressure differential and the maximum injection pressure differential that the offshore reservoir can withstand.

[0135] It should be noted that the embodiments of this specification have the following beneficial effects through the above content:

[0136] Improved safety: By presetting the maximum production pressure differential and the maximum injection pressure differential, it is possible to effectively prevent reservoir damage or safety accidents caused by excessive pressure. Understanding and complying with the maximum bearing pressure of the reservoir helps to maintain the stability and production safety of the reservoir.

[0137] Reservoir protection: Based on factors such as the permeability, porosity, geological structure, lithological characteristics, and sedimentary characteristics of the reservoir, it is possible to more accurately judge the bearing capacity of the reservoir, thereby avoiding reservoir rupture, pollution, or other forms of damage caused by overpressure exploitation.

[0138] Enhanced Oil Recovery: Appropriate production pressure differential and injection pressure differential contribute to improving the oil recovery rate in the reservoir. By precisely controlling the pressure, the production strategy can be optimized, enabling more crude oil to be effectively extracted.

[0139] Extended Reservoir Life: Through scientific management of reservoir pressure, the decline rate of the reservoir can be slowed down, and the production cycle of the reservoir can be extended, thereby maximizing economic benefits.

[0140] Furthermore, in the embodiments of this specification, if the final production pressure differential and / or the final injection pressure differential exceed the pre-set maximum production pressure differential and / or the maximum injection pressure differential, the production pressure differential and / or the injection pressure differential can be adjusted according to the pressure differential adjustment plan; the production pressure differential and / or the injection pressure differential of the marine reservoir in the current marine reservoir parameters can be adjusted according to the maximum production pressure differential and / or the maximum injection pressure differential.

[0141] It should be noted that the embodiments of this specification have the following beneficial effects through the above content:

[0142] Protect Reservoir Stability: By determining the adjustment value of the pressure differential according to the pressure differential adjustment plan and adjusting the pressure differential of the current reservoir according to the limit of the maximum pressure differential, it is possible to avoid the adverse effects of excessive or too low pressure on the stability of the reservoir, thereby protecting the production capacity and long-term sustainable exploitation of the reservoir.

[0143] Reduce the Risk of Reservoir Damage: Timely adjustment of the production pressure differential and the injection pressure differential to keep them within an appropriate range can avoid the risk of reservoir damage caused by too high or too low pressure differentials, such as reservoir fracture, pore collapse, etc.

[0144] It should be noted that the embodiments of this specification have the following beneficial effects through the above content:

[0145] Increase Oil Production: By analyzing and adjusting the current marine reservoir parameters, this method can effectively control and adjust the production pressure differential and the injection pressure differential. Through the pressure differential adjustment plan obtained from the pre-trained neural network model, the production pressure differential and the injection pressure differential of the marine reservoir can be precisely adjusted. By reasonably adjusting the production pressure differential and the injection pressure differential, the pressure distribution in the reservoir can be improved, the fluidity of the oil in the reservoir can be enhanced, and thus the oil production per unit time can be effectively increased.

[0146] Enhanced Oil Recovery: By effectively controlling and adjusting the production pressure differential and the injection pressure differential, the oil production capacity in the reservoir can be increased, the fluidity of the oil in the reservoir can be enhanced, and the oil in the reservoir can be promoted to move towards the wellhead. This will contribute to improving the oil recovery rate, that is, the ratio between the total amount of oil obtained from the reservoir and the total amount of recoverable oil.

[0147] Improve economic efficiency: By increasing the oil production per unit time and the recovery rate, the oilfield production and production efficiency can be significantly increased, thus bringing more oil output. This will improve the economic efficiency of the oilfield and increase the income and profits of oil enterprises.

[0148] Fast response and precise adjustment: This method uses a pre-trained neural network model to calculate the differential pressure adjustment plan, which features fast response and precise adjustment. By inputting the current marine reservoir parameters, a differential pressure adjustment plan suitable for actual conditions can be quickly obtained, and the production differential pressure and injection pressure differential can be precisely adjusted. This will improve the flexibility and response ability of the reservoir exploitation process.

[0149] Figure 2 The structural schematic diagram of an oil production increase device for a marine reservoir based on a neural network provided by one or more embodiments of this specification includes:

[0150] At least one processor; and,

[0151] A memory communicatively connected to the at least one processor; wherein,

[0152] The memory stores instructions executable by the at least one processor, and when the instructions are executed by the at least one processor, the at least one processor is enabled to:

[0153] When exploiting a marine reservoir, obtain the current marine reservoir parameters, where the current marine reservoir parameters include the production differential pressure, injection pressure differential, reservoir exploitation ratio, and oil production per unit time of the marine reservoir;

[0154] If the oil production per unit time of the marine reservoir in the current marine reservoir parameters is lower than the preset unit oil production;

[0155] Input the production differential pressure, injection pressure differential, and reservoir exploitation ratio of the marine reservoir in the current marine reservoir parameters, and the preset unit oil production into a pre-trained production adjustment model to obtain a differential pressure adjustment plan. The production adjustment model is a multi-layer perceptron neural network model including multiple fully connected layers, and the differential pressure adjustment plan includes adjusting the production differential pressure and / or injection pressure differential, and the production differential pressure adjustment value and / or injection pressure differential adjustment value;

[0156] Adjust the production differential pressure and / or injection pressure differential of the marine reservoir in the current marine reservoir parameters according to the differential pressure adjustment plan to increase the oil production per unit time of the current marine reservoir.

[0157] A non-volatile computer storage medium provided by one or more embodiments of this specification stores computer-executable instructions, and when the computer-executable instructions are executed by a computer, they can implement:

[0158] When extracting from a marine reservoir, obtain the current marine reservoir parameters, where the current marine reservoir parameters include the production pressure difference, injection pressure difference, reservoir extraction ratio, and oil production per unit time of the marine reservoir;

[0159] If the oil production per unit time of the marine reservoir in the current marine reservoir parameters is lower than the preset oil production per unit;

[0160] Input the production pressure difference, injection pressure difference, and reservoir extraction ratio of the marine reservoir in the current marine reservoir parameters, as well as the preset oil production per unit, into a pre-trained production adjustment model to obtain a pressure difference adjustment plan. The production adjustment model is a multi-layer perceptron neural network model including multiple fully connected layers. The pressure difference adjustment plan includes adjusting the production pressure difference and / or injection pressure difference, and the production pressure difference adjustment value and / or injection pressure difference adjustment value;

[0161] Adjust the production pressure difference and / or injection pressure difference of the marine reservoir in the current marine reservoir parameters according to the pressure difference adjustment plan to increase the oil production per unit time of the current marine reservoir.

[0162] Each embodiment in this specification is described in a progressive manner. For the same or similar parts among the embodiments, reference can be made to each other. Each embodiment focuses on the differences from other embodiments. In particular, for the device and non-volatile computer storage medium embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can refer to the partial description of the method embodiments.

[0163] The specific embodiments of this specification are described above. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims can be performed in a different order than in the embodiments and still achieve the desired result. Additionally, the processes depicted in the figures do not necessarily require the specific order or sequential order shown to achieve the desired result. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0164] The above is only one or more embodiments of this specification and is not used to limit this specification. For those skilled in the art, one or more embodiments of this specification can have various changes and modifications. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of one or more embodiments of this specification shall be included within the scope of the claims of this specification.

Claims

1. An enhanced oil production method for offshore oil reservoirs based on neural networks, characterized in that, Including: When extracting from a marine oil reservoir, obtain the current marine oil reservoir parameters, where the current marine oil reservoir parameters include the production pressure difference, injection pressure difference, oil reservoir extraction ratio, and oil production per unit time of the marine oil reservoir; If the oil production per unit time of the marine oil reservoir in the current marine oil reservoir parameters is lower than the preset unit oil production; Input the production pressure difference, injection pressure difference, and oil reservoir extraction ratio of the marine oil reservoir in the current marine oil reservoir parameters, as well as the preset unit oil production, into a pre-trained production adjustment model to obtain a pressure difference adjustment plan. The production adjustment model is a multi-layer perceptron neural network model including multiple fully connected layers. The pressure difference adjustment plan includes adjusting the production pressure difference and / or injection pressure difference, as well as the production pressure difference adjustment value and / or injection pressure difference adjustment value; Adjust the production pressure difference and / or injection pressure difference of the marine oil reservoir in the current marine oil reservoir parameters according to the pressure difference adjustment plan to increase the oil production per unit time of the current marine oil reservoir.

2. The method according to claim 1, characterized in that The current marine oil reservoir parameters further include marine geological characteristics; The step of inputting the production pressure difference, injection pressure difference, and oil reservoir extraction ratio of the marine oil reservoir in the current marine oil reservoir parameters, as well as the preset unit oil production, into a pre-trained production adjustment model to obtain a pressure difference adjustment plan includes: Input the production pressure difference, injection pressure difference, oil reservoir extraction ratio, and marine geological characteristics of the marine oil reservoir in the current marine oil reservoir parameters, as well as the preset unit oil production, into the production adjustment model to obtain a pressure difference adjustment plan.

3. The method according to claim 2, characterized in that, The marine geological characteristics include geological structure, lithological characteristics, and sedimentary characteristics.

4. The method according to claim 2, characterized in that, The current marine oil reservoir parameters further include marine oil reservoir characteristics; Before adjusting the production pressure difference and / or injection pressure difference of the marine oil reservoir in the current marine oil reservoir parameters according to the pressure difference adjustment plan, the method further includes: Input the production pressure difference, injection pressure difference, and marine oil reservoir characteristics of the marine oil reservoir in the current marine oil reservoir parameters into a pressure difference optimization model to obtain a pressure difference optimization plan. The pressure difference optimization model is an optimization model based on big data analysis. The pressure difference optimization plan includes optimizing the production pressure difference and / or injection pressure difference, as well as the production pressure difference optimization value and / or injection pressure difference optimization value; Compare the error between the pressure difference optimization plan and the pressure difference adjustment plan; If the error is less than the preset threshold, perform the adjustment of the production pressure difference and / or injection pressure difference of the marine oil reservoir in the current marine oil reservoir parameters according to the pressure difference adjustment plan.

5. The method according to claim 4, characterized in that, The marine oil reservoir characteristics include the permeability and porosity of the marine oil reservoir reservoir.

6. The method according to claim 5, characterized in that, Before adjusting the production pressure difference and / or injection pressure difference of the marine oil reservoir in the current marine oil reservoir parameters according to the pressure difference adjustment plan, the method further includes: Determine the final production pressure difference and / or final injection pressure difference according to the production pressure difference adjustment value and / or injection pressure difference adjustment value; Judge whether the final production pressure difference and / or final injection pressure difference exceed the preset maximum production pressure difference and / or maximum injection pressure difference; If not, perform the adjustment of the production pressure difference and / or injection pressure difference of the marine oil reservoir in the current marine oil reservoir parameters according to the pressure difference adjustment plan.

7. The method according to claim 6, wherein Before determining whether the final production pressure difference and / or the final injection pressure difference exceeds the preset maximum production pressure difference and / or the maximum injection pressure difference, the method further includes: Based on the permeability and porosity of the marine reservoir in the marine reservoir characteristics, and the geological structure, lithological characteristics, and sedimentary characteristics in the marine geological characteristics, obtain the maximum production pressure difference and the maximum injection pressure difference that the marine reservoir can withstand.

8. The method according to claim 6, wherein If the final production pressure difference and / or the final injection pressure difference exceeds the preset maximum production pressure difference and / or the maximum injection pressure difference, the method further includes: Determine the adjusted production pressure difference and / or injection pressure difference according to the pressure difference adjustment plan; Adjust the production pressure difference and / or injection pressure difference of the marine reservoir in the current marine reservoir parameters according to the maximum production pressure difference and / or the maximum injection pressure difference.

9. An enhanced oil production device for offshore oil reservoirs based on a neural network, characterized in that, Including: At least one processor; And, A memory communicatively connected to the at least one processor; wherein, The memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can: During the exploitation of the marine reservoir, obtain the current marine reservoir parameters, where the current marine reservoir parameters include the production pressure difference, injection pressure difference, reservoir exploitation ratio, and oil production per unit time of the marine reservoir; If the oil production per unit time of the marine reservoir in the current marine reservoir parameters is lower than the preset oil production per unit; Input the production pressure difference, injection pressure difference, and reservoir exploitation ratio of the marine reservoir in the current marine reservoir parameters, and the preset oil production per unit into a pre-trained production adjustment model to obtain a pressure difference adjustment plan. The production adjustment model is a multi-layer perceptron neural network model including multiple fully connected layers, and the pressure difference adjustment plan includes adjusting the production pressure difference and / or injection pressure difference, and the production pressure difference adjustment value and / or injection pressure difference adjustment value; Adjust the production pressure difference and / or injection pressure difference of the marine reservoir in the current marine reservoir parameters according to the pressure difference adjustment plan to increase the oil production per unit time of the current marine reservoir.

10. A non-volatile computer storage medium, characterized in that, Stores computer-executable instructions that can be implemented when executed by a computer: During the exploitation of the marine reservoir, obtain the current marine reservoir parameters, where the current marine reservoir parameters include the production pressure difference, injection pressure difference, reservoir exploitation ratio, and oil production per unit time of the marine reservoir; If the oil production per unit time of the marine reservoir in the current marine reservoir parameters is lower than the preset oil production per unit; Input the production pressure difference, injection pressure difference, and reservoir exploitation ratio of the marine reservoir in the current marine reservoir parameters, and the preset oil production per unit into a pre-trained production adjustment model to obtain a pressure difference adjustment plan. The production adjustment model is a multi-layer perceptron neural network model including multiple fully connected layers, and the pressure difference adjustment plan includes adjusting the production pressure difference and / or injection pressure difference, and the production pressure difference adjustment value and / or injection pressure difference adjustment value; Adjust the production pressure difference and / or injection pressure difference of the marine reservoir in the current marine reservoir parameters according to the pressure difference adjustment plan to increase the oil production per unit time of the current marine reservoir.

Images