Geothermal well productivity prediction adjustment method, device, equipment, storage medium and product
By collecting static and dynamic data from geothermal wells and using a multi-layer neural network structure for prediction, the problem of low accuracy in geothermal well production prediction has been solved, and dynamic optimization of geothermal well production and improvement of energy utilization efficiency have been achieved.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- PETROCHINA SHENZHEN NEW ENERGY RESEARCH INSTITUTE CO LTD
- Filing Date
- 2024-11-18
- Publication Date
- 2026-05-19
AI Technical Summary
The low accuracy of geothermal well production capacity prediction leads to low energy utilization efficiency, as it is difficult to fully consider the nonlinear relationships and dynamic changes of complex factors such as geological conditions, fluid properties, wellbore conditions, and demand variations.
The system collects static and dynamic data from geothermal wells, uses a multi-layer neural network structure to predict and capture the nonlinear characteristics of geothermal well productivity, and makes dynamic adjustments based on actual production needs.
It significantly improves the accuracy of geothermal well production prediction, enables dynamic optimization of geothermal well production, improves energy utilization efficiency, and reduces operating costs.
Smart Images
Figure CN122066005A_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of geothermal energy development and utilization technology, and in particular to geothermal well production capacity prediction and adjustment methods, devices, equipment, storage media and products. Background Technology
[0002] Geothermal energy, as a clean and renewable energy source, occupies an important position in the global energy structure. In the field of geothermal energy development, the prediction and adjustment of geothermal well production capacity has always been a research hotspot and a challenge. However, the production process of geothermal wells is affected by a variety of complex factors, including geological conditions, fluid properties, wellbore condition, surface pipelines, and changes in demand, resulting in large fluctuations in production capacity and making accurate prediction difficult.
[0003] Currently, traditional capacity forecasting methods are mostly based on empirical formulas or statistical models, which make it difficult to fully consider the nonlinear relationships and dynamic changes between various factors, resulting in low forecast accuracy and thus low energy utilization efficiency.
[0004] Therefore, improving prediction accuracy is a problem that urgently needs to be solved. Summary of the Invention
[0005] The main purpose of this application is to provide a method, apparatus, equipment, storage medium and product for predicting and adjusting the production capacity of geothermal wells, which aims to solve the technical problem of low energy utilization efficiency caused by low prediction accuracy of geothermal well production capacity.
[0006] To achieve the above objectives, this application proposes a method for predicting and adjusting geothermal well productivity, the method comprising:
[0007] Collect static and dynamic data from geothermal wells, which are used to represent the reservoir characteristics and real-time production parameters of the geothermal wells;
[0008] The static and dynamic data of the geothermal well are input into the target geothermal well production capacity prediction model. By introducing a multi-layer neural network structure, the static and dynamic data of the geothermal well are predicted to obtain the predicted production capacity index. The multi-layer neural network structure is used to capture the nonlinear characteristics of the geothermal well production capacity.
[0009] Based on actual production needs and the predicted production capacity indicators, the production management of geothermal wells is dynamically adjusted.
[0010] In one embodiment, the target geothermal well production capacity prediction model includes a feature extraction sub-model. The step of inputting the static and dynamic data of the geothermal well into the target geothermal well production capacity prediction model, and predicting the static and dynamic data of the geothermal well by introducing a multi-layer neural network structure to obtain the predicted production capacity index includes:
[0011] The static and dynamic data of the geothermal well are input into the feature extraction sub-model, and the nonlinear features of the geothermal well productivity are captured through a multi-layer neural network structure to generate initial nonlinear feature information.
[0012] The initial nonlinear feature information is nonlinearly mapped by an activation function to obtain the predicted production capacity index. The nonlinear mapping is used to improve the fitting accuracy of the target geothermal well production capacity prediction model to complex data patterns.
[0013] In one embodiment, the multilayer neural network includes an input layer, a hidden layer, and a prediction layer. The step of obtaining the predicted production capacity index by nonlinearly mapping the initial nonlinear feature information through an activation function includes:
[0014] The initial nonlinear feature information is transmitted to at least one hidden layer through the input layer, and the initial nonlinear feature information is nonlinearly mapped and compressed layer by layer through an activation function to obtain the target nonlinear feature information;
[0015] The target nonlinear feature information is transmitted to the prediction layer, and the predicted production capacity index is output through a linear activation function.
[0016] In one embodiment, before the step of inputting the static and dynamic data of the geothermal well into the target geothermal well productivity prediction model, the following steps are included:
[0017] The static and dynamic data of the geothermal wells are preprocessed to obtain training and validation sets;
[0018] The training set is input into the initial geothermal well productivity prediction model for model training to obtain initial prediction values;
[0019] The prediction error between the initial predicted value and the actual value is measured by the regression loss function, and the model parameters are adjusted by the optimization algorithm to obtain the target geothermal well production capacity prediction model.
[0020] In one embodiment, the step of measuring the prediction error between the initial predicted value and the actual value through a regression loss function, and adjusting the model parameters through an optimization algorithm to obtain the target geothermal well productivity prediction model includes:
[0021] Calculate the squared error between the initial predicted value and the actual value and take the average value to obtain the prediction error between the initial predicted value and the actual value;
[0022] The prediction error is fed back to the optimization algorithm to adjust the weights and bias parameters of the neural network until the regression loss function converges to the set minimum error threshold.
[0023] When the regression loss function converges to the set minimum error threshold, the current neural network parameters are used as the model parameters of the target geothermal well production capacity prediction model to obtain the target geothermal well production capacity prediction model.
[0024] In one embodiment, the steps of measuring the prediction error between the initial predicted value and the actual value using a regression loss function, and adjusting the model parameters using an optimization algorithm to obtain the target geothermal well productivity prediction model, further include:
[0025] The target geothermal well productivity prediction model is optimized by increasing or decreasing the number of hidden layers in the current neural network and adjusting the number of neurons in each hidden layer. The increase or decrease in the number of hidden layers in the current neural network is used to test the fitting effect of the target geothermal well productivity prediction model at different depths. The adjustment of the number of neurons is used to enhance the neural network's ability to express the geothermal well productivity characteristics.
[0026] Based on the optimized target geothermal well production capacity prediction model, when the regression loss function converges to the set minimum error threshold, the current neural network parameters are used as the model parameters of the target geothermal well production capacity prediction model, thus obtaining the target geothermal well production capacity prediction model.
[0027] Furthermore, to achieve the above objectives, this application also proposes a geothermal well production capacity prediction and adjustment device, which includes:
[0028] The data acquisition module is used to acquire static and dynamic data of the geothermal well, which are used to represent the reservoir characteristics and real-time production parameters of the geothermal well.
[0029] The index prediction module is used to input the static and dynamic data of the geothermal well into the target geothermal well production capacity prediction model. By introducing a multi-layer neural network structure, the static and dynamic data of the geothermal well are predicted to obtain the predicted production capacity index. The multi-layer neural network structure is used to capture the nonlinear characteristics of the geothermal well production capacity.
[0030] The dynamic adjustment module is used to dynamically adjust the production management of geothermal wells based on actual production needs and the predicted production capacity indicators.
[0031] In addition, to achieve the above objectives, this application also proposes a geothermal well production capacity prediction and adjustment device, the device comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the geothermal well production capacity prediction and adjustment method as described above.
[0032] In addition, to achieve the above objectives, this application also proposes a storage medium, which is a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, it implements the steps of the geothermal well production capacity prediction and adjustment method described above.
[0033] In addition, to achieve the above objectives, this application also provides a computer program product, which includes a computer program that, when executed by a processor, implements the steps of the geothermal well production capacity prediction and adjustment method described above.
[0034] One or more technical solutions proposed in this application have at least the following technical effects:
[0035] This process involves collecting static and dynamic data from geothermal wells. This data represents the reservoir characteristics and real-time production parameters of the wells. The static and dynamic data are then input into a target geothermal well production capacity prediction model. A multi-layer neural network structure is introduced to predict the production capacity based on this data, obtaining a predicted production capacity index. This multi-layer neural network structure captures the nonlinear characteristics of geothermal well production capacity. Based on actual production needs and the predicted production capacity index, the production management of the geothermal wells is dynamically adjusted. By collecting static and dynamic data from geothermal wells, the reservoir characteristics and real-time production parameters are obtained. The introduction of a multi-layer neural network structure allows the model to more effectively handle nonlinear characteristics, significantly improving prediction accuracy. Simultaneously, by adjusting strategies in a timely manner based on actual production needs and predicted production capacity index, the production management of geothermal wells can be dynamically adjusted, achieving dynamic optimization of geothermal well production and improving energy utilization efficiency. Furthermore, through accurate prediction and reasonable adjustment, the operating costs of geothermal wells can be reduced, promoting the intelligent and refined development of geothermal energy while contributing to a green and low-carbon energy transition. Attached Figure Description
[0036] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.
[0037] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0038] Figure 1 This is a flowchart illustrating the first embodiment of the geothermal well production capacity prediction and adjustment method of this application;
[0039] Figure 2This is a schematic diagram of the production dynamic management system according to an embodiment of this application;
[0040] Figure 3 This is a flowchart illustrating the second embodiment of the geothermal well production capacity prediction and adjustment method of this application;
[0041] Figure 4 This is a schematic diagram of a multilayer neural network structure according to an embodiment of this application;
[0042] Figure 5 This is a schematic diagram of training input data in an embodiment of this application;
[0043] Figure 6 This is a schematic diagram of the predicted input data in an embodiment of this application;
[0044] Figure 7 This is a schematic diagram showing the distribution of actual and predicted results in the training set according to an embodiment of this application;
[0045] Figure 8 This is a schematic diagram showing the distribution of actual and predicted results in the verification set of this application embodiment;
[0046] Figure 9 This is a schematic diagram of the module structure of the geothermal well production capacity prediction and adjustment device according to an embodiment of this application;
[0047] Figure 10 This is a schematic diagram of the equipment structure of the hardware operating environment involved in the geothermal well production capacity prediction and adjustment method in this application embodiment.
[0048] The purpose, features, and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation
[0049] It should be understood that the specific embodiments described herein are merely illustrative of the technical solutions of this application and are not intended to limit this application.
[0050] To better understand the technical solution of this application, a detailed description will be provided below in conjunction with the accompanying drawings and specific implementation methods.
[0051] Geothermal energy, as a clean and renewable energy source, occupies an important position in the global energy structure. In the field of geothermal energy development, the prediction and adjustment of geothermal well production capacity has always been a research hotspot and a challenge. However, the production process of geothermal wells is affected by a variety of complex factors, including geological conditions, fluid properties, wellbore condition, surface pipelines, and demand changes, resulting in large fluctuations in production capacity and making accurate prediction difficult. Traditional production capacity prediction methods are mostly based on empirical formulas or statistical models, which cannot fully consider the nonlinear relationships and dynamic changes between various factors, leading to low prediction accuracy and lagging adjustment strategies.
[0052] This application provides a solution that collects static and dynamic data from geothermal wells, which represent the reservoir characteristics and real-time production parameters of the wells. The static and dynamic data are input into a target geothermal well production capacity prediction model. A multi-layer neural network structure is introduced to predict the static and dynamic data, yielding a predicted production capacity index. This multi-layer neural network structure captures the nonlinear characteristics of geothermal well production capacity. Based on actual production needs and the predicted production capacity index, the production management of the geothermal well is dynamically adjusted. By collecting static and dynamic data from geothermal wells, the reservoir characteristics and real-time production parameters are obtained. The introduction of a multi-layer neural network structure allows the model to more effectively handle nonlinear characteristics, significantly improving prediction accuracy. Simultaneously, by adjusting strategies in a timely manner based on actual production needs and predicted production capacity index, the production management of the geothermal well can be dynamically adjusted, achieving dynamic optimization of geothermal well production and improving energy utilization efficiency.
[0053] Based on this, the embodiments of this application provide a method for predicting and adjusting the production capacity of geothermal wells, referring to... Figure 1 , Figure 1 This is a flowchart illustrating the first embodiment of the geothermal well production capacity prediction and adjustment method of this application.
[0054] In this embodiment, the geothermal well production capacity prediction and adjustment method includes steps S10 to S30:
[0055] Step S10: Collect static and dynamic data from the geothermal well.
[0056] It should be noted that static and dynamic data are used to represent the reservoir characteristics and real-time production parameters of geothermal wells. For example, static and dynamic data can be collected through a Supervisory Control and Data Acquisition (SCADA) system, such as... Figure 2 As shown, the production dynamic management system consists of geothermal reservoirs, production wells, injection wells, and related pumps and other equipment. Production wells are responsible for extracting the heat-carrying medium (mostly water) from the reservoir. Driven by bottom hole pressure, pumps, or both, the heat-carrying medium flows through pipelines in the wellbore to the wellhead equipment, and then enters a heat exchanger for heat exchange. The reinjection system is responsible for reinjecting the heat-exchanged medium back into the reservoir. It forms a closed loop with the extraction equipment (such as wellbore, pumps, heat exchangers, and some surface pipelines) to minimize chemical reactions between the extracted fluid and air, pipelines, etc., which could lead to scaling and affect normal equipment operation. Simultaneously, it minimizes the possibility of the extracted fluid polluting the environment or contaminating the underground reservoir or groundwater due to reinjection. The static data read from the reservoir includes, but is not limited to, the perforation depth of the extraction layer, reservoir thickness, and porosity. Dynamic data includes, but is not limited to, bottom hole pressure, bottom hole temperature, daily injection volume, and daily production volume.
[0057] Step S20: Input the static and dynamic data of the geothermal well into the target geothermal well production capacity prediction model. By introducing a multi-layer neural network structure, the static and dynamic data of the geothermal well are predicted to obtain the predicted production capacity index.
[0058] It should be noted that the multi-layer neural network structure is used to capture the nonlinear characteristics of geothermal well productivity. Nonlinear characteristics can be understood as complex, high-order relationships existing in the data, such as the interaction between static and dynamic data or the nonlinear change law of dynamic data over time.
[0059] Step S30: Dynamically adjust the production management of geothermal wells based on actual production needs and predicted production capacity indicators.
[0060] For example, actual production demand can be the demand for geothermal well capacity based on current production conditions and market requirements, such as heat energy demand, environmental protection requirements, or economic benefits. The production management of geothermal wells can be dynamically adjusted through a production dynamic management system. Based on capacity forecasts and changes in demand, key parameters for extraction and utilization, such as bottom hole pressure, wellhead flow rate, and flow distribution in surface transportation pipelines, can be intelligently and automatically adjusted in a timely and appropriate manner to maintain the normal operation of the geothermal energy development and utilization system.
[0061] In this embodiment, reservoir characteristics and real-time production parameters of geothermal wells are obtained by collecting static and dynamic data. By introducing a multi-layer neural network structure, the model can more effectively handle nonlinear features and significantly improve prediction accuracy. Simultaneously, based on actual production needs and predicted production capacity indicators, strategies can be adjusted in a timely manner to dynamically optimize geothermal well production management, thereby improving energy utilization efficiency.
[0062] Reference Figure 3 , Figure 3 This is a flowchart illustrating the second embodiment of the geothermal well productivity prediction and adjustment method of this application, based on the above. Figure 1 The first embodiment shown presents a second embodiment of the geothermal well production capacity prediction and adjustment method of this application.
[0063] In the second embodiment, step S20 includes:
[0064] Step S201: Input the static and dynamic data of the geothermal well into the feature extraction sub-model, and capture the nonlinear features of the geothermal well production capacity through a multi-layer neural network structure to generate initial nonlinear feature information.
[0065] It should be noted that a multi-layer neural network can include an input layer, hidden layers, and a prediction layer. The initial nonlinear feature information can be understood as a high-dimensional feature vector extracted from the static and dynamic data of the geothermal well after processing by the feature extraction sub-model. For example, the input layer can be the starting part of the neural network, receiving and transmitting the preprocessed static and dynamic data; the hidden layer can be the main part of the neural network responsible for feature extraction and nonlinear mapping; and the prediction layer can be understood as the output layer, used to generate the prediction result.
[0066] Step S202: The initial nonlinear feature information is nonlinearly mapped using an activation function to obtain the predicted production capacity index.
[0067] It should be noted that step S202 includes: transmitting initial nonlinear feature information through the input layer to at least one hidden layer; performing nonlinear mapping and layer-by-layer compression on the initial nonlinear feature information through an activation function to obtain target nonlinear feature information; transmitting the target nonlinear feature information to the prediction layer; and outputting the predicted production capacity index through a linear activation function. The nonlinear mapping is used to improve the fitting accuracy of the target geothermal well production capacity prediction model to complex data patterns.
[0068] It should be noted that activation functions can be used to introduce nonlinearity, helping neural networks capture complex input-output relationships. The ReLU (Rectified Linear Unit) activation function can be used to process hidden layer features, retaining non-negative values and suppressing negative values. Linear activation functions can be used in prediction layers to output continuous values for regression problems.
[0069] For example, such as Figure 4 As shown, a multilayer neural network can consist of 5 layers, including a data input layer, a deep learning layer 1 (composed of 128 neurons), a deep learning layer 2 (composed of 32 neurons), a deep learning layer 3 (composed of 8 neurons), and a prediction layer.
[0070] This embodiment uses a feature extraction sub-model and a multi-layer neural network structure to extract high-dimensional nonlinear features from static and dynamic data of geothermal wells. This fully captures the complex relationship between reservoir characteristics and real-time production parameters. By using a linear activation function as the output activation method of the prediction layer, the rationality of the predicted production capacity index is ensured. By extracting and transforming the complex characteristics in the input data through nonlinear mapping, the fitting error and prediction error of the model can be effectively reduced, and the prediction accuracy can be improved.
[0071] In one embodiment, before the step of inputting the static and dynamic data of the geothermal well into the target geothermal well production capacity prediction model, the method includes: preprocessing the static and dynamic data of the geothermal well to obtain a training set and a validation set; inputting the training set into the initial geothermal well production capacity prediction model for model training to obtain an initial prediction value; measuring the prediction error between the initial prediction value and the actual value through a regression loss function, and adjusting the model parameters through an optimization algorithm to obtain the target geothermal well production capacity prediction model.
[0072] It should be noted that the initial predicted value can be the production capacity prediction derived from the training set input data under the initial parameter configuration of the neural network model. The initial predicted value usually deviates significantly from the actual value and can serve as the starting point for optimizing the model. The actual value can be the real production capacity indicator derived from the actual operating data of geothermal wells, which is usually obtained through monitoring equipment.
[0073] It should be noted that the steps of measuring the prediction error between the initial predicted value and the actual value through the regression loss function and adjusting the model parameters through the optimization algorithm to obtain the target geothermal well production capacity prediction model include: calculating the squared error between the initial predicted value and the actual value and taking the average value to obtain the prediction error between the initial predicted value and the actual value; feeding the prediction error back to the optimization algorithm to adjust the weights and bias parameters of the neural network until the regression loss function converges to the set minimum error threshold; when the regression loss function converges to the set minimum error threshold, using the current neural network parameters as the model parameters of the target geothermal well production capacity prediction model to obtain the target geothermal well production capacity prediction model.
[0074] For example, Figure 5 The table shown represents the training input data. Figure 6 The table shown represents the prediction input data (taking temperature prediction as an example). Structured training and validation sets can be read into the data series. The static data can include the perforation depth (perferration_depth_m), reservoir thickness (formation_thickness_m), and porosity of the production layer; the dynamic data can include bottom hole pressure (bhp_Mpa), bottom hole temperature (temperature_degC), daily injection rate (injection_rate_m3_per_day), and daily production rate (production_rate_m3_per_day). The final comparison results are as follows... Figure 7 and Figure 8 As shown, Figure 7 To train the distribution of actual and predicted results, Figure 8 To verify the distribution of actual and predicted results in the validation set, it can be seen that the validation set is similar to the training set, and the two are relatively discrete.
[0075] In this embodiment, the prediction error is accurately quantified by calculating the squared error between the initial predicted value and the actual value and taking the average. This allows for a comprehensive evaluation of the model's fitting ability. The prediction error is passed to the optimization algorithm through a feedback mechanism, gradually adjusting the weights and bias parameters of the neural network to ensure continuous model optimization. When the regression loss function converges to a set threshold, the model has reached its optimal training state, avoiding overfitting or underfitting. Multiple iterative adjustments ensure the high accuracy and reliability of the target geothermal well productivity prediction model.
[0076] In one embodiment, based on the above embodiment, the step of measuring the prediction error between the initial predicted value and the actual value through a regression loss function and adjusting the model parameters through an optimization algorithm to obtain the target geothermal well production capacity prediction model further includes: optimizing the target geothermal well production capacity prediction model by increasing or decreasing the number of hidden layers in the current neural network and adjusting the number of neurons in each hidden layer; based on the optimized target geothermal well production capacity prediction model, determining that when the regression loss function converges to a set minimum error threshold, the current neural network parameters are used as the model parameters of the target geothermal well production capacity prediction model to obtain the target geothermal well production capacity prediction model.
[0077] It should be noted that increasing or decreasing the number of hidden layers in the current neural network is used to test the fitting effect of the target geothermal well productivity prediction model at different depths, and adjusting the number of neurons is used to enhance the neural network's ability to express the geothermal well productivity characteristics.
[0078] In this embodiment, by increasing or decreasing the number of hidden layers, the model can test network structures at different depths, thereby optimizing the model's ability to extract nonlinear features from static and dynamic geothermal well data. Dynamically adjusting the number of neurons avoids overfitting caused by an excessively large network size, while ensuring the network size is large enough to capture key features of geothermal well productivity, thus ensuring the final target geothermal well productivity prediction model has better generalization ability.
[0079] It should be noted that the above examples are only for understanding this application and do not constitute a limitation on the geothermal well production capacity prediction and adjustment method of this application. Any simple modifications based on this technical concept are within the protection scope of this application.
[0080] This application also provides a geothermal well production capacity prediction and adjustment device, please refer to... Figure 9 The geothermal well production capacity prediction and adjustment device includes:
[0081] The data acquisition module 10 is used to acquire static and dynamic data of the geothermal well, which are used to represent the reservoir characteristics and real-time production parameters of the geothermal well.
[0082] The index prediction module 20 is used to input the static and dynamic data of the geothermal well into the target geothermal well production capacity prediction model. By introducing a multi-layer neural network structure, the static and dynamic data of the geothermal well are predicted to obtain the predicted production capacity index. The multi-layer neural network structure is used to capture the nonlinear characteristics of the geothermal well production capacity.
[0083] The dynamic adjustment module 30 is used to dynamically adjust the production management of geothermal wells based on actual production needs and the predicted production capacity indicators.
[0084] The geothermal well production capacity prediction and adjustment device provided in this application, employing the geothermal well production capacity prediction and adjustment method in the above embodiments, can solve the technical problem of low energy utilization efficiency caused by low prediction accuracy of geothermal well production capacity. Compared with the prior art, the beneficial effects of the geothermal well production capacity prediction and adjustment device provided in this application are the same as those of the geothermal well production capacity prediction and adjustment method provided in the above embodiments, and other technical features in the geothermal well production capacity prediction and adjustment device are the same as those disclosed in the methods of the above embodiments, and will not be repeated here.
[0085] This application provides a geothermal well production capacity prediction and adjustment device, which includes: 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 to enable the at least one processor to perform the geothermal well production capacity prediction and adjustment method in the above embodiment 1.
[0086] The following is for reference. Figure 10 The diagram illustrates a structural schematic suitable for implementing the geothermal well production capacity prediction and adjustment device in the embodiments of this application. The geothermal well production capacity prediction and adjustment device in the embodiments of this application may include, but is not limited to, mobile terminals such as mobile phones, laptops, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Description), PMPs (Portable Media Players), vehicle terminals (e.g., vehicle navigation terminals), and fixed terminals such as digital TVs and desktop computers. Figure 10 The geothermal well production capacity prediction and adjustment device shown is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of this application.
[0087] like Figure 10As shown, the geothermal well production capacity prediction and adjustment device may include a processing unit 1001 (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 1002 or a program loaded from a storage device 1003 into a random access memory (RAM) 1004. The RAM 1004 also stores various programs and data required for the operation of the geothermal well production capacity prediction and adjustment device. The processing unit 1001, ROM 1002, and RAM 1004 are interconnected via a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems can be connected to I / O interface 1006: input devices 1007 including, for example, touchscreens, touchpads, keyboards, mice, image sensors, microphones, accelerometers, gyroscopes, etc.; output devices 1008 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; storage devices 1003 including, for example, magnetic tapes, hard disks, etc.; and communication devices 1009. Communication device 1009 allows the geothermal well production forecasting and adjustment equipment to exchange data wirelessly or via wired communication with other devices. Although Figure 10 Geothermal well productivity prediction and adjustment equipment with various systems is shown; however, it should be understood that implementation or possession of all the systems shown is not required. More or fewer systems may be implemented alternatively.
[0088] Specifically, according to the embodiments disclosed in this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments disclosed in this application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device, or installed from storage device 1003, or installed from ROM 1002. When the computer program is executed by processing device 1001, it performs the functions defined in the methods of the embodiments disclosed in this application.
[0089] The geothermal well production capacity prediction and adjustment equipment provided in this application, employing the geothermal well production capacity prediction and adjustment method described in the above embodiments, can solve the technical problem of low energy utilization efficiency caused by low prediction accuracy of geothermal well production capacity. Compared with the prior art, the beneficial effects of the geothermal well production capacity prediction and adjustment equipment provided in this application are the same as those of the geothermal well production capacity prediction and adjustment method provided in the above embodiments, and other technical features of this geothermal well production capacity prediction and adjustment equipment are the same as those disclosed in the method of the previous embodiment, and will not be repeated here.
[0090] It should be understood that the various parts disclosed in this application can be implemented using hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in any suitable manner in one or more embodiments or examples.
[0091] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.
[0092] This application provides a computer-readable storage medium having computer-readable program instructions (i.e., a computer program) stored thereon, the computer-readable program instructions being used to execute the geothermal well production capacity prediction and adjustment method in the above embodiments.
[0093] The computer-readable storage medium provided in this application may be, for example, a USB flash drive, but is not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections having one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, system, or device. The program code contained on the computer-readable storage medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination thereof.
[0094] The aforementioned computer-readable storage medium may be included in the geothermal well production capacity prediction and adjustment equipment; or it may exist independently and not be assembled into the geothermal well production capacity prediction and adjustment equipment.
[0095] The aforementioned computer-readable storage medium carries one or more programs. When these programs are executed by the geothermal well production capacity prediction and adjustment device, the geothermal well production capacity prediction and adjustment device: collects static and dynamic data of the geothermal well, wherein the static and dynamic data are used to represent the reservoir characteristics and real-time production parameters of the geothermal well; inputs the static and dynamic data of the geothermal well into the target geothermal well production capacity prediction model, and predicts the static and dynamic data of the geothermal well by introducing a multi-layer neural network structure to obtain a predicted production capacity index, wherein the multi-layer neural network structure is used to capture the nonlinear characteristics of the geothermal well production capacity; and dynamically adjusts the production management of the geothermal well based on actual production needs and the predicted production capacity index.
[0096] Computer program code for performing the operations of this application can be written in one or more programming languages or a combination thereof, including object-oriented programming languages such as Java, Smalltalk, and C++, and conventional procedural programming languages such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a Local Area Network (LAN) or a Wide Area Network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).
[0097] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.
[0098] The modules described in the embodiments of this application can be implemented in software or hardware. The names of the modules do not necessarily limit the functionality of the unit itself.
[0099] The readable storage medium provided in this application is a computer-readable storage medium that stores computer-readable program instructions (i.e., a computer program) for executing the above-described geothermal well production capacity prediction and adjustment method. This solves the technical problem of low energy utilization efficiency caused by low prediction accuracy of geothermal well production capacity. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in this application are the same as those of the geothermal well production capacity prediction and adjustment method provided in the above embodiments, and will not be repeated here.
[0100] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the geothermal well production capacity prediction and adjustment method described above.
[0101] The computer program product provided in this application can solve the technical problem of low energy utilization efficiency caused by low prediction accuracy of geothermal well production capacity. Compared with the prior art, the beneficial effects of the computer program product provided in this application are the same as those of the geothermal well production capacity prediction and adjustment method provided in the above embodiments, and will not be repeated here.
[0102] The above description is only a part of the embodiments of this application and does not limit the patent scope of this application. All equivalent structural transformations made under the technical concept of this application and using the contents of the specification and drawings of this application, or direct / indirect applications in other related technical fields, are included in the patent protection scope of this application.
Claims
1. A method for predicting and adjusting the production capacity of geothermal wells, characterized in that, The method includes: Collect static and dynamic data from geothermal wells, which are used to represent the reservoir characteristics and real-time production parameters of the geothermal wells; The static and dynamic data of the geothermal well are input into the target geothermal well production capacity prediction model. By introducing a multi-layer neural network structure, the static and dynamic data of the geothermal well are predicted to obtain the predicted production capacity index. The multi-layer neural network structure is used to capture the nonlinear characteristics of the geothermal well production capacity. Based on actual production needs and the predicted production capacity indicators, the production management of geothermal wells is dynamically adjusted.
2. The method as described in claim 1, characterized in that, The target geothermal well production capacity prediction model includes a feature extraction sub-model. The step of inputting the static and dynamic data of the geothermal well into the target geothermal well production capacity prediction model, and predicting the static and dynamic data of the geothermal well by introducing a multi-layer neural network structure to obtain the predicted production capacity index includes: The static and dynamic data of the geothermal well are input into the feature extraction sub-model, and the nonlinear features of the geothermal well productivity are captured through a multi-layer neural network structure to generate initial nonlinear feature information. The initial nonlinear feature information is nonlinearly mapped by an activation function to obtain the predicted production capacity index. The nonlinear mapping is used to improve the fitting accuracy of the target geothermal well production capacity prediction model to complex data patterns.
3. The method as described in claim 2, characterized in that, The multi-layer neural network includes an input layer, a hidden layer, and a prediction layer. The step of obtaining the predicted production capacity index by nonlinearly mapping the initial nonlinear feature information through an activation function includes: The initial nonlinear feature information is transmitted to at least one hidden layer through the input layer, and the initial nonlinear feature information is nonlinearly mapped and compressed layer by layer through an activation function to obtain the target nonlinear feature information; The target nonlinear feature information is transmitted to the prediction layer, and the predicted production capacity index is output through a linear activation function.
4. The method according to any one of claims 1 to 3, characterized in that, Before the step of inputting the static and dynamic data of the geothermal well into the target geothermal well productivity prediction model, the following steps are included: The static and dynamic data of the geothermal wells are preprocessed to obtain training and validation sets; The training set is input into the initial geothermal well productivity prediction model for model training to obtain initial prediction values; The prediction error between the initial predicted value and the actual value is measured by the regression loss function, and the model parameters are adjusted by the optimization algorithm to obtain the target geothermal well production capacity prediction model.
5. The method as described in claim 4, characterized in that, The steps of measuring the prediction error between the initial predicted value and the actual value through a regression loss function, and adjusting the model parameters through an optimization algorithm to obtain the target geothermal well productivity prediction model include: Calculate the squared error between the initial predicted value and the actual value and take the average value to obtain the prediction error between the initial predicted value and the actual value; The prediction error is fed back to the optimization algorithm to adjust the weights and bias parameters of the neural network until the regression loss function converges to the set minimum error threshold. When the regression loss function converges to the set minimum error threshold, the current neural network parameters are used as the model parameters of the target geothermal well production capacity prediction model to obtain the target geothermal well production capacity prediction model.
6. The method as described in claim 5, characterized in that, The steps of measuring the prediction error between the initial predicted value and the actual value using a regression loss function, and adjusting the model parameters through an optimization algorithm to obtain the target geothermal well productivity prediction model, also include: The target geothermal well productivity prediction model is optimized by increasing or decreasing the number of hidden layers in the current neural network and adjusting the number of neurons in each hidden layer. The increase or decrease in the number of hidden layers in the current neural network is used to test the fitting effect of the target geothermal well productivity prediction model at different depths. The adjustment of the number of neurons is used to enhance the neural network's ability to express the geothermal well productivity characteristics. Based on the optimized target geothermal well production capacity prediction model, when the regression loss function converges to the set minimum error threshold, the current neural network parameters are used as the model parameters of the target geothermal well production capacity prediction model, thus obtaining the target geothermal well production capacity prediction model.
7. A geothermal well production capacity prediction and adjustment device, characterized in that, The device includes: The data acquisition module is used to acquire static and dynamic data of the geothermal well, which are used to represent the reservoir characteristics and real-time production parameters of the geothermal well. The index prediction module is used to input the static and dynamic data of the geothermal well into the target geothermal well production capacity prediction model. By introducing a multi-layer neural network structure, the static and dynamic data of the geothermal well are predicted to obtain the predicted production capacity index. The multi-layer neural network structure is used to capture the nonlinear characteristics of the geothermal well production capacity. The dynamic adjustment module is used to dynamically adjust the production management of geothermal wells based on actual production needs and the predicted production capacity indicators.
8. A geothermal well productivity prediction and adjustment device, characterized in that, The device includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the geothermal well production capacity prediction and adjustment method as described in any one of claims 1 to 6.
9. A storage medium, characterized in that, The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, it implements the steps of the geothermal well production capacity prediction and adjustment method as described in any one of claims 1 to 6.
10. A computer program product, characterized in that, The computer program product includes a computer program that, when executed by a processor, implements the steps of the geothermal well production capacity prediction and adjustment method as described in any one of claims 1 to 6.