SAGD underground heater intelligent energy supply system based on multi-energy complementation

Abstract

The invention provides an SAGD underground heater intelligent energy supply system based on multi-energy complementation, and belongs to the technical field of thickened oil recovery, and the SAGD underground heater intelligent energy supply system comprises a new energy power generation module which is used for generating power by using solar energy and / or wind energy; the energy storage module is used for storing electric energy when the new energy power generation module generates excessive power and releasing the electric energy to the underground heater module when the new energy power generation module generates insufficient power; and the intelligent control module is used for regulating and controlling the new energy power generation module, the energy storage module and the underground heater module according to the power generation data of the new energy power generation module, the energy storage state data of the energy storage module and the operating parameters of the underground heater module which are acquired in real time. The system has the advantages that new energy power generation and energy storage are organically combined, and smooth output and efficient utilization of energy are achieved; system operation data are monitored and analyzed in real time, an energy distribution strategy and operation parameters of an underground electric heater are dynamically adjusted, accurate heating is achieved, the energy utilization efficiency is improved, and energy consumption and carbon emission are reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of heavy oil production, and in particular to an intelligent energy supply system for a SAGD downhole heater based on multi-energy complementarity. Background Art

[0002] Steam-assisted gravity drainage (SAGD) is a cutting-edge technology for developing ultra-heavy oil. Its core mechanism is to inject steam into a steam injection well. The steam overlies the formation to form a steam cavity. The steam cavity expands upward and laterally, exchanging heat with the crude oil in the oil layer. The heated crude oil and steam condensate are then discharged by gravity to the horizontal production well below for production.

[0003] Traditional SAGD technology suffers from high energy consumption and large carbon emissions during heavy oil extraction. To address these issues, SAGD downhole electric heating technology has been widely researched and applied in recent years.

[0004] For example, Jiusheng Electric's oil well electric heating system mainly relies on industrial frequency power for heating. Although it has certain advantages in heating performance, it lacks effective complementarity with other forms of energy. When encountering power grid failures or tight power supply, the stability and reliability of the system will be greatly reduced. In addition, due to the underutilization of renewable energy, it is impossible to achieve the diversification and sustainable use of energy, which is not conducive to reducing energy costs and carbon emissions. In terms of intelligent control, its electrical control system is only used for basic operation control and monitoring. It is difficult to dynamically adjust the heating power and energy distribution strategy according to the real-time status of the oil reservoir (such as temperature, pressure, crude oil viscosity, etc.) and the situation of new energy power generation, which leads to energy waste and the inability to achieve optimal energy utilization. The core component is the integrated mineral insulated heating cable with hot and cold sections. Although it has good high-temperature performance, it has the problem of high maintenance and replacement costs. In addition, the service life of the cable is affected by the harsh environment underground and requires regular inspection and maintenance, which increases operating costs.

[0005] The THOR downhole heater developed by Cavitas is powered by a downhole permanent magnet motor (PMM), which has a relatively single power source. Failure or performance degradation of the PMM could impact the normal operation of the entire heating system. Furthermore, PMM operation is susceptible to downhole environmental factors (such as temperature, humidity, and corrosive gases), requiring additional protective measures, increasing equipment complexity and cost. While suitable for both injection and production wells, this heater may not achieve optimal heating performance in specific geological conditions or reservoir types. For example, its heating capacity and efficiency may be limited in deep reservoirs, with extremely high crude oil viscosities, or in complex geological structures. Furthermore, the heater's speed is controlled by a variable speed drive (VSD) to achieve real-time, comprehensive control of downhole temperature, but it lacks remote monitoring and intelligent adjustment capabilities. Operators lack real-time access to the downhole heater's operating status and data, making it difficult to identify and resolve issues promptly. This is especially true when faced with complex and changing reservoir conditions, as heating parameters cannot be automatically adjusted based on actual conditions, impacting heating effectiveness and energy efficiency.

[0006] Chinese patent CN114810017B discloses a downhole composite heater for in-situ development of underground mineral resources. This system integrates both electric and combustion heating functions into a single heater. While this improves heating flexibility and reliability, it also increases the device's structural complexity, making installation, commissioning, and maintenance more difficult and requiring specialized technicians. Furthermore, in the harsh underground environment, the coordinated operation of multiple components is prone to malfunction, increasing maintenance costs and downtime. The combustion heating function requires the injection of combustion gas and combustion-supporting gas into the well, which poses certain safety risks. Gas leaks or incomplete combustion can cause explosions, fires, and other safety hazards. The high-temperature exhaust gas produced by combustion may contain harmful substances, posing a threat to the underground environment and the health of workers. The electric heating rod is a key component of the electric heating function, but its lifespan is limited to a maximum of 3,000 hours, making it impossible to guarantee long-term continuous heating. When long-term continuous heating is required, the electric heating rod must be frequently replaced, increasing operating costs and maintenance workload. Furthermore, the replacement process can affect the normal operation of the entire heating system and reduce production efficiency. Summary of the Invention

[0007] In order to solve the above technical problems, the present invention provides a SAGD downhole heater intelligent energy supply system based on multi-energy complementarity, which solves the problems of high energy consumption and large carbon emissions of traditional SAGD technology, realizes the organic integration of heavy oil extraction and new energy green electricity, and improves energy utilization efficiency and heavy oil recovery rate.

[0008] The technical problem solved by the present invention can be achieved by adopting the following technical solutions:

[0009] An intelligent energy supply system for SAGD downhole heaters based on multi-energy complementarity, comprising:

[0010] New energy power generation module, used to generate electricity using solar energy and / or wind energy;

[0011] an energy storage module, connected to the new energy power generation module and the downhole heater module, respectively, for storing electric energy when the new energy power generation module generates excess electricity, and releasing electric energy to the downhole heater module when the new energy power generation module generates insufficient electricity;

[0012] An intelligent control module is respectively connected to the new energy power generation module, the energy storage module and the downhole heater module, and is used to regulate the new energy power generation module, the energy storage module and the downhole heater module based on the real-time collected power generation data of the new energy power generation module, the energy storage status data of the energy storage module and the operating parameters of the downhole heater module.

[0013] Preferably, the new energy power generation module includes:

[0014] A photovoltaic power generation unit, comprising a plurality of photovoltaic panels, configured to adjust the photovoltaic panels according to control instructions from the intelligent control module;

[0015] A wind power generation unit, which is composed of a plurality of wind turbines and is used to adjust the blade angles of the wind turbines according to control instructions from the intelligent control module.

[0016] Preferably, the energy storage mode of the energy storage module includes one or more combinations of battery energy storage, molten salt thermal energy storage, and pumped storage.

[0017] Preferably, the downhole heater module includes electric heaters installed in the horizontal sections of the steam injection well and the production well, respectively, for adjusting the heating power and heating time of the electric heaters according to control instructions from the intelligent control module.

[0018] Preferably, the power generation data of the new energy power generation module includes one or more combinations of solar irradiance, wind speed, photovoltaic panel output voltage, current, wind turbine speed, and output power;

[0019] The energy storage status data of the energy storage module includes one or more combinations of battery state of charge, charge and discharge current, battery temperature, molten salt thermal energy storage system temperature, energy storage capacity, pumped storage water level, and flow rate;

[0020] The operating parameters of the downhole heater module include one or more combinations of heater temperature, heater power, heater current, reservoir temperature, reservoir pressure, and crude oil viscosity.

[0021] Preferably, the intelligent control module includes:

[0022] a data preprocessing unit, configured to perform data cleaning and normalization processing on the power generation data of the new energy power generation module, the energy storage status data of the energy storage module, and the operating parameters of the downhole heater module, to obtain preprocessed power generation data, preprocessed energy storage status data, and preprocessed operating parameters;

[0023] a first data analysis unit, connected to the data preprocessing unit, for analyzing the preprocessed power generation data to generate a control instruction for the new energy power generation module;

[0024] a second data analysis unit, connected to the data preprocessing unit, for performing data analysis on the preprocessed energy storage state data to generate a control instruction for the energy storage module;

[0025] The third data analysis unit is connected to the data preprocessing unit and is used to perform data analysis on the preprocessed operating parameters to generate control instructions for the downhole heater module.

[0026] Preferably, the first data analysis unit includes:

[0027] A power generation trend analysis subunit, configured to perform time series analysis on the photovoltaic power generation data and the wind power generation data in the pre-processed power generation data to determine peak power generation periods and valley power generation periods;

[0028] A power generation efficiency analysis subunit is used to analyze the pre-processed power generation data according to the weather forecast data, calculate the actual photoelectric conversion efficiency of the photovoltaic panels and the wind energy conversion efficiency of the wind turbines, and compare them with the corresponding theoretical efficiencies to determine the factors affecting the power generation efficiency;

[0029] The correlation analysis subunit is connected to the power generation efficiency analysis subunit and is used to perform correlation calculations on the power generation efficiency influencing factors to determine key influencing factors of the power generation.

[0030] Preferably, the second data analysis unit includes:

[0031] an energy storage state evaluation subunit, configured to estimate the state of charge based on the preprocessed energy storage state data;

[0032] The charge-discharge strategy optimization subunit is connected to the energy storage state evaluation subunit and is used to determine an optimized charge-discharge strategy according to the state of charge, the power generation data and the expected heating effect of the downhole heater module.

[0033] Preferably, the third data analysis unit includes:

[0034] A heating effect evaluation subunit is used to evaluate the heating effect based on the reservoir temperature, pressure, and crude oil viscosity in the pre-processed operating parameters to determine whether the expected heating effect is achieved;

[0035] The operating parameter optimization subunit is connected to the heating effect evaluation subunit and is used to determine the optimal operating parameter combination according to the real-time state of the reservoir and power generation data and a pre-established heating model when the expected heating effect is not achieved.

[0036] Preferably, the heating model is:

[0037] P total =k2(P res )×P temp (T,T trarer )+ΔP other

[0038] Among them, P temp (T,T traret ) represents the basic power calculated based on the temperature difference, T traret represents the target temperature, T represents the real-time temperature; k2(P res ) represents the pressure correction factor, P res Represents reservoir pressure; ΔP other represents the correction term; P total Indicates total power.

[0039] The advantages or beneficial effects of the technical solution of the present invention are:

[0040] The SAGD downhole heater intelligent energy supply system based on multi-energy complementarity proposed in the present invention adopts an organic combination of new energy power generation modules and energy storage modules. It stores electric energy when the new energy power generation module generates excess electricity, and releases electric energy to the downhole heater module when the new energy power generation module generates insufficient electricity, thereby achieving smooth output and efficient utilization of energy, ensuring stable power supply to the downhole heater module, reducing the impact of renewable energy on the main energy system, and improving the reliability and stability of energy supply; the intelligent control module dynamically adjusts the energy allocation strategy and the operating parameters of the downhole electric heater by real-time monitoring and analysis of the system's operating data, achieving precise heating, further improving energy utilization efficiency, and reducing energy consumption and carbon emissions. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Figure 1 This is a structural block diagram of a SAGD downhole heater intelligent energy supply system based on multi-energy complementarity in a preferred embodiment of the present invention;

[0042] Figure 2 This is a block diagram of the overall structure of a SAGD downhole heater intelligent energy supply system based on multi-energy complementarity in a preferred embodiment of the present invention;

[0043] Figure 3 This is a structural block diagram of the first data analysis in a preferred embodiment of the present invention;

[0044] Figure 4 This is a structural block diagram of the second data analysis in a preferred embodiment of the present invention;

[0045] Figure 5 This is a structural block diagram of the third data analysis in a preferred embodiment of the present invention. DETAILED DESCRIPTION

[0046] Multi-energy complementarity is an energy use approach that uses multiple energy sources to complement each other, based on different resource conditions and energy users, to alleviate energy supply and demand conflicts, rationally protect and utilize natural resources, and achieve better environmental benefits. Multi-energy complementarity energy systems have received widespread attention and research.

[0047] The utilization of renewable energy represented by solar energy and wind energy has developed rapidly. However, renewable energy is intermittent, unstable and uncontrollable. After being connected to the power grid, it has a great impact on the main energy system. Therefore, technologies such as energy storage and capacity configuration optimization methods of multi-energy complementary energy systems are needed to achieve continuous, stable and controllable energy output from renewable energy.

[0048] Currently, research on multi-energy complementary energy systems focuses primarily on capacity configuration optimization and operation scheduling strategies. Many scholars have proposed different optimization methods and models to improve the economic and environmental performance of the system. For example, Chen Haisheng et al. proposed a wind, solar, and energy storage multi-energy complementary energy system, established an energy model for the system, and solved the simulation model using an improved non-dominated genetic algorithm to obtain the optimal capacity configuration and operation plan for the system. In response to the shortcomings of mainstream battery energy storage, which are expensive and have a short operating life, Professor Guo Su's team proposed a new energy storage system based on an electric heater, molten salt heat storage, and a steam turbine unit. They also conducted research on capacity configuration optimization and technical and economic evaluation.

[0049] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making any creative efforts shall fall within the scope of protection of the present invention.

[0050] It should be noted that, in the absence of conflict, the embodiments of the present invention and the features in the embodiments may be combined with each other.

[0051] The present invention will be further described below with reference to the accompanying drawings and specific embodiments, but they are not intended to limit the present invention.

[0052] See also Figure 1 and Figure 2 In a preferred embodiment of the present invention, based on the above-mentioned problems existing in the prior art, a SAGD downhole heater intelligent energy supply system based on multi-energy complementarity is provided, which mainly includes a new energy power generation module 1, an energy storage module 2, a downhole heater module 3 and an intelligent control module 4.

[0053] New energy power generation module 1: includes a photovoltaic power generation unit 11 and a wind power generation unit 12, which are used to generate electricity using solar energy and / or wind energy. Photovoltaic power generation unit 11 is composed of multiple high-efficiency photovoltaic panels with high conversion efficiency and good stability, capable of efficiently converting solar energy into electricity under various lighting conditions. Wind power generation unit 12 is composed of multiple advanced wind turbines that can adjust blade angles according to different wind speeds and directions to achieve maximum wind energy capture efficiency. New energy power generation module 1 transmits the generated electricity to energy storage module 2 and intelligent control module 4.

[0054] The energy storage module 2 is connected to the new energy power generation module 1 and the downhole heater module 3 respectively. The energy storage module 2 adopts a variety of energy storage methods, such as battery energy storage, molten salt thermal energy storage, pumped storage, etc. The battery energy storage system has the characteristics of fast response speed and can quickly adjust the supply and demand balance of electric energy; the molten salt thermal energy storage system has the characteristics of high energy storage density and long energy storage time, and can be used to store large amounts of electric energy for a long time. The energy storage module 2 is used to store electric energy when the new energy power generation module 1 generates excess electricity, and to release electric energy to the downhole heater module 3 when the new energy power generation module 1 generates insufficient electricity, so as to ensure a stable power supply to the downhole heater module 3;

[0055] The intelligent control module 4 is respectively connected to the new energy power generation module 1, the energy storage module 2 and the downhole heater module 3, and is used to regulate the new energy power generation module 1, the energy storage module 2 and the downhole heater module 3 based on the real-time collected power generation data of the new energy power generation module 1, the energy storage status data of the energy storage module 2 and the operating parameters of the downhole heater module 3.

[0056] The working principle and process of the present invention are as follows:

[0057] During the renewable energy generation phase, when there is sufficient sunlight or strong wind, the photovoltaic power generation unit 11 and the wind power generation unit 12 convert solar and wind energy into electrical energy. Some of this electrical energy is directly fed to the downhole heater module 3, providing the energy required for heating; the rest is fed to the energy storage module 2 for storage.

[0058] Energy storage phase: When excess renewable energy generation occurs, energy storage module 2 begins storing energy. Different energy storage methods are allocated and managed based on their characteristics and advantages. For example, electrochemical energy storage is preferred when rapid adjustments to the balance of power supply and demand are required.

[0059] Intelligent Control Stage: Intelligent Control Module 4 monitors the system's operating status in real time and dynamically adjusts energy allocation strategies based on renewable energy generation, energy storage status, and downhole heater demand. For example, at night or when light or wind is insufficient, Intelligent Control Module 4 controls the energy storage module 2 to release power based on the remaining charge in the energy storage module 2 and the downhole heater's real-time demand, ensuring stable downhole heater operation. Furthermore, Intelligent Control Module 4 can adjust the downhole heater's heating power in real time based on reservoir temperature, pressure, and other parameters, achieving precise heating and improving energy efficiency.

[0060] Downhole heating stage: The downhole heater module 3 heats the oil reservoir according to the instructions of the intelligent control module 4. Through electrical heating, the viscosity of the crude oil in the reservoir is reduced, and its fluidity is enhanced, so that it flows into the production well under the action of gravity, realizing the recovery of heavy oil.

[0061] In view of the problem that renewable energy represented by solar energy and wind energy in the existing multi-energy complementary energy system has the characteristics of intermittency, instability and uncontrollability, and has a great impact on the main energy system after being connected to the power grid. The present invention solves the problem of intermittency and instability of renewable energy through the organic combination of new energy power generation module 1 (including photovoltaic power generation unit 11 and wind power generation unit 12) and energy storage module 2. The new energy power generation module 1 converts solar energy and wind energy into electrical energy, while the energy storage module 2 adopts a variety of energy storage methods, such as battery energy storage, molten salt thermal energy storage, pumped storage, etc., to store electrical energy when there is excess power generation from new energy and release electrical energy when there is insufficient power generation from new energy. In this way, smooth output and efficient utilization of energy can be achieved, stable power supply of the downhole heater module 3 is guaranteed, the impact of renewable energy on the main energy system is reduced, and the reliability and stability of energy supply are improved.

[0062] Traditional SAGD (Saturated Aggregate Degassing) (SAGD) heavy oil extraction processes, from steam production to crude oil extraction, involve significant energy losses. The extensive use of traditional fossil fuels such as natural gas and coal for steam heating generates significant carbon dioxide emissions. This present invention applies new energy to heavy oil extraction, reducing reliance on traditional fossil fuels. The electricity generated by the new energy generation module 1 is directly used by the downhole heater module 3 to heat the reservoir, avoiding the high energy consumption and carbon emissions of traditional steam heating methods. Simultaneously, the intelligent control module 4 monitors and analyzes system operating data in real time, leveraging big data and artificial intelligence algorithms to dynamically adjust energy allocation strategies and downhole heater operating parameters for precise heating. This further improves energy efficiency and reduces the energy consumption and carbon emissions of traditional SAGD technology. For example, compared to traditional SAGD technology, SAGD downhole high-power electric heating startup technology can reduce carbon emissions by 95%, saving 36,000 tons of steam and over 2.4 million cubic meters of natural gas per well group.

[0063] In view of the problems that some downhole heating devices in the prior art may have, such as incomplete functions, low heating efficiency, and poor reliability. The downhole heater module 3 of the present invention adopts a downhole high-power electric heater 31, which is installed in the horizontal section of the SAGD steam injection well and the production well. The electric heater 31 adopts advanced heating materials and a unique heating structure, which can heat the oil reservoir quickly and evenly, thereby improving the heating efficiency. At the same time, the insulation and protection measures of the electric heater are strengthened to ensure safe operation in the harsh environment underground and improve reliability. The downhole heater module 3 is connected to the intelligent control module 4, receives the control instructions of the intelligent control module 4, and adjusts the heating power and heating time of the downhole heater in real time according to the temperature, pressure and other parameters of the oil reservoir, thereby achieving precise heating and further optimizing the heating effect.

[0064] Existing multi-energy complementary energy systems may have shortcomings in terms of comprehensive energy optimization and intelligent control. The intelligent control module 4 of the present invention is the core of the entire system. Using high-precision sensors, it collects real-time power generation data from the new energy generation module 1, the energy storage status data from the energy storage module 2, and operating parameters of the downhole heater module 3, such as temperature and power. Using advanced big data and artificial intelligence algorithms, the intelligent control module 4 conducts in-depth analysis and processing of this data, enabling precise intelligent control of the new energy generation module 1, the energy storage module 2, and the downhole heater module 3. Furthermore, the intelligent control module 4 dynamically adjusts the energy allocation strategy based on the new energy generation status and the energy storage status of the energy storage module. For example, when new energy generation is sufficient, the intelligent control module 4 prioritizes new energy power to the downhole heater module 3 and uses excess power for other purposes or stores it in the energy storage module 2. When new energy generation is insufficient, the intelligent control module 4 rationally releases power from the energy storage module based on the energy storage status of the energy storage module 2 and the needs of the downhole heater module 3, ensuring stable operation of the downhole heater. At the same time, the intelligent control module 4 can also adjust the heating power of the downhole electric heater 31 in real time based on parameters such as reservoir temperature and pressure, achieving precise heating and improving energy efficiency. This intelligent control method improves the system's automation level and operational efficiency, achieving optimal energy utilization and stable system operation.

[0065] As a preferred embodiment, the new energy power generation module 1 includes:

[0066] Photovoltaic power generation unit 11, which is composed of a plurality of photovoltaic panels and is used to adjust the photovoltaic panels according to the control instructions from the intelligent control module 4;

[0067] The wind power generation unit 12 is composed of a plurality of wind turbines and is used to adjust the blade angles of the wind turbines according to control instructions from the intelligent control module 4 .

[0068] As a preferred embodiment, the energy storage mode of the energy storage module 2 includes one or more combinations of battery energy storage 21, molten salt thermal energy storage 22, and pumped storage 23.

[0069] As a preferred embodiment, the downhole heater module 3 includes electric heaters 31 installed in the horizontal sections of the steam injection well and the production well, respectively, for adjusting the heating power and heating time of the electric heater 31 according to the control instructions from the intelligent control module 4.

[0070] As a preferred embodiment, the power generation data of the new energy power generation module 1 includes one or more combinations of environmental parameters such as solar irradiance and wind speed and operating parameters such as photovoltaic panel output voltage, current, wind turbine speed, and output power;

[0071] The energy storage status data of the energy storage module 2 includes one or more combinations of battery state of charge (SOC), charge and discharge current, battery temperature, molten salt thermal energy storage system temperature, energy storage capacity, pumped storage water level, and flow rate;

[0072] The operating parameters of the downhole heater module 3 include one or more combinations of heater temperature, heater power, heater current, reservoir temperature, reservoir pressure, and crude oil viscosity.

[0073] As a preferred embodiment, the intelligent control module 4 includes:

[0074] The data preprocessing unit 41 is used to clean and normalize the power generation data of the new energy power generation module 1, the energy storage status data of the energy storage module 2, and the operating parameters of the downhole heater module 3 to obtain preprocessed power generation data, preprocessed energy storage status data, and preprocessed operating parameters.

[0075] Specifically, considering that the collected data may contain noise, missing values, or outliers, this embodiment performs data cleaning on the real-time collected data. For example, filtering algorithms such as moving average filtering and median filtering are used to process noisy data. For missing values, if the proportion is small, interpolation methods such as linear interpolation and spline interpolation can be used to fill the missing values. If the proportion of missing values ​​is large, historical data and empirical estimates can be combined. Outliers can be identified and corrected by setting thresholds or using statistical methods.

[0076] Considering that some algorithms are more sensitive to data scale, in this embodiment, the collected data also needs to be normalized. Tree models (such as random forests) are usually not affected by data scale; distance-based algorithms (such as KNN, SVM using RBF kernel) and gradient descent optimization models (such as neural networks) need normalization. Common normalization methods include minimum and maximum normalization and Z-score normalization. For time series data, a rolling window can be used for normalization.

[0077] The intelligent control module 4 can automatically adjust the system's operating parameters according to different operating conditions and needs to achieve optimal energy utilization efficiency and system performance. For example, by analyzing and learning from historical data, the intelligent control module 4 can predict the trend of renewable energy generation and changes in demand for downhole heaters, and prepare for energy allocation and adjustment in advance. When renewable energy generation is sufficient, the intelligent control module 4 can accurately calculate the amount of electricity that needs to be stored and how to store it; when renewable energy generation is insufficient, it can reasonably allocate the electricity released by the energy storage module 2 based on the energy storage status of the energy storage module 2 and the urgency of the downhole heater. This intelligent control method improves the system's automation level and operating efficiency, avoids energy waste, and reduces operating costs.

[0078] As a preferred embodiment, the intelligent control module 4 includes:

[0079] The first data analysis unit 42 is connected to the data preprocessing unit 41 and is used to analyze the preprocessed power generation data to generate a control instruction for the new energy power generation module 1;

[0080] The second data analysis unit 43 is connected to the data preprocessing unit 41 and is used to perform data analysis on the preprocessed energy storage state data to generate a control instruction for the energy storage module 2;

[0081] The third data analysis unit 44 is connected to the data preprocessing unit 41 and is used to perform data analysis on the preprocessed operating parameters to generate control instructions for the downhole heater module 3 .

[0082] As a preferred embodiment, the first data analysis unit 42 includes:

[0083] The power generation trend analysis subunit 421 is used to perform time series analysis on the photovoltaic power generation data and wind power generation data in the pre-processed power generation data to determine the peak and valley periods of power generation;

[0084] The power generation efficiency analysis subunit 422 is used to analyze the pre-processed power generation data based on the weather forecast data, calculate the actual photovoltaic conversion efficiency of the photovoltaic panels and the wind energy conversion efficiency of the wind turbines, and compare them with the corresponding theoretical efficiencies to determine the factors affecting the power generation efficiency;

[0085] The correlation analysis subunit 423 is connected to the power generation efficiency analysis subunit 422 and is used to perform correlation calculations on factors affecting power generation efficiency and determine key factors affecting power generation.

[0086] Specifically, in the data analysis of the new energy power generation module, this embodiment first performs a time series analysis on the photovoltaic power generation and wind power generation data, and determines the peak and valley periods of power generation by drawing power time curves, providing a basis for energy distribution and energy storage strategy formulation.

[0087] Next, analyze power generation efficiency by taking into account environmental factors such as solar irradiance (or light intensity) and wind speed. The actual photovoltaic conversion efficiency of a photovoltaic panel is calculated as the output power divided by (solar irradiance multiplied by the panel area). When comparing actual efficiency with theoretical or expected efficiency, the theoretical efficiency must be corrected based on the rated efficiency under standard test conditions (STC), taking into account actual solar irradiance and panel temperature. Calculate the wind turbine's wind energy conversion efficiency and compare it with the theoretical efficiency to identify factors that affect power generation efficiency.

[0088] Finally, through correlation analysis, the correlation coefficient is calculated to determine the key factors affecting power generation, such as the correlation between wind speed and wind power generation, and the correlation between solar irradiance and photovoltaic power generation.

[0089] As a preferred embodiment, the second data analysis unit 43 includes:

[0090] The energy storage state evaluation subunit 431 is used to estimate the state of charge based on the pre-processed energy storage state data;

[0091] The charge-discharge strategy optimization subunit 432 is connected to the energy storage state evaluation subunit 431 and is used to determine an optimized charge-discharge strategy according to the state of charge, power generation data and the expected heating effect of the downhole heater module 3 .

[0092] Specifically, this embodiment analyzes energy storage module data by first estimating battery SOC changes based on battery SOC and charge / discharge currents to ensure safe operation of the energy storage system. Molten salt thermal energy storage systems use "remaining available thermal energy" or "duration at the current heat output" to assess energy storage status. For pumped hydro storage, energy storage status is assessed based on water level and flow rate.

[0093] Next, the charging and discharging strategy is optimized based on renewable energy generation and downhole heater demand. When renewable energy generation is in excess, the energy storage module is charged. When it is insufficient, the discharge power is appropriately controlled to avoid excessive discharge. For pumped storage, strategy optimization must consider factors such as reservoir capacity, hydraulic efficiency, and start-up and shutdown losses to achieve peak load shifting and maximize system backup benefits.

[0094] More specifically, the second data analysis unit 43 also includes an energy storage life prediction subunit, which processes the preprocessed energy storage status data based on a pretrained life prediction model to obtain a predicted energy storage life. Energy storage system life prediction considers factors such as charge / discharge depth and temperature, and can utilize empirical, physical, or data-driven (machine learning) models. Model sample data can be supported by accelerated aging test data or a large amount of historical data.

[0095] As a preferred embodiment, the third data analysis unit 44 includes:

[0096] The heating effect evaluation subunit 441 is used to evaluate the heating effect based on the pre-processed operating parameters such as reservoir temperature, pressure, and crude oil viscosity to determine whether the expected heating effect is achieved;

[0097] The operating parameter optimization subunit 442 is connected to the heating effect evaluation subunit 441 and is used to determine the optimal operating parameter combination according to the real-time state of the reservoir and power generation data and a pre-established heating model when the expected heating effect is not achieved.

[0098] Specifically, in this embodiment, the downhole heater module data analysis first evaluates the heating effect based on parameters such as reservoir temperature, pressure, and crude oil viscosity. The rate of crude oil viscosity reduction and the magnitude of reservoir temperature increase are calculated to determine whether the desired effect has been achieved. If the effect is poor, the cause is analyzed, such as insufficient heater power or uneven heating.

[0099] Then, combining the real-time status of the reservoir and the situation of new energy power generation, a heating model was established to analyze the impact of different parameters on heating effect and energy consumption, and determine the optimal operating parameter combination.

[0100] Furthermore, to further enhance the economic efficiency and safety of system operation, this embodiment dynamically and rationally adjusts the heating power of the downhole electric heater 31 based on real-time key reservoir parameters (such as temperature and pressure) to improve oil recovery efficiency, thereby enhancing heating efficiency and energy utilization efficiency, and optimizing SAGD production results. For example, when the reservoir temperature is low, the heating power is increased to accelerate the reservoir heating rate; when the reservoir temperature approaches the target temperature, the heating power is appropriately reduced to avoid excessive heating and energy waste.

[0101] Establishing an accurate heating model with power parameter relationships is the basis for intelligent adjustment. This model comprehensively considers thermodynamic principles, reservoir properties, and equipment characteristics.

[0102] For the reservoir temperature and the heating power P of the downhole electric heater 31 temp The empirical model can be expressed as:

[0103] P temp =k1×(T trarer T) a

[0104] Among them, k1 represents the thermal properties of the reservoir (specific heat capacity C p , thermal conductivity λ), heater efficiency, wellbore configuration and other related comprehensive coefficients;

[0105] T represents the real-time temperature of the reservoir;

[0106] T traret represents the target temperature; under a specific reservoir and heater configuration, the required heating power is related to (T traret T) is positively correlated, but the relationship is usually nonlinear. In the initial low-temperature stage, heat loss is large, the heating requirement is high, and the power demand is high; as the target temperature is approached, the power demand decreases.

[0107] a represents an empirical exponent, usually a ≥ 1, reflecting a nonlinear relationship (higher power demand in the initial stage). k1 and a are calibrated using historical data, numerical simulations, or field tests.

[0108] Heating power (P) is the heat input per unit time t, Q, where P = dQ / dt. When the reservoir's real-time temperature is lower than the target temperature, heat input (Q) is required to overcome heat loss, heat the reservoir rock and fluid, and reduce the crude oil viscosity (μ). Crude oil viscosity generally decreases exponentially with increasing temperature (μ∝e -bT ), liquidity is significantly enhanced.

[0109] The above empirical model is only an example. In practical applications, a more complex function form (such as including heat capacity and thermal conductivity terms) can also be used.

[0110] For the reservoir pressure P res The relationship with heating power can be expressed as:

[0111] k2=f(P res )

[0112] Among them, P res represents the reservoir pressure, which indirectly affects the power demand by affecting the fluid phase and thermodynamic conditions;

[0113] The specific form of f can be determined based on the PVT (pressure, volume, temperature) characteristics of the reservoir.

[0114] For example: k2=c×(P res / P re f ) b Among them, P re f represents the reference pressure, c and b are coefficients. Alternatively, a piecewise linear function can be used within a specific pressure range.

[0115] k2 represents the pressure correction factor; under high pressure conditions, k2>1, at which time the power needs to be increased; under low pressure conditions, k2≤1, at which time the power can be maintained or reduced.

[0116] Under high pressure, the boiling point of fluids (especially water) increases. Maintaining a specific temperature (especially near or above the atmospheric boiling point) requires more energy. Pressure also influences the development of the steam chamber and the amount of dissolved gas in the crude oil, which in turn affects fluidity. High pressure requires higher temperatures or greater power to achieve equivalent viscosity reduction.

[0117] Based on the above relationship and considering temperature and pressure together, the final heating model is:

[0118] P total =k2(P res )×P temp (T,T traret )+ΔP other

[0119] Among them, P totalIndicates total power; P temp (T,T traret ) represents the basic power calculated based on the temperature difference (such as the nonlinear model mentioned above), T traret represents the target temperature, T represents the real-time temperature; k2(P res ) represents the pressure correction factor, P res represents reservoir pressure;

[0120] ΔP other Indicates other correction items (optional), which can introduce other potential influencing factors, such as:

[0121] Modification of steam chamber development stage: steam chamber expansion stage (more energy is needed to heat the cold zone) vs. stable oil drainage stage (maintaining the steam chamber);

[0122] Correction for changes in fluid production rate / fluid properties: changes in heat loss patterns at high water cuts and high fluid production rates;

[0123] Neighboring well interference correction: Mutual influence between multi-well SAGD well groups.

[0124] The heating model can be continuously verified, optimized and updated through numerical simulation (CMGSTARS, Eclipse Thermal, etc.), historical production data fitting, field tests, etc., and machine learning (such as data-driven models) can be used to assist in improving prediction accuracy.

[0125] More specifically, based on the SAGD life cycle and current temperature status, the adjustment phases are divided according to the set temperature thresholds T1 and T2:

[0126] Start preheating stage (T< <T traret , T <T1=0.7*T traret ): In this stage, the goal is to quickly establish inter-well thermal connectivity and form an initial steam chamber. Directly apply the maximum safe power P max Or operate close to maximum power, give priority to the heating rate, and closely monitor the pressure rise rate.

[0127] Steam chamber expansion and temperature rise stage (T1≤T <T2,T2=T traret ΔT1, ΔT1=1020℃): In this stage, the goal is to continuously expand the steam chamber volume and steadily increase the reservoir temperature to near the target value. The prediction based on the above heating model is applied according to the real-time reservoir temperature T and reservoir pressure P res , use the model to calculate the total power P total , and used as the set value. Combined with the temperature rise rate feedback, fine-tune the power. The power setting value is usually lower than the maximum safe power P max .

[0128] Stable production stage (T≥T2): In this stage, the steam chamber is kept stable and the reservoir temperature is kept within the optimal window (T optimal ±δT,T traret ±5℃) to achieve efficient gravity oil drainage. optimal is the optimal temperature, and δ represents the temperature variation coefficient. optimal Deviation (PID control or more advanced algorithm), and reservoir pressure P res , dynamically fine-tune the power to the optimal power P maintain , which is usually significantly lower than P max The goal is to minimize power fluctuations and maintain system stability. The setting of ΔT should take reservoir heterogeneity into consideration.

[0129] More specifically, the third data analysis unit 44 also includes a fault diagnosis and early warning subunit, which monitors and analyzes the preprocessed heater operating parameters in real time and uses thresholds to perform basic fault diagnosis. Fault diagnosis using machine learning algorithms relies on high-quality historical data with clear fault type labels, requiring the accumulation of fault case data for model training.

[0130] To be more specific, the intelligent control module 4 stores and manages long-term accumulated data based on the established big data analysis platform, uses data mining, machine learning and other technologies to mine the potential information and patterns of the data, and finds the relationship and optimization strategy between new energy power generation, energy storage and downhole heaters through correlation analysis.

[0131] Artificial intelligence algorithms are applied to the intelligent control module 4. Machine learning, deep learning, and reinforcement learning algorithms (such as neural networks, random forests, and LSTM) are used to establish prediction models for renewable energy generation, energy storage demand, and downhole heater load. In addition to historical power generation data, the renewable energy generation prediction model can also incorporate weather forecast data, such as solar irradiance, cloud cover, wind speed, and wind direction, to improve accuracy. Reinforcement learning is implemented by constructing an environmental simulator or carefully conducting online learning in the actual system, and introducing safety constraints and reward functions.

[0132] The intelligent control module 4 can also visualize data analysis and processing results in the form of charts, reports, and other formats. For real-time data collection systems, visualization and decision-making latency must be kept within acceptable limits. Key monitoring parameters (such as SOC limit violations and equipment tripping) require response times in seconds, while trend analysis and strategy recommendations can be relaxed to minutes. The system also features alarm and early warning capabilities, providing timely notifications of key parameter limit violations, equipment failures, and potential risks, assisting operators in decision-making.

[0133] The above are only preferred embodiments of the present invention and do not limit the implementation mode and protection scope of the present invention. For those skilled in the art, it should be aware that all solutions obtained by equivalent substitutions and obvious changes made using the contents of this specification and illustrations should be included in the protection scope of the present invention.

Claims

1. An intelligent energy supply system for SAGD downhole heaters based on multi-energy complementarity, characterized in that: include: New energy power generation module, used to generate electricity using solar energy and / or wind energy; an energy storage module, connected to the new energy power generation module and the downhole heater module, respectively, for storing electric energy when the new energy power generation module generates excess electricity, and releasing electric energy to the downhole heater module when the new energy power generation module generates insufficient electricity; An intelligent control module is respectively connected to the new energy power generation module, the energy storage module and the downhole heater module, and is used to regulate the new energy power generation module, the energy storage module and the downhole heater module based on the real-time collected power generation data of the new energy power generation module, the energy storage status data of the energy storage module and the operating parameters of the downhole heater module.

2. The SAGD downhole heater intelligent energy supply system based on multi-energy complementarity according to claim 1 is characterized in that: The new energy power generation module includes: A photovoltaic power generation unit, comprising a plurality of photovoltaic panels, configured to adjust the photovoltaic panels according to control instructions from the intelligent control module; A wind power generation unit, which is composed of a plurality of wind turbines and is used to adjust the blade angles of the wind turbines according to control instructions from the intelligent control module.

3. The SAGD downhole heater intelligent energy supply system based on multi-energy complementarity according to claim 1 is characterized in that: The energy storage mode of the energy storage module includes one or more combinations of battery energy storage, molten salt thermal energy storage, and pumped storage.

4. The SAGD downhole heater intelligent energy supply system based on multi-energy complementarity according to claim 1 is characterized in that: The downhole heater module includes electric heaters installed in the horizontal sections of the steam injection well and the production well, respectively, and is used to adjust the heating power and heating time of the electric heaters according to the control instructions from the intelligent control module.

5. The SAGD downhole heater intelligent energy supply system based on multi-energy complementarity according to claim 1 is characterized in that: The power generation data of the new energy power generation module includes one or more combinations of solar irradiance, wind speed, photovoltaic panel output voltage, current, wind turbine speed, and output power; The energy storage status data of the energy storage module includes one or more combinations of battery state of charge, charge and discharge current, battery temperature, molten salt thermal energy storage system temperature, energy storage capacity, pumped storage water level, and flow rate; The operating parameters of the downhole heater module include one or more combinations of heater temperature, heater power, heater current, reservoir temperature, reservoir pressure, and crude oil viscosity.

6. The SAGD downhole heater intelligent energy supply system based on multi-energy complementarity according to claim 1 is characterized in that: The intelligent control module includes: a data preprocessing unit, configured to perform data cleaning and normalization processing on the power generation data of the new energy power generation module, the energy storage status data of the energy storage module, and the operating parameters of the downhole heater module, to obtain preprocessed power generation data, preprocessed energy storage status data, and preprocessed operating parameters; a first data analysis unit, connected to the data preprocessing unit, for analyzing the preprocessed power generation data to generate a control instruction for the new energy power generation module; a second data analysis unit, connected to the data preprocessing unit, for performing data analysis on the preprocessed energy storage state data to generate a control instruction for the energy storage module; The third data analysis unit is connected to the data preprocessing unit and is used to perform data analysis on the preprocessed operating parameters to generate control instructions for the downhole heater module.

7. The SAGD downhole heater intelligent energy supply system based on multi-energy complementarity according to claim 6 is characterized in that: The first data analysis unit includes: A power generation trend analysis subunit, configured to perform time series analysis on the photovoltaic power generation data and the wind power generation data in the pre-processed power generation data to determine peak power generation periods and valley power generation periods; A power generation efficiency analysis subunit is used to analyze the pre-processed power generation data according to the weather forecast data, calculate the actual photoelectric conversion efficiency of the photovoltaic panels and the wind energy conversion efficiency of the wind turbines, and compare them with the corresponding theoretical efficiencies to determine the factors affecting the power generation efficiency; The correlation analysis subunit is connected to the power generation efficiency analysis subunit and is used to perform correlation calculations on the power generation efficiency influencing factors to determine key influencing factors of the power generation.

8. The SAGD downhole heater intelligent energy supply system based on multi-energy complementarity according to claim 6 is characterized in that: The second data analysis unit includes: an energy storage state evaluation subunit, configured to estimate the state of charge based on the preprocessed energy storage state data; The charge-discharge strategy optimization subunit is connected to the energy storage state evaluation subunit and is used to determine an optimized charge-discharge strategy based on the charge state, the power generation data and the expected heating effect of the downhole heater module.

9. The SAGD downhole heater intelligent energy supply system based on multi-energy complementarity according to claim 6 is characterized in that: The third data analysis unit includes: A heating effect evaluation subunit is used to evaluate the heating effect based on the reservoir temperature, pressure, and crude oil viscosity in the pre-processed operating parameters to determine whether the expected heating effect is achieved; The operating parameter optimization subunit is connected to the heating effect evaluation subunit and is used to determine the optimal operating parameter combination according to the real-time state of the reservoir and power generation data and a pre-established heating model when the expected heating effect is not achieved.

10. The SAGD downhole heater intelligent energy supply system based on multi-energy complementarity according to claim 9 is characterized in that: The heating model is: P total =k2(P res )×P temp (T,T traret )+ΔP other Among them, P temp (T,T traret ) represents the basic power calculated based on the temperature difference, T traret represents the target temperature, T represents the real-time temperature; k2(P res ) represents the pressure correction factor, P res Represents reservoir pressure; ΔP other represents the correction term; P total Indicates total power.

Images