Seabed compressed air energy storage system and method

Abstract

The invention relates to a seabed compressed air energy storage system and method, and the system comprises an energy and power module which comprises an offshore wind generating set and / or a photovoltaic array, and the power output of the energy and power module is connected to a multi-stage intercooling compressor through a converter device; the gas storage and heat storage module comprises at least one storage tank, and a heat storage unit is fixedly arranged in the middle of the interior of the storage tank; the heat storage unit comprises a heat storage body, and a fluid channel for air circulation is formed in the heat storage body; the power generation and feedback module comprises a multi-stage rethermal expansion machine and a coaxially connected generator; and the intelligent control module comprises a central controller, a digital twinborn model and an AI optimization algorithm which are deployed in the central controller, a data collector and a data actuator. Therefore, according to the system, the heat storage unit is integrated in the storage tank, integration of gas storage and heat storage is achieved, a heat energy circulation path of in-situ storage and in-situ utilization is adopted, and the back-and-forth efficiency of the system is effectively improved under the condition that additional fuel is not needed.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of energy storage, in particular to a seabed compressed air energy storage system and method. BACKGROUND

[0002] As a large-scale and long-time physical energy storage technology, compressed air energy storage (CAES) has important strategic value in promoting efficient consumption of fluctuating renewable energy such as wind power and photovoltaic power, and supporting peak regulation and frequency regulation of new power systems.

[0003] Traditional CAES systems usually rely on natural geological structures such as underground salt caves and abandoned mines as gas storage spaces. Such solutions have significant limitations. On the one hand, geographical resources are unevenly distributed, limiting the flexibility of system site selection; on the other hand, their energy cycle efficiency is generally low, with a typical non-adiabatic system round-trip efficiency of only about 50%, the root cause being that a large amount of high-temperature compression heat generated during compression is directly discharged to the environment without being recovered, and additional fossil fuels such as natural gas are burned to reheat the air during the subsequent expansion power generation stage, not only leading to the system's dependence on fossil fuels, but also causing energy waste.

[0004] In order to break through the geographical condition restrictions, in recent years, researchers have proposed deploying CAES systems in the seabed to achieve approximately constant pressure gas storage using deep-sea hydrostatic pressure. There are two main technical routes: one is based on flexible gas storage bags, such as the deep-sea flexible gas storage device proposed by the Institute of Engineering Thermophysics of the Chinese Academy of Sciences, which balances the internal gas pressure through the external pressure of seawater, and in theory can maintain stable operating pressure; the second is the water-gas displacement scheme based on rigid water storage tanks, such as the system developed by Zhongneng Dayuan, which directly uses seawater static pressure to maintain the storage pressure by discharging seawater in the tank and injecting compressed air.

[0005] However, the above seabed CAES solutions still have obvious technical defects. Flexible gas storage bags are prone to material aging, fatigue cracking and other problems in the complex marine environment of high pressure, high salt and low temperature, and their durability and safety cannot be guaranteed; at the same time, their thermal management generally relies on external independent heat exchangers, resulting in low system integration and large heat loss. While the rigid water storage tank solution has improved structural strength, it does not have an effective compression heat recovery mechanism, and the compression heat is still wasted, making it difficult to break through the traditional bottleneck in overall system efficiency. More importantly, both solutions use "external heat exchange" or "no heat recovery" in thermal management, and fail to achieve in-situ storage and precise recycling of compression heat within the gas storage unit.

[0006] In addition, the control strategy of the existing system is generally simple, and lacks deep coordination with external signals such as wind and light power prediction, grid dispatching instructions, etc. In the face of rapid fluctuations of strong intermittent power sources such as offshore wind power, the system response is lagging, the regulation capacity is weak, and it is difficult to achieve efficient absorption of renewable energy and high-quality power support for the power grid. SUMMARY

[0007] In view of the above problems of the prior art, the present application provides a submarine compressed air energy storage system and method, which integrates a heat storage unit in the storage tank, realizes the integration of gas storage and heat storage, adopts an in-situ storage and in-situ utilization heat energy circulation path, and discards the traditional external heat exchange mode, thereby effectively improving the round-trip efficiency of the system without additional fuel.

[0008] To achieve the above purpose, the first aspect of the present application provides a submarine compressed air energy storage system, comprising:

[0009] An energy and power module comprising an offshore wind turbine generator set and / or a photovoltaic array, the power output of which is connected to a multi-stage inter-cooled compressor through a variable frequency device; the outlet of the multi-stage inter-cooled compressor is connected to the inlet of the storage tank through a pipeline;

[0010] A gas storage and heat storage module comprising at least one storage tank, a heat storage unit is fixedly arranged in the center of the storage tank, and an annular air flow space is formed between the heat storage unit and the tank wall; the heat storage unit comprises a heat storage body, and a fluid passage for air flow is arranged on the heat storage body;

[0011] A power generation and feedback module comprising a multi-stage reheating expander and a generator connected coaxially; wherein the gas inlets of the multi-stage reheating expander are respectively connected to the outlet of the storage tank through a pipeline and a main control valve, and the exhaust port of the multi-stage reheating expander directly leads to the external environment;

[0012] An intelligent control module comprising a central controller, a digital twin model and an AI optimization algorithm deployed in the central controller, a data collector, and a data executor; the central controller is in bidirectional communication connection with the data collector and the data executor through a data bus.

[0013] Therefore, the seabed compressed air energy storage system of the present application realizes efficient energy storage and release by integrating energy and power modules, gas storage and heat storage modules, power generation and feedback modules, and intelligent control modules. Specifically, by arranging a central heat storage unit inside the storage tank and making the air charging and discharging processes pass through the heat storage unit, the compressed heat is stored and utilized in situ, completely abandoning the traditional "external heat exchange" mode relying on external heat exchangers, effectively solving the problem of low heat management efficiency caused by large heat loss and lack of heat recovery in existing solutions. At the same time, this design does not need to burn fossil fuels to supplement heat, successfully overcoming the dependence of traditional non-adiabatic compressed air energy storage systems on fossil energy, significantly improving the round-trip efficiency of the system to 65%-70%. In addition, the intelligent control module uses a central controller combined with a digital twin model and an AI optimization algorithm, which can not only monitor and adjust the system operating state in real time, but also predict future energy demand, realizing forward-looking energy management.

[0014] As a possible implementation manner, the multi-stage inter-cooled compressor is driven by an electric motor, and each stage is equipped with an inter-stage cooler for cooling the high-temperature air compressed by the stage.

[0015] Therefore, by using a multi-stage inter-cooled compressor driven by an electric motor and arranging an inter-stage cooler after each stage of compression, the temperature of the air during compression is effectively reduced, significantly reducing the compression power consumption and improving the compression efficiency. At the same time, the inter-stage cooling suppresses the thermal stress damage of high temperature to the equipment materials, to some extent, prolonging the service life of the compressor.

[0016] As a possible implementation manner, the gas storage and heat storage module includes a plurality of storage tanks, each of which is connected in parallel through a pipe network to form a gas storage and heat storage cluster, and each storage tank can independently perform air charging or discharging operation.

[0017] Therefore, by connecting multiple storage tanks in parallel to form a gas storage and heat storage cluster and supporting independent air charging or discharging operation of each storage tank, the operation flexibility and scheduling capability of the system are significantly improved. On the one hand, the optimal combination of storage tanks can be dynamically selected to participate in air charging and discharging according to the output fluctuation of renewable energy, to realize smooth adjustment of power; on the other hand, by balancing the use frequency and load of each storage tank, fatigue damage caused by excessive circulation of a single tank is effectively avoided, prolonging the service life of the overall system. In addition, the modular cluster design also enhances the scalability and fault tolerance of the system, such as when a single storage tank is under maintenance or fails, the remaining storage tanks can still operate normally, ensuring continuous and stable energy supply of the system.

[0018] As a possible implementation manner, the storage tank is a cylindrical pressure vessel with a fixed volume; the upper and lower ends of the storage tank are respectively provided with an upper head and a lower head;

[0019] The storage tank is made of high-strength alloy steel resistant to seawater corrosion / concrete.

[0020] Thus, the storage tank made of steel or concrete has higher structural strength, excellent seawater corrosion resistance and longer service life compared with the existing flexible gas storage bag solution, significantly improving the structural stability and operation reliability of the storage tank in harsh environments such as deep sea high pressure, high salt and low temperature.

[0021] As a possible implementation manner, the heat storage body is in a honeycomb, porous mesh or channel structure.

[0022] Thus, the structure significantly increases the effective heat exchange area between the heat storage body and the compressed air, thereby achieving more efficient and uniform heat exchange during the charging and discharging process.

[0023] As a possible implementation manner, the heat storage body is made of cordierite-silicon carbide composite ceramic, refractory brick or encapsulated phase change material.

[0024] Thus, the above-mentioned materials have excellent high-temperature resistance, good thermal conductivity and high specific heat capacity, and can operate stably for a long time under harsh working conditions such as high pressure, high humidity and frequent thermal cycling on the seabed. Among them, cordierite-silicon carbide composite ceramic has low thermal expansion coefficient and high thermal shock resistance, effectively inhibiting thermal stress cracking; refractory brick has low cost and high structural strength, suitable for large-capacity heat storage; and encapsulated phase change material realizes near-constant temperature heat storage / heat release through phase change latent heat, significantly improving the heat energy utilization efficiency and temperature regulation accuracy. All of the above are significantly better than traditional metal or single ceramic materials, not only prolonging the service life of the heat storage unit, but also improving the overall energy density and round-trip efficiency of the system.

[0025] To achieve the above-mentioned purpose, the second aspect of the present application also provides a control method applied to the seabed compressed air energy storage system of the first aspect, comprising:

[0026] In the charging phase, the electric energy from the offshore wind turbine generator set and / or photovoltaic array drives the multi-stage intercooling compressor through the current conversion device to generate high-temperature and high-pressure compressed air; the high-temperature and high-pressure compressed air is controlled to flow through each intercooler in turn, and then passes through the fluid channel in the heat storage unit inside the storage tank, so that the compression heat is absorbed by the heat storage body, thereby cooling the air to a normal temperature and high pressure state and storing it in the storage tank;

[0027] In the discharging phase, the main control valve is opened, the normal temperature and high pressure air flows out of the storage tank, and again flows through the fluid channel of the heat storage unit to absorb the stored heat and be heated to high-temperature and high-pressure air; the high-temperature and high-pressure air is introduced into the multi-stage reheating expander to expand and do work, driving the coaxial generator to feedback electric energy to the power grid.

[0028] Thus, by efficiently recovering and storing the compression heat in the heat storage unit integrated in the tank during the charging phase, the compressed air is stored in a normal temperature and high pressure state, significantly reducing the thermal stress and material requirements of the tank; during the discharging phase, the stored heat is released back to the air in situ using the heat storage unit again, so that the air is heated to a high temperature and high pressure working medium to re-enter the expander to do work, thereby avoiding the dependence of the traditional non-adiabatic compressed air energy storage system on fossil fuel combustion. The entire charging and discharging process realizes in-situ storage and in-situ utilization of compression heat, greatly reduces the heat loss of external heat exchange links, and improves the energy cycle efficiency of the system, which can reach 65%-70%.

[0029] To achieve the above purpose, the third aspect of the present application further provides a multi-tank cluster cooperative control method applied to the seabed compressed air energy storage system of the first aspect, comprising:

[0030] When the seabed compressed air energy storage system contains multiple parallel tanks, the state parameters of each tank are obtained, including real-time pressure, average temperature of the heat storage body, and remaining available capacity;

[0031] A multi-objective reward function R = w1*power tracking accuracy-w2*total pipeline pressure fluctuation-w3*system comprehensive thermal stress is constructed; wherein w1 is the power tracking accuracy weight, w2 is the pressure fluctuation penalty weight, and w3 is the thermal stress penalty weight;

[0032] The AI optimization algorithm is used to determine the weight coefficients w1, w2 and w3, and to generate a charging and discharging decision strategy; wherein the charging and discharging decision strategy includes dynamically deciding to perform air charging or air discharging operation on one or more tanks, and the corresponding gas flow rate.

[0033] Thus, the multi-tank cluster cooperative control method can dynamically combine multiple tanks to participate in air charging or discharging operation, realize flexible deployment of high-pressure and high-temperature state tanks, and maximize the single energy conversion efficiency; when part of the tanks are in maintenance or low efficiency state, the system can automatically exclude them from the scheduling sequence to ensure that the overall performance is not affected by local faults.

[0034] To achieve the above purpose, the fourth aspect of the present application further provides a predictive control method applied to the seabed compressed air energy storage system of the first aspect, comprising:

[0035] acquire system current state data, including real-time pressure of each tank, temperature of the heat storage unit, and use the three-dimensional non-steady heat transfer model of the heat storage unit in the digital twin model to deduce the temperature field distribution inside the heat storage unit in real time to represent the current thermodynamic state of the system; acquire wind and light power prediction data of the offshore wind turbine generator set and / or photovoltaic array and input the same as a feedforward signal to the digital twin model; based on the current thermodynamic state and the wind and light power prediction data, predict the thermodynamic state of the system in a future preset period of time through the digital twin model; maximize the system round-trip efficiency as the target, adopt a rolling time domain optimization method to determine a control sequence; output a control instruction according to the control sequence, the control instruction including: a speed setting value of the multi-stage intercooling compressor, an opening degree instruction of the main control valve, and a guide vane angle adjustment instruction of the multi-stage reheat expander.

[0036] In this way, by fusing real-time sensing data and wind and light power prediction data, the digital twin model performs rolling time domain simulation, deduces the temperature field inside the heat storage unit and predicts the future thermodynamic state of the system, based on the prediction capability, the central controller can generate a control strategy in advance before the renewable energy output or load demand changes, which has foresight, therefore, promotes the system to transition from the traditional “passive response” operation mode to the “active prediction” intelligent paradigm. BRIEF DESCRIPTION OF DRAWINGS

[0037] Figure 1 is an architectural diagram of a submarine compressed air energy storage system provided by the present application;

[0038] Figure 2 is a structural composition schematic diagram of a gas storage and heat storage module provided by the present application;

[0039] Figure 3 is a partial sectional view of a tank provided by the present application;

[0040] Figure 4 is a workflow diagram of embodiment one provided by the present application;

[0041] Figure 5 is a structural schematic diagram of a computing device provided by the present application.

[0042] It should be understood that in the above structural schematic diagram, the size and shape of each block diagram are only for reference and should not constitute exclusive interpretation of the embodiments of the present application. The relative position and inclusion relationship between each block diagram presented by the structural schematic diagram only schematically represent the structural association between each block diagram, and is not limited to the physical connection mode of the embodiments of the present application. DETAILED DESCRIPTION

[0043] The technical solutions provided by the present application are further described below in combination with the drawings and examples. It should be understood that the system structure and service scenarios provided in the examples of the present application are mainly to illustrate possible implementation manners of the technical solutions of the present application, and should not be interpreted as the only limitation of the technical solutions of the present application. Those skilled in the art can know that with the evolution of system structure and the appearance of new service scenarios, the technical solutions provided by the present application are also applicable to similar technical problems.

[0044] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which the present application belongs. If there is an inconsistency, the meaning indicated in the present specification or derived from the content described in the present specification shall prevail. In addition, the terms used herein are only for the purpose of describing the embodiments of the present application and are not intended to limit the present application.

[0045] The embodiments of the present application provide a seabed compressed air energy storage system, as shown in Figure 1 , comprising:

[0046] The energy and power module 100 comprises an offshore wind turbine generator set 101 and / or a photovoltaic array 102, and the power output thereof is connected to a multi-stage inter-cooled compressor 103 through a variable flow device; the outlet of the multi-stage inter-cooled compressor 103 is connected to the inlet of a storage tank 201 through a pipeline;

[0047] The gas and heat storage module 200, as shown in Figure 2 and Figure 3 , comprises at least one storage tank 201, and a heat storage unit 202 is centrally fixed inside the storage tank 201 through an internal support structure 205, and an annular air flow space is formed between the heat storage unit 202 and the tank wall; the heat storage unit 202 comprises a heat storage body 203, and a fluid passage 204 for air flow is provided on the heat storage body 203;

[0048] The power generation and feedback module 300 comprises a multi-stage reheat expander 301 and a generator 302 coaxially connected; the gas inlet of the multi-stage reheat expander 301 is connected to the outlet of the storage tank 201 through a pipeline and a main control valve 303, and the gas outlet of the multi-stage reheat expander 301 directly leads to the external environment;

[0049] The intelligent control module 400 includes a central controller 401, a digital twin model 402 and an AI optimization algorithm 403 deployed in the central controller 401, a data collector 404, and a data executor 405; the central controller 401 is in bidirectional communication connection with the data collector 404 and the data executor 405 through a data bus. The data collector 404 includes a pressure sensor, a temperature sensor, and a flow sensor; and the data executor 405 includes a compressor speed controller, a valve opening controller, and an expander guide vane controller.

[0050] Thus, the seabed compressed air energy storage system of the present application realizes efficient energy storage and release by integrating the energy and power module 100, the gas storage and heat storage module 200, the power generation and feedback module 300, and the intelligent control module 400. Specifically, by arranging the centrally located heat storage unit 202 inside the storage tank 201 and making the charging and discharging processes both pass through the heat storage unit 202, the in-situ storage and utilization of compression heat is realized, and the traditional “external heat exchange” mode relying on external heat exchangers is completely abandoned, effectively solving the problem of low heat management efficiency caused by large heat loss and lack of heat recovery in existing solutions. At the same time, this design does not need to burn fossil fuels for heating, successfully overcoming the dependence of traditional non-adiabatic compressed air energy storage systems on fossil fuels, significantly improving the round-trip efficiency of the system to 65%-70%. In addition, the intelligent control module 400 uses a central controller 401 combined with a digital twin model 402 and an AI optimization algorithm 403, which not only can monitor and adjust the system operating state in real time, but also can predict future energy demand, realizing forward-looking energy management.

[0051] In some embodiments, the multi-stage inter-cooled compressor 103 is driven by an electric motor, and each stage is equipped with an inter-stage cooler 104 for cooling the high-temperature air after compression.

[0052] The energy and power module 100 can include one or more multi-stage inter-cooled compressors 103, and each stage is equipped with an inter-stage cooler 104, that is, the number of compressors and coolers is the same.

[0053] Thus, by using a multi-stage inter-cooled compressor 103 driven by an electric motor and setting an inter-stage cooler 104 after each stage of compression, the temperature of the air during compression is effectively reduced, thereby significantly reducing compression power consumption and improving compression efficiency. At the same time, inter-stage cooling suppresses the thermal stress damage of high temperature to equipment materials, to some extent, prolonging the service life of the compressor.

[0054] In some embodiments, the gas and heat storage module 200 includes a plurality of the storage tanks 201, each of which is connected in parallel through a pipe network to form a gas and heat storage cluster, and each of the storage tanks 201 can be independently charged or discharged.

[0055] In this way, by connecting a plurality of storage tanks 201 in parallel to form a gas and heat storage cluster and supporting independent charging or discharging of each storage tank 201, the flexibility and scheduling capability of the system are significantly improved. On the one hand, the optimal combination of storage tanks 201 can be dynamically selected to participate in charging and discharging according to the output fluctuation of renewable energy, so as to realize smooth adjustment of power; on the other hand, by balancing the use frequency and load of each storage tank 201, fatigue damage caused by excessive cycling of a single tank can be effectively avoided, and the overall system life can be prolonged. In addition, the modular cluster design also enhances the scalability and fault tolerance of the system, such as when a single storage tank 201 is under maintenance or fails, the remaining storage tanks 201 can still operate normally, ensuring continuous and stable power supply of the system.

[0056] In some embodiments, as shown in Figure 3 The upper and lower ends of the storage tank 201 are respectively provided with an upper head 209 and a lower head 210.

[0057] The storage tank 201 is made of high-strength alloy steel resistant to seawater corrosion or concrete.

[0058] In some embodiments, the upper head 209 and the lower head 210 can be hemispherical. In this way, the cylindrical barrel combined with the hemispherical head design can effectively reduce stress concentration and enhance fatigue resistance, and is particularly suitable for long-term safe operation in deep-sea high-pressure environments.

[0059] In addition to high-strength alloy steel or ordinary concrete structure, the storage tank 201 can also be made of prestressed concrete or lined with a steel membrane in the concrete to balance pressure and corrosion resistance.

[0060] In this way, the storage tank 201 made of steel or concrete has higher structural strength, excellent seawater corrosion resistance, and longer service life compared to existing flexible gas storage bag solutions, significantly improving the structural stability and operational reliability of the storage tank 201 in harsh environments such as deep-sea high pressure, high salt, and low temperature.

[0061] It is worth mentioning that, Figure 3 In the figure, reference number 206-1 indicates the inlet of the storage tank 201, reference number 206-2 indicates the gas outlet of the storage tank 201, and reference number 208 indicates the tank body of the storage tank 201.

[0062] In some embodiments, the heat storage body 203 is a honeycomb, porous mesh, or channel structure.

[0063] Exemplarily, the hole density of the heat storage body 203 can be 200-400 CPSI (holes / square inch), and the heat capacity is not less than 850 J / (kg·K).

[0064] It should be understood that the above parameters are only exemplary, and in actual application, the user can flexibly set the hole density and heat capacity of the heat storage unit 202 according to specific working conditions and use requirements, which are not specifically limited here, so as to improve the adaptability and design flexibility of the system in different application scenarios.

[0065] In this way, the structure significantly increases the effective heat exchange area between the heat storage body 203 and the compressed air, thereby realizing more efficient and more uniform heat exchange during the charging and discharging process.

[0066] In some embodiments, the heat storage body 203 is made of cordierite-silicon carbide composite ceramic, refractory brick or encapsulated phase change material.

[0067] In this way, the above-mentioned materials have excellent high-temperature resistance, good thermal conductivity and high specific heat capacity, and can be stably operated for a long time under the harsh working conditions of high pressure, high humidity and frequent thermal cycles on the seabed. Among them, the cordierite-silicon carbide composite ceramic has a low thermal expansion coefficient and high thermal shock resistance, effectively inhibiting thermal stress cracking; the refractory brick has low cost and high structural strength, and is suitable for large-capacity heat storage; and the encapsulated phase change material realizes near-constant temperature heat storage / heat release through phase change latent heat, significantly improving the heat energy utilization efficiency and temperature regulation accuracy. All of the above are significantly better than traditional metal or single ceramic materials, not only prolonging the service life of the heat storage unit 202, but also improving the overall energy density and round-trip efficiency of the system.

[0068] The embodiment of the present application also provides a control method applied to a seabed compressed air energy storage system, comprising:

[0069] In the charging phase, the electric energy from the offshore wind turbine generator set and / or photovoltaic array is driven by a current conversion device to generate high-temperature and high-pressure compressed air; the high-temperature and high-pressure compressed air is controlled to flow through each inter-stage cooler in turn, and then passes through the fluid channel in the heat storage unit inside the storage tank, so that the compression heat is absorbed by the heat storage body, thereby cooling the air to a normal temperature and high pressure state and storing it in the storage tank.

[0070] In the discharging phase, the main control valve is opened, so that the normal temperature and high pressure air flows out of the storage tank and again flows through the fluid channel of the heat storage unit to absorb the stored heat and be heated to high-temperature and high-pressure air; the high-temperature and high-pressure air is introduced into the multi-stage reheating expander to expand and do work, driving the coaxial generator to feedback electric energy to the power grid.

[0071] Thus, by efficiently recovering and storing the compression heat in the heat storage unit integrated in the tank during the charging phase, the compressed air is stored in a normal temperature and high pressure state, significantly reducing the thermal stress and material requirements of the tank; during the discharging phase, the stored heat is released back to the air in situ using the heat storage unit, causing the air to warm up to a high temperature and high pressure working medium to re-enter the expander to do work, thereby avoiding the dependence on fossil fuel re-combustion of traditional non-adiabatic compressed air energy storage systems. The entire charging and discharging process realizes the "in-situ storage and in-situ utilization" of the compression heat, greatly reducing the heat loss of the external heat exchange link and improving the energy cycle efficiency of the system, which can reach 65%-70%.

[0072] The embodiments of the present application also provide a multi-tank cluster cooperative control method applied to a seabed compressed air energy storage system, comprising:

[0073] When the seabed compressed air energy storage system contains multiple parallel tanks, the state parameters of each tank are obtained, including real-time pressure, average temperature of the heat storage body, and remaining available capacity; wherein the real-time pressure and the average temperature of the heat storage body can be obtained based on a data collector; the remaining available capacity can be calculated according to the pressure, temperature and fixed volume of the tank;

[0074] A multi-objective reward function R = w1*power tracking accuracy-w2*total pipeline pressure fluctuation-w3*system comprehensive thermal stress is constructed; wherein w1 is the power tracking accuracy weight, w2 is the pressure fluctuation penalty weight, and w3 is the thermal stress penalty weight;

[0075] The AI optimization algorithm is used to determine the weight coefficients w1, w2 and w3, and to generate a charging and discharging decision strategy; wherein the charging and discharging decision strategy includes dynamically deciding to perform air charging or air discharging operation on one or more tanks, and the corresponding gas flow rate.

[0076] The weight coefficient w1 is used to prioritize the fast and accurate response to the grid dispatching instruction;

[0077] The weight coefficient w2 is used to prioritize the maintenance of the stability of the output main pipeline pressure, and to protect the core equipment such as the compressor and the expander;

[0078] The weight coefficient w3 is used to prioritize the thermal safety of the built-in heat storage unit and the tank body, and to prolong the service life.

[0079] The above scheme will be specifically described by an example as follows.

[0080] When the seabed compressed air energy storage system contains multiple parallel tanks, the intelligent control module performs the following cooperative control process to realize the optimized scheduling of the air and heat storage cluster:

[0081] Step S1: system initialization and parameter setting

[0082] The central controller initiates the multi-tank cluster collaborative control mode, initializes system parameters, including the rated volume, design pressure, and design temperature of each tank; the thermal physical property parameters of the heat storage body (such as specific heat capacity and thermal conductivity); the combined working characteristic curve of the compressor set and the expander set; etc.

[0083] Step S2: Real-time data acquisition and state evaluation

[0084] The data acquisition device continuously acquires real-time state data at a preset sampling period (such as 1 second), and then the central controller calculates and updates the system state vector S = [P_i, T_i, V_remaining_i, P_header, P_demand,...] in real time based on the acquired data. The data to be acquired includes:

[0085] Tank state parameters: the real-time gas pressure P_i inside each tank, the average temperature T_i of the heat storage body, and the remaining available capacity V_remaining_i calculated based on the pressure and volume.

[0086] System operating parameters: the outlet header pressure P_header of the multi-stage intercooling compressor, the total opening of the main control valve, and the current speed / power of the compressor and expander.

[0087] External instructions and prediction data: real-time dispatch power instructions P_demand from the power grid, and ultra-short-term wind and solar power prediction data of offshore wind turbine generators and / or photovoltaic arrays obtained from the energy management system.

[0088] Step S3: Multi-objective reward function construction and optimization solution

[0089] The AI optimization algorithm in the central controller constructs a multi-objective reward function R for decision evaluation based on the current system state vector S: a multi-objective reward function is constructed, R = w1*power tracking accuracy - w2*total line pressure fluctuation - w3*system comprehensive thermal stress; where w1 is the power tracking accuracy weight, w2 is the pressure fluctuation penalty weight, and w3 is the thermal stress penalty weight.

[0090] The AI optimization algorithm (such as an Actor-Critic framework based on deep reinforcement learning (DRL) or a heuristic optimization algorithm) aims to maximize the cumulative reward R, and solves the optimal charging and discharging decision strategy, mainly the tank selection decision and flow decision, under the consideration of device physical constraints (such as pressure limits, valve opening limits, and flow rate limits).

[0091] Step S4: Strategy decomposition and instruction issuance

[0092] The central controller decomposes the decision strategy into specific and executable control instructions:

[0093] For the selected tank to be charged: generate instructions to open its intake branch valve and adjust the speed or inter-stage distribution of the multi-stage inter-cooled compressor to match the target output flow rate.

[0094] For the selected tank to be discharged: generate instructions to open its discharge branch valve and main control valve and adjust the guide vane angle of the multi-stage reheat expander to match the target power generation and gas flow rate.

[0095] For the idle tank: keep its intake and discharge valves closed in the pressure-maintaining and heat-storing state. Control instructions are issued through the data bus to the corresponding data actuators, including the compressor speed controller, each tank branch valve opening controller, main control valve opening controller, and expander guide vane controller.

[0096] Step S5: Closed-loop feedback and adaptive learning

[0097] After the system executes the control instructions, the data collector collects the new round of system state data.

[0098] The central controller calculates the actual reward R_actual and compares it with the predicted value of the AI optimization algorithm.

[0099] The AI optimization algorithm uses this feedback information (state, action, reward, new state) to update and train its decision-making model (such as neural network weights) online or periodically, achieving continuous optimization and adaptation of the strategy. For example, by learning the optimal tank group scheduling rules under different wind and light fluctuation patterns, the system's adaptability to renewable energy intermittency is improved.

[0100] Step S6: Abnormal handling and fault-tolerant scheduling

[0101] The collaborative control process has an embedded abnormality monitoring mechanism. If the data collector detects that the pressure of a certain tank abnormally rises, the temperature sensor fails, or the valve fails, the central controller immediately marks the tank as "unavailable state".

[0102] In subsequent decision-making, the AI optimization algorithm excludes the "unavailable state" tank from the selection set and automatically recalculates the optimal strategy based only on healthy tanks, achieving fault-tolerant operation of the system and ensuring that the overall function is not interrupted by a single point failure.

[0103] In this way, the multi-tank cluster collaborative control method can dynamically combine multiple tanks to participate in charging and discharging operations, realize flexible deployment of high-pressure and high-temperature state tanks, and maximize the single energy conversion efficiency; when some tanks are in maintenance or low-efficiency state, the system can automatically exclude them from the scheduling sequence to ensure that the overall performance is not affected by local faults.

[0104] The embodiment of the application also provides a prediction control method applied to the seabed compressed air energy storage system, comprising the following steps:

[0105] obtaining current state data of the system, including real-time pressures of the storage tanks, temperatures of the heat storage units, and using a three-dimensional non-steady heat transfer model of the heat storage units in the digital twin model to deduce a temperature field distribution inside the heat storage units in real time to represent a current thermodynamic state of the system; obtaining wind and light power prediction data of the offshore wind turbine generator set and / or the photovoltaic array and inputting the wind and light power prediction data as a feedforward signal to the digital twin model; predicting, based on the current thermodynamic state and the wind and light power prediction data, a thermodynamic state of the system in a future preset time period through the digital twin model; taking maximum system round-trip efficiency as an objective, determining a control sequence by using a rolling horizon optimization method; and outputting a control instruction according to the control sequence, wherein the control instruction comprises a speed setting value of the multistage intercooling compressor, an opening degree instruction of the main control valve and a guide vane angle adjustment instruction of the multistage reheating expander.

[0106] The above scheme will be specifically described by an example as follows.

[0107] When the seabed compressed air energy storage system is running, the central controller in the intelligent control module performs the following prediction control process to realize forward-looking optimization control of the system.

[0108] Step F1: Digital twin model initialization and real-time synchronization

[0109] The central controller starts the prediction control mode, loads and initializes the pre-generated digital twin model, mainly including a three-dimensional non-steady heat transfer model of the heat storage units, an aerodynamic thermodynamic network model and a device performance and constraint model.

[0110] The system real-time state data collected by the data collector (step F2) is input into the digital twin model, and the model state is corrected in real time through data assimilation technology (such as Kalman filtering and state observer) to ensure that the digital twin model (402) is highly consistent with the physical system in the thermodynamic state.

[0111] Step F2: Obtain current state data and wind and light power prediction data

[0112] Real-time data collection: The data collector collects and uploads the following system current state data at a preset frequency (such as once per second): real-time gas pressures (P_i) of the storage tanks, temperature data of the heat storage units, including temperatures (T_ij) of key positions (such as the inlet, the outlet and the center) for calculating the average temperature and verifying the model, current speeds of the multistage intercooling compressors, outlet pressures and temperatures of the multistage intercooling compressors, current openings of the main control valves, inlet pressures and temperatures of the multistage reheating expanders, current power generation powers of the multistage reheating expanders and wind and light power prediction data.

[0113] Step F3: State inference and ahead prediction based on digital twin model

[0114] (1) Solve the current thermodynamic state. The central controller uses the three-dimensional transient heat transfer model of the thermal storage unit in the digital twin model, taking the real-time pressure and temperature data obtained in step F2 as boundary conditions and initial conditions, to perform real-time three-dimensional temperature field solving, and output the detailed three-dimensional temperature distribution cloud of the thermal storage body at the current time, accurately representing the current thermodynamic state (State_current) of the system.

[0115] (2) Future state prediction. The central controller takes the wind and light power prediction data (P_predict(t)) as an external input disturbance, and combines the current thermodynamic state (State_current) to drive the digital twin model to perform ahead simulation calculation on the dynamic behavior of the system in the future preset period (such as the next 4 hours). The prediction content includes: the pressure change trend of each tank at each time in the future, the evolution process of the three-dimensional temperature field inside the thermal storage unit at each time in the future, the real-time heat storage amount of the thermal storage body, the temperature and pressure prediction values of the key nodes (compressor outlet, expander inlet) of the system, and the round-trip efficiency prediction values of the system under different control strategies.

[0116] Step F4: Solve the optimal control sequence in rolling time domain

[0117] Optimization problem construction: At each control decision period (such as every 5 minutes), the central controller constructs an optimal control problem (OCP) in a finite time domain (prediction time domain) with the goal of maximizing the system round-trip efficiency, while considering equipment safety constraints (pressure, temperature, stress limits) and grid scheduling requirements.

[0118] Constraint conditions: including device physical limits (speed range, opening range, angle range), state variable safety range (upper and lower pressure limits, upper and lower temperature limits), and system dynamic equations described by the digital twin model (402) as equality constraints.

[0119] Rolling optimization solving: Use the rolling time domain optimization method under the model predictive control (MPC) framework.

[0120] At each decision period, based on the latest system state prediction (step F3), solve the OCP constructed above to obtain the optimal control sequence (U_opt) in the future control time domain.

[0121] Only the first control instruction in the optimal control sequence (i.e. the instruction that should be executed immediately at the current time) is output to the actuator.

[0122] Repeat steps F2 to F4: collect new real-time data, update model state, roll forward prediction, and re-solve optimization problem to achieve closed-loop optimal control for the next decision cycle.

[0123] Optimization algorithm: the optimization solution can be selected from algorithms suitable for nonlinear constraint optimization problems, such as sequential quadratic programming (SQP), interior point method, or combined with AI optimization algorithm (such as reinforcement learning strategy network) for efficient approximate solution.

[0124] Step F5: control command output and execution

[0125] The central controller sends the current time control command obtained by the rolling optimization solution to the corresponding data executor through the data bus: sends the speed set value to the compressor speed controller; sends the opening degree command of the main control valve to the valve controller; sends the guide vane angle adjustment command of the multi-stage reheating expander to the expander controller.

[0126] Step F6: model self-correction and strategy iteration

[0127] (1) Online correction of model parameters: during system operation, continuously compare the prediction results of the digital twin model with the actual measurement data (step F2). If the deviation exceeds the preset threshold, trigger the model parameter automatic calibration program, and use system identification technology (such as least squares method) to fine-tune the key parameters (such as heat transfer coefficient, resistance coefficient) in the model online to maintain the prediction accuracy of the model.

[0128] (2) Control strategy iteration update: AI optimization algorithm can periodically (such as every week) use accumulated historical operation data (state, control, performance) to perform offline training and optimization on the prediction control strategy (such as the cost function weight in MPC, the constraint handling method) to realize the continuous evolution of the control strategy, so as to cope with the performance degradation of the equipment or the change of the operating environment.

[0129] In this way, by fusing real-time sensor data and wind and light power prediction data, the digital twin model performs rolling time domain simulation to deduce the internal temperature field of the heat storage unit and predict the future thermodynamic state of the system. Based on this prediction capability, the central controller can generate control strategies in advance before the renewable energy output or load demand changes, which is proactive, thus promoting the system to transition from traditional "passive response" operation mode to "active prediction" intelligent paradigm.

[0130] In order to illustrate the above technical solutions, a specific embodiment will be described as follows.

[0131] The core of the seabed compressed air energy storage system described in the application is that the compression heat is stored in situ during the charging phase and the heat released by the heat storage body is reused during the discharging phase. The entire "charging-heat storage-discharging-heat release" process is uniformly scheduled by an intelligent control module.

[0132] In combination Figure 4 The specific implementation steps of the present application will be described in detail below in conjunction with the flowchart.

[0133] Step one: charging and heat storage process

[0134] When the output of renewable energy sources (such as offshore wind power or photovoltaics) is abundant, the grid dispatch center or local energy management system issues a charging instruction and target charging power to the system. After receiving the instruction, the central controller 401 of the intelligent control module 400 starts the initialization program.

[0135] At this time, the digital twin model 402 receives the system state data uploaded by the data collector 404, including the current pressure of each tank 201, the temperature of the heat storage unit 202, and the wind and light power prediction data from the offshore wind turbine generator set 101 and / or the photovoltaic array 102. The digital twin model 402 real-time deduces the temperature field distribution inside the heat storage unit 202 to represent the current thermodynamic state of the system; and according to the current thermodynamic state and the wind and light power prediction data, the digital twin model 402 makes an advance prediction of the system's thermodynamic state in the future preset period. On this basis, the AI optimization algorithm 403 calculates the optimal compressor start sequence and initial speed setting value, and issues control instructions to the data executor 405, with the goal of maximizing the overall round-trip efficiency of the system and balancing the cycle life of each tank 201.

[0136] Subsequently, the multi-stage inter-cooled compressor 103 starts according to the instruction. Air is compressed in stages, and at the outlet of each stage, the inter-cooled cooler 104 cools the compressed air to reduce the power consumption required for the next stage of compression, thereby improving the overall efficiency of the compression process.

[0137] The high-pressure air is guided through a high-pressure delivery pipeline to the top inlet of a certain tank 201 selected by the AI optimization algorithm 403. Inside the tank 201, the air is forced to flow downward through the heat storage unit 202 under the driving force of pressure difference. The heat storage body 203 is made of high specific heat capacity material such as cordierite-silicon carbide composite ceramic, and has a honeycomb structure with dense micro-scale fluid channels 204 inside. During the flow through the channels, the high-pressure air and the heat storage body 203 undergo intense convective heat exchange, efficiently transferring the sensible heat carried by the air to the heat storage body 203. Since the tank 201 is immersed in low-temperature seawater for a long time, the tank wall has good natural heat dissipation conditions, further promoting air cooling. Finally, the air temperature in the annular gas storage space has dropped to near the ambient seawater temperature, while the pressure remains essentially unchanged. Therefore, the actual storage in the tank 201 is air at room temperature and high pressure, while the large amount of waste heat generated during the compression process is stored in the form of sensible heat inside the heat storage body 203. This is the first step of "spatial and temporal transfer of heat" - storing the instantaneous compression heat for later use during discharging.

[0138] Step two: discharging and heat releasing process

[0139] When the grid needs to be peaking or the renewable energy output is insufficient, the system receives a discharge instruction. The central controller 401 activates the AI optimization algorithm 403 again. At this time, the algorithm no longer only focuses on pressure, but prioritizes the thermal state of each tank 201 heat storage unit 202: the higher the temperature of the heat storage body 203, the more heat can be released, the higher the inlet air temperature of the expander, and the higher the power generation efficiency.

[0140] The AI optimization algorithm 403 accordingly selects the tank 201 with the optimal thermal state as the discharge source, and opens the main control valve 303. The normal-temperature high-pressure air in the tank 201 flows out under the action of pressure difference. The key is that the outflowing air does not directly enter the expander, but flows through the shape fluid passage 204 of the heat storage unit 202 again, but in the opposite direction, usually from the bottom to the top. In this process, the lower-temperature high-pressure air absorbs the stored sensible heat from the high-temperature heat storage body 203, and is rapidly heated to become a high-temperature high-pressure working medium. Subsequently, the air enters the multi-stage reheating expander 301, expands and does work at each stage, driving the coaxially connected generator 302 to feed back electric energy to the grid. The expanded low-pressure air is directly discharged into the atmosphere, completing the entire energy release cycle.

[0141] At this point, without burning fossil fuels or relying on external heat sources, the system successfully recycles the compressed heat stored in the charging stage in the discharging stage, significantly improves the enthalpy drop and power generation efficiency of the expansion process, and makes the overall round-trip efficiency of the system reach 65%-70%.

[0142] Figure 5 is a structural schematic diagram of a computing device 600 provided by an embodiment of the present application. The computing device performs the method described above, as shown in Figure 5 The computing device 600 includes a processor 610, a memory 620, and a communication interface 630.

[0143] It should be understood that Figure 5 The communication interface 630 in the computing device 600 shown can be used for communication with other devices, and can specifically include one or more transceiver circuits or interface circuits.

[0144] The processor 610 can be connected to the memory 620. The memory 620 can be used to store program codes and data. Therefore, the memory 620 can be an internal storage unit of the processor 610, can be an external storage unit independent of the processor 610, or can be a component including the internal storage unit of the processor 610 and the external storage unit independent of the processor 610.

[0145] Optionally, the computing device 600 can further include a bus. The bus can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For brevity, Figure 5 A single bus or a single type of bus is shown in the figure, but it is to be understood that the application can be implemented on other buses or bus systems.

[0146] It should be appreciated that in the embodiments of the present application, the processor 610 can be a central processing unit (CPU). The processor can also be other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), field programmable gate arrays (FPGA) or other programmable logic devices, discrete gates or transistor logic, discrete hardware components, etc. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor. Alternatively, the processor 610 can be one or more integrated circuits executing programs to implement the techniques described in the embodiments of the present application.

[0147] The memory 620 can include a read-only memory and a random access memory, and provide instructions and data for the processor 610. A portion of the memory 620 can also include a non-volatile random access memory. For example, the processor 610 can also store device type information.

[0148] When the computing device 600 is running, the processor 610 executes computer-executable instructions in the memory 620 to perform any of the operation steps of the above method and any optional embodiments thereof.

[0149] It should be understood that the computing device 600 according to the embodiments of the present application can correspond to a subject performing the corresponding method according to the embodiments of the present application, and the above and other operations and / or functions of the various modules in the computing device 600 are respectively for implementing the corresponding processes of the methods of the embodiments, and for brevity, will not be repeated here.

[0150] Those skilled in the art can clearly understand that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be realized by electronic hardware or a combination of computer software and electronic hardware. Whether the functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0151] Those skilled in the art can clearly understand that, for the convenience and brevity of the description, the specific working processes of the above-described system, device and unit can refer to the corresponding processes in the foregoing method embodiments, which will not be repeated here.

[0152] In several embodiments provided in the present application, it should be understood that the disclosed system, device and method can be implemented in other ways. For example, the above-described device embodiments are only schematic, for example, the division of the units is only a logical function division, and actual implementation can have another division manner, for example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the units shown or discussed can be indirect coupling or communication connection through some interface, device or unit, and can be electrical, mechanical or other forms.

[0153] The units described as separate components can or can not be physically separated, and the components shown as units can or can not be physical units, that is, they can be located in one place, or can be distributed on a plurality of network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the embodiment.

[0154] In addition, each functional unit in each embodiment of the present application can be integrated in one processing unit, or each unit can be physically present separately, or two or more units can be integrated in one unit.

[0155] If the functions are implemented in the form of software function units and sold or used as independent products, they can be stored in a computer readable storage medium. Based on this understanding, the technical solutions of the present application essentially or the parts that make contributions to the prior art or parts of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present application. The aforementioned storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and various program code storage media.

[0156] The embodiments of the present application also provide a computer readable storage medium, which stores a computer program. The program is executed by a processor to perform the above method, which includes at least one of the schemes described in the above embodiments.

[0157] The computer storage medium of the embodiments of the present application can adopt any combination of one or more computer readable media. The computer readable medium can be a computer readable signal medium or a computer readable storage medium. The computer readable storage medium may, for example, but is not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or apparatus, or any combination of the above. More specific examples (non-exhaustive list) of the computer readable storage medium include: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this document, the computer readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, device or apparatus.

[0158] The computer readable signal medium can include a data signal propagated in a baseband or as a part of a carrier wave, in which a computer readable program code is carried. Such a propagated data signal can take various forms, including but not limited to an electromagnetic signal, an optical signal or any suitable combination of the above. The computer readable signal medium can also be any computer readable medium other than the computer readable storage medium, which can send, propagate or transmit a program for use by or in conjunction with an instruction execution system, device or apparatus.

[0159] The program code contained on a computer-readable medium may be transmitted using any suitable medium, including, but not limited to, wireless, wire, optical fiber, RF, etc., or any suitable combination thereof.

[0160] 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 it can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0161] Furthermore, the terms "first, second, third, etc." or similar terms such as module A, module B, and module C used in the specification and claims are only used to distinguish similar objects and do not represent a specific ordering of objects. It is understood that, where permissible, a specific order or sequence may be interchanged so that the embodiments of this application described herein can be implemented in an order other than that illustrated or described herein.

[0162] In the above description, the labels of the steps involved, such as S110, S120, etc., do not mean that the steps will necessarily be executed. The order of the steps can be interchanged or executed simultaneously if permitted.

[0163] The term "comprising" as used in the specification and claims should not be construed as limiting itself to what follows; it does not exclude other elements or steps. Therefore, it should be interpreted as specifying the presence of the mentioned feature, integral, step, or component, but does not exclude the presence or addition of one or more other features, integrals, steps, or components, or groups thereof. Thus, the statement "device comprising means A and B" should not be limited to a device consisting solely of components A and B.

[0164] The terms "an embodiment" or "an embodiment" as used in this specification mean that a particular feature, structure, or characteristic described in conjunction with that embodiment is included in at least one embodiment of this application. Therefore, the terms "in one embodiment" or "in an embodiment" appearing throughout this specification do not necessarily refer to the same embodiment, but may refer to the same embodiment. Furthermore, in one or more embodiments, the particular features, structures, or characteristics can be combined in any suitable manner, as will be apparent to those skilled in the art from this disclosure.

[0165] Note that the above are merely preferred embodiments and the technical principles employed in this application. Those skilled in the art will understand that this application is not limited to the specific embodiments described herein, and various obvious changes, readjustments, and substitutions can be made without departing from the scope of protection of this application. Therefore, although this application has been described in detail through the above embodiments, this application is not limited to the above embodiments, and may include many other equivalent embodiments without departing from the concept of this application, all of which fall within the scope of protection of this application.

Claims

1. A subsea compressed air energy storage system, characterized in that, include: The energy and power module (100) includes an offshore wind turbine generator (101) and / or a photovoltaic array (102), the power output of which is connected to a multi-stage intercooled compressor (103) via a converter; the outlet of the multi-stage intercooled compressor (103) is connected to the inlet of a storage tank (201) via a pipeline; The gas and heat storage module (200) includes at least one storage tank (201), and a heat storage unit (202) is fixedly disposed in the center inside the storage tank (201). An annular airflow space is formed between the heat storage unit (202) and the tank wall. The heat storage unit (202) includes a heat storage body (203), and the heat storage body (203) is provided with a fluid channel (204) for air circulation. The power generation and feedback module (300) includes a multi-stage reheat expander (301) and a generator (302) connected coaxially; wherein, the air inlet of the multi-stage reheat expander (301) is connected to the outlet of the storage tank (201) through a pipeline and a main control valve (303), and the exhaust port of the multi-stage reheat expander (301) is directly connected to the external environment; The intelligent control module (400) includes a central controller (401), a digital twin model (402) and an AI optimization algorithm (403) deployed in the central controller (401), a data acquisition unit (404), and a data actuator (405); the central controller (401) is bidirectionally connected to the data acquisition unit (404) and the data actuator (405) via a data bus.

2. The system according to claim 1, characterized in that, The multi-stage intercooled compressor (103) is driven by an electric motor, and each stage of compression is equipped with an interstage cooler (104), which is used to cool the high-temperature air after compression.

3. The system according to claim 1, characterized in that, The gas and heat storage module (200) includes several storage tanks (201), and each storage tank (201) is connected in parallel through a pipeline network to form a gas and heat storage cluster. Each storage tank (201) can be independently filled or vented.

4. The system according to claim 1, characterized in that, The storage tank (201) is a cylindrical pressure vessel with a fixed volume; the upper and lower ends of the storage tank (201) are respectively provided with an upper end cap (209) and a lower end cap (210). The storage tank (201) is made of high-strength alloy steel / concrete that is resistant to seawater corrosion.

5. The system according to claim 1, characterized in that, The heat storage body (203) has a honeycomb, porous mesh or channel structure.

6. The system according to claim 5, characterized in that, The heat storage body (203) is made of cordierite-silicon carbide composite ceramic, refractory brick or encapsulated phase change material.

7. A thermal management control method applied to a subsea compressed air energy storage system as described in any one of claims 1 to 6, characterized in that, include: During the charging phase, electrical energy from offshore wind turbines and / or photovoltaic arrays is used to drive a multi-stage intercooled compressor through a converter to generate high-temperature and high-pressure compressed air. After the high-temperature and high-pressure compressed air flows through each stage of intercooler, it passes through the fluid channel in the heat storage unit inside the storage tank, so that the heat of compression is absorbed by the heat storage body, thereby cooling the air to a normal temperature and high pressure state and storing it in the storage tank. During the discharge phase, the main control valve is opened, allowing the ambient temperature high-pressure air to flow out of the storage tank and flow through the fluid channel of the heat storage unit again, absorbing the stored heat and heating up to high temperature high-pressure air; the high temperature high-pressure air is then introduced into a multi-stage reheat expander to expand and do work, driving a coaxial generator to feed electrical energy back to the grid.

8. A multi-tank cluster collaborative control method applied to a subsea compressed air energy storage system as described in any one of claims 1 to 6, characterized in that, include: When the subsea compressed air energy storage system contains multiple parallel storage tanks, the status parameters of each storage tank are obtained, including real-time pressure, average temperature of the heat storage body, and remaining available capacity. Construct a multi-objective reward function: R = w1 * power tracking accuracy – w2 * total pipeline pressure fluctuation – w3 * system comprehensive thermal stress; where w1 is the power tracking accuracy weight, w2 is the pressure fluctuation penalty weight, and w3 is the thermal stress penalty weight. Using AI optimization algorithms, weight coefficients w1, w2, and w3 are determined, and a charging and discharging decision strategy is generated. The charging and discharging decision strategy includes dynamically deciding whether to perform charging or discharging operations on one or more storage tanks, as well as the corresponding gas flow rate.

9. A predictive control method applied to a subsea compressed air energy storage system as described in any one of claims 1 to 6, characterized in that, include: The system acquires current state data, including real-time pressure of each storage tank and temperature of the thermal storage unit. Using a three-dimensional unsteady-state heat transfer model of the thermal storage unit within the digital twin model, it simulates the temperature field distribution inside the thermal storage unit in real time to characterize the current thermodynamic state of the system. It also acquires wind and solar power prediction data for offshore wind turbines and / or photovoltaic arrays, and inputs this data as a feedforward signal into the digital twin model. Based on the current thermodynamic state and the wind and solar power prediction data, the system's thermodynamic state for a future preset time period is predicted using the digital twin model. With the goal of maximizing the system's round-trip efficiency, a rolling time-domain optimization method is used to determine the control sequence; According to the control sequence, control commands are output, including: a speed setpoint for the multi-stage intercooled compressor, an opening command for the main control valve, and an adjustment command for the guide vane angle of the multi-stage reheat expander.

10. A storage medium, characterized in that, It stores program instructions, which, when executed by a computer, cause the computer to perform the thermal management control method, multi-tank cluster collaborative control method, or predictive control method according to any one of claims 7-9.

Images