Compressed air energy storage system based on efficient environment temperature time-sharing regulation and control optimization

Abstract

The invention relates to a compressed air energy storage system based on efficient environment temperature time-sharing regulation and control optimization, and the system comprises an environment perception and mode triggering module which collects environment and system parameters, and triggers a time-sharing regulation and control strategy; the energy storage module is used for realizing fused salt heat storage and large-flow operation of a circulating pump by enhancing efficient heat exchange of compressor cooling and an interstage cooling system in a daytime mode, switching a medium path by adopting compressor load reduction in cooperation with a valve in a night mode, and maintaining a system temperature base line in combination with fused salt heat release; the energy release module realizes efficient energy release through energy conversion of a multi-stage expansion machine, dynamic thermal management of a cooling load regulating valve, stable control of a pressure maintaining device and energy efficiency improvement of waste heat recovery; and the dynamic regulation and control and optimization module is used for carrying out real-time optimization and dynamic regulation and control on system parameters based on an LSTM neural network and an NSGA-II multi-objective optimization algorithm. According to the system, cooperative control of the compressor and the expansion machine can be achieved, energy loss is reduced, and the comprehensive energy efficiency and adaptability of the system are improved.

Description

Technical Field

[0001] This invention relates to the field of energy storage and conversion technology, and in particular to a compressed air energy storage system based on efficient time-sharing regulation and optimization of ambient temperature. Background Technology

[0002] Compressed air energy storage systems have become a key technology supporting the stable operation of grids with a high proportion of renewable energy due to their advantages such as large scale, long cycle, and low cost. However, traditional systems mostly adopt fixed temperature thresholds or static control strategies, which are difficult to adapt to dynamic environmental changes such as diurnal temperature differences, resulting in significant energy losses, poor equipment stability, and low system efficiency.

[0003] While existing technologies include advanced adiabatic compressed air energy storage systems that utilize thermal storage devices to recover compression heat, they still suffer from problems such as insufficient adaptability to environmental temperature fluctuations, inaccurate thermal management, and poor system synergy. Therefore, there is an urgent need for an optimized solution that can dynamically adapt to environmental temperatures, maximize energy efficiency, and ensure stable system operation. Summary of the Invention

[0004] To address the shortcomings of existing technologies, this invention proposes a compressed air energy storage system based on efficient ambient temperature time-sharing regulation optimization. The aim is to achieve coordinated control of the compressor and expander through time-sharing strategies and intelligent algorithms, thereby reducing energy loss and improving the overall energy efficiency and adaptability of the system.

[0005] To achieve the above objectives, the technical solution adopted by the present invention is: a compressed air energy storage system based on efficient ambient temperature time-sharing regulation and optimization, including an environmental sensing and mode triggering module, an energy storage module, an energy release module, and a dynamic regulation and optimization module;

[0006] The environmental perception and mode triggering module collects environmental and system parameters in real time and triggers time-sharing control strategies.

[0007] The energy storage module includes a centrifugal compressor, an interstage cooling system, a circulating pump and valves, and a molten salt thermal storage tank. In the high-temperature mode during the day, the energy storage module achieves molten salt thermal storage and high-flow operation of the circulating pump by enhancing compressor cooling and efficient heat exchange between the interstage cooling system. In the low-temperature mode at night, the compressor load is reduced and the valves are used to switch the medium path, combined with molten salt heat release to maintain the system temperature baseline.

[0008] The energy release module includes a multi-stage expander, a cooling load regulating valve, a pressure maintaining device, and a low-temperature waste heat utilization device. The energy release module achieves efficient energy release through the high-efficiency energy conversion of the multi-stage expander, the dynamic thermal management of the cooling load regulating valve, the stable control of the pressure maintaining device, and the energy efficiency improvement of waste heat recovery.

[0009] The dynamic control and optimization module is based on LSTM neural network and NSGA-II multi-objective optimization algorithm to optimize and dynamically control system parameters in real time, and to verify and correct the strategy through digital twin platform.

[0010] Furthermore, the environmental perception and mode triggering module includes a temperature sensor, a pressure sensor, a time acquisition card, and a time-division multiplexing device. The temperature sensor is used to collect ambient temperature data, the pressure sensor is used to collect system pressure data, and the time acquisition card is used to acquire time data and integrate ambient temperature, system pressure, and time data to complete signal conditioning, analog-to-digital conversion, and real-time transmission to the time-division multiplexing device. The time-division multiplexing device is used to divide daytime and nighttime periods based on time data, switch the system's operating mode in conjunction with ambient temperature data, and determine whether the system pressure is stable within a safe range based on system pressure data. The system's operating modes include a daytime high-temperature mode, a nighttime low-temperature mode, and a standby mode.

[0011] Furthermore, the time-division device divides daytime and nighttime periods based on time data and a preset time-division function; the time-division function is:

[0012]

[0013] Where H(t) is the unit step function based on time t;

[0014] The time-sharing device switches the system's operating mode according to the following formula:

[0015]

[0016] Among them, System Mode indicates the system's operating mode, Daytime Mode indicates the daytime high-temperature mode, Nighttime Mode indicates the nighttime low-temperature mode, Standby Mode indicates the standby mode, and T... env (t) represents the ambient temperature data collected in real time by the temperature sensor, T day threshold T represents the temperature threshold that triggers the daytime high temperature mode. night threshold This indicates the temperature threshold that triggers the nighttime low temperature mode;

[0017] The environmental perception and mode triggering module collects real-time pressure data from the system's gas storage tank and expander inlet pressure data via pressure sensors, and determines whether the system pressure is stable within a safe range using the following formula:

[0018]

[0019] in, This indicates the real-time pressure of the gas storage tank as collected by the pressure sensor. This indicates the expander inlet pressure, which is collected in real time by the pressure sensor. , These are the upper and lower limits of the set safe pressure for the gas storage tank. , These are the upper and lower limits of the set expander inlet safety pressure, respectively.

[0020] Furthermore, the centrifugal compressor compresses air to a supercritical state, providing a high-pressure gas foundation for energy storage, and employs multi-stage impellers for progressive pressurization; the formula for calculating the total pressure ratio of the centrifugal compressor is:

[0021]

[0022] in, This indicates the total pressure ratio of the centrifugal compressor. This represents the pressure ratio of the i-th stage of the centrifugal compressor, and n represents the number of compression stages of the centrifugal compressor.

[0023] The interstage cooling system reduces compression power loss and improves heat storage efficiency by lowering the air temperature during compression. It employs a multi-stage cooler, with the coolant consisting of 50% ethanol and 50% water. The energy balance equation for the interstage cooling system is:

[0024]

[0025] in, Indicates the mass flow rate of air. This represents the specific heat capacity of air at constant pressure. Indicates the compressor outlet temperature. Indicates the temperature after cooling. This indicates the temperature difference before and after cooling. This indicates the thermal power of the molten salt being introduced into the molten salt vessel;

[0026] The heat between stages is transferred to the molten salt thermal storage tank to achieve cascade utilization of thermal energy, reduce energy loss and improve nighttime cooling efficiency; at the same time, the circulating pump and valves ensure the safe delivery and pressure regulation of the medium; the molten salt thermal storage tank uses nitrate as the medium to store compression heat or solar thermal energy.

[0027] Furthermore, the multi-stage expander is used to achieve efficient energy conversion of high-pressure air, reduce temperature gradient stress through multi-stage expansion, and improve mechanical energy recovery efficiency; in order to prevent the material thermal stress from exceeding the limit, the temperature drop of each expansion stage is controlled within the range of 50-70°C.

[0028] The single-stage expansion output power of the multi-stage expander is:

[0029]

[0030] in, This represents the output work of the i-th stage of a multi-stage expander. The specific enthalpy of the inlet air in a single-stage expansion. The specific enthalpy of the outlet air in a single-stage expansion;

[0031] The power generation of the multi-stage expander is:

[0032]

[0033] in, This represents the total power generation of the multi-stage expander, where n represents the number of stages in the multi-stage expander. Indicates power generation efficiency. Indicates runtime;

[0034] The cooling load regulating valve is used to dynamically adjust the interstage cooling intensity of the multi-stage expander, achieving dynamic thermal management that matches changes in ambient temperature; the valve position control function of the cooling load regulating valve is:

[0035]

[0036] in, This represents the valve position control parameters output by the NSGA-II multi-objective optimization algorithm. T represents the NSGA-II multi-objective optimization algorithm. env (t) represents the ambient temperature, T exp,in (t) represents the expander inlet temperature;

[0037] The pressure maintaining device is used to stabilize the expander inlet pressure and ensure that the expander inlet pressure remains stable at the set value;

[0038] The low-temperature waste heat recovery device is used to recover the exhaust waste heat of the multi-stage expander, improve the overall energy efficiency of the system, and start the thermoelectric decoupling mode in the low-temperature night mode.

[0039] Furthermore, the dynamic control and optimization module includes an LSTM+NSGA-II algorithm module; in the LSTM+NSGA-II algorithm module, the LSTM neural network predicts the changing trend of key system parameters through real-time data obtained by the environmental perception and pattern triggering module. On this basis, the NSGA-II multi-objective optimization algorithm solves the optimal solution set of key system parameters, including compressor speed and valve opening, by minimizing heat loss.

[0040] Furthermore, the NSGA-II multi-objective optimization algorithm is used to solve multi-objective optimization problems, and its objective function includes:

[0041] Minimize heat loss:

[0042]

[0043] in, Indicates heat loss, Represents the decision vector. This represents the system's heat loss power, where α, β, and γ are all heat loss weights. , , Used for normalization processing;

[0044] And ensure that power generation is not lower than the threshold. :

[0045]

[0046] in, This indicates the amount of electricity generated.

[0047] Furthermore, the NSGA-II multi-objective optimization algorithm dynamically adjusts the heat loss weight α according to the time-division function H(t):

[0048]

[0049] Where, α day For daytime high temperature mode, α day =0.7, α night For nighttime low temperature mode, α night =0.3, used to strengthen the control of heat loss at different time periods.

[0050] Furthermore, the dynamic control and optimization module includes security protection components, wherein hardware protection directly protects physical devices through voltage and current threshold settings, while network protection defends against external attacks through firewall mechanisms to ensure the security of data and control links.

[0051] Furthermore, the dynamic control and optimization module includes a digital twin platform and a 5G communication module; the digital twin platform is used to provide a verification and optimization environment for control strategies, which simulates the operation of instructions generated by the LSTM+NSGA-II algorithm module in virtual space to verify their effectiveness and security, and supports online correction and predictive maintenance of the strategy.

[0052] The 5G communication module provides a high-speed channel for data interaction. It is responsible for transmitting sensor data and device status to the cloud platform with low latency, and at the same time, it quickly sends control commands generated by the optimization algorithm to each actuator to achieve real-time monitoring.

[0053] Compared with the prior art, the present invention has the following beneficial effects:

[0054] 1. Compared with traditional compressed air energy storage systems, this invention achieves dynamic adaptation of the operating strategy to the ambient temperature through time-sharing control of ambient temperature, effectively overcoming the limitations of static control.

[0055] 2. Compared with traditional compressed air energy storage systems, this invention achieves deep synergy between the energy storage module and the energy release module by integrating a molten salt thermal storage tank and an intelligent valve control system. During the day, the system stores the high-grade heat energy generated during the compression process in the molten salt tank; at night, the stored heat energy is used to preheat the expander inlet air, not only improving the expander's working efficiency but also solving the potential damage problem of low-temperature air to the equipment. The system recovers the waste heat from the expander exhaust through a low-temperature waste heat recovery device for heating or cooling, achieving cascaded and efficient utilization of thermal energy. This design expands the system from a single power storage system into a combined heat and power (CHP) integrated energy system, significantly improving the overall energy utilization rate.

[0056] 3. Compared to traditional compressed air energy storage systems, this invention utilizes an intelligent decision-making framework combining LSTM and NSGA-II. This framework enables advanced prediction of core state parameters such as air tank pressure and critical node temperatures, providing forward-looking information for control. The NSGA-II multi-objective optimization algorithm then solves in parallel for the optimal solution set of multiple conflicting objectives, such as minimizing heat loss and maximizing net energy gain, thereby outputting the optimal configuration of key parameters like compressor speed and valve opening in real time. This algorithmic fusion strategy endows the system with adaptive optimization capabilities to cope with complex operating conditions.

[0057] 4. Compared to traditional compressed air energy storage systems, this invention constructs a highly reliable architecture integrating digital twins and 5G communication. The digital twin platform, by establishing a virtual mapping of the system, supports the simulation verification and predictive maintenance of operational strategies, significantly reducing the risk of on-site trial and error and operation and maintenance costs. The 5G communication network provides high-speed, low-latency transmission guarantees for massive amounts of sensing data and control commands, ensuring the real-time nature of state perception and decision-making control. Furthermore, the system integrates hardware protection circuits for overvoltage and overcurrent protection, as well as a network firewall, forming a comprehensive hardware and software security protection system that meets the stringent reliability and safety requirements of critical energy infrastructure. Attached Figure Description

[0058] Figure 1 This is a block diagram illustrating the implementation principle of a compressed air energy storage system based on efficient ambient temperature time-sharing regulation optimization, as provided in an embodiment of the present invention.

[0059] Figure 2 This is a schematic diagram of the compressed air energy storage system based on efficient time-sharing control optimization of ambient temperature, provided in an embodiment of the present invention.

[0060] Figure 3This is a flowchart illustrating the implementation of the NSGA-II multi-objective optimization algorithm in an embodiment of the present invention.

[0061] Figure 4 A flowchart of the compressed air energy storage system based on efficient ambient temperature time-sharing regulation optimization provided in this embodiment of the invention;

[0062] Figure 5 This is a compressor temperature monitoring diagram in an embodiment of the present invention;

[0063] Figure 6 This is a comparison diagram of system heat loss in an embodiment of the present invention;

[0064] Figure 7 This is a comparison chart of energy recovery performance in embodiments of the present invention;

[0065] Figure 8 This is a schematic diagram of algorithm prediction optimization in an embodiment of the present invention. Detailed Implementation

[0066] The present invention will be further described below with reference to the accompanying drawings and embodiments.

[0067] It should be noted that the following detailed descriptions are exemplary and intended to provide further explanation of this application. Unless otherwise specified, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application pertains.

[0068] It should be noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the exemplary embodiments according to this application. As used herein, the singular form is intended to include the plural form as well, unless the context clearly indicates otherwise. Furthermore, it should be understood that when the terms "comprising" and / or "including" are used in this specification, they indicate the presence of features, steps, operations, devices, components, and / or combinations thereof.

[0069] like Figure 1-2 As shown, this embodiment provides a compressed air energy storage system based on efficient ambient temperature time-sharing regulation optimization, including an environmental sensing and mode triggering module, an energy storage module, an energy release module, and a dynamic regulation and optimization module.

[0070] The environmental perception and mode triggering module collects environmental and system parameters in real time and triggers time-sharing control strategies to solve the problems of energy loss and equipment stability caused by day-night temperature differences in traditional systems.

[0071] The energy storage module includes a centrifugal compressor 2, an interstage cooling system, a circulating pump and valves, and a molten salt thermal storage tank 3. In the high-temperature mode during the day, the energy storage module achieves molten salt thermal storage and high-flow operation of the circulating pump by enhancing compressor cooling and efficient heat exchange between the interstage cooling system. In the low-temperature mode at night, the compressor load is reduced and the valves are used to switch the medium path, combined with molten salt heat release to maintain the system temperature baseline.

[0072] The energy release module includes a multi-stage expander 4, a cooling load regulating valve, a pressure maintaining device, and a low-temperature waste heat utilization device 5. The energy release module achieves efficient energy release through the efficient energy conversion of the multi-stage expander, the dynamic thermal management of the cooling load regulating valve, the stable control of the pressure maintaining device, and the energy efficiency improvement of waste heat recovery.

[0073] The dynamic control and optimization module is based on LSTM neural network and NSGA-II multi-objective optimization algorithm to optimize and dynamically control system parameters in real time, and to verify and correct the strategy through digital twin platform 6.

[0074] 1. Environmental perception and pattern triggering module

[0075] The environmental perception and mode triggering module includes a temperature sensor 1, a pressure sensor, a time acquisition card, and a time-division multiplexing device. The temperature sensor collects ambient temperature data. The pressure sensor collects system pressure data. The time acquisition card acquires time data and integrates ambient temperature, system pressure, and time data, performing signal conditioning, analog-to-digital conversion, and real-time transmission to the time-division multiplexing device. The time-division multiplexing device divides the system into day and night periods based on time data, switches the system's operating mode based on ambient temperature data, and determines whether the system pressure is stable within a safe range based on system pressure data. The system's operating modes include a daytime high-temperature mode, a nighttime low-temperature mode, and a standby mode.

[0076] The time-division device divides daytime and nighttime periods based on time data and a preset time-division function. The time-division function is:

[0077]

[0078] Where H(t) is a unit step function based on time t. When H(t)=1, the system starts the daytime high temperature mode, prioritizing the enhanced cooling and heat storage strategies of the energy storage module; when H(t)=0, the system starts the nighttime low temperature mode, prioritizing the efficient power generation and waste heat recovery strategies of the energy release module.

[0079] The time-sharing device switches the system's operating mode according to the following formula:

[0080]

[0081] Among them, System Mode indicates the system's operating mode, Daytime Mode indicates the daytime high-temperature mode, Nighttime Mode indicates the nighttime low-temperature mode, Standby Mode indicates the standby mode, and T... env (t) represents the ambient temperature data collected in real time by the temperature sensor, T day threshold T represents the temperature threshold that triggers the daytime high temperature mode. night threshold This indicates the temperature threshold that triggers the nighttime low temperature mode.

[0082] The environmental perception and mode triggering module collects real-time pressure data from the system's gas storage tank and expander inlet pressure data via pressure sensors, and determines whether the system pressure is stable within a safe range using the following formula:

[0083]

[0084] in, This indicates the real-time pressure of the gas storage tank as collected by the pressure sensor. This indicates the expander inlet pressure, which is collected in real time by the pressure sensor. , These are the upper and lower limits of the set safe pressure for the gas storage tank. , These are the upper and lower limits of the set expander inlet safety pressure, respectively.

[0085] 2. Energy storage module

[0086] The centrifugal compressor compresses air to a supercritical state, providing a high-pressure gas foundation for energy storage, and employs multi-stage impellers for progressive pressurization; the formula for calculating the total pressure ratio of the centrifugal compressor is:

[0087]

[0088] in, This indicates the total pressure ratio of the centrifugal compressor. This represents the pressure ratio of the i-th stage of the centrifugal compressor, and n represents the number of compression stages of the centrifugal compressor.

[0089] The interstage cooling system reduces compression power loss and improves heat storage efficiency by lowering the air temperature during compression. It employs a multi-stage cooler, with the coolant consisting of 50% ethanol and 50% water. The energy balance equation for the interstage cooling system is:

[0090]

[0091] in, Indicates the mass flow rate of air. This represents the specific heat capacity of air at constant pressure. Indicates the compressor outlet temperature. Indicates the temperature after cooling. This indicates the temperature difference before and after cooling. This indicates the thermal power of the molten salt being introduced into the molten salt tank.

[0092] The heat between stages is introduced into the molten salt thermal storage tank through circulating pumps and valves, realizing the cascade utilization of thermal energy, reducing energy loss and improving nighttime cooling efficiency; at the same time, the circulating pumps and valves ensure the safe delivery and pressure regulation of the medium; the molten salt thermal storage tank uses nitrate as the medium to store compression heat or solar thermal energy.

[0093] During low daytime temperatures, the compressor speed is reduced to decrease the heat generated during compression, thus meeting the thermal management requirements of the low-temperature environment. The coolant flow rate is also adjusted via valves to reduce heat exchange power. Although energy storage is the primary function during the day, the multi-stage expander and waste heat recovery device of the energy storage module may passively intervene during low daytime temperatures to achieve thermal energy dispatch.

[0094] 3. Energy release module

[0095] The multi-stage expander is used to achieve efficient energy conversion of high-pressure air. Through multi-stage expansion, it reduces temperature gradient stress and improves mechanical energy recovery efficiency. To prevent excessive thermal stress on the material, the temperature drop of each expansion stage is controlled within the range of 50-70°C.

[0096] The single-stage expansion output power of the multi-stage expander is:

[0097]

[0098] in, This represents the output work of the i-th stage of a multi-stage expander. The specific enthalpy of the inlet air in a single-stage expansion. Specific enthalpy (kJ / kg) of the outlet air in a single-stage expansion.

[0099] The power generation of the multi-stage expander is:

[0100]

[0101] in, This represents the total power generation of the multi-stage expander, where n represents the number of stages in the multi-stage expander. Indicates power generation efficiency. Indicates runtime (s).

[0102] The cooling load regulating valve is used to dynamically adjust the interstage cooling intensity of the multi-stage expander, achieving dynamic thermal management that matches changes in ambient temperature. The valve position control function of the cooling load regulating valve is:

[0103]

[0104] in, This represents the valve position control parameters output by the NSGA-II multi-objective optimization algorithm. T represents the NSGA-II multi-objective optimization algorithm. env (t) represents the ambient temperature, T exp,in (t) represents the expander inlet temperature.

[0105] The pressure maintaining device is used to stabilize the expander inlet pressure, ensuring that the expander inlet pressure remains stable at the set value, and preventing sudden pressure changes that could lead to a decrease in efficiency.

[0106] The low-temperature waste heat recovery device is used to recover the exhaust waste heat (40-80℃) of the multi-stage expander, improve the overall energy efficiency of the system, and start the thermoelectric decoupling mode in the low-temperature night mode.

[0107] 4. Dynamic control and optimization module

[0108] The dynamic control and optimization module includes an LSTM+NSGA-II algorithm module, a security protection component, a digital twin platform, and a 5G communication module.

[0109] The LSTM+NSGA-II algorithm module serves as the decision-making center. The LSTM neural network predicts the changing trends of key system parameters using real-time data acquired by the environmental perception and pattern triggering modules. Based on this, the NSGA-II multi-objective optimization algorithm minimizes heat loss to find the optimal solution set for key system parameters such as compressor speed and valve opening.

[0110] The LSTM neural network mainly consists of a forget gate, an input gate, a memory gate, and an output gate. The forget gate selectively forgets the gas storage tank pressure data input from the previous node; the input gate inputs the current compressor outlet temperature data; the memory gate selectively remembers the molten salt thermal storage tank temperature data; and the output gate outputs the expander cooling valve opening command. The calculation formula is as follows:

[0111] in, , , , This describes the information update process for the forget gate, input gate, memory gate, and output gate. , , , Its corresponding weight matrix, , , , Its corresponding bias constant; This is a temporary state; It is the sigmoid activation function; It is the hyperbolic tangent function; This is the current compressor outlet temperature data; The gas tank pressure data input from the previous node; This is used to output the expansion tank cooling valve opening command. An LSTM neural network prediction model is employed to address energy loss caused by diurnal temperature variations.

[0112] The NSGA-II multi-objective optimization algorithm is used to solve multi-objective optimization problems, and its objective function includes:

[0113] 1) Minimize heat loss:

[0114]

[0115] in, Indicates heat loss, Represents the decision vector. This represents the system's heat loss power, where α, β, and γ are all heat loss weights. , , , Used for normalization.

[0116] 2) Ensure that power generation is not lower than the threshold. :

[0117]

[0118] in, It indicates the amount of electricity generated, while also taking into account the economic efficiency of the system.

[0119] like Figure 3 As shown, the specific implementation process of the NSGA-II multi-objective optimization algorithm is as follows:

[0120] Step 1: Population Initialization

[0121] Generation size is initial population Randomly initialize each individual And calculate its objective function value. and .

[0122] Step 2: Non-dominated sorting

[0123] Perform fast non-dominated sorting on the objective function values, individual Dominate The requirements are:

[0124]

[0125] The non-dominated layers are divided according to the dominance relationship, where F1 is the optimal Pareto front.

[0126] Step 3: Crowding Calculation

[0127] To maintain the diversity of the solution set, the crowding degree is calculated for each layer of individuals:

[0128]

[0129] in, Individual The level of congestion, and These are the maximum and minimum values ​​of the k-th objective function in the current population.

[0130] Step Four: Elite Retention and Iteration

[0131] Merge parent and offspring populations, and select the optimal population based on non-dominance level and crowding. Individuals enter the next generation, repeating until convergence.

[0132] A major innovation of this system lies in its adoption of different operating strategies based on the diurnal temperature range. The objective focus of the NSGA-II multi-objective optimization algorithm should also change dynamically accordingly, rather than using fixed weights. Therefore, in this invention, the NSGA-II multi-objective optimization algorithm dynamically adjusts the heat loss weight α based on the time-sharing function H(t):

[0133]

[0134] Where, α day For daytime high temperature mode, α day =0.7, α night For nighttime low temperature mode, α night =0.3, used to strengthen the control of heat loss at different time periods.

[0135] This invention prioritizes equipment safety as a fundamental prerequisite for optimization. Traditional multi-objective optimization algorithms may focus solely on performance metrics while neglecting practical engineering limitations. Therefore, for temperature gradient constraints, thermal stress constraints are introduced to prevent equipment damage:

[0136]

[0137] Furthermore, the constraint dominance principle is adopted, and individuals that violate the thermal constraint are automatically downgraded.

[0138] There is a delay in the response of thermodynamic systems to control commands. By the time the algorithm calculates the optimal valve opening based on the current temperature and executes it, the temperature may have changed, causing the command to be no longer optimal when it actually takes effect, and it may even exacerbate system fluctuations.

[0139] Therefore, this invention integrates an LSTM prediction model to predict the system thermal state in advance for LSTM-assisted heat loss estimation:

[0140]

[0141] By incorporating the predicted values ​​into the objective function calculation, we can overcome system inertia and achieve forward-looking optimization.

[0142] In the security protection components, hardware protection directly protects physical devices by setting voltage and current thresholds, while network protection defends against external attacks through firewall mechanisms, ensuring the security of data and control links.

[0143] The digital twin platform is used to provide a verification and optimization environment for control strategies. It simulates the operation of instructions generated by the LSTM+NSGA-II algorithm module in a virtual space to verify their effectiveness and security, and supports online correction and predictive maintenance of the strategy.

[0144] The 5G communication module provides a high-speed channel for data interaction. It is responsible for transmitting sensor data and device status to the cloud platform with low latency, and at the same time, it quickly sends control commands generated by the optimization algorithm to each actuator to achieve real-time monitoring.

[0145] The compressed air energy storage system based on efficient ambient temperature time-sharing regulation optimization provided in this embodiment has the following working process: Figure 4 As shown. During its operation, the compressor temperature monitoring results are as follows: Figure 5 As shown, the system heat loss is compared to, for example Figure 6 As shown, energy recovery performance is compared to, for example Figure 7 As shown, the algorithm predicts the optimization results as follows: Figure 8 As shown.

[0146] This invention optimizes the compressed air energy storage system by adjusting the ambient temperature over time and combining it with the LSTM+NSGA-II intelligent algorithm, achieving a comprehensive improvement in energy efficiency, reliability, and adaptability. This invention effectively reduces energy loss, optimizes thermal management, and expands system functionality through module collaboration, providing an efficient and intelligent energy storage solution for grids with a high proportion of renewable energy.

[0147] The above description is merely a preferred embodiment of the present invention and is not intended to limit the invention in any other way. Any person skilled in the art may make changes or modifications to the above-disclosed technical content to create equivalent embodiments. However, any simple modifications, equivalent changes, and modifications made to the above embodiments based on the technical essence of the present invention without departing from the scope of the present invention shall still fall within the protection scope of the present invention.

Claims

1. A compressed air energy storage system based on efficient ambient temperature time-sharing regulation optimization, characterized in that, The system comprises an environment sensing and mode triggering module, an energy storage module, an energy release module, and a dynamic regulation and optimization module. The environment sensing and mode triggering module collects environmental and system parameters in real time and triggers a time-sharing regulation strategy. The energy storage module comprises a centrifugal compressor, an inter-stage cooling system, a circulating pump, valves, and a molten salt heat storage tank. The energy release module comprises multi-stage expanders, cooling load regulating valves, pressure maintaining devices, and low-temperature waste heat utilization devices. The dynamic regulation and optimization module performs real-time optimization and dynamic regulation on system parameters based on an LSTM neural network and an NSGA-II multi-objective optimization algorithm, and performs strategy verification and correction through a digital twin platform.

2. The high-efficiency ambient temperature based time-sharing regulated optimized compressed air energy storage system of claim 1, wherein, The environment sensing and mode triggering module comprises temperature sensors, pressure sensors, time acquisition cards, and time-sharing devices. The system has a daytime high-temperature mode, a nighttime low-temperature mode, and a standby mode.

3. The high-efficiency ambient temperature based time-sharing regulated optimized compressed air energy storage system of claim 2, wherein, The time-sharing device divides daytime and nighttime periods based on a preset time-sharing function according to time data. The time-sharing device switches the system's operation mode according to the following formula. The environment sensing and mode triggering module collects system gas tank pressure data and expander inlet pressure data in real time through pressure sensors, and determines whether the system pressure is stable in a safe range according to the following formula. wherein System Mode represents the running mode of the system, Daytime Mode represents the daytime high-temperature mode, Nighttime Mode represents the nighttime low-temperature mode, Standby Mode represents the standby mode, T env (t) represents the environmental temperature data collected by the temperature sensor in real time, T day threshold represents the temperature threshold for triggering the daytime high-temperature mode, T night threshold represents the temperature threshold for triggering the nighttime low-temperature mode; The centrifugal compressor compresses air to a supercritical state to provide high-pressure gas for energy storage, and uses multiple impellers to gradually increase the pressure. wherein, P tank represents the pressure of the gas storage tank collected by the pressure sensor in real time, P inlet represents the inlet pressure of the expander collected by the pressure sensor in real time, , P tank max and P tank min represent the upper and lower limits of the safety pressure of the gas storage tank respectively, , P inlet max and P inlet min represent the upper and lower limits of the safety pressure of the expander inlet respectively.

4. The high-efficiency ambient temperature based time-sharing regulated optimized compressed air energy storage system of claim 1, wherein, The inter-stage cooling system reduces air temperature during the compression process to reduce compression power loss and improve heat storage efficiency, and uses multiple coolers. wherein represents the total pressure ratio of the centrifugal compressor, represents the pressure ratio of the i-th stage of the centrifugal compressor, n represents the number of compression stages of the centrifugal compressor; The energy balance equation of the inter-stage cooling system is wherein, represents the mass flow rate of air, represents the specific heat capacity of air at constant pressure, represents the temperature at the outlet of the compressor, represents the temperature after cooling, represents the temperature difference before and after cooling, represents the thermal power introduced into the molten salt tank; The inter-stage heat is introduced into the molten salt heat storage tank to realize the heat energy cascade utilization, reduce energy loss and improve the night cooling performance; meanwhile, the circulating pump and the valve ensure the safe delivery and pressure regulation of the medium; the molten salt heat storage tank takes nitrate as the medium and stores the compressed heat or solar heat.

5. The high-efficiency ambient temperature based time-sharing regulated optimized compressed air energy storage system of claim 1, wherein, The multi-stage expander is used for realizing efficient energy conversion of high-pressure air, reducing the temperature gradient stress through multi-stage expansion and improving the mechanical energy recovery efficiency; in order to prevent the thermal stress of the material from exceeding the limit, the temperature drop of each stage of expansion is controlled in the range of 50-70°C; The output power of each stage of expansion of the multi-stage expander is: wherein, represents the i-th stage expansion output power of the multi-stage expander, represents the specific enthalpy of the inlet air of the single-stage expansion, represents the specific enthalpy of the outlet air of the single-stage expansion; The power generation of the multi-stage expander is: wherein, represents the total power generation of the multi-stage expander, n represents the number of stages of the multi-stage expander, represents the power generation efficiency, represents the operation time length; The cooling load regulating valve is used for dynamically adjusting the inter-stage cooling intensity of the multi-stage expander, realizing the dynamic thermal management matched with the change of the environment temperature; the valve position control function of the cooling load regulating valve is: wherein, represents the valve position control parameter output by the NSGA-II multi-objective optimization algorithm, represents the NSGA-II multi-objective optimization algorithm, T env (t) represents the ambient temperature, T exp,in (t) represents the expander inlet temperature; The pressure maintaining device is used for stabilizing the inlet pressure of the expander and ensuring that the inlet pressure of the expander is stable at the set value; The low-temperature waste heat utilization device is used for recovering the exhaust waste heat of the multi-stage expander, improving the comprehensive energy efficiency of the system and starting the thermal-electric decoupling mode in the night low-temperature mode.

6. The high-efficiency ambient temperature-based time-sharing regulated optimized compressed air energy storage system of claim 1, wherein, The dynamic regulation and optimization module comprises an LSTM+NSGA-II algorithm module; in the LSTM+NSGA-II algorithm module, the LSTM neural network predicts the change trend of the key parameters of the system through the real-time data obtained by the environment perception and mode triggering module, and on this basis, the NSGA-II multi-objective optimization algorithm solves the optimal solution set of the key parameters of the compressor speed and the valve opening degree by minimizing the heat loss.

7. The high-efficiency ambient temperature-based time-sharing regulated optimized compressed air energy storage system of claim 6, wherein, The NSGA-II multi-objective optimization algorithm is used for solving a multi-objective optimization problem, and the objective function comprises: Minimizing the heat loss: wherein, represents the heat loss, represents the decision vector, represents the system heat loss power, and a, β, γ are heat loss weights, , , for normalization processing; and ensuring that the amount of generated power is not lower than a threshold : wherein, represents the amount of generated power.

8. The high-efficiency ambient temperature-based time-sharing regulated optimized compressed air energy storage system of claim 7, wherein, The NSGA-II multi-objective optimization algorithm dynamically adjusts the heat loss weight α according to the time division function H(t): Where, α day For daytime high temperature mode, α day =0.7, α night For nighttime low temperature mode, α night =0.3, used to strengthen the control of heat loss at different time periods.

9. The high-efficiency ambient temperature-based time-shared regulated optimized compressed air energy storage system of claim 1, wherein, The dynamic regulation and optimization module comprises a safety protection component, wherein the hardware protection directly protects the physical equipment through voltage and current threshold setting, and the network protection resists external attacks through the firewall mechanism to ensure the safety of the data and control link.

10. The high-efficiency ambient temperature-based time-shared regulated optimized compressed air energy storage system of claim 1, wherein, The dynamic regulation and optimization module comprises a digital twin platform and a 5G communication module; the digital twin platform is used for providing a verification and optimization environment of the control strategy, simulates the instructions generated by the LSTM+NSGA-II algorithm module in the virtual space, verifies the effectiveness and safety thereof and supports online correction and predictive maintenance of the strategy; The 5G communication module provides a high-speed channel for data interaction, is responsible for low-latency transmission of sensor data and device states to the cloud platform, and simultaneously rapidly issues the control instructions generated by the optimization algorithm to each actuator, realizing real-time monitoring.

Images