Power plant steam extraction energy storage and power generation optimization method and system based on fused salt heat storage

Abstract

The invention provides a power plant steam extraction energy storage and power generation optimization method and system based on fused salt heat storage, and relates to the technical field of electric power. The extracted steam is introduced into a multi-stage tandem type steam-molten salt heat exchanger group; when the load of the power grid is higher than a preset dynamic threshold value, conveying the high-temperature fused salt to the cascade fused salt-water heat exchanger group by adopting a multi-path parallel fused salt conveying system; in the fused salt-water heat exchanger group, a structure of combining countercurrent flow heat exchange and a spiral heat exchange pipe is adopted, so that the heat exchange efficiency is improved, and superheated steam is generated; the generated high-temperature and high-pressure steam is conveyed to the improved steam turbine with the variable air inlet area, the air inlet area is dynamically adjusted according to the power grid load requirement, and the efficiency of the steam turbine is optimized; the intelligent power grid technology and the demand side response strategy are utilized to realize bidirectional interaction between the power generation end and the power utilization end, and power supply and demand are dynamically balanced.

Description

Technical Field

[0001] The present invention relates to electric power technology, and in particular to a method and system for optimizing power plant steam extraction energy storage and power generation based on molten salt heat storage. Background Art

[0002] Among many energy storage technologies, molten salt heat storage technology has become an important form of energy storage due to its high energy storage density, good thermal stability and long service life, especially suitable for large-scale cogeneration and solar power generation systems. The molten salt heat storage system can effectively regulate the output of the power generation system, balance the grid load and improve energy efficiency by storing heat energy at high load and releasing heat energy at low load.

[0003] Traditional energy storage methods, such as battery storage and pumped storage, have certain regulatory functions, but their application in power systems still faces problems such as high cost, low efficiency, and limited scale. In contrast, the molten salt thermal storage technology combined with the application of the power plant steam extraction system can not only achieve efficient storage and release of thermal energy, but also convert excess electrical energy into thermal energy for storage through steam extraction storage, and generate electricity through steam turbines when needed, further improving the power generation efficiency of the power plant. Summary of the invention

[0004] The embodiments of the present invention provide a method and system for power plant extraction steam storage and power generation optimization based on molten salt heat storage, which can solve the problems in the prior art.

[0005] According to a first aspect of the embodiments of the present invention,

[0006] Provides power plant extraction steam energy storage and power generation optimization methods based on molten salt heat storage, including:

[0007] Construct a multi-level grid load monitoring system, including macro-regional grid load, meso-city grid load and micro-user electricity load, to collect and analyze load data in real time; when the comprehensive grid load is lower than the preset dynamic threshold, control the steam turbine to perform variable-condition steam extraction operation, and use intelligent regulating valve group to accurately control the steam extraction volume and pressure; introduce the extracted steam into a multi-stage series steam-molten salt heat exchanger group, and during the heat exchange process, use eddy current enhanced heat exchange technology to improve the molten salt's absorption efficiency of steam heat; use phase change material composite molten salt technology to increase the heat capacity and energy storage density of molten salt, while reducing the freezing point of molten salt and expanding the system's operating temperature range;

[0008] A high-temperature molten salt storage tank that combines multi-layer insulation and vacuum insulation is used to minimize heat loss, and a temperature gradient monitoring system is set up inside the storage tank; a molten salt physical property parameter prediction model based on deep learning is established to predict the key parameters of the specific heat capacity and thermal conductivity of molten salt at different temperatures and pressures in real time; when the grid load is higher than the preset dynamic threshold, a multi-channel parallel molten salt delivery system is used to transport the high-temperature molten salt to the cascade molten salt-water heat exchanger group; in the molten salt-water heat exchanger group, a structure combining countercurrent heat exchange and spiral heat exchange tubes is used to improve the heat exchange efficiency and generate superheated steam;

[0009] The generated high-temperature and high-pressure steam is transported to an improved steam turbine with a variable air inlet area, and the air inlet area is dynamically adjusted according to the load demand of the power grid to optimize the efficiency of the steam turbine. By using smart grid technology and demand-side response strategies, two-way interaction between the power generation end and the power consumption end is achieved, dynamically balancing the supply and demand of electricity.

[0010] In an optional embodiment,

[0011] When the integrated power grid load is lower than the preset dynamic threshold, the steam turbine is controlled to perform variable-condition steam extraction operation, and the intelligent regulating valve group is used to accurately control the steam extraction volume and pressure; the extracted steam is introduced into a multi-stage series steam-molten salt heat exchanger group. During the heat exchange process, the eddy current enhanced heat exchange technology is used to improve the molten salt's absorption efficiency of steam heat; the phase change material composite molten salt technology is used to increase the heat capacity and energy storage density of the molten salt, while reducing the freezing point of the molten salt, and expanding the system's operating temperature range, including:

[0012] Calculate the required steam extraction amount according to the difference between the comprehensive power grid load and the dynamic threshold; adjust the opening of the intelligent regulating valve group according to the calculated required steam extraction amount; and accurately control the steam extraction amount and steam extraction pressure through the intelligent regulating valve group;

[0013] A vortex generator is arranged inside the heat exchanger; a vortex is generated in the molten salt flow by the vortex generator; the vortex is used to enhance the heat transfer between the molten salt and the wall surface of the heat exchanger, thereby improving the absorption efficiency of the molten salt to the steam heat;

[0014] Select a phase change material that matches the operating temperature range of the molten salt; evenly disperse the phase change material in the molten salt in the form of nanoparticles; increase the effective specific heat capacity of the composite molten salt through the phase change process of the phase change material; and utilize the latent heat of the phase change material to increase the energy storage density of the composite molten salt.

[0015] In an optional embodiment,

[0016] A molten salt physical property parameter prediction model based on deep learning is established to predict the key parameters of the specific heat capacity and thermal conductivity of molten salt at different temperatures and pressures in real time; when the grid load is higher than the preset dynamic threshold, a multi-channel parallel molten salt delivery system is used to transport the high-temperature molten salt to the cascade molten salt-water heat exchanger group, including:

[0017] Constructing a multi-layer recurrent neural network model, the multi-layer recurrent neural network model includes an input layer, a plurality of long short-term memory network layers and an output layer, wherein the input layer receives the temperature, pressure and composition data of the molten salt, and the output layer outputs the specific heat capacity and thermal conductivity of the molten salt;

[0018] The multi-layer recurrent neural network model is trained using historical operation data, and the network parameters are optimized by a back propagation algorithm so as to minimize the mean square error between the model output and the actual measurement value;

[0019] During the operation of the molten salt energy storage system, the temperature, pressure and composition data of the molten salt are collected in real time, and the collected data are input into the trained multi-layer recurrent neural network model to obtain the predicted values ​​of the specific heat capacity and thermal conductivity of the molten salt under the current working conditions;

[0020] Based on the predicted values ​​of specific heat capacity and thermal conductivity, the energy storage density and heat transfer efficiency of the molten salt are calculated;

[0021] Real-time monitoring of grid load. When the grid load exceeds the preset dynamic threshold, the molten salt energy release process is triggered. The optimal molten salt energy release flow rate is determined based on the calculated energy storage density and heat transfer efficiency, combined with the current grid load demand.

[0022] A multi-channel parallel molten salt delivery system is used, which includes a plurality of parallel molten salt delivery pipelines, each of which is provided with an independently controlled variable frequency pump and an electric regulating valve;

[0023] Based on the determined optimal energy release flow, the fuzzy adaptive PID control algorithm is used to simultaneously adjust the speed of the variable frequency pump and the opening of the electric control valve in each parallel pipeline to achieve precise control of the total flow of molten salt;

[0024] The high-temperature molten salt in each parallel pipeline is collected and transported to the cascade molten salt-water heat exchanger group, wherein the cascade molten salt-water heat exchanger group includes a plurality of heat exchange units connected in series, and the heat exchange area and flow channel structure of each heat exchange unit are optimized and designed according to the physical properties of the molten salt and the target heat exchange efficiency;

[0025] In the molten salt-water heat exchange process, based on the predicted molten salt physical properties, a dynamic adaptive control strategy is adopted to adjust the molten salt and water side flow distribution ratio of each heat exchange unit in real time to maximize the heat recovery efficiency and steam quality.

[0026] In an optional embodiment,

[0027] Based on the determined optimal energy release flow, the fuzzy adaptive PID control algorithm is used to simultaneously adjust the speed of the variable frequency pump and the opening of the electric control valve in each parallel pipeline to achieve precise control of the total flow of molten salt, including:

[0028] Obtain the current optimal energy release flow target value of the system, which is calculated based on the current grid load demand and the state of the molten salt energy storage system;

[0029] Real-time collection of actual flow and pressure data of each parallel pipeline in a multi-channel parallel molten salt delivery system, wherein the multi-channel parallel molten salt delivery system includes at least two parallel pipelines, each of which is provided with a variable frequency pump and an electric regulating valve;

[0030] Calculate the deviation between the total flow rate of molten salt and the target value of the optimal energy release flow rate, and input the deviation into the fuzzy controller; the fuzzy controller performs fuzzy reasoning on the input deviation and its rate of change based on a preset fuzzy rule base, and outputs the adjustment amount of the proportional coefficient, integral coefficient and differential coefficient of the PID controller;

[0031] According to the adjustment amount output by the fuzzy controller, the proportional coefficient, integral coefficient and differential coefficient of the PID controller are dynamically updated; the speed adjustment amount of the variable frequency pump and the opening adjustment amount of the electric control valve of each parallel pipeline are calculated using the updated PID controller parameters;

[0032] The calculated adjustment amount is applied to the variable frequency pump and electric control valve of each parallel pipeline respectively, wherein the speed adjustment of the variable frequency pump is realized by the frequency converter, and the opening adjustment of the electric control valve is realized by the actuator;

[0033] The new deviation between the adjusted total molten salt flow rate and the optimal energy release flow rate target value is calculated. If the new deviation is less than the preset threshold, the current control parameters are maintained; if the new deviation is greater than or equal to the preset threshold, the control adjustment continues.

[0034] In an optional embodiment,

[0035] The generated high-temperature and high-pressure steam is transported to an improved steam turbine with a variable inlet area. The inlet area is dynamically adjusted according to the grid load demand to optimize the efficiency of the steam turbine, including:

[0036] receiving real-time power demand data from a smart grid, the real-time power demand data including a current load level, a short-term load forecast, and a user-side adjustable load capacity; calculating an optimal steam turbine inlet area based on the real-time power demand data using an artificial neural network algorithm to obtain an optimal inlet area value, the input of the artificial neural network algorithm including the current load level, the short-term load forecast, the user-side adjustable load capacity, the current steam parameters, and a steam turbine characteristic curve; sending the calculated optimal inlet area value to a control system of an improved steam turbine with a variable inlet area, the improved steam turbine with a variable inlet area including an adjustable inlet nozzle group and a movable guide vane group matched therewith;

[0037] The control system receives the optimal intake area value and synchronously adjusts the nozzle opening of the intake nozzle group and the position of the movable guide vane group through a precision servo mechanism to achieve precise adjustment of the turbine intake area;

[0038] While adjusting the intake area, the operating parameters of the steam turbine are monitored in real time, including intake pressure, intake temperature, exhaust pressure, shaft power and speed. Based on the monitored operating parameters, the current operating efficiency of the steam turbine is calculated in real time using a thermodynamic model. The calculated current operating efficiency is compared with the preset target efficiency. If the efficiency difference exceeds the preset threshold, the optimal intake area is recalculated.

[0039] A demand response signal is sent to the user side through the smart grid, and the demand response signal includes electricity price information and load adjustment suggestions.

[0040] In an optional embodiment,

[0041] The generated high-temperature and high-pressure steam is transported to the improved steam turbine with variable air inlet area, and the air inlet area is dynamically adjusted according to the load demand of the power grid to optimize the efficiency of the steam turbine; the smart grid technology and demand-side response strategy are used to achieve two-way interaction between the power generation end and the power consumption end, and dynamically balance the power supply and demand, including:

[0042] An improved steam turbine with a variable air inlet area is provided, wherein the improved steam turbine with a variable air inlet area includes an adjustable air inlet nozzle group and a movable guide vane group matched therewith; grid load demand data is collected in real time through a smart grid system, wherein the grid load demand data includes a current load level, a short-term load forecast, and an adjustable load capacity on the user side;

[0043] Based on the collected grid load demand data, the optimal steam turbine inlet area is calculated using a pre-trained deep reinforcement learning model, the input of which includes the current load level, short-term load forecast, user-side adjustable load capacity, current steam parameters and turbine characteristic curve; the calculated optimal inlet area value is transmitted to the control system of the improved steam turbine with variable inlet area;

[0044] After receiving the optimal intake area value, the control system synchronously adjusts the nozzle opening of the intake nozzle group and the position of the movable guide vane group through a high-precision servo mechanism. While adjusting the intake area, it monitors the operating parameters of the steam turbine in real time, including intake pressure, intake temperature, exhaust pressure, shaft power and speed; and uses a thermodynamic model to calculate the current operating efficiency of the steam turbine in real time;

[0045] Sending a demand response signal to the user side through the smart grid system, the demand response signal includes real-time electricity price information and load adjustment suggestions; receiving response data from the user side, the response data includes the load amount actually adjusted by the user and the adjustment time; updating the grid load demand data based on the response data of the user side, especially updating the adjustable load capacity of the user side; using a recurrent neural network algorithm, analyzing the user response pattern based on historical data, and establishing a user response behavior prediction model;

[0046] On the power generation side, the amount of high-temperature and high-pressure steam generated is dynamically adjusted based on the turbine operating efficiency and grid load demand data. On the electricity consumption side, the user's electricity consumption behavior is predicted in advance based on the user response behavior prediction model, and load adjustment suggestions are sent in advance through the smart grid system to achieve precise matching between the power generation side and the electricity consumption side. This enables two-way interaction between the power generation side and the electricity consumption side to dynamically balance the supply and demand of electricity.

[0047] According to a second aspect of the embodiments of the present invention,

[0048] Provides power plant extraction steam energy storage and power generation optimization system based on molten salt heat storage, including:

[0049] The first unit is used to build a multi-level power grid load monitoring system, including macro-regional power grid load, meso-city power grid load and micro-user power load, and collect and analyze load data in real time; when the comprehensive power grid load is lower than the preset dynamic threshold, the steam turbine is controlled to perform variable-condition steam extraction operation, and the intelligent regulating valve group is used to accurately control the steam extraction volume and pressure; the extracted steam is introduced into a multi-stage series steam-molten salt heat exchanger group, and during the heat exchange process, eddy current enhanced heat exchange technology is used to improve the molten salt's absorption efficiency of steam heat; the phase change material composite molten salt technology is used to increase the heat capacity and energy storage density of the molten salt, while reducing the freezing point of the molten salt and expanding the system's operating temperature range;

[0050] The second unit is used to use a high-temperature molten salt storage tank that combines multi-layer insulation and vacuum insulation to minimize heat loss, and set up a temperature gradient monitoring system inside the storage tank; establish a molten salt physical property parameter prediction model based on deep learning to predict the key parameters of the specific heat capacity and thermal conductivity of molten salt at different temperatures and pressures in real time; when the grid load is higher than the preset dynamic threshold, a multi-channel parallel molten salt delivery system is used to transport the high-temperature molten salt to the cascade molten salt-water heat exchanger group; in the molten salt-water heat exchanger group, a structure combining countercurrent heat exchange and spiral heat exchange tubes is used to improve the heat exchange efficiency and generate superheated steam;

[0051] The third unit is used to transport the generated high-temperature and high-pressure steam to an improved steam turbine with a variable air inlet area, dynamically adjust the air inlet area according to the load demand of the power grid, and optimize the efficiency of the steam turbine; use smart grid technology and demand-side response strategies to achieve two-way interaction between the power generation end and the power consumption end, and dynamically balance the supply and demand of electricity.

[0052] According to a third aspect of the embodiments of the present invention,

[0053] An electronic device is provided, comprising:

[0054] processor;

[0055] a memory for storing processor-executable instructions;

[0056] The processor is configured to call the instructions stored in the memory to execute the aforementioned method.

[0057] A fourth aspect of the embodiments of the present invention is:

[0058] A computer-readable storage medium is provided, on which computer program instructions are stored. When the computer program instructions are executed by a processor, the aforementioned method is implemented.

[0059] This application significantly improves the heat absorption efficiency of molten salt to steam through precise steam extraction control and eddy current heat exchange technology. Phase change material composite molten salt technology significantly improves the energy storage density and system flexibility, adapting to a wider range of working conditions. The lower freezing point and higher heat capacity of molten salt enable the system to operate stably under low load conditions, avoiding heat energy waste.

[0060] This application achieves high-precision prediction of the physical parameters of molten salt through the introduction of deep learning models, thereby optimizing the operating efficiency of the energy storage system. The main technical advantages include: Accurate prediction of physical parameters: The deep learning-based model can predict the specific heat capacity and thermal conductivity of molten salt in real time, improving the response speed and control accuracy of the system. Accurate control of the energy release process: The fuzzy adaptive PID algorithm is used to accurately control the molten salt flow rate to ensure the stability and reliability of the system under different working conditions. Efficient heat recovery: A dynamic adaptive control strategy is adopted to optimize the flow distribution in the heat exchanger in real time, improving the heat recovery efficiency and steam quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0061] Figure 1 It is a flow chart of a method for optimizing power generation and extracting steam energy storage in a power plant based on molten salt heat storage according to an embodiment of the present invention;

[0062] Figure 2 It is a structural schematic diagram of a power plant extraction steam storage and power generation optimization system based on molten salt heat storage according to an embodiment of the present invention. DETAILED DESCRIPTION

[0063] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0064] The technical solution of the present invention is described in detail with specific embodiments below. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described in detail in some embodiments.

[0065] Figure 1 Schematic diagram of the process of the power plant extraction steam storage and power generation optimization method based on molten salt heat storage according to the embodiment of the present invention, as shown in FIG. Figure 1 As shown, the method includes:

[0066] S101. Construct a multi-level grid load monitoring system, including macro-regional grid load, meso-city grid load and micro-user electricity load, and collect and analyze load data in real time; when the comprehensive grid load is lower than the preset dynamic threshold, control the steam turbine to perform variable-condition steam extraction operation, and use intelligent regulating valve group to accurately control the steam extraction volume and pressure; introduce the extracted steam into a multi-stage series steam-molten salt heat exchanger group, and during the heat exchange process, use eddy current enhanced heat exchange technology to improve the absorption efficiency of molten salt to steam heat; use phase change material composite molten salt technology to increase the heat capacity and energy storage density of molten salt, while reducing the freezing point of molten salt and expanding the system operating temperature range;

[0067] S102. Use a high-temperature molten salt storage tank that combines multi-layer insulation and vacuum insulation to minimize heat loss, and set up a temperature gradient monitoring system inside the storage tank; establish a molten salt physical property parameter prediction model based on deep learning to predict the key parameters of the specific heat capacity and thermal conductivity of molten salt at different temperatures and pressures in real time; when the grid load is higher than the preset dynamic threshold, use a multi-channel parallel molten salt delivery system to transport the high-temperature molten salt to the cascade molten salt-water heat exchanger group; in the molten salt-water heat exchanger group, use a structure that combines countercurrent heat exchange and spiral heat exchange tubes to improve heat exchange efficiency and generate superheated steam;

[0068] S103. The generated high-temperature and high-pressure steam is transported to the improved steam turbine with variable air inlet area, and the air inlet area is dynamically adjusted according to the load demand of the power grid to optimize the efficiency of the steam turbine; smart grid technology and demand-side response strategy are used to achieve two-way interaction between the power generation end and the power consumption end, and dynamically balance the supply and demand of electricity.

[0069] In an optional embodiment,

[0070] When the integrated power grid load is lower than the preset dynamic threshold, the steam turbine is controlled to perform variable-condition steam extraction operation, and the intelligent regulating valve group is used to accurately control the steam extraction volume and pressure; the extracted steam is introduced into a multi-stage series steam-molten salt heat exchanger group. During the heat exchange process, the eddy current enhanced heat exchange technology is used to improve the molten salt's absorption efficiency of steam heat; the phase change material composite molten salt technology is used to increase the heat capacity and energy storage density of the molten salt, while reducing the freezing point of the molten salt, and expanding the system's operating temperature range, including:

[0071] Calculate the required steam extraction amount according to the difference between the comprehensive power grid load and the dynamic threshold; adjust the opening of the intelligent regulating valve group according to the calculated required steam extraction amount; and accurately control the steam extraction amount and steam extraction pressure through the intelligent regulating valve group;

[0072] A vortex generator is arranged inside the heat exchanger; a vortex is generated in the molten salt flow by the vortex generator; the vortex is used to enhance the heat transfer between the molten salt and the wall surface of the heat exchanger, thereby improving the absorption efficiency of the molten salt to the steam heat;

[0073] Select a phase change material that matches the operating temperature range of the molten salt; evenly disperse the phase change material in the molten salt in the form of nanoparticles; increase the effective specific heat capacity of the composite molten salt through the phase change process of the phase change material; and utilize the latent heat of the phase change material to increase the energy storage density of the composite molten salt.

[0074] For example, based on the difference between the comprehensive grid load and the dynamic threshold, this paper proposes a thermal energy storage and conversion system that controls the steam extraction operation of the steam turbine under variable operating conditions through an intelligent regulating valve group and introduces the extraction steam into a multi-stage series steam-molten salt heat exchanger group. This technical solution combines eddy current enhanced heat exchange technology and phase change material composite molten salt technology to improve the heat capacity and energy storage density of molten salt, while expanding the operating temperature range of the system.

[0075] When the grid load is at a low point, the excess electric energy can be converted into heat energy and stored in the molten salt system through the variable operating steam extraction operation of the steam turbine. In this process, the extracted steam passes through a multi-stage series steam-molten salt heat exchanger group to exchange heat with the molten salt. The molten salt absorbs the heat of the steam and stores it. When the grid load is at a peak, the heat energy in the molten salt can be released in an appropriate manner for power generation or other thermal energy needs.

[0076] According to the dynamic changes of the grid load, it is necessary to first monitor the real-time comprehensive grid load value and compare it with the preset dynamic threshold. When the grid load is lower than the preset dynamic threshold, the system starts the steam extraction operation.

[0077] The system continuously monitors the difference between the grid load and the preset dynamic threshold, and determines the thermal power to be transferred based on the real-time load situation, that is, calculates the required steam extraction volume. This calculation will be based on the size of the load difference to ensure that the steam extraction volume is adapted to the load difference.

[0078] According to the calculated steam extraction volume, the intelligent regulating valve group will accurately adjust the opening to control the steam volume and steam pressure entering the heat exchanger system. Here, the intelligent regulating valve group should have a high response speed and regulation accuracy to ensure real-time control of the steam extraction volume and pressure.

[0079] When the grid load fluctuates, the opening can be adjusted quickly to adapt to changes in steam demand. The steam flow and pressure can be accurately controlled according to system requirements to prevent excessive or insufficient steam from entering the heat exchanger.

[0080] After the steam enters the heat exchanger, the system uses eddy current enhanced heat exchange technology to improve the heat absorption efficiency of the molten salt to the steam.

[0081] A vortex generator is installed inside the heat exchanger. The function of the vortex generator is to generate vortices in the molten salt during the flow process, thereby breaking the thermal boundary layer that may be formed between the molten salt layer and the wall of the heat exchanger. Through the disturbance of the vortex, the contact heat exchange efficiency between the molten salt and the steam in the heat exchanger is significantly improved.

[0082] The design of the vortex generator should take into account the velocity, temperature and fluid characteristics of the molten salt flow. In practice, the vortex generator can increase the heat exchange efficiency of the heat exchanger by about 20%-30%, which means that the system can absorb more heat under the same heat exchange area.

[0083] In order to further improve the energy storage density and heat capacity of molten salt, the system adopts phase change material composite molten salt technology.

[0084] First, select a phase change material that matches the operating temperature range of the molten salt. The selection of phase change materials needs to consider the matching of its phase change temperature with the operating temperature of the molten salt to ensure that the phase change material can fully absorb and release latent heat during the heat exchange process.

[0085] For example, if the system operating temperature range is 200°C-500°C, a molten salt such as sodium chloride-potassium can be selected, and a phase change material with a melting point of about 300°C (such as lithium titanate) can be added to the molten salt.

[0086] Phase change materials are evenly dispersed in the molten salt in the form of nanoparticles, so that they can fully participate in the absorption and release of heat during the heat exchange process. Nanoparticle phase change materials can be effectively distributed in the heat exchanger and quickly complete the phase change process.

[0087] Through the latent heat storage capacity of phase change materials, the energy storage density of composite molten salt can be increased by 15%-25%. For example, after adding 5% phase change material to molten salt, the energy storage capacity per cubic meter of composite molten salt can be increased from the original 400MJ / m 3 Increased to 500MJ / m 3 , greatly improving energy storage efficiency.

[0088] By properly selecting phase change materials, the freezing point of molten salt can be effectively lowered, broadening the operating temperature range of the system. In this case, the addition of phase change materials lowered the freezing point of molten salt by about 10°C, further improving the stability and operational flexibility of the system.

[0089] In a practical application scenario, assuming that the grid load is 350MW and the preset dynamic threshold is 400MW, when the load is lower than the threshold, the system starts the steam extraction operation.

[0090] Based on the load difference of 50MW, the system calculates that the amount of steam that needs to be extracted from the turbine is 80 tons / hour. At this time, the intelligent regulating valve group adjusts the valve opening to 30% based on the calculation results to ensure accurate control of the steam volume and pressure. In the multi-stage series heat exchanger, the vortex generator increases the efficiency of molten salt absorbing steam heat by 25%, and the molten salt temperature at the heat exchanger outlet is increased from the original 450°C to 480°C. By adding 10% phase change material to the molten salt, the energy storage density of the molten salt is increased from 450MJ / m 3 Increased to 540MJ / m 3 The freezing point of the molten salt was also lowered from 250°C to 240°C, ensuring that the system can operate normally at lower temperatures.

[0091] This technical solution realizes the efficient conversion of grid load regulation and thermal energy storage through the organic combination of intelligent regulating valve group, eddy current enhanced heat exchange technology and phase change material composite molten salt technology. Its main advantages are reflected in the following aspects:

[0092] Through precise steam extraction control and eddy current heat exchange technology, the heat absorption efficiency of molten salt to steam is significantly improved. Phase change material composite molten salt technology significantly improves the energy storage density and system flexibility, adapting to a wider range of working conditions. The lower freezing point and higher heat capacity of molten salt enable the system to operate stably under low load conditions, avoiding heat energy waste.

[0093] In an optional embodiment,

[0094] A molten salt physical property parameter prediction model based on deep learning is established to predict the key parameters of the specific heat capacity and thermal conductivity of molten salt at different temperatures and pressures in real time; when the grid load is higher than the preset dynamic threshold, a multi-channel parallel molten salt delivery system is used to transport the high-temperature molten salt to the cascade molten salt-water heat exchanger group, including:

[0095] Constructing a multi-layer recurrent neural network model, the multi-layer recurrent neural network model includes an input layer, a plurality of long short-term memory network layers and an output layer, wherein the input layer receives the temperature, pressure and composition data of the molten salt, and the output layer outputs the specific heat capacity and thermal conductivity of the molten salt;

[0096] The multi-layer recurrent neural network model is trained using historical operation data, and the network parameters are optimized by a back propagation algorithm so as to minimize the mean square error between the model output and the actual measurement value;

[0097] During the operation of the molten salt energy storage system, the temperature, pressure and composition data of the molten salt are collected in real time, and the collected data are input into the trained multi-layer recurrent neural network model to obtain the predicted values ​​of the specific heat capacity and thermal conductivity of the molten salt under the current working conditions;

[0098] Based on the predicted values ​​of specific heat capacity and thermal conductivity, the energy storage density and heat transfer efficiency of the molten salt are calculated;

[0099] Real-time monitoring of grid load. When the grid load exceeds the preset dynamic threshold, the molten salt energy release process is triggered. The optimal molten salt energy release flow rate is determined based on the calculated energy storage density and heat transfer efficiency, combined with the current grid load demand.

[0100] A multi-channel parallel molten salt delivery system is used, which includes a plurality of parallel molten salt delivery pipelines, each of which is provided with an independently controlled variable frequency pump and an electric regulating valve;

[0101] Based on the determined optimal energy release flow, the fuzzy adaptive PID control algorithm is used to simultaneously adjust the speed of the variable frequency pump and the opening of the electric control valve in each parallel pipeline to achieve precise control of the total flow of molten salt;

[0102] The high-temperature molten salt in each parallel pipeline is collected and transported to the cascade molten salt-water heat exchanger group, wherein the cascade molten salt-water heat exchanger group includes a plurality of heat exchange units connected in series, and the heat exchange area and flow channel structure of each heat exchange unit are optimized and designed according to the physical properties of the molten salt and the target heat exchange efficiency;

[0103] In the molten salt-water heat exchange process, based on the predicted molten salt physical properties, a dynamic adaptive control strategy is adopted to adjust the molten salt and water side flow distribution ratio of each heat exchange unit in real time to maximize the heat recovery efficiency and steam quality.

[0104] For example, this solution constructs a multi-layer recurrent neural network model to predict the key physical parameters (specific heat capacity, thermal conductivity) of molten salt in real time, and combines the dynamic changes of power grid load to achieve efficient energy release of molten salt using a multi-channel parallel molten salt delivery system. The goal of this solution is to achieve intelligent control and optimization of the molten salt energy storage system and maximize the efficiency of heat recovery.

[0105] The molten salt energy storage system stores excess heat in molten salt and releases heat to supplement power generation demand when the grid load is peak. The specific heat capacity and thermal conductivity of molten salt are key parameters that affect the performance of the energy storage system, so accurate prediction and real-time monitoring of these physical parameters are essential for the optimal operation of the system. This system uses a multi-layer recurrent neural network based on deep learning to predict the physical parameters of molten salt in real time, and combines the grid load conditions to use a multi-channel parallel molten salt delivery system to accurately control the release process of heat energy.

[0106] A multi-layer recurrent neural network (RNN) model is constructed, which includes an input layer, multiple long short-term memory network (LSTM) layers, and an output layer. The input layer receives data such as the temperature, pressure, and composition of the molten salt, and the output layer is used to predict the specific heat capacity and thermal conductivity of the molten salt.

[0107] Input data: including the temperature of the molten salt (for example, the range between 200°C and 600°C), the pressure (for example, the range between 1MPa and 10MPa), and the chemical composition of the molten salt (such as a mixture of sodium chloride, potassium chloride, etc. in different proportions).

[0108] Output data: specific heat capacity and thermal conductivity of molten salt, which are key parameters for subsequent calculation of energy storage density and heat transfer efficiency.

[0109] Model training: The designed RNN model is trained using the system's historical operating data (including experimental measurements of molten salt properties at different temperatures, pressures, and components). The model parameters are optimized through the back propagation algorithm to minimize the error between the model's predicted values ​​and the actual measured values.

[0110] Assuming that the actual measurement range of the specific heat capacity of the molten salt in the system under different working conditions is 1.5 J / g·K to 2.5 J / g·K, and the range of thermal conductivity is 0.5 W / m·K to 1.5 W / m·K, the prediction error of the model can be kept within 5% through historical data training.

[0111] Data collection and prediction: During the operation of the molten salt energy storage system, the temperature, pressure and composition data of the molten salt are collected in real time, and these data are input into the trained multi-layer recurrent neural network model to obtain the predicted values ​​of the specific heat capacity and thermal conductivity of the molten salt under the current operating conditions.

[0112] During the operation of the system, when the molten salt temperature is 450°C, the pressure is 5 MPa, and the composition is 60% sodium chloride and 40% potassium chloride, the model predicts that the specific heat capacity of the molten salt is 2.2 J / g·K and the thermal conductivity is 1.0 W / m·K.

[0113] Energy storage density calculation: Based on the predicted specific heat capacity, combined with the current temperature and mass of the molten salt, the energy storage density of the molten salt is calculated to evaluate the thermal energy storage capacity of the system. If the mass of the molten salt in a certain energy storage unit is 1,000 tons, the temperature is 500°C, and the predicted specific heat capacity is 2.3 J / g·K, the energy storage density of the unit can reach a certain calorific value.

[0114] Calculation of heat transfer efficiency: Based on the predicted value of thermal conductivity and combined with the heat exchanger structure in the system, the heat transfer efficiency of the molten salt during the heat exchange process is calculated to evaluate the thermal energy release efficiency of the system.

[0115] In the steam generator, when the thermal conductivity of the molten salt is 1.2 W / m·K, the heat transfer efficiency of the heat exchanger is increased by 10%, thereby improving the overall heat energy recovery efficiency.

[0116] Grid load monitoring: Real-time monitoring of grid load. When the load exceeds the preset dynamic threshold, the system automatically triggers the molten salt energy release process to meet the grid's additional power generation needs. Optimal energy release flow calculation: Based on the energy storage density and heat transfer efficiency calculated above, combined with the current grid load demand, the system determines the optimal molten salt energy release flow. In this process, the system needs to comprehensively consider the molten salt temperature, flow rate and expected thermal energy demand to ensure a smooth and efficient energy release process.

[0117] When the grid load is 500MW, the system calculates that the thermal energy to be released is 300MJ. Combined with the current molten salt energy storage density and heat transfer efficiency, the system determines that the optimal molten salt energy release flow rate is 60 tons per minute.

[0118] Parallel conveying system structure: adopts a multi-channel parallel molten salt conveying system, and each conveying pipeline is equipped with an independently controlled variable frequency pump and electric regulating valve. The purpose of this design is to increase the flexibility and reliability of the system by working in parallel with multiple conveying pipelines.

[0119] Control of variable frequency pump and regulating valve: According to the optimal energy release flow, the fuzzy adaptive PID control algorithm is adopted to adjust the speed of the variable frequency pump and the opening of the electric regulating valve in each parallel pipeline in real time to achieve precise control of the total flow of molten salt.

[0120] If the total molten salt flow rate required by the system is 60 tons per minute, the system can control three parallel pipelines, set the flow rate of each pipeline to 20 tons / minute, and adjust the pump speed and valve opening of each pipeline through the fuzzy adaptive PID algorithm to ensure accurate matching of the total flow rate.

[0121] Heat exchanger group design: The molten salt is transported to the cascade molten salt-water heat exchanger group, which consists of multiple heat exchange units connected in series. The heat exchange area and flow channel structure of each heat exchange unit are optimized according to the physical properties of the molten salt and the target heat exchange efficiency to ensure the maximum heat exchange efficiency of the system.

[0122] In a certain heat exchange unit, based on the thermal conductivity of molten salt of 1.1W / m·K, the system designed a heat exchanger with a high-efficiency fin structure. The heat exchange area is 500 square meters, which significantly improves the heat recovery per unit time.

[0123] Dynamic adaptive control of flow distribution: In the molten salt-water heat exchange process, based on the predicted values ​​of the specific heat capacity and thermal conductivity of the molten salt, a dynamic adaptive control strategy is adopted to adjust the flow distribution ratio of the molten salt and water sides in real time to maximize the heat recovery efficiency and steam quality of the system.

[0124] During operation, if the predicted thermal conductivity of molten salt changes, the system can dynamically adjust the ratio of molten salt flow to water flow, thereby ensuring that the outlet temperature and pressure of the steam are always maintained within the preset range, thereby improving the steam quality and power generation efficiency.

[0125] In a practical application scenario, it is assumed that the grid load increases from 400MW to 600MW, triggering the molten salt energy release process.

[0126] Physical property parameter prediction: The real-time collected molten salt temperature is 500°C, the pressure is 6MPa, and the composition is 70% sodium chloride and 30% potassium chloride. The multi-layer recurrent neural network model predicts that the specific heat capacity of the molten salt is 2.4J / g·K and the thermal conductivity is 1.3W / m·K.

[0127] Flow control: According to the load demand of the power grid, the system calculates the optimal molten salt energy release flow rate to be 80 tons per minute. Through the fuzzy adaptive PID control algorithm, the four parallel pipelines are adjusted, and the flow rate of each pipeline is set to 20 tons / minute to ensure that the total flow rate reaches the target value.

[0128] Optimization of heat exchange process: In the cascade heat exchanger group, based on the predicted thermal conductivity of molten salt, the system dynamically adjusts the flow distribution ratio of molten salt and water, ultimately achieving efficient heat recovery, generating high-quality steam, and meeting the power generation needs of the power grid.

[0129] This technical solution achieves high-precision prediction of molten salt physical parameters through the introduction of deep learning models, thereby optimizing the operating efficiency of the energy storage system. The main technical advantages include:

[0130] Accurately predict physical parameters: The deep learning-based model can predict the specific heat capacity and thermal conductivity of molten salt in real time, improving the system's response speed and control accuracy. Accurately control the energy release process: The fuzzy adaptive PID algorithm accurately controls the molten salt flow rate to ensure the stability and reliability of the system under different working conditions. Efficient heat recovery: The dynamic adaptive control strategy is used to optimize the flow distribution in the heat exchanger in real time, improving the heat recovery efficiency and steam quality.

[0131] In an optional embodiment,

[0132] Based on the determined optimal energy release flow, the fuzzy adaptive PID control algorithm is used to simultaneously adjust the speed of the variable frequency pump and the opening of the electric control valve in each parallel pipeline to achieve precise control of the total flow of molten salt, including:

[0133] Obtain the current optimal energy release flow target value of the system, which is calculated based on the current grid load demand and the state of the molten salt energy storage system;

[0134] Real-time collection of actual flow and pressure data of each parallel pipeline in a multi-channel parallel molten salt delivery system, wherein the multi-channel parallel molten salt delivery system includes at least two parallel pipelines, each of which is provided with a variable frequency pump and an electric regulating valve;

[0135] Calculate the deviation between the total flow rate of molten salt and the target value of the optimal energy release flow rate, and input the deviation into the fuzzy controller; the fuzzy controller performs fuzzy reasoning on the input deviation and its change rate based on a preset fuzzy rule base, and outputs the adjustment amount of the proportional coefficient, integral coefficient and differential coefficient of the PID controller;

[0136] According to the adjustment amount output by the fuzzy controller, the proportional coefficient, integral coefficient and differential coefficient of the PID controller are dynamically updated; the speed adjustment amount of the variable frequency pump and the opening adjustment amount of the electric control valve of each parallel pipeline are calculated using the updated PID controller parameters;

[0137] The calculated adjustment amount is applied to the variable frequency pump and electric control valve of each parallel pipeline respectively, wherein the speed adjustment of the variable frequency pump is realized by the frequency converter, and the opening adjustment of the electric control valve is realized by the actuator;

[0138] The new deviation between the adjusted total molten salt flow rate and the optimal energy release flow rate target value is calculated. If the new deviation is less than the preset threshold, the current control parameters are maintained; if the new deviation is greater than or equal to the preset threshold, the control adjustment continues.

[0139] For example, by real-time collection of flow and pressure data of a multi-channel parallel molten salt delivery system, the fuzzy controller is used to dynamically adjust the PID controller parameters to ensure the precise match between the total molten salt flow and the grid load demand. In the molten salt energy storage system, the flow control of molten salt is a key link to ensure that the system energy release matches the grid load demand. In order to achieve precise control of the molten salt flow, this solution uses a fuzzy adaptive PID control algorithm to dynamically adjust the speed of the variable frequency pump and the opening of the electric control valve in the multi-channel parallel molten salt delivery system to ensure that the total flow of the molten salt is always maintained near the optimal energy release flow target value.

[0140] According to the current grid load demand and the state of the molten salt energy storage system, the optimal energy release flow target value of the system is calculated. This value is the molten salt flow rate that the system needs to release under the current load conditions to ensure that the energy storage system can release thermal energy according to the grid demand. Assuming that the current grid load is 500MW and the temperature of the molten salt in the energy storage system is 450℃, the system determines through calculation that the optimal energy release flow target value is 80 tons of molten salt per minute.

[0141] The multi-channel parallel molten salt delivery system consists of at least two parallel pipelines, each of which is equipped with a variable frequency pump and an electric regulating valve. The variable frequency pump is used to adjust the flow rate of the molten salt, and the electric regulating valve is used to control the opening of the pipeline, thereby affecting the flow resistance and flow rate of the molten salt.

[0142] The actual flow and pressure data of each parallel pipeline are collected in real time to ensure that the operating status of all pipelines can be monitored in real time. There are three parallel pipelines in the system. Through the flow sensors installed on the pipelines, the flow data of each pipeline is obtained in real time, such as 10 tons / minute, 30 tons / minute and 35 tons / minute. At the same time, the pressure sensor collects the pressure data in the pipeline in real time to ensure the safe operation of the system.

[0143] Flow deviation calculation: Compare the total molten salt flow collected in real time with the optimal energy release flow target value to calculate the current flow deviation. The flow deviation is the difference between the current actual total flow and the target flow, reflecting the flow control accuracy of the current system.

[0144] Assuming that the current total flow rate is 75 tons / minute and the optimal energy release flow rate is 80 tons / minute, the flow deviation is 5 tons / minute.

[0145] Fuzzy controller input: The flow deviation and its rate of change are input into the fuzzy controller. The fuzzy controller performs fuzzy reasoning on the input deviation and rate of change based on the preset fuzzy rule base to obtain the adjustment amount of the proportional coefficient, integral coefficient and differential coefficient of the PID controller. Fuzzy rule base design: The fuzzy rule base is established based on system experience and expert knowledge to define the impact of deviation and rate of change on controller parameters. For example, when the flow deviation is large and the rate of change is small, the system should increase the proportional coefficient of the PID controller to quickly reduce the deviation.

[0146] PID controller adaptive adjustment: According to the adjustment amount output by the fuzzy controller, the proportional coefficient, integral coefficient and differential coefficient of the PID controller are dynamically updated. The adjustment amount of these coefficients is calculated in real time based on the current system state to ensure that the response ability of the PID controller can adapt to the dynamic changes of the system. At a certain moment, the fuzzy controller determines that the current flow deviation is large, and the output adjustment amount is: the proportional coefficient increases by 0.1, the integral coefficient increases by 0.05, and the differential coefficient remains unchanged. The system applies these adjustments to the PID controller, and the updated PID controller can respond to flow deviations more quickly.

[0147] Control quantity calculation: Use the updated PID controller parameters to calculate the speed adjustment of the variable frequency pump and the opening adjustment of the electric control valve in each parallel pipeline. The speed adjustment of the variable frequency pump is achieved through the frequency converter, and the opening adjustment of the electric control valve is achieved through the actuator. After calculating the adjustment amount, the system decides to increase the speed of the variable frequency pump in the first parallel pipeline by 10% and the opening of the electric control valve by 5%; the speed of the variable frequency pump in the second pipeline is increased by 5%, and the electric control valve remains unchanged; the speed of the variable frequency pump in the third pipeline remains unchanged, but the opening of the electric control valve is reduced by 5%.

[0148] Execute adjustments: Apply the calculated adjustments to the variable frequency pumps and electric control valves in each parallel pipeline to ensure that the flow in each pipeline is accurately controlled.

[0149] Deviation recalculation: After the speed of the variable frequency pump and the opening of the electric control valve of each parallel pipeline are adjusted, the system will recalculate the total flow of molten salt and compare it with the optimal energy release flow target value to obtain a new flow deviation. After adjustment, the total flow of molten salt in the system increased to 78 tons / minute, and the new flow deviation was 2 tons / minute. Control judgment: If the new flow deviation is less than the preset threshold, the current control parameters are maintained; if the new deviation is greater than or equal to the preset threshold, the system will continue to make control adjustments until the flow deviation is within an acceptable range. If the new deviation is 2 tons / minute, the preset threshold of the system is 1 ton / minute, and the system will continue to make control adjustments, otherwise the current control state is maintained.

[0150] Assume that in a certain actual application scenario, the grid load suddenly increases to 600MW, and the system calculates that the optimal molten salt energy release flow rate is 100 tons per minute. The system achieves precise flow control through the following steps: Obtain the optimal energy release flow target value: The system calculates the optimal energy release flow rate as 100 tons / minute from the grid load demand. Real-time collection of flow and pressure data: The flow rates of the three parallel pipelines in the system are 30 tons, 35 tons, and 25 tons, respectively, with a total flow rate of 90 tons / minute.

[0151] Flow deviation calculation: The current flow deviation is calculated to be 10 tons / minute. After the flow deviation and the rate of change are input into the fuzzy controller, the fuzzy controller outputs the adjustment amount for adjusting the parameters of the PID controller. PID parameter adjustment: The fuzzy controller outputs the proportional coefficient increased by 0.2, the integral coefficient increased by 0.1, and the differential coefficient remains unchanged. The system applies these adjustments to the PID controller. Adjust the speed of the variable frequency pump and the opening of the electric control valve: The system decides to increase the speed of the variable frequency pump of the three pipelines by 10%, 8% and 5% respectively, and adjust the opening of the electric control valve to increase by 5%, remain unchanged, and decrease by 3% respectively. Recalculate the flow deviation: After the adjustment, the total flow of the system increases to 98 tons / minute, and the new flow deviation is 2 tons / minute, which meets the system preset 3 tons / minute deviation threshold, and the system control parameters remain unchanged.

[0152] This technical solution achieves precise control of the total flow of molten salt through the fuzzy adaptive PID control algorithm, ensuring that the molten salt energy storage system can quickly respond to changes in grid load. Its main technical advantages include:

[0153] Dynamic adjustment of PID controller parameters: Through the introduction of fuzzy controller, the system can automatically adjust the parameters of PID controller according to the real-time flow deviation and its rate of change, which enhances the system's responsiveness and control accuracy. Flexible control of multiple parallel pipelines: By independently controlling the speed of the variable frequency pump and the opening of the electric regulating valve in each parallel pipeline, the system can flexibly adjust the molten salt flow to ensure that the total flow always meets the optimal energy release flow target value. Efficient flow control accuracy: The fuzzy adaptive PID control algorithm can ensure that the flow deviation is always kept within the preset threshold range, avoiding the response lag problem of traditional PID controllers under complex working conditions and improving the system's operating efficiency.

[0154] In an optional embodiment,

[0155] The generated high-temperature and high-pressure steam is transported to an improved steam turbine with a variable inlet area. The inlet area is dynamically adjusted according to the grid load demand to optimize the efficiency of the steam turbine, including:

[0156] receiving real-time power demand data from a smart grid, the real-time power demand data including a current load level, a short-term load forecast, and a user-side adjustable load capacity; calculating an optimal steam turbine inlet area based on the real-time power demand data using an artificial neural network algorithm to obtain an optimal inlet area value, the input of the artificial neural network algorithm including the current load level, the short-term load forecast, the user-side adjustable load capacity, the current steam parameters, and a steam turbine characteristic curve; sending the calculated optimal inlet area value to a control system of an improved steam turbine with a variable inlet area, the improved steam turbine with a variable inlet area including an adjustable inlet nozzle group and a movable guide vane group matched therewith;

[0157] The control system receives the optimal intake area value and synchronously adjusts the nozzle opening of the intake nozzle group and the position of the movable guide vane group through a precision servo mechanism to achieve precise adjustment of the turbine intake area;

[0158] While adjusting the intake area, the operating parameters of the steam turbine are monitored in real time, including intake pressure, intake temperature, exhaust pressure, shaft power and speed. Based on the monitored operating parameters, the current operating efficiency of the steam turbine is calculated in real time using a thermodynamic model. The calculated current operating efficiency is compared with the preset target efficiency. If the efficiency difference exceeds the preset threshold, the optimal intake area is recalculated.

[0159] A demand response signal is sent to the user side through the smart grid, and the demand response signal includes electricity price information and load adjustment suggestions.

[0160] For example, a variable inlet area steam turbine dynamically changes the inlet area by adjusting the position and opening of the inlet nozzle group and the guide vane group to adapt to the real-time changes in the grid load. This design can effectively optimize the operating efficiency of the steam turbine, especially when the grid load fluctuates greatly, ensuring that the power generation system can quickly respond to load demand, reduce energy waste and improve economy.

[0161] The system receives power demand data from the smart grid in real time. The data includes the current grid load level, short-term load forecast (such as the load change trend in the next few hours), and the adjustable load capacity on the user side. Assuming that the current grid load is 450MW, the short-term load forecast shows that the load will increase to 500MW in the next hour, and the adjustable load capacity on the user side is 50MW. The smart grid predicts the future change trend of the grid load through data collection and analysis, and transmits it to the turbine control system.

[0162] In order to accurately control the air intake area of ​​the steam turbine, the system uses an artificial neural network algorithm for calculation. The input data of the algorithm includes the current grid load level, short-term load forecast, adjustable load capacity on the user side, current steam parameters (such as steam temperature and pressure), and the characteristic curve of the steam turbine (such as the operating performance of the steam turbine under different air intake areas and steam parameters).

[0163] Assuming that the current steam temperature is 550℃ and the pressure is 8MPa, the characteristic curve of the steam turbine shows the relationship between the efficiency and output power of the steam turbine under different intake areas. The artificial neural network learns the relationship between these input data and the efficiency of the steam turbine through training and outputs the optimal intake area value. The artificial neural network calculates the optimal intake area value of the steam turbine based on the above-mentioned grid load and steam parameters input to ensure that the system can maintain the highest operating efficiency under the current and expected loads. The system calculates that the current optimal intake area is 80 square centimeters, which ensures that the steam turbine reaches the best operating state under a load of 450MW.

[0164] The calculated optimal intake area value is sent to the turbine control system. The control system is mainly responsible for adjusting the intake nozzle group and guide vane group inside the turbine. These components are designed to be flexible and ensure that the intake area can be changed quickly according to demand. Adjustable intake nozzle group and guide vane group: The intake nozzle group of the turbine and the movable guide vane group that cooperates with it are adjusted by a precision servo mechanism, which can achieve high-precision synchronous movement to ensure that the intake area can be adjusted quickly and accurately.

[0165] The control system uses a precision servo mechanism to synchronously adjust the nozzle opening of the intake nozzle group and the position of the movable guide vane group to achieve precise adjustment of the turbine intake area. The high response speed of the servo mechanism ensures that the turbine intake adjustment can adapt to dynamic load requirements. When the system calculates that the optimal intake area is 80 square centimeters, the servo mechanism synchronously adjusts the nozzle opening and the position of the guide vane group to increase the opening from the original 75 square centimeters to 80 square centimeters to meet the current load requirements.

[0166] While adjusting the intake area, the system monitors the key operating parameters of the steam turbine in real time. These parameters include intake pressure, intake temperature, exhaust pressure, shaft power and speed. By monitoring these parameters, the system can obtain the real-time working status of the steam turbine and provide data support for subsequent efficiency calculations. Assume that the current intake pressure is 8MPa, the intake temperature is 550℃, the exhaust pressure is 0.1MPa, the shaft power is 450MW, and the speed is 3000 rpm. These data are fed back to the control system in real time through sensors to monitor the operating status of the steam turbine.

[0167] The system uses a model based on thermodynamic principles to calculate the current operating efficiency of the steam turbine in real time. The model calculates the actual operating efficiency of the steam turbine through the inlet and outlet parameters of steam (such as pressure and temperature) and the speed and shaft power of the steam turbine. Under the current operating conditions, the system calculates that the operating efficiency of the steam turbine is 88%. This efficiency value reflects the energy conversion efficiency of the steam turbine under the current load.

[0168] The system compares the calculated current operating efficiency with the preset target efficiency. If the difference between the current efficiency and the target efficiency exceeds the preset threshold, the system will recalculate the optimal intake area to further optimize the operation of the turbine. Assume that the preset target efficiency is 90%, and the current efficiency is 88%, and the difference between the two is 2%. This difference exceeds the 1% threshold set by the system, so the system decides to recalculate the intake area to further optimize the operation of the turbine.

[0169] In order to further optimize the system's load regulation capabilities, the smart grid will send demand response signals to the user side. These signals contain electricity price information and load regulation suggestions. By adjusting the load on the user side, the system can further balance the supply and demand relationship of the power grid and reduce the pressure caused by load fluctuations. When the grid load is high, the smart grid sends a demand response signal to the user, suggesting that the user reduce the power load by 50MW and provide corresponding electricity price discounts to encourage users to participate in load regulation.

[0170] Receiving power demand data: The real-time power demand data transmitted by the smart grid shows that the current load is 600MW. The short-term load forecast shows that the load may further increase to 650MW. The adjustable load capacity on the user side is 50MW.

[0171] Calculate the optimal intake area: The system uses an artificial neural network algorithm and combines input data (such as the current load of 600MW, the predicted load of 650MW, steam parameters, etc.) to calculate that the optimal intake area of ​​the current turbine is 90 square centimeters. Adjust the intake nozzle and guide vane group: After receiving the optimal intake area, the control system synchronously adjusts the intake nozzle and guide vane group through the servo mechanism to adjust the intake area from 85 square centimeters to 90 square centimeters. Real-time monitoring of operating parameters: While adjusting the intake area, the system monitors the intake pressure (8.5MPa), intake temperature (560℃), exhaust pressure (0.12MPa), shaft power (600MW) and speed (3000 rpm) of the turbine. Calculate the current operating efficiency: The system uses a thermodynamic model to calculate that the current operating efficiency of the turbine is 89%, and compares it with the preset target efficiency (90%). The efficiency difference is 1%, which is less than the threshold set by the system, so no further adjustment is required. Sending load adjustment signals: The smart grid sends demand response signals to the user side, suggesting that the user reduce the load usage by 50MW and providing corresponding electricity price discounts.

[0172] This technical solution achieves dynamic adjustment of the turbine air intake area driven by load demand through the close integration of smart grid and steam turbine control system, ensuring that the system can achieve optimal operating efficiency under different load conditions. Its main technical advantages include:

[0173] AI-based intake area optimization: Through the artificial neural network algorithm, the system can calculate the optimal intake area according to the real-time load demand and steam parameters to ensure the efficient operation of the turbine under dynamic load conditions. Precision servo control: The introduction of the servo mechanism enables the adjustment of the turbine intake nozzle and guide vane group to respond quickly to load changes, significantly improving the flexibility and response speed of the system. Real-time efficiency monitoring and optimization: The system monitors the operating efficiency of the turbine in real time through a thermodynamic model to ensure timely adjustments when the load fluctuates and improve energy utilization efficiency. Load regulation capability of the smart grid: Through the interaction between the smart grid and the user side, the system can balance the load fluctuations of the power grid and further optimize the operating performance of the power generation system.

[0174] In an optional embodiment,

[0175] The generated high-temperature and high-pressure steam is transported to the improved steam turbine with variable air inlet area, and the air inlet area is dynamically adjusted according to the load demand of the power grid to optimize the efficiency of the steam turbine; the smart grid technology and demand-side response strategy are used to achieve two-way interaction between the power generation end and the power consumption end, and dynamically balance the power supply and demand, including:

[0176] An improved steam turbine with a variable air inlet area is provided, wherein the improved steam turbine with a variable air inlet area includes an adjustable air inlet nozzle group and a movable guide vane group matched therewith; grid load demand data is collected in real time through a smart grid system, wherein the grid load demand data includes a current load level, a short-term load forecast, and an adjustable load capacity on the user side;

[0177] Based on the collected grid load demand data, the optimal steam turbine inlet area is calculated using a pre-trained deep reinforcement learning model, the input of which includes the current load level, short-term load forecast, user-side adjustable load capacity, current steam parameters and turbine characteristic curve; the calculated optimal inlet area value is transmitted to the control system of the improved steam turbine with variable inlet area;

[0178] After receiving the optimal intake area value, the control system synchronously adjusts the nozzle opening of the intake nozzle group and the position of the movable guide vane group through a high-precision servo mechanism. While adjusting the intake area, it monitors the operating parameters of the steam turbine in real time, including intake pressure, intake temperature, exhaust pressure, shaft power and speed; and uses a thermodynamic model to calculate the current operating efficiency of the steam turbine in real time;

[0179] Sending a demand response signal to the user side through the smart grid system, the demand response signal includes real-time electricity price information and load adjustment suggestions; receiving response data from the user side, the response data includes the load amount actually adjusted by the user and the adjustment time; updating the grid load demand data based on the response data of the user side, especially updating the adjustable load capacity of the user side; using a recurrent neural network algorithm, analyzing the user response pattern based on historical data, and establishing a user response behavior prediction model;

[0180] On the power generation side, the amount of high-temperature and high-pressure steam generated is dynamically adjusted based on the turbine operating efficiency and grid load demand data. On the electricity consumption side, the user's electricity consumption behavior is predicted in advance based on the user response behavior prediction model, and load adjustment suggestions are sent in advance through the smart grid system to achieve precise matching between the power generation side and the electricity consumption side. This enables two-way interaction between the power generation side and the electricity consumption side to dynamically balance the supply and demand of electricity.

[0181] For example, as the proportion of renewable energy generation in the power grid increases, the difficulty of regulating the power system has increased significantly. How to achieve efficient coordination between the power generation end and the power consumption end has become a key issue for the stable operation of the power system. By introducing smart grid technology and demand-side response strategies, combined with an improved steam turbine control scheme with variable air intake area, a dynamic balance of power supply and demand can be achieved to meet the needs of power grid load fluctuations.

[0182] The improved steam turbine with variable inlet area is equipped with an adjustable inlet nozzle group and a movable guide vane group. The inlet nozzle group adjusts the steam flow entering the steam turbine by changing the opening of the nozzle, and the movable guide vane group is adjusted accordingly according to the change of steam flow to ensure the energy conversion efficiency of the steam turbine. Assuming that the rated power of a steam turbine is 500MW, the inlet nozzle group can be adjusted within the range of 30 square centimeters to 100 square centimeters, and the position of the guide vane group is adjusted synchronously according to the opening of the nozzle to ensure the best match between steam flow and energy conversion.

[0183] Smart grid data collection: Through the smart grid system, real-time collection of grid load demand data, including current load level, short-term load forecast, and adjustable load capacity on the user side, is carried out. Grid load demand data provides the necessary basic data for subsequent calculation of turbine intake area.

[0184] The current grid load is 450MW, and the short-term load forecast shows that the load will increase to 500MW in the next two hours. The adjustable load capacity on the user side is 50MW. Smart grids monitor the operation status and load changes of the grid in real time through sensors and data acquisition systems.

[0185] Introduction of deep reinforcement learning model: To calculate the optimal turbine inlet area, the system uses a pre-trained deep reinforcement learning model. The inputs to the model include the current grid load level, short-term load forecast, user-side adjustable load capacity, current steam parameters (such as steam temperature and pressure), and the turbine characteristic curve. By learning the relationship between these variables, the model is able to output the turbine inlet area that best suits the current operating conditions. Assume that the current load level is 450MW, the steam temperature is 550°C, and the steam pressure is 8MPa. The deep reinforcement learning model is trained to find that the current optimal inlet area is 85 square centimeters to ensure that the turbine operates at the highest efficiency under the current load.

[0186] Control system receiving and adjusting: The optimal intake area value is sent to the control system of the improved steam turbine through the data transmission system. The core task of the control system is to synchronously adjust the opening of the intake nozzle group and the position of the movable guide vane group through the high-precision servo mechanism after receiving the optimal intake area value.

[0187] Working principle of servo mechanism: The servo mechanism is responsible for converting the optimal intake area value into specific mechanical actions, such as adjusting the nozzle opening from 70 square centimeters to 85 square centimeters, and at the same time adjusting the position of the guide vane group to match the new steam flow.

[0188] Operating parameter monitoring: During the process of adjusting the intake area, the system monitors the key operating parameters of the steam turbine in real time. These parameters include intake pressure, intake temperature, exhaust pressure, shaft power and speed. Through real-time monitoring of these parameters, the system can obtain the actual working status of the steam turbine and provide data support for subsequent efficiency calculations.

[0189] The current intake pressure is 8MPa, the intake temperature is 550℃, the exhaust pressure is 0.12MPa, the shaft power is 450MW, and the speed is 3000 rpm. These data are fed back to the control system in real time through sensors to monitor the operating status of the steam turbine. Efficiency calculation: The system uses a thermodynamic model to calculate the current operating efficiency of the steam turbine based on the operating parameters monitored in real time. This efficiency value is used to evaluate the energy conversion efficiency of the steam turbine under different load conditions. The system calculates that the current operating efficiency of the steam turbine is 88%. By comparing historical data and target efficiency, the system can further optimize the operating parameters of the steam turbine.

[0190] Sending and receiving demand response signals: Demand response signals are sent to users through the smart grid system. Demand response signals contain real-time electricity price information and load adjustment suggestions, aiming to guide users to adjust their electricity usage according to the grid load conditions. After the user responds, the system receives data from the user, including the actual load amount and adjustment time adjusted by the user. Assuming that the current grid load is 450MW, the grid recommends users to reduce load usage by 50MW through demand response signals and provide corresponding electricity price discounts. After the user responds, the load is actually reduced by 40MW, and the corresponding adjustment time is fed back as 30 minutes.

[0191] Load demand data update: Based on the response data fed back by the user side, the system updates the load demand data of the power grid, especially the adjustable load capacity on the user side. This updated data provides a more accurate basis for the subsequent turbine air intake area adjustment and power supply and demand balance. The user actually reduced the load by 40MW, and the system updated the adjustable load capacity on the user side from 50MW to 40MW, and adjusted the corresponding load forecasting model.

[0192] User response behavior prediction model: The system uses a recurrent neural network algorithm to analyze user response patterns based on historical data. Through this model, the user's response behavior under different electricity prices and load regulation suggestions can be predicted, thus providing a basis for the subsequent demand response signal transmission. By analyzing the user response data of the past year, the system established a prediction model for user response behavior. The model predicts that if the electricity price rises by 10% in the future, the load regulation amount responded by users will reach 45MW.

[0193] Steam production adjustment: According to the operating efficiency of the steam turbine and the grid load demand data, the system can dynamically adjust the production of high-temperature and high-pressure steam to ensure accurate matching between the power generation end and the power consumption end. The adjustment of steam production depends on the real-time changes in the air intake area of ​​the steam turbine and the grid load. The current grid load is 450MW, the operating efficiency of the steam turbine is 88%, and the steam production is 500 tons per hour. When the load increases to 500MW, the system dynamically adjusts the steam production to 550 tons / hour to meet the load demand of the grid.

[0194] Prediction of user electricity consumption behavior: Based on the user response behavior prediction model, the system can predict the user's electricity consumption behavior in advance, and send load adjustment suggestions in advance through the smart grid system before the load peak arrives to ensure accurate matching between the power generation end and the power consumption end. According to the prediction model, the system speculates that the load will increase by 50MW in the next hour, and the user-side load may react slowly. To this end, the system sends load adjustment suggestions to users in advance, suggesting that users reduce their electricity load by 40MW before the load peak, and provides corresponding electricity price incentives.

[0195] In a practical application scenario, the grid load suddenly rises to 600MW. The system dynamically adjusts the turbine air intake area and achieves precise matching between the power generation end and the power consumption end through the following steps:

[0196] Real-time collection of grid load demand data: Smart grid data shows that the current load is 600MW, and short-term load forecasts show that the future load will rise to 650MW. The user-side adjustable load capacity is 50MW. Calculate the optimal intake area: The system uses a deep reinforcement learning model, combined with load demand data and steam parameters, to calculate the optimal intake area of ​​the current turbine to be 95 square centimeters. Adjust the intake nozzle and guide vane group: After receiving the optimal intake area, the control system synchronously adjusts the nozzle opening and the position of the guide vane group through the servo mechanism to adjust the intake area from 85 square centimeters to 95 square centimeters.

[0197] The system monitors the intake pressure of 8.5MPa, the intake temperature of 560℃, the exhaust pressure of 0.12MPa, the shaft power of 600MW, and the speed of 3000 rpm. The calculated operating efficiency is 89%. The power grid sends a demand response signal to the user, recommending a load reduction of 50MW and providing an electricity price incentive. The user actually reduces the load by 40MW, and the feedback adjustment time is 30 minutes. Update load data and predict user behavior: The system updates the adjustable load capacity on the user side to 40MW, and predicts that the user may further reduce the load by 35MW during future load peaks.

[0198] This technical solution successfully achieves a dynamic balance between power supply and demand through the close integration of smart grid and variable air intake area steam turbine. Its main technical advantages include:

[0199] Inlet area optimization based on deep reinforcement learning: Through the deep reinforcement learning model, the system can calculate the optimal intake area according to the real-time load demand and steam parameters to ensure the efficient operation of the turbine under dynamic load conditions. Precision servo control and real-time monitoring: The high-precision control of the servo mechanism enables the turbine's intake nozzle and guide vane group to respond quickly to load changes, significantly improving the system's response speed and control accuracy. Demand response capability of smart grid: Through the interaction between the smart grid and users, the system can predict users' electricity consumption behavior in advance, send load adjustment suggestions, and further optimize the supply and demand balance of the power system.

[0200] Figure 2 Schematic diagram of the structure of the power plant extraction steam storage and power generation optimization system based on molten salt heat storage according to an embodiment of the present invention. Figure 2 As shown, the system comprises:

[0201] The first unit is used to build a multi-level power grid load monitoring system, including macro-regional power grid load, meso-city power grid load and micro-user power load, and collect and analyze load data in real time; when the comprehensive power grid load is lower than the preset dynamic threshold, the steam turbine is controlled to perform variable-condition steam extraction operation, and the intelligent regulating valve group is used to accurately control the steam extraction volume and pressure; the extracted steam is introduced into a multi-stage series steam-molten salt heat exchanger group, and during the heat exchange process, eddy current enhanced heat exchange technology is used to improve the molten salt's absorption efficiency of steam heat; the phase change material composite molten salt technology is used to increase the heat capacity and energy storage density of the molten salt, while reducing the freezing point of the molten salt and expanding the system's operating temperature range;

[0202] The second unit is used to use a high-temperature molten salt storage tank that combines multi-layer insulation and vacuum insulation to minimize heat loss, and set up a temperature gradient monitoring system inside the storage tank; establish a molten salt physical property parameter prediction model based on deep learning to predict the key parameters of the specific heat capacity and thermal conductivity of molten salt at different temperatures and pressures in real time; when the grid load is higher than the preset dynamic threshold, a multi-channel parallel molten salt delivery system is used to transport the high-temperature molten salt to the cascade molten salt-water heat exchanger group; in the molten salt-water heat exchanger group, a structure combining countercurrent heat exchange and spiral heat exchange tubes is used to improve the heat exchange efficiency and generate superheated steam;

[0203] The third unit is used to transport the generated high-temperature and high-pressure steam to an improved steam turbine with a variable air inlet area, dynamically adjust the air inlet area according to the load demand of the power grid, and optimize the efficiency of the steam turbine; use smart grid technology and demand-side response strategies to achieve two-way interaction between the power generation end and the power consumption end, and dynamically balance the supply and demand of electricity.

[0204] According to a third aspect of the embodiments of the present invention,

[0205] An electronic device is provided, comprising:

[0206] processor;

[0207] a memory for storing processor-executable instructions;

[0208] The processor is configured to call the instructions stored in the memory to execute the aforementioned method.

[0209] A fourth aspect of the embodiments of the present invention is:

[0210] A computer-readable storage medium is provided, on which computer program instructions are stored. When the computer program instructions are executed by a processor, the aforementioned method is implemented.

[0211] The present invention may be a method, an apparatus, a system and / or a computer program product. The computer program product may include a computer-readable storage medium carrying computer-readable program instructions for executing various aspects of the present invention.

[0212] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for optimizing power plant steam extraction energy storage and power generation based on molten salt heat storage, characterized in that: include: Construct a multi-level grid load monitoring system, including macro-regional grid load, meso-city grid load and micro-user electricity load, to collect and analyze load data in real time; when the comprehensive grid load is lower than the preset dynamic threshold, control the steam turbine to perform variable-condition steam extraction operation, and use intelligent regulating valve group to accurately control the steam extraction volume and pressure; introduce the extracted steam into a multi-stage series steam-molten salt heat exchanger group, and during the heat exchange process, use eddy current enhanced heat exchange technology to improve the molten salt's absorption efficiency of steam heat; use phase change material composite molten salt technology to increase the heat capacity and energy storage density of molten salt, while reducing the freezing point of molten salt and expanding the system's operating temperature range; A high-temperature molten salt storage tank that combines multi-layer insulation and vacuum insulation is used to minimize heat loss, and a temperature gradient monitoring system is set up inside the storage tank; a molten salt physical property parameter prediction model based on deep learning is established to predict the key parameters of the specific heat capacity and thermal conductivity of molten salt at different temperatures and pressures in real time; when the grid load is higher than the preset dynamic threshold, a multi-channel parallel molten salt delivery system is used to transport the high-temperature molten salt to the cascade molten salt-water heat exchanger group; in the molten salt-water heat exchanger group, a structure combining countercurrent heat exchange and spiral heat exchange tubes is used to improve the heat exchange efficiency and generate superheated steam; The generated high-temperature and high-pressure steam is transported to an improved steam turbine with a variable air inlet area, and the air inlet area is dynamically adjusted according to the load demand of the power grid to optimize the efficiency of the steam turbine. By using smart grid technology and demand-side response strategies, two-way interaction between the power generation end and the power consumption end is achieved, dynamically balancing the supply and demand of electricity.

2. The method according to claim 1, characterized in that When the integrated power grid load is lower than the preset dynamic threshold, the steam turbine is controlled to perform variable-condition steam extraction operation, and the intelligent regulating valve group is used to accurately control the steam extraction volume and pressure; the extracted steam is introduced into a multi-stage series steam-molten salt heat exchanger group. During the heat exchange process, the eddy current enhanced heat exchange technology is used to improve the molten salt's absorption efficiency of steam heat; the phase change material composite molten salt technology is used to increase the heat capacity and energy storage density of the molten salt, while reducing the freezing point of the molten salt, and expanding the system's operating temperature range, including: Calculate the required steam extraction amount according to the difference between the comprehensive power grid load and the dynamic threshold; adjust the opening of the intelligent regulating valve group according to the calculated required steam extraction amount; and accurately control the steam extraction amount and steam extraction pressure through the intelligent regulating valve group; A vortex generator is arranged inside the heat exchanger; a vortex is generated in the molten salt flow by the vortex generator; the vortex is used to enhance the heat transfer between the molten salt and the wall surface of the heat exchanger, thereby improving the absorption efficiency of the molten salt to the steam heat; Select a phase change material that matches the operating temperature range of the molten salt; evenly disperse the phase change material in the molten salt in the form of nanoparticles; increase the effective specific heat capacity of the composite molten salt through the phase change process of the phase change material; and utilize the latent heat of the phase change material to increase the energy storage density of the composite molten salt.

3. The method according to claim 1, characterized in that A molten salt physical property parameter prediction model based on deep learning is established to predict the key parameters of the specific heat capacity and thermal conductivity of molten salt at different temperatures and pressures in real time; when the grid load is higher than the preset dynamic threshold, a multi-channel parallel molten salt delivery system is used to transport the high-temperature molten salt to the cascade molten salt-water heat exchanger group, including: Constructing a multi-layer recurrent neural network model, the multi-layer recurrent neural network model includes an input layer, a plurality of long short-term memory network layers and an output layer, wherein the input layer receives the temperature, pressure and composition data of the molten salt, and the output layer outputs the specific heat capacity and thermal conductivity of the molten salt; The multi-layer recurrent neural network model is trained using historical operation data, and the network parameters are optimized by a back propagation algorithm so as to minimize the mean square error between the model output and the actual measurement value; During the operation of the molten salt energy storage system, the temperature, pressure and composition data of the molten salt are collected in real time, and the collected data are input into the trained multi-layer recurrent neural network model to obtain the predicted values ​​of the specific heat capacity and thermal conductivity of the molten salt under the current working conditions; Based on the predicted values ​​of specific heat capacity and thermal conductivity, the energy storage density and heat transfer efficiency of the molten salt are calculated; Real-time monitoring of grid load. When the grid load exceeds the preset dynamic threshold, the molten salt energy release process is triggered. The optimal molten salt energy release flow rate is determined based on the calculated energy storage density and heat transfer efficiency, combined with the current grid load demand. A multi-channel parallel molten salt delivery system is used, which includes a plurality of parallel molten salt delivery pipelines, each of which is provided with an independently controlled variable frequency pump and an electric regulating valve; Based on the determined optimal energy release flow, the fuzzy adaptive PID control algorithm is used to simultaneously adjust the speed of the variable frequency pump and the opening of the electric control valve in each parallel pipeline to achieve precise control of the total flow of molten salt; The high-temperature molten salt in each parallel pipeline is collected and transported to the cascade molten salt-water heat exchanger group, wherein the cascade molten salt-water heat exchanger group includes a plurality of heat exchange units connected in series, and the heat exchange area and flow channel structure of each heat exchange unit are optimized and designed according to the physical properties of the molten salt and the target heat exchange efficiency; In the molten salt-water heat exchange process, based on the predicted molten salt physical properties, a dynamic adaptive control strategy is adopted to adjust the molten salt and water side flow distribution ratio of each heat exchange unit in real time to maximize the heat recovery efficiency and steam quality.

4. The method according to claim 3, characterized in that Based on the determined optimal energy release flow, the fuzzy adaptive PID control algorithm is used to simultaneously adjust the speed of the variable frequency pump and the opening of the electric control valve in each parallel pipeline to achieve precise control of the total flow of molten salt, including: Obtain the current optimal energy release flow target value of the system, which is calculated based on the current grid load demand and the state of the molten salt energy storage system; Real-time collection of actual flow and pressure data of each parallel pipeline in a multi-channel parallel molten salt delivery system, wherein the multi-channel parallel molten salt delivery system includes at least two parallel pipelines, each of which is provided with a variable frequency pump and an electric regulating valve; Calculate the deviation between the total flow rate of molten salt and the target value of the optimal energy release flow rate, and input the deviation into the fuzzy controller; the fuzzy controller performs fuzzy reasoning on the input deviation and its change rate based on a preset fuzzy rule base, and outputs the adjustment amount of the proportional coefficient, integral coefficient and differential coefficient of the PID controller; According to the adjustment amount output by the fuzzy controller, the proportional coefficient, integral coefficient and differential coefficient of the PID controller are dynamically updated; the speed adjustment amount of the variable frequency pump and the opening adjustment amount of the electric control valve of each parallel pipeline are calculated using the updated PID controller parameters; The calculated adjustment amount is applied to the variable frequency pump and electric control valve of each parallel pipeline respectively, wherein the speed adjustment of the variable frequency pump is realized by the frequency converter, and the opening adjustment of the electric control valve is realized by the actuator; The new deviation between the adjusted total molten salt flow rate and the optimal energy release flow rate target value is calculated. If the new deviation is less than the preset threshold, the current control parameters are maintained; if the new deviation is greater than or equal to the preset threshold, the control adjustment continues.

5. The method according to claim 1, characterized in that The generated high-temperature and high-pressure steam is transported to an improved steam turbine with a variable inlet area. The inlet area is dynamically adjusted according to the grid load demand to optimize the efficiency of the steam turbine, including: receiving real-time power demand data from a smart grid, the real-time power demand data including a current load level, a short-term load forecast, and a user-side adjustable load capacity; calculating an optimal steam turbine inlet area based on the real-time power demand data using an artificial neural network algorithm to obtain an optimal inlet area value, the input of the artificial neural network algorithm including the current load level, the short-term load forecast, the user-side adjustable load capacity, the current steam parameters, and a steam turbine characteristic curve; sending the calculated optimal inlet area value to a control system of an improved steam turbine with a variable inlet area, the improved steam turbine with a variable inlet area including an adjustable inlet nozzle group and a movable guide vane group matched therewith; The control system receives the optimal intake area value and synchronously adjusts the nozzle opening of the intake nozzle group and the position of the movable guide vane group through a precision servo mechanism to achieve precise adjustment of the turbine intake area; While adjusting the intake area, the operating parameters of the steam turbine are monitored in real time, including intake pressure, intake temperature, exhaust pressure, shaft power and speed. Based on the monitored operating parameters, the current operating efficiency of the steam turbine is calculated in real time using a thermodynamic model. The calculated current operating efficiency is compared with the preset target efficiency. If the efficiency difference exceeds the preset threshold, the optimal intake area is recalculated. A demand response signal is sent to the user side through the smart grid, and the demand response signal includes electricity price information and load adjustment suggestions.

6. The method according to claim 1, characterized in that The generated high-temperature and high-pressure steam is transported to the improved steam turbine with variable air inlet area, and the air inlet area is dynamically adjusted according to the load demand of the power grid to optimize the efficiency of the steam turbine; the smart grid technology and demand-side response strategy are used to achieve two-way interaction between the power generation end and the power consumption end, and dynamically balance the power supply and demand, including: An improved steam turbine with a variable air inlet area is provided, wherein the improved steam turbine with a variable air inlet area includes an adjustable air inlet nozzle group and a movable guide vane group matched therewith; grid load demand data is collected in real time through a smart grid system, wherein the grid load demand data includes a current load level, a short-term load forecast, and an adjustable load capacity on the user side; Based on the collected grid load demand data, the optimal steam turbine inlet area is calculated using a pre-trained deep reinforcement learning model, the input of which includes the current load level, short-term load forecast, user-side adjustable load capacity, current steam parameters and turbine characteristic curve; the calculated optimal inlet area value is transmitted to the control system of the improved steam turbine with variable inlet area; After receiving the optimal intake area value, the control system synchronously adjusts the nozzle opening of the intake nozzle group and the position of the movable guide vane group through a high-precision servo mechanism. While adjusting the intake area, it monitors the operating parameters of the steam turbine in real time, including intake pressure, intake temperature, exhaust pressure, shaft power and speed; and uses a thermodynamic model to calculate the current operating efficiency of the steam turbine in real time; Sending a demand response signal to the user side through the smart grid system, the demand response signal includes real-time electricity price information and load adjustment suggestions; receiving response data from the user side, the response data includes the load amount actually adjusted by the user and the adjustment time; updating the grid load demand data based on the response data of the user side, especially updating the adjustable load capacity of the user side; using a recurrent neural network algorithm, analyzing the user response pattern based on historical data, and establishing a user response behavior prediction model; On the power generation side, the amount of high-temperature and high-pressure steam generated is dynamically adjusted based on the turbine operating efficiency and grid load demand data. On the electricity consumption side, the user's electricity consumption behavior is predicted in advance based on the user response behavior prediction model, and load adjustment suggestions are sent in advance through the smart grid system to achieve precise matching between the power generation side and the electricity consumption side. This enables two-way interaction between the power generation side and the electricity consumption side to dynamically balance the supply and demand of electricity.

7. A power plant steam extraction storage and power generation optimization system based on molten salt heat storage, used to implement the method described in any one of claims 1 to 6, characterized in that: include: The first unit is used to build a multi-level power grid load monitoring system, including macro-regional power grid load, meso-city power grid load and micro-user power load, and collect and analyze load data in real time; when the comprehensive power grid load is lower than the preset dynamic threshold, the steam turbine is controlled to perform variable-condition steam extraction operation, and the intelligent regulating valve group is used to accurately control the steam extraction volume and pressure; the extracted steam is introduced into a multi-stage series steam-molten salt heat exchanger group, and during the heat exchange process, eddy current enhanced heat exchange technology is used to improve the molten salt's absorption efficiency of steam heat; the phase change material composite molten salt technology is used to increase the heat capacity and energy storage density of the molten salt, while reducing the freezing point of the molten salt and expanding the system's operating temperature range; The second unit is used to use a high-temperature molten salt storage tank that combines multi-layer insulation and vacuum insulation to minimize heat loss, and set up a temperature gradient monitoring system inside the storage tank; establish a molten salt physical property parameter prediction model based on deep learning to predict the key parameters of the specific heat capacity and thermal conductivity of molten salt at different temperatures and pressures in real time; when the grid load is higher than the preset dynamic threshold, a multi-channel parallel molten salt delivery system is used to transport the high-temperature molten salt to the cascade molten salt-water heat exchanger group; in the molten salt-water heat exchanger group, a structure combining countercurrent heat exchange and spiral heat exchange tubes is used to improve the heat exchange efficiency and generate superheated steam; The third unit is used to transport the generated high-temperature and high-pressure steam to an improved steam turbine with a variable air inlet area, dynamically adjust the air inlet area according to the load demand of the power grid, and optimize the efficiency of the steam turbine; use smart grid technology and demand-side response strategies to achieve two-way interaction between the power generation end and the power consumption end, and dynamically balance the supply and demand of electricity.

8. An electronic device, characterized in that: include: processor; a memory for storing processor-executable instructions; The processor is configured to call the instructions stored in the memory to execute the method according to any one of claims 1 to 6.

9. A computer-readable storage medium having computer program instructions stored thereon, characterized in that: When the computer program instructions are executed by a processor, the method according to any one of claims 1 to 6 is implemented.

Images