Night energy storage method and system for central heating water tank of cigarette factory and storage medium

Abstract

The invention relates to the technical field of centralized heat supply water tank energy storage, in particular to a night energy storage method and system for a cigarette factory centralized heat supply water tank and a storage medium. The total operation time of the heat storage system is obtained according to the input variable data; determining the starting time of the heat storage system based on the total operation time; under the condition that the heat storage system is started, liquid level data of the system in the running state are collected in real time; obtaining the opening degree of a bypass valve according to the liquid level data; and controlling the opening and closing degree of the bypass valve based on the opening and closing degree of the bypass valve to balance the liquid levels of the cold water area and the hot water area. According to the implementation mode, the heat storage system, the heat production system and the balance system are coordinated through multiple technologies, the data driving concept penetrates through a heat storage-heat production-balance full chain, experience control is replaced with an intelligent algorithm, and the purposes that the prediction precision of the total heat storage amount is improved, the operation efficiency of heat pump equipment is improved, and the water tank liquid level control response speed is increased are achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of energy storage in centralized hot water supply tanks, and in particular to a nighttime energy storage method, system and storage medium for centralized hot water supply tanks in cigarette factories. Background Art

[0002] Globally, low-carbon and energy-saving initiatives have become a widespread trend and a key direction for social development. Many industries, particularly manufacturing, are facing an urgent need for transformation and upgrading. Cigarette factories, as part of the traditional industrial sector, are actively responding to the nation's call for green development, committed to reducing energy consumption and carbon emissions throughout the production process, continuously strengthening technological innovation, and utilizing energy efficiently and rationally to achieve the goals of clean production and sustainable development.

[0003] The cigarette production process requires a large amount of heat energy, including hot water and steam. To this end, factories typically install centralized hot water tanks, each divided into cold and hot water zones. Hot water is supplied to the load side, then flows back to the cold water zone. After passing through heating equipment, it enters the hot water zone, forming a circulation system. However, traditional nighttime water tank heat storage methods typically utilize off-peak electricity to store heat overnight, attempting to maximize heat storage capacity. However, this approach lacks consideration for heat storage capacity saturation, leading to a certain degree of energy waste.

[0004] Cigarette factories have unique heating requirements. Due to production process requirements, the hot water temperature range is strictly limited, requiring nighttime heat storage at set values. Furthermore, the production process's heat requirements vary depending on seasonal temperatures. Furthermore, since there is no load-side return flow at night, level control in both the cold and hot water zones is also a challenge.

[0005] Therefore, the traditional nighttime heat storage method can no longer meet the special needs of cigarette factories. There is an urgent need for a new nighttime energy storage system that can achieve precise heat storage, maximize energy efficiency, and effectively solve liquid level control problems to adapt to the production process requirements and green development goals of cigarette factories. Summary of the Invention

[0006] One of the purposes of the present invention is to provide a nighttime energy storage method, system and storage medium for a centralized hot water tank in a cigarette factory, so as to solve the technical problems in the prior art of the lack of precise temperature control during the nighttime heat storage process of the centralized hot water tank and the inability to flexibly adjust the heat storage strategy according to actual needs.

[0007] In order to achieve the above object, the present invention provides a nighttime energy storage method for a centralized hot water tank in a cigarette factory, comprising: Get input variable data; Obtaining the total operating time of the heat storage system according to the input variable data; determining a thermal storage system startup time based on the total operating time; When the heat storage system is started, the liquid level data of the system operation status is collected in real time; Obtaining the opening and closing degree of the bypass valve according to the liquid level data; The opening and closing degree of the bypass valve is controlled based on the opening and closing degree of the bypass valve to balance the liquid levels of the cold water area and the hot water area.

[0008] Optionally, obtaining the total operating time of the thermal storage system according to the input variable data includes: Construct a water temperature prediction model for the thermal storage system; Based on the input variable data, the water temperature prediction model is optimized using an objective function to obtain a target water temperature; Obtaining the total heating capacity required by the hot water storage tank according to the target water temperature; The total operating time of the heat storage system is obtained according to the total heating amount.

[0009] Optionally, based on the input variable data, optimizing the water temperature prediction model using an objective function to obtain the target water temperature includes: According to formula (1), the water temperature prediction model training is optimized. , (1) in, is the heating energy consumption weight coefficient, is the heating energy consumption, is the temperature deviation weight coefficient, is the target water temperature, is the ambient temperature.

[0010] Optionally, obtaining the total heating amount required for the hot water storage tank according to the target water temperature includes: According to formula (2) to formula (4), the total heating amount is obtained. , (2) , (3) , (4) in, is the total heating capacity, is the total heat required to raise the water temperature in the tank to the target temperature, is the specific heat capacity of water, is the density of water, is the effective volume of water in the tank, is the target water temperature, Current tank water temperature, It is the sum of sensible heat and latent heat during the heating process of the phase change material in the hot water storage tank. is the heat loss, is the heat transfer coefficient of the water tank, is the cross-sectional area of the water tank, is the ambient temperature, is the time interval.

[0011] Optionally, obtaining the total operating time of the heat storage system according to the total heating amount includes: According to formula (5) to formula (7), the total running time is obtained. , (5) , (6) , (7) in, is the total running time, is the total heating capacity, For the The coefficient of performance of the heat pump, For the Rated input electrical power of each heat pump, For the The actual heat transfer efficiency of the heat pump, is the initial heat transfer efficiency, is the dynamic efficiency adjustment factor, is the ambient temperature, is the cumulative running time, is the current load rate.

[0012] Optionally, when the heat storage system is started, real-time collection of liquid level data of the system operation status and establishment of a liquid level dynamic model include: According to formula (8), the liquid level dynamic model is established. , (8) in, is the liquid level of the cold water tank, is the flow rate into the tank, is the flow coefficient, is the opening and closing degree of the bypass valve, is the cross-sectional area of the water tank.

[0013] Optionally, obtaining the opening and closing degree of the bypass valve according to the liquid level data includes: According to formula (9), the cost function is established. , (9) in, is the cost function, is the weight coefficient of the liquid level deviation penalty term, is the desired liquid level to be set, is the weight coefficient of the energy consumption penalty term.

[0014] Optionally, obtaining the opening and closing degree of the bypass valve according to the liquid level data includes: According to formula (10), the cost function is optimized to obtain the optimal control input. , (10) in, is the current liquid level status, Current time The optimal control input for the bypass valve opening and closing degree.

[0015] On the other hand, the present invention further provides a nighttime energy storage system for a centralized hot water tank in a cigarette factory, the system comprising a processor configured to execute any of the above-described methods.

[0016] In another aspect, the present invention further provides a computer-readable storage medium having instructions stored thereon. When the instructions are executed by a processor, any of the above methods is implemented.

[0017] Beneficial effects of the present invention: The embodiments of this invention significantly improve heat storage efficiency and energy utilization through the collaborative innovation of multiple technologies. A machine learning model is employed in the heat storage system to analyze historical data such as air temperature, production, and water temperature to predict the optimal total nighttime heat storage, enabling dynamic and precise control of heat balance. A dynamic equipment adjustment model is constructed in the heat production system to optimize heat production efficiency and startup time based on real-time heat pump operating data, achieving the optimal match between energy consumption and production needs. Model predictive control is introduced in the balancing system to stably control the liquid level and water flow balance in the hot and cold zones of the water tank by calculating the optimal bypass valve opening in real time. This multi-technology collaboration addresses the energy waste caused by the traditional system's focus on maximum heat storage, improving the accuracy of total heat storage prediction, increasing the operating efficiency of the heat pump equipment, and accelerating the response speed of the water tank level control. Compared to existing technologies, this invention incorporates a data-driven approach throughout the entire heat storage-generation-balancing chain, replacing empirical control with intelligent algorithms. This significantly improves the system's overall energy efficiency while meeting the stringent requirements of cigarette production processes, achieving the dual advantages of energy conservation and consumption reduction and stable production.

[0018] Other features and advantages of the embodiments of the present invention will be described in detail in the subsequent detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] The accompanying drawings are used to provide a further understanding of the embodiments of the present invention and constitute a part of the specification. Together with the following detailed description, they are used to explain the embodiments of the present invention, but do not constitute a limitation of the embodiments of the present invention. In the accompanying drawings: Figure 1This is a flow chart of a nighttime energy storage method for a centralized hot water tank in a cigarette factory according to one embodiment of the present invention; Figure 2 The figure is a flow chart of a method for obtaining the total operating time of a thermal storage system according to one embodiment of the present invention. DETAILED DESCRIPTION

[0020] The following describes the specific implementation of the embodiment of the present invention in detail with reference to the accompanying drawings. It should be understood that the specific implementation described herein is only used to illustrate and explain the embodiment of the present invention and is not used to limit the embodiment of the present invention.

[0021] It should be noted that the acquisition, transmission, storage, use, and processing of data in the technical solution of this application are in compliance with the relevant provisions of laws and regulations. In the embodiments of this application, certain software, components, models, and other existing solutions in the industry may be mentioned. These should be considered as exemplary. Their purpose is only to illustrate the feasibility of implementing the technical solution of this application, but it does not mean that the applicant has or will necessarily use such solutions.

[0022] like Figure 1 Shown is a flow chart of a nighttime energy storage method for a centralized hot water tank in a cigarette factory according to one embodiment of the present invention. Figure 1 In the embodiment of the present invention, the energy storage method may include the following steps: In step S10, input variable data is obtained; In step S11, the total operating time of the thermal storage system is obtained according to the input variable data; In step S12, the start time of the thermal storage system is determined based on the total operating time; In step S13, when the heat storage system is started, the liquid level data of the system operation status is collected in real time and a liquid level dynamic model is established; In step S14, the opening and closing degree of the bypass valve is obtained according to the liquid level data; In step S15 , the opening and closing degree of the bypass valve is controlled based on the opening and closing degree of the bypass valve to balance the liquid levels in the cold water area and the hot water area.

[0023] In this Figure 1 In the illustrated nighttime energy storage method for a centralized hot water tank in a cigarette factory, step S10 is used to obtain input variable data. Because the heat demand of the production process varies with seasonal temperatures, factors such as temperature and production volume must be considered to accurately predict future energy usage. In this embodiment, step S10 obtains input variable data by collecting and organizing historical data, including temperature, production volume, tank water temperature at the end of production, tank water temperature at the start of production, and heat output of the dual-source heat pump during production. The data is then cleaned and standardized, and missing and outliers are addressed.

[0024] After obtaining the variables that affect the nighttime energy storage of the centralized hot water tank, step S11 is used to obtain the total operating time of the heat storage system. In this embodiment, in order to accurately predict the total operating time of the heat storage system, step S11 may be to use a machine learning model to predict the total operating time of the heat storage system. Furthermore, the specific method for obtaining the total operating time of the heat storage system in step S11 may be various forms known to those skilled in the art. In one example of the present invention, step S11 may include the following: Figure 2 The steps shown in Figure 2 In the embodiment, step S11 may include: In step S20, a water temperature prediction model of the thermal storage system is constructed; In step S21, based on the input variable data, the water temperature prediction model is optimized using the objective function to obtain the target water temperature; In step S22, the total heating amount required by the water storage tank is obtained according to the target water temperature; In step S23, the total operating time of the heat storage system is obtained according to the total heating amount.

[0025] In this Figure 2 In the method shown, step S20 is used to construct a water temperature prediction model for the heat storage system. In this embodiment, step S20 can be a machine learning model constructed using a three-layer neural network to predict the target water temperature in the nighttime heat storage mode. Furthermore, the specific method for constructing the water temperature prediction model for the heat storage system in step S20 can be a variety of forms known to those skilled in the art. In one example of the present invention, step S20 can be a model whose input layer is key operating parameters, including ambient temperature, next day's discharge volume, current water tank water temperature, and average daily heat production of the heat pump. The output layer is the target water temperature after nighttime heating. The model training process adopts a supervised learning strategy. The input data is calculated by the neural network to obtain a predicted value, which is compared with the actual value to calculate the loss function. Based on the loss value, the gradient descent algorithm is used to return the error layer by layer, adjust the weights and biases of each layer, and optimize the model parameters. The training process is repeated until the model error converges to the set threshold to ensure that the prediction accuracy meets the engineering requirements. This model dynamically optimizes the nighttime heat storage strategy in a data-driven manner. Compared with traditional empirical control methods, it can significantly improve the accuracy of water temperature prediction, reduce energy waste, and meet the high requirements of cigarette factories for heating stability.

[0026] Step S21 is used to optimize the water temperature prediction model using an objective function to obtain the target water temperature. Step S21 can achieve the goal of satisfying that the output temperature is within the specified range and that energy consumption is minimized. Specifically, in this example, step S21 can be, for example, to optimize the water temperature prediction model training using formula (1): , (1) in, is the heating energy consumption weight coefficient, is the heating energy consumption, is the temperature deviation weight coefficient, is the target water temperature, The model's predictive performance is evaluated through cross-validation. Model parameters and the weight coefficients of the optimization objective function are adjusted to ensure that the model accurately predicts and optimizes the target heating temperature of the nighttime heat storage tank. During the model deployment phase, the trained optimization model is integrated into the actual production system, and a real-time monitoring mechanism is established to continuously track key indicators such as prediction error and energy consumption. Based on online data and actual operational feedback, the model undergoes regular incremental learning or retraining to adapt to changes in the production environment (such as seasonal temperature fluctuations and production schedule adjustments), ensuring long-term stable and efficient system operation.

[0027] Step S22 is used to obtain the total heating capacity required by the water storage tank based on the target water temperature. Since heat loss occurs during the heat storage process, the total heating capacity needs to take into account the heat loss value. Specifically, in this example, step S22 can be, for example, using formula (3) and formula (4) to calculate the water storage capacity and heat loss of the water tank respectively: , (3) , (4) in, is the total heat required to raise the water temperature in the tank to the target temperature, is the specific heat capacity of water, is the density of water, is the effective volume of water in the tank, is the target water temperature, Current tank water temperature, It is the sum of sensible heat and latent heat during the heating process of the phase change material in the hot water storage tank. is the heat loss, is the heat transfer coefficient of the water tank, is the cross-sectional area of the water tank, is the ambient temperature, is the time interval.

[0028] Finally, the total heating required by the water storage tank at night is obtained based on the water storage heat and heat loss in the water tank, as shown in formula (2): , (2) in, is the total heating capacity.

[0029] Step S23 is used to obtain the total operating time of the heat storage system based on the total heating amount. In this embodiment, the model of each heat pump and the basic parameters provided by the manufacturer, such as rated power, rated COP, operating range, etc., can be determined first. Daily operating data such as outdoor temperature, indoor load demand, water flow rate, etc. are collected. Based on the parameters provided by the manufacturer and the theoretical thermodynamic model, a mathematical model of each heat pump is established. Specifically, in this example, the basic heating power of each heat pump can be expressed, for example, using formula (11): , (11) in, For the The coefficient of performance of the heat pump, For the Rated input electrical power of each heat pump.

[0030] Due to the ambient temperature ( ) can affect the COP value, long-term operation time ( ) may result in decreased efficiency, and nighttime loads ( ) situation, and define an adjustment factor based on this as the operating influencing factor. Specifically, in this example, the adjustment factor can be defined by, for example, formula (7) : , (7) in, is the dynamic efficiency adjustment factor, is the ambient temperature, is the cumulative running time, is the current load rate.

[0031] In this example, the heat transfer efficiency can be dynamically adjusted by, for example, formula (6): , (6) in, For the The actual heat transfer efficiency of the heat pump, is the initial heat transfer efficiency.

[0032] The total heat storage demand calculated in step S22 , the total running time to meet the requirements can be calculated using formula (5): , (5) After the total operating time to meet the demand is obtained, step S12 is used to determine how long before the start of production each day to start the nighttime heat storage system.

[0033] In step S13, when the heat storage system is started, the liquid level data of the system operation status is collected in real time and a liquid level dynamic model is established. In actual situations, due to the various energy losses in the actual fluid and the fact that the actual flow conditions may be different from the ideal conditions, a flow coefficient is usually introduced. To modify the theoretical formula to more accurately reflect the actual flow situation. Specifically, in this example, it can be to collect the liquid level of the system operation status in real time and obtain system parameters, including obtaining the liquid level of the cold water tank , the cross-sectional area of the water tank , flow coefficient , bypass valve opening and closing degree , the flow rate into the water tank Based on the above parameters, a liquid level dynamic model is established. Specifically, in this example, step S13 may be, for example, to use formula (8) to obtain the relationship between the change of liquid level over time and the opening and closing degree of the control input bypass valve: , (8).

[0034] Among them, the flow coefficient The bypass valve structure, fluid properties, and energy loss during flow are comprehensively considered; the degree of opening and closing of the bypass valve Affects the flow area of the fluid, thus affecting the flow rate; This example demonstrates the impact of liquid level on outflow rate: a higher liquid level results in faster outflow and, consequently, a greater outflow rate, reflecting the nonlinear relationship between liquid level and flow rate. In this example, sensors monitor the liquid levels in the cold and hot water zones, as well as the operating status of the heat pump, in real time. Control objectives and constraints are set to determine target ranges for the liquid levels in the cold and hot water zones, for example, the liquid levels should fluctuate between minimum and maximum allowable values.

[0035] Step S14 is used to obtain the bypass valve opening degree based on the liquid level data. In this embodiment, a cost function may be defined and the bypass valve opening degree may be obtained by optimizing the cost function. Specifically, in this example, the cost function may include a liquid level deviation penalty term and an energy consumption penalty term. Step S14 may, for example, use formula (9) to define the cost function: , (9) in, is the cost function, is the weight coefficient of the liquid level deviation penalty term, is the desired liquid level to be set, is the weight coefficient of the energy consumption penalty term. is the liquid level deviation penalty term, which is used to measure the degree to which the liquid level deviates from the expected value; is the energy penalty term, which reflects the energy consumed by the change in the opening and closing degree of the bypass valve. By optimizing this cost function, a balance can be achieved between liquid level control accuracy and energy consumption.

[0036] After establishing the cost function, the model predictive control (MPC) optimization problem is set up, and at each time step , the current liquid level status The input is fed into the Model Predictive Control (MPC) controller. The MPC controller uses a numerical optimization algorithm (gradient descent) to solve the optimal control input sequence in the prediction time domain. , so that the cost function Minimum, among which To predict the time domain length, is the current liquid level status, Current time Through this operation and iterative process, the control input sequence that makes the cost function optimal in the prediction time domain is found, and the optimal control input sequence for the current time step is obtained. The optimal control input , the optimized control input is implemented into the system, that is, the opening and closing degree of the bypass valve is adjusted, the system status and new measurement data are continuously monitored for feedback control, and compared with the reference signal to evaluate the current control effect. On the other hand, the current state of the next time step is , input into the MPC controller, update the controller input information for the next optimization calculation, and repeat the above steps for real-time update. Regularly evaluate the stability of the liquid level and the system performance. Based on the evaluation results, adjust the parameters and settings of the MPC controller to further optimize the system operation effect.

[0037] After the bypass valve opening and closing degree is obtained, step S15 is used to control the bypass valve opening and closing degree to balance the liquid levels in the cold water area and the hot water area.

[0038] On the other hand, the present invention further provides a nighttime energy storage system for a centralized hot water tank in a cigarette factory, the system comprising a processor configured to execute any of the above-described methods.

[0039] In another aspect, the present invention further provides a computer-readable storage medium having instructions stored thereon. When the instructions are executed by a processor, any of the above methods is implemented.

[0040] Beneficial effects of the present invention: The embodiments of this invention significantly improve heat storage efficiency and energy utilization through the collaborative innovation of multiple technologies. A machine learning model is employed in the heat storage system to analyze historical data such as air temperature, production, and water temperature to predict the optimal total nighttime heat storage, enabling dynamic and precise control of heat balance. A dynamic equipment adjustment model is constructed in the heat production system to optimize heat production efficiency and startup time based on real-time heat pump operating data, achieving the optimal match between energy consumption and production needs. Model predictive control is introduced in the balancing system to stably control the liquid level and water flow balance in the hot and cold zones of the water tank by calculating the optimal bypass valve opening in real time. This multi-technology collaboration addresses the energy waste caused by the traditional system's focus on maximum heat storage, improving the accuracy of total heat storage prediction, increasing the operating efficiency of the heat pump equipment, and accelerating the response speed of the water tank level control. Compared to existing technologies, this invention incorporates a data-driven approach throughout the entire heat storage-generation-balancing chain, replacing empirical control with intelligent algorithms. This significantly improves the system's overall energy efficiency while meeting the stringent requirements of cigarette production processes, achieving the dual advantages of energy conservation and consumption reduction and stable production.

[0041] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware. Furthermore, the present application may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0042] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0043] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0044] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 The steps for the function specified in one or more boxes.

[0045] In a typical configuration, a computing device includes one or more processors (CPUs), input / output interfaces, network interfaces, and memory.

[0046] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0047] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can be implemented using any method or technology for information storage. Information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase-change RAM (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassettes, magnetic disk storage or other magnetic storage devices, or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer-readable media does not include transitory computer-readable media, such as modulated data signals and carrier waves.

[0048] It should also be noted that the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, commodity, or apparatus that includes a series of elements includes not only those elements but also other elements not explicitly listed, or includes elements inherent to such process, method, commodity, or apparatus. In the absence of further limitations, an element defined by the phrase "comprises a ..." does not exclude the presence of other identical elements in the process, method, commodity, or apparatus that includes the element.

[0049] The above are merely embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application should all be included within the scope of the claims of the present application.

Claims

1. A nighttime energy storage method for a central heating water tank in a cigarette factory, characterized in that: The nighttime energy storage method comprises: Get input variable data; Obtaining the total operating time of the heat storage system according to the input variable data; determining a thermal storage system startup time based on the total operating time; When the heat storage system is started, the liquid level data of the system operation status is collected in real time and a liquid level dynamic model is established; Obtaining the opening and closing degree of the bypass valve according to the liquid level data; The opening and closing degree of the bypass valve is controlled based on the opening and closing degree of the bypass valve to balance the liquid levels of the cold water area and the hot water area.

2. The nighttime energy storage method according to claim 1, characterized in that: Obtaining the total operating time of the thermal storage system according to the input variable data includes: Construct a water temperature prediction model for the thermal storage system; Based on the input variable data, the water temperature prediction model is optimized using an objective function to obtain a target water temperature; Obtaining the total heating capacity required by the hot water storage tank according to the target water temperature; The total operating time of the heat storage system is obtained according to the total heating amount.

3. The nighttime energy storage method according to claim 2, characterized in that: Based on the input variable data, the water temperature prediction model is optimized using an objective function to obtain the target water temperature, including: According to formula (1), the water temperature prediction model training is optimized. ，（1） in, is the heating energy consumption weight coefficient, is the heating energy consumption, is the temperature deviation weight coefficient, is the target water temperature, is the ambient temperature.

4. The nighttime energy storage method according to claim 2, characterized in that: The total heating capacity required to obtain the hot water storage tank according to the target water temperature includes: According to formula (2) to formula (4), the total heating amount is obtained. ，（2） ，（3） ，（4） in, is the total heating capacity, is the total heat required to raise the water temperature in the tank to the target temperature, is the specific heat capacity of water, is the density of water, is the effective volume of water in the tank, is the target water temperature, Current tank water temperature, It is the sum of sensible heat and latent heat during the heating process of the phase change material in the hot water storage tank. is the heat loss, is the heat transfer coefficient of the water tank, is the cross-sectional area of the water tank, is the ambient temperature, is the time interval.

5. The nighttime energy storage method according to claim 2, characterized in that: According to the total heating amount, obtaining the total operating time of the heat storage system includes: According to formula (5) to formula (7), the total running time is obtained. ，（5） ，（6） ，（7） in, is the total running time, is the total heating capacity, For the The coefficient of performance of the heat pump, For the Rated input electrical power of each heat pump, For the The actual heat transfer efficiency of the heat pump, is the initial heat transfer efficiency, is the dynamic efficiency adjustment factor, is the ambient temperature, is the cumulative running time, is the current load rate.

6. The nighttime energy storage method according to claim 1, characterized in that: When the heat storage system is started, real-time collection of the system operating status liquid level data and establishment of a liquid level dynamic model include: According to formula (8), the liquid level dynamic model is established. ，（8） in, is the liquid level of the cold water tank, is the flow rate into the tank, is the flow coefficient, is the opening and closing degree of the bypass valve, is the cross-sectional area of the water tank.

7. The nighttime energy storage method according to claim 6, characterized in that: Acquiring the opening and closing degree of the bypass valve according to the liquid level data includes: According to formula (9), the cost function is established. ，（9） in, is the cost function, is the weight coefficient of the liquid level deviation penalty term, is the desired liquid level to be set, is the weight coefficient of the energy consumption penalty term.

8. The nighttime energy storage method according to claim 7, characterized in that: Acquiring the opening and closing degree of the bypass valve according to the liquid level data includes: According to formula (10), the cost function is optimized to obtain the optimal control input. ，（10） in, is the current liquid level status, Current time The optimal control input for the bypass valve opening and closing degree.

9. A nighttime energy storage system for a centrally-used hot water tank in a cigarette factory, characterized in that: The system comprises a processor configured to execute the method according to any one of claims 1 to 8.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores instructions, and when the instructions are executed by a processor, the method according to any one of claims 1 to 8 is implemented.

Images