Flow battery electrolyte equalization control method, system and equipment and storage medium

Abstract

The embodiment of the invention relates to the field of flow batteries, and discloses a flow battery electrolyte equalization control method, system and device and a storage medium, and the method comprises the following steps: obtaining a state space of a flow battery electrolyte multi-process system; matching the state space of the flow battery electrolyte multi-process system with the input dimension of the neural network, and outputting the behavior space of the flow battery electrolyte multi-process system to form a balance control base model; setting an optimization target for realizing the balance control of the electrolyte multi-process system of the flow battery; and training an equalization control base model based on the optimization target to form an equalization control model. The problem of electrolyte temperature control of the flow battery can be effectively solved, the efficiency of the battery is improved, and the service life of the battery is prolonged; the consistency and stability control of the electrolyte temperature, energy and liquid level of all process systems can be realized; energy of a heat management system and a pump valve can be effectively utilized, and energy consumption is reduced.

Description

Technical Field

[0001] The present disclosure relates to the technical field of liquid flow batteries, and in particular to a method, system, device and storage medium for controlling electrolyte balance of a liquid flow battery in a multi-process system. Background Art

[0002] In the field of battery technology, liquid flow battery is a new type of battery energy storage technology. Its electrolyte flows through a group of circulating pumps in a process system composed of storage tanks, pipelines, and battery stacks. Multiple process systems form an energy storage module through the electrical series-parallel architecture of the battery stack. The energy storage module stores and releases energy through electrochemical reactions. However, the temperature of the electrolyte has an important influence on the performance of the battery. Too high or too low temperature will reduce the efficiency and life of the battery. Therefore, how to effectively control the temperature and energy balance of the electrolyte to ensure the efficient and stable operation of the battery is an urgent problem to be solved in the field of battery technology. In the field of temperature control technology, the traditional temperature control method is mainly to detect the electrolyte temperature of the storage tank and pipeline, as well as the temperature of the supply and return water of the thermal management system, and then adjust the operating power of the thermal management system and the opening of the electric regulating valve on the electrolyte pipeline to achieve the control of the electrolyte temperature. However, this method often cannot achieve consistency and stability control of the electrolyte temperature of all process systems. In addition, the energy imbalance and liquid level imbalance between different process systems on the same electrical circuit also greatly affect the capacity of the liquid flow energy storage system. In the field of reinforcement learning technology, deep reinforcement learning (DQN) is an emerging machine learning method that learns the optimal strategy to achieve specific goals through the interaction between the agent and the environment. However, there is little research on the application of deep reinforcement learning to electrolyte temperature control and energy balance control in flow batteries.

[0003] The existing solutions mainly detect the electrolyte temperature of different process system tanks and pipelines, as well as the supply and return water temperature of the thermal management system, and then adjust the operating power of the thermal management system, the opening of the electric regulating valve on the electrolyte pipeline and the mixing pump to achieve the control of the electrolyte temperature. The existing active and passive energy balance is mostly designed in the form of lithium battery energy storage. The one with high power automatically discharges heat and discharges to balance, or the one with high power charges the one with low power. However, when controlling the electrolyte temperature, the existing technology often cannot achieve the consistency and stability control of the electrolyte temperature of all process systems. This is because different process systems may have different temperature characteristics, and the existing control methods often cannot take these differences into account, resulting in the difficulty in ensuring the consistency and stability of the electrolyte temperature. In addition, the existing control methods often cannot effectively utilize the energy of the thermal management system, resulting in energy waste. The energy balance method in the form of lithium battery is less applicable to liquid flow batteries and cannot even be reused. Summary of the invention

[0004] The embodiments of the present disclosure provide a flow battery electrolyte balancing control method, system, device and storage medium to solve or alleviate one or more of the above technical problems in the prior art.

[0005] According to one aspect of the present disclosure, a flow battery electrolyte equalization control method is provided, comprising:

[0006] Obtain the state space of the multi-process system of flow battery electrolyte;

[0007] Match the state space of the flow battery electrolyte multi-process system with the input dimension of the neural network, output the behavior space of the flow battery electrolyte multi-process system, and form a balanced control base model;

[0008] Set optimization goals to achieve balanced control of multi-process systems for flow battery electrolytes;

[0009] The balanced control base model is trained based on the optimization target to form a balanced control model.

[0010] In one possible implementation, the state space includes the electrolyte temperature and liquid level of each electrolyte storage tank in the liquid flow battery electrolyte multi-process system, and the open circuit voltage of the process system in the same electrical string; the behavior space includes the given pump frequency, outlet valve and overflow valve opening of each electrolyte storage tank in the liquid flow battery electrolyte multi-process system, and the thermal management system power.

[0011] In a possible implementation, the electrolyte temperature T of each electrolyte storage tank in the liquid flow battery electrolyte multi-process system is t for:

[0012]

[0013] The electrolyte level L of each electrolyte storage tank in the multi-process system of liquid flow battery electrolyte t for:

[0014]

[0015] In the multi-process system of liquid flow battery electrolyte, the open circuit voltage V of the process system in the same electrical string t for:

[0016] V t =(V t 1 ,V t 2 ,L,V t i ),i∈(1,2,L,N);

[0017] The state space S is expressed as:

[0018]

[0019] Where, T t po Indicates the temperature value of all cathode storage tanks in the same electrical string process system; T t ne It represents the temperature value of all negative electrode storage tanks in the same electrical string process system; t represents the time step; N represents the total number of sets of the same electrical string process system; Indicates the liquid level value of all cathode storage tanks in the same electrical string process system; Indicates the liquid level value of all negative electrode storage tanks in the same electrical string process system; T t scal represents the normalized electrolyte temperature of each electrolyte storage tank in the multi-process system of liquid flow battery electrolyte, Normalized electrolyte level of each electrolyte storage tank in the multi-process system of liquid flow battery electrolyte, V t scal Normalized open circuit voltage of the process system in the same electrical string in the multi-process system of liquid flow battery electrolyte;

[0020] Given pump frequency FQS for each electrolyte tank in the multi-process system of flow battery electrolyte t for:

[0021]

[0022] PVS of the opening of the outlet valve and overflow valve of each electrolyte storage tank in the multi-process system of liquid flow battery electrolyte t for:

[0023]

[0024] Thermal management system power TPS of liquid flow battery electrolyte multi-process system t for:

[0025]

[0026] The behavior space A is expressed as:

[0027] A=(FQS t ,PVS t ,TPS t ),t∈(1,2,…∞);

[0028] In the formula, Indicates the pump frequency setting value of all cathode storage tanks in the same electrical string process system; Indicates the pump frequency setting value of all negative electrode storage tanks in the same electrical string process system; Indicates the outlet valve opening setting value of all positive / negative storage tanks in the same electrical string process system; Indicates the overflow valve opening setting value of all positive / negative storage tanks in the same electrical string process system; It represents the operating power setting value of each thermal management system equipped with the same electrical string process system; t represents the time step; N represents the total number of the same electrical string process system; M represents the total number of thermal management systems in the same electrical string process system.

[0029] In a possible implementation, the optimization objectives of achieving balanced control of the multi-process system of the electrolyte of the flow battery include: minimizing the difference between the electrolyte temperature of the positive and negative electrode storage tanks and the target temperature, minimizing the temperature balance of the electrolyte of the positive and negative electrode storage tanks, minimizing the balance of the open circuit voltage, minimizing the balance of the electrolyte level of the positive and negative electrode storage tanks, and minimizing the total power of the pump valve and thermal management system;

[0030] The sub-optimization function of the difference between the electrolyte temperature of the positive and negative tanks and the target temperature is expressed as:

[0031]

[0032] In the formula, Respectively represent the upper and lower limits of the given target temperature range; T t i Indicates the electrolyte temperature value of any positive or negative electrode storage tank; Respectively represent the upper and lower limits of the temperature acquisition range, N represents the total number of process systems of the same electrical string;

[0033] The optimization function of the electrolyte temperature balance property of the positive and negative electrode storage tanks is expressed as:

[0034]

[0035] In the formula, Indicates the electrolyte temperature balance index of the positive and negative electrode storage tanks in the same process system. Indicates the electrolyte temperature balance index of the positive electrode storage tank of N process systems, It represents the electrolyte temperature balance index of the negative electrode storage tanks of N process systems; ω T ,ρ T Indicates that different indicators are in the overall The proportion of indicators; They represent the upper and lower limits of the temperature acquisition range respectively; N represents the total number of process systems of the same electrical string; It represents the average temperature value of all cathode storage tanks in the same electrical string process system; It represents the average temperature value of all negative electrode storage tanks in the same electrical string process system;

[0036] The open circuit voltage balance property optimization function is expressed as:

[0037]

[0038] In the formula, It represents the mean value of the open circuit voltage of the process system; They represent the upper and lower limits of the open circuit voltage acquisition range respectively;

[0039] The optimization function of the electrolyte temperature balance property of the positive and negative electrode storage tanks is expressed as:

[0040]

[0041] In the formula, It indicates the average value of the liquid level of all cathode storage tanks in the same electrical string process system; It indicates the average value of the liquid level of all negative electrode storage tanks in the same electrical string process system; Respectively represent the upper and lower limits of the liquid level acquisition range;

[0042] The total power sub-optimization function of the pump valve and thermal management system is expressed as:

[0043]

[0044] In the formula, TS represents the time interval within 1 time step t; Indicates the power of the positive and negative electrode pumps; Indicates the power of normal operation of the outlet valve and the relief valve; Indicates the operating power of the thermal management system; E max Indicates the set maximum tolerable energy consumption value.

[0045] In a possible implementation, training a balanced control base model based on the optimization target to form a balanced control model includes:

[0046] Integrate all optimization objectives to form a reward function:

[0047]

[0048] According to the reward function, the loss function of the equilibrium control base model is generated:

[0049]

[0050] In the formula, represents the sub-optimization function of the difference between the electrolyte temperature of the positive and negative electrode storage tanks and the target temperature; Represents the optimization function of the temperature balance of the electrolyte in the positive and negative electrode tanks; represents the open circuit voltage balance property optimization function; E represents the optimization function of the temperature balance of the electrolyte in the positive and negative electrode tanks; t represents the total power sub-optimization function of the pump, valve and thermal management system; α, β, ε, η, and λ represent the proportion of different optimization objectives in the overall objective.

[0051] According to one aspect of the present disclosure, a flow battery electrolyte equalization control system is provided, comprising:

[0052] An acquisition unit, used for acquiring a state space of a multi-process system of an electrolyte of a flow battery;

[0053] Establishing a unit for matching the state space of the flow battery electrolyte multi-process system with the input dimension of the neural network, outputting the behavior space of the flow battery electrolyte multi-process system, and forming a balanced control base model;

[0054] A setting unit, used to set an optimization target for achieving balanced control of a multi-process system of an electrolyte of a flow battery;

[0055] The training unit is used to train the balanced control base model based on the optimization target to form a balanced control model.

[0056] It is worth noting that the state space represents the state characteristics of the system in which the algorithm is located, which can be regarded as the acquisition unit and is the input information of the algorithm; the behavior space represents the executable actions of the system equipment in which the algorithm is located, which should be regarded as the interaction unit and is the output information of the algorithm; the optimization goal represents the algorithm's judgment (scoring) of the quality of the executed actions; the algorithm process explanation: at the initial moment, the algorithm obtains the state characteristics of the current system, that is, the acquisition unit, and obtains a system state in the state space; according to the obtained system state, a set of device actions in the behavior space are selected to be executed, which has an impact on the environment; the environment generates feedback on the action, the state changes, and a new system state is obtained; combined with the new state of the environment feedback and the optimization goal, the quality of the action is judged (equivalent to scoring the quality of the action); according to the scoring of the action, the neural network is optimized, and training and learning are carried out, so that the algorithm can be closer to the optimization goal when it selects the action output according to the input system state next time. This is a sequential decision-making process. The algorithm calculates from the first action to an infinite number of continuous actions, so that the overall set of actions has the best impact on the environment, that is, to make the environmental state as close to the optimization goal as possible.

[0057] In one possible implementation, the state space includes the electrolyte temperature and liquid level of each electrolyte storage tank in the liquid flow battery electrolyte multi-process system, and the open circuit voltage of the process system in the same electrical string; the behavior space includes the given pump frequency, outlet valve and overflow valve opening of each electrolyte storage tank in the liquid flow battery electrolyte multi-process system, and the thermal management system power.

[0058] In a possible implementation, the electrolyte temperature T of each electrolyte storage tank in the liquid flow battery electrolyte multi-process system is t for:

[0059]

[0060] The electrolyte level L of each electrolyte storage tank in the multi-process system of liquid flow battery electrolyte t for:

[0061]

[0062] In the multi-process system of liquid flow battery electrolyte, the open circuit voltage V of the process system in the same electrical string t for:

[0063] V t =(V t 1 ,V t 2 ,L,V t i ),i∈(1,2,L,N);

[0064] Where, T t po Indicates the temperature value of all cathode storage tanks in the same electrical string process system; T t ne It represents the temperature value of all negative electrode storage tanks in the same electrical string process system; t represents the time step; N represents the total number of sets of the same electrical string process system; Indicates the liquid level value of all cathode storage tanks in the same electrical string process system; Indicates the liquid level value of all negative electrode storage tanks in the same electrical string process system;

[0065] Given pump frequency FQS for each electrolyte tank in the multi-process system of flow battery electrolyte t for:

[0066]

[0067] PVS of the opening of the outlet valve and overflow valve of each electrolyte storage tank in the multi-process system of liquid flow battery electrolyte t for:

[0068]

[0069] Thermal management system power TPS of liquid flow battery electrolyte multi-process system t for:

[0070]

[0071] In the formula, Indicates the pump frequency setting value of all cathode storage tanks in the same electrical string process system; Indicates the pump frequency setting value of all negative electrode storage tanks in the same electrical string process system; Indicates the outlet valve opening setting value of all positive / negative storage tanks in the same electrical string process system; Indicates the overflow valve opening setting value of all positive / negative storage tanks in the same electrical string process system; It represents the operating power setting value of each thermal management system equipped with the same electrical string process system; t represents the time step; N represents the total number of the same electrical string process system; M represents the total number of thermal management systems in the same electrical string process system.

[0072] In a possible implementation, the optimization objectives of achieving balanced control of the multi-process system of the electrolyte of the flow battery include: minimizing the difference between the electrolyte temperature of the positive and negative electrode storage tanks and the target temperature, minimizing the temperature balance of the electrolyte of the positive and negative electrode storage tanks, minimizing the balance of the open circuit voltage, minimizing the balance of the electrolyte level of the positive and negative electrode storage tanks, and minimizing the total power of the pump valve and thermal management system;

[0073] The sub-optimization function of the difference between the electrolyte temperature of the positive and negative tanks and the target temperature is expressed as:

[0074]

[0075] In the formula, Respectively represent the upper and lower limits of the given target temperature range; T t i Indicates the electrolyte temperature value of any positive or negative electrode storage tank; Respectively represent the upper and lower limits of the temperature acquisition range, N represents the total number of process systems of the same electrical string;

[0076] The optimization function of the electrolyte temperature balance property of the positive and negative electrode storage tanks is expressed as:

[0077]

[0078] In the formula, Indicates the electrolyte temperature balance index of the positive and negative electrode storage tanks in the same process system. Indicates the electrolyte temperature balance index of the positive electrode storage tank of N process systems, It represents the electrolyte temperature balance index of the negative electrode storage tanks of N process systems; ω T ,ρ T Indicates that different indicators are in the overall The proportion of indicators; They represent the upper and lower limits of the temperature acquisition range respectively; N represents the total number of process systems of the same electrical string; It represents the average temperature value of all cathode storage tanks in the same electrical string process system; It represents the average temperature value of all negative electrode storage tanks in the same electrical string process system;

[0079] The open circuit voltage balance property optimization function is expressed as:

[0080]

[0081] In the formula, It represents the mean value of the open circuit voltage of the process system; They represent the upper and lower limits of the open circuit voltage acquisition range respectively;

[0082] The optimization function of the electrolyte temperature balance property of the positive and negative electrode storage tanks is expressed as:

[0083]

[0084] In the formula, It indicates the average value of the liquid level of all cathode storage tanks in the same electrical string process system; It indicates the average value of the liquid level of all negative electrode storage tanks in the same electrical string process system; Respectively represent the upper and lower limits of the liquid level acquisition range;

[0085] The total power sub-optimization function of the pump valve and thermal management system is expressed as:

[0086]

[0087] In the formula, TS represents the time interval within 1 time step t; Indicates the power of the positive and negative electrode pumps; Indicates the power of normal operation of the outlet valve and the relief valve; Indicates the operating power of the thermal management system; E max Indicates the set maximum tolerable energy consumption value.

[0088] In a possible implementation, the training unit includes:

[0089] The integration module is used to integrate all optimization objectives to form a reward function:

[0090]

[0091] The generation module is used to generate the loss function of the equilibrium control base model according to the reward function:

[0092]

[0093] In the formula, represents the sub-optimization function of the difference between the electrolyte temperature of the positive and negative electrode storage tanks and the target temperature; Represents the optimization function of the temperature balance of the electrolyte in the positive and negative electrode tanks; represents the open circuit voltage balance property optimization function; E represents the optimization function of the temperature balance of the electrolyte in the positive and negative electrode tanks; t represents the total power sub-optimization function of the pump, valve and thermal management system; α, β, ε, η, and λ represent the proportion of different optimization objectives in the overall objective.

[0094] According to one aspect of the present disclosure, there is provided a device, comprising:

[0095] Processor and memory;

[0096] The memory is used to store a computer program, and the processor calls the computer program stored in the memory to execute any of the above-mentioned liquid flow battery electrolyte balancing control methods.

[0097] According to one aspect of the present disclosure, a computer-readable storage medium is provided, in which a computer program is stored. When the computer program is executed by a processor, the processor is enabled to execute any of the above-mentioned methods for controlling electrolyte balancing of a flow battery.

[0098] The present disclosure has the following beneficial effects: First, the present disclosure can effectively solve the problem of electrolyte temperature control in flow batteries, improve the efficiency and life of batteries, and has important significance for the field of battery manufacturing. Secondly, the present disclosure can achieve consistency and stability control of electrolyte temperature, energy, and liquid level in all process systems. For the field of power energy storage, this can improve the stability and reliability of the energy storage system, thereby improving the operating efficiency of the power system; finally, the present disclosure can effectively utilize the energy of the thermal management system and pumps and valves to reduce energy consumption. For the field of industrial thermal management, this can reduce energy waste and improve energy utilization efficiency.

[0099] The details of one or more embodiments of the present application are presented in the following drawings and descriptions. Other features and advantages of the present application will become apparent from the accompanying drawings. It should be understood that the above general description and the detailed descriptions below are only exemplary and explanatory and cannot limit the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0100] The accompanying drawings herein are incorporated into the specification and constitute a part of the specification, illustrate embodiments consistent with the present disclosure, and together with the specification are used to explain the principles of the present disclosure. Obviously, the accompanying drawings described below are only some embodiments of the present disclosure, and for ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without creative work.

[0101] Figure 1is a flow chart of a flow battery electrolyte equalization control method of the present exemplary embodiment;

[0102] Figure 2 is a schematic diagram of a piping system of this exemplary embodiment;

[0103] Figure 3 is a schematic diagram of a thermal management heat exchange system of this exemplary embodiment;

[0104] Figure 4 is a block diagram of a flow battery electrolyte equalization control system of the present exemplary embodiment;

[0105] Figure 5 It is a schematic diagram of the structure of a device of this exemplary embodiment. DETAILED DESCRIPTION

[0106] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in a variety of forms and should not be construed as being limited to the examples set forth herein; on the contrary, these embodiments are provided so that the present disclosure will be more comprehensive and complete, and the concepts of the example embodiments are fully conveyed to those skilled in the art. The described features, structures, or characteristics may be combined in one or more embodiments in any suitable manner. In the following description, many specific details are provided to provide a full understanding of the embodiments of the present disclosure. However, those skilled in the art will appreciate that the technical solutions of the present disclosure may be practiced while omitting one or more of the specific details, or other methods, components, devices, steps, etc. may be adopted. In other cases, known technical solutions are not shown or described in detail to avoid obscuring various aspects of the present disclosure.

[0107] In addition, the accompanying drawings are only schematic illustrations of the present disclosure and are not necessarily drawn to scale. The same reference numerals in the figures represent the same or similar parts, and thus their repeated description will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities and do not necessarily correspond to physically or logically independent entities. These functional entities can be implemented in software form, or implemented in one or more hardware units or integrated circuits, or implemented in different networks and / or processor devices and / or microcontroller devices.

[0108] The flowcharts shown in the accompanying drawings are only exemplary and do not necessarily include all the steps. For example, some steps may be decomposed, while some steps may be combined or partially combined, so the actual execution order may change according to the actual situation.

[0109] The terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the terms used in this way can be interchanged where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein, for example.

[0110] In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product, or apparatus comprising a series of steps or sub-modules is not necessarily limited to those steps or sub-modules explicitly listed, but may include other steps or sub-modules not explicitly listed or inherent to these processes, methods, products, or apparatuses.

[0111] Figure 1 is a flow chart of a flow battery electrolyte equalization control method of this exemplary embodiment. Figure 1 As shown, an exemplary embodiment of the present disclosure provides a flow battery electrolyte balancing control method, comprising:

[0112] Obtain the state space of the multi-process system of flow battery electrolyte;

[0113] Match the state space of the flow battery electrolyte multi-process system with the input dimension of the neural network, output the behavior space of the flow battery electrolyte multi-process system, and form a balanced control base model;

[0114] Set optimization goals to achieve balanced control of multi-process systems for flow battery electrolytes;

[0115] The balanced control base model is trained based on the optimization target to form a balanced control model.

[0116] This embodiment can achieve consistency and stability control of the electrolyte temperature, liquid level, and energy of all process systems; it takes into account the differences in the electrolyte, liquid level, and energy characteristics of different process systems; it can effectively utilize the energy of the thermal management system, avoid reducing the system's charging and discharging capacity and efficiency, and avoid causing waste of system configuration capacity and energy; it can simultaneously solve the problems of energy balance and liquid level balance between different process systems while achieving temperature balance.

[0117] This embodiment mainly adopts the following technical means to achieve the above purpose:

[0118] Build a complete set of flow battery electrolyte balance control system, including temperature balance, liquid level balance and energy balance. The system includes storage tanks, pipelines and thermal management systems of multiple process systems. By setting temperature sensors at various key locations, the temperature of the electrolyte and the temperature of the supply and return water of the thermal management system, the tank level, OCV voltage (Open Circuit Voltage, open circuit voltage), etc. are monitored in real time.

[0119] Specifically, all positive electrode storage tanks of multiple process systems need to be interconnected to form a liquid flow loop, and the same is true for all negative electrode storage tanks. In this embodiment, the same set of positive and negative electrode storage tanks do not need to be interconnected, and the same applies to multiple sets of positive and negative electrode storage tanks. Figure 2 ), near the original pump outlet pipeline at the bottom of the tank, set up the liquid outlet connecting pipeline of all tanks, and set up an outlet valve on each pump outlet pipeline, and select the outlet tank by controlling the outlet valve switch. Set up a liquid connecting pipeline on the top of the tank, and control the direction of the reflux liquid by controlling the switch of the overflow valve near each tank. The overflow valve should preferably be lower than the normal operating tank liquid level of the energy storage system.

[0120] Thermal management system deployment example Figure 3 The principle of the thermal management system is the heat exchange system design, which integrates compressors, dry coolers, electric heating, medium pumps, supply and return liquid temperature, pressure instruments and other equipment, and has working modes such as cooling, heating, and self-circulation. The heat pump equipment heats or cools the water system heat exchange medium, and transmits the medium to the heat exchanger inside each storage tank through the integrated circulation pump and closed pipeline for heat exchange, and finally flows back to the heat pump equipment.

[0121] Each storage tank is equipped with a tank liquid temperature sensor and a liquid level height meter, and each process system is equipped with an OCV battery voltage sensor, which can obtain the temperature and liquid level information of the relevant storage tanks and the open circuit voltage of each process system in real time.

[0122] In particular, in order to save system construction and operation and maintenance costs, the pumps, valves, and instruments involved in this embodiment are original system facilities, and most of the pipelines involved are original system facilities, with relatively small modifications. Therefore, this embodiment is designed Figure 2 The related liquid level, energy and temperature balance only operate during the non-charging and discharging period and not simultaneously with charging and discharging.

[0123] This embodiment targets the process systems on the same electrical string and adopts the reinforcement learning doubledqn algorithm to process and analyze the collected temperature, liquid level, OCV voltage data, pump valve, and thermal management system energy consumption. By adjusting the cooling and heating standby conditions, operating power, and the electric regulating valve opening and pump frequency settings on the electrolyte pipeline, balanced control of electrolyte temperature, liquid level, and energy is achieved while saving energy.

[0124] Specifically, the state space includes the electrolyte temperature (T) and liquid level (L) of each electrolyte storage tank in the multi-process system of the flow battery electrolyte, and the open circuit voltage (V) of the process system in the same electrical string;

[0125] The behavior space includes the given pump frequency (FQS), outlet valve and overflow valve opening (PVS) of each electrolyte storage tank of the liquid flow battery electrolyte multi-process system, and the thermal management system power (TPS).

[0126] Specifically, in the flow battery electrolyte balance control method:

[0127] The electrolyte temperature T of each electrolyte storage tank in the multi-process system of liquid flow battery electrolyte t for:

[0128]

[0129] The electrolyte level L of each electrolyte storage tank in the multi-process system of liquid flow battery electrolyte t for:

[0130]

[0131] In the multi-process system of liquid flow battery electrolyte, the open circuit voltage V of the process system in the same electrical string t for:

[0132] V t =(V t 1 ,V t 2 ,L,V t i ),i∈(1,2,L,N);

[0133] Where, T t po Indicates the temperature value of all cathode storage tanks in the same electrical string process system; T t ne Represents the temperature value of all negative electrode storage tanks in the same electrical string process system; t represents the time step; (t∈N+, the time granularity of the time step depends on the shortest data acquisition cycle); N represents the total number of sets of the same electrical string process system; Indicates the liquid level value of all cathode storage tanks in the same electrical string process system; Indicates the liquid level value of all negative electrode storage tanks in the same electrical string process system;

[0134] It is worth noting that in order to eliminate the influence of the original data magnitude on the algorithm, the following homogenization algorithm is used to unify the dimensions (data normalization):

[0135]

[0136] Among them, x represents the real-time value of any state evaluation point, L scal Indicates the lower limit of the evaluation point range (reference collection point instrument range), H scal Indicates the upper limit of the evaluation point range (reference collection point instrument range), X scal Represents the result after normalization of x data.

[0137] In summary, the state space (S) of this embodiment is expressed as:

[0138]

[0139] Given pump frequency FQS for each electrolyte tank in the multi-process system of flow battery electrolyte t for:

[0140]

[0141] PVS of the opening of the outlet valve and overflow valve of each electrolyte storage tank in the multi-process system of liquid flow battery electrolyte t for:

[0142]

[0143] Thermal management system power TPS of liquid flow battery electrolyte multi-process system t for:

[0144]

[0145] In the formula, Indicates the pump frequency setting value of all cathode storage tanks in the same electrical string process system; Indicates the pump frequency setting value of all negative electrode storage tanks in the same electrical string process system; Indicates the outlet valve opening setting value of all positive / negative storage tanks in the same electrical string process system; Indicates the overflow valve opening setting value of all positive / negative storage tanks in the same electrical string process system; It represents the operating power setting value of each thermal management system equipped with the same electrical string process system; t represents the time step (t∈N+, the time granularity of the time step depends on the shortest data acquisition cycle); N represents the total number of the same electrical string process system, and M represents the total number of thermal management systems in the same electrical string process system.

[0146] In summary, the behavior space (A) of this embodiment is expressed as:

[0147] A=(FQS t ,PVS t ,TPS t),t∈(1,2,…∞).

[0148] It is worth noting that, in order to adapt to the physical characteristics and service life requirements of pump equipment, valve equipment, and thermal management equipment, this embodiment designs the restriction measures between the time steps of the control quantity to prevent the control output time steps of the behavior space from being too different. The following takes the pump frequency (FQS) control output restriction measures as an example for explanation, and the control output restriction principles of the valve opening (PVS) and the thermal management system power (TPS) are the same.

[0149]

[0150] Among them, a is the given maximum allowable pump frequency value; d is the given minimum allowable pump frequency value; b is the given maximum value of the pump frequency difference between steps; c is the given minimum value of the pump frequency difference between steps.

[0151] Specifically, the optimization goals of achieving balanced control of the multi-process system of the electrolyte of the flow battery include: minimizing the difference between the electrolyte temperature of the positive and negative electrode storage tanks and the target temperature, minimizing the temperature balance of the electrolyte of the positive and negative electrode storage tanks, minimizing the balance of the open circuit voltage, minimizing the balance of the electrolyte level of the positive and negative electrode storage tanks, and minimizing the total power of the pump valve and thermal management system; according to these minimization goals and setting the importance coefficient of each indicator, the algorithm reward function is designed, specifically:

[0152] The sub-optimization function of the difference between the electrolyte temperature of the positive and negative tanks and the target temperature is expressed as:

[0153]

[0154] In the formula, Respectively represent the upper and lower limits of the given target temperature range; T t i Indicates the electrolyte temperature value of any positive or negative electrode storage tank; Respectively represent the upper and lower limits of the temperature acquisition range, The target temperature difference is planned to be between 0 and 1; N represents the total number of process systems of the same electrical string;

[0155] The optimization function of the electrolyte temperature balance property of the positive and negative electrode storage tanks is expressed as:

[0156]

[0157] It is worth noting that the optimization objective consists of three parts, including: the electrolyte temperature balance index of the positive and negative storage tanks in the same process system, the electrolyte temperature balance index of the positive storage tanks of N process systems, and the electrolyte temperature balance index of the negative storage tanks of N process systems. ω T ,ρ TThe three optimization indicators in Table 3 are connected to achieve temperature balance within and between process systems. Specifically, in the formula, Indicates the electrolyte temperature balance index of the positive and negative electrode storage tanks in the same process system. Indicates the electrolyte temperature balance index of the positive electrode storage tank of N process systems, It represents the electrolyte temperature balance index of the negative electrode storage tanks of N process systems; ω T ,ρ T Indicates that different indicators are in the overall The proportion of indicators; They represent the upper and lower limits of the temperature acquisition range respectively; N represents the total number of process systems of the same electrical string; It represents the average temperature value of all cathode storage tanks in the same electrical string process system; It represents the average temperature value of all negative electrode storage tanks in the same electrical string process system; the electrolyte temperature balance index of the positive and negative electrode storage tanks is planned to be between 0 and 1, and the part exceeding it is truncated and not considered.

[0158] The open circuit voltage balance property optimization function is expressed as:

[0159]

[0160] In the formula, It represents the mean value of the open circuit voltage of the process system; They represent the upper and lower limits of the open circuit voltage acquisition range respectively;

[0161] The design of the liquid level balance of the positive and negative electrode storage tanks is consistent with the optimization goal of the electrolyte temperature balance of the positive and negative electrode storage tanks. The optimization function of the electrolyte temperature balance of the positive and negative electrode storage tanks is expressed as:

[0162]

[0163] In the formula, It indicates the average value of the liquid level of all cathode storage tanks in the same electrical string process system; It indicates the average value of the liquid level of all negative electrode storage tanks in the same electrical string process system; Respectively represent the upper and lower limits of the liquid level acquisition range;

[0164] The total power sub-optimization function of the pump valve and thermal management system is expressed as:

[0165]

[0166] In the formula, TS represents the time interval within one time step t. The time unit here is set to seconds (the unit can be converted to hours according to the actual time interval used). It is used to calculate the integral of power and time within a time step, so as to obtain real-time energy consumption data. Indicates the power of the positive and negative electrode pumps; Indicates the power of normal operation of the outlet valve and the relief valve; Indicates the operating power of the thermal management system; E max Indicates the maximum tolerable energy consumption value, which is used to plan the power to the range of 0 to 1.

[0167] In summary, all optimization objectives are integrated to form the reward function of this technical solution:

[0168]

[0169] Among them, α, β, ε, η, and λ represent the proportion of different optimization objectives in the overall objective. By adjusting the size of the proportion coefficient, different optimization objectives can be emphasized in algorithm optimization. Adding a negative sign to the reward function can transform the minimization optimization objective into the maximization optimization objective.

[0170] The overall algorithm design of this embodiment is described as follows:

[0171] (1) In reinforcement learning, the Q function is a function that evaluates the quality of actions (control outputs) in the behavior space. It is also the future cumulative value of the reward function in the model. By continuously selecting actions from the behavior space and updating the Q function, each time the action that maximizes the Q function is selected, thereby maximizing the overall target reward value of the sequential decision-making behavior. That is:

[0172]

[0173] Among them, γ is the discount factor, which indicates the importance attached to future rewards (environmental impact); s t ,s t+1 ∈S; a t ,a t+1 ∈A;

[0174] (2) Establishment of Double DQN neural network. The algorithm of this embodiment uses a neural network to fit the Q function, relies on the neural network to update parameters, and realizes the update of the Q function in reinforcement learning. Specifically, it includes the following steps:

[0175] The dimension of the neural network input layer is set to match the state space of the technical solution, that is, the dimension of the state at each time step is the dimension of the neural network input layer (the number of neurons);

[0176] Set the middle layer of the neural network. The number of middle layers (hidden layers) and the number of neurons in each layer can be optimally set through data experiments;

[0177] The dimension of the output layer of the neural network is set to match the behavior space of the technical solution, that is, the dimension of the action at each time step is the dimension of the output layer of the neural network (the number of neurons);

[0178] The activation function of each layer is used to match the output value with the action value. Non-linear activation functions include sigmoid function, ReLU function and Tanh function.

[0179] Since the optimization direction of the neural network is to minimize the loss function, which is opposite to the optimization direction of reinforcement learning to maximize the Q function, the loss function of the neural network is set to:

[0180]

[0181] Two identical neural networks are established, and the behavior value (Q1) is selected from one of the neural networks, and the other is used to update the fitted Q function (Q2). Q2 is updated once per time step, and the weight parameters of Q2 are regularly copied to Q1 (for example, Q2 parameters are copied to Q1 every 100 training time steps), so as to meet the requirements of different update rates and reduce the overestimation of the Q function.

[0182] This embodiment designs a slowly varying physical quantity temperature, and the temperature transfer speed is slow. Therefore, the time granularity TS of each time step t in this embodiment should be reasonably set. It can also be optimized through state folding, which requires synchronously changing the state space dimension and the neural network input layer dimension, the average dimension of the reward function sub-optimization target, etc.

[0183] (3) This embodiment supports full-process online real-time learning. However, due to the safety, stability and other control requirements of the energy storage power site, the algorithm needs to be partially pre-trained and deployed at the project site with pre-trained algorithm parameters to improve the initial stability of the algorithm.

[0184] (4) This embodiment sets a temperature imbalance threshold, a liquid level imbalance threshold, and an OCV voltage imbalance threshold. If any of the three indicators exceeds the limit, the algorithm is activated to perform a balancing process. Under the premise of saving energy consumption, the temperature balance, liquid level balance, and energy (OCV voltage) balance indicators are achieved, thereby maximizing the capacity of the system, reducing non-chemical attenuation, and extending the life of the liquid flow energy storage system.

[0185] This embodiment supports full-process online real-time learning, but due to the safety, stability and other control requirements of the energy storage power site, the algorithm needs to be partially pre-trained and deployed at the project site with pre-trained algorithm parameters to improve the initial stability of the algorithm.

[0186] This embodiment detects the electrolyte temperature of different process system tanks and pipelines, as well as the supply and return water temperature of the thermal management system, and uses the reinforcement learning doubledqn algorithm to achieve accurate control of the electrolyte index balance of all process systems. Biased optimization can be performed by adjusting the weight coefficients of different optimization sub-goals.

[0187] This embodiment sets a temperature imbalance threshold, a liquid level imbalance threshold, and an OCV voltage imbalance threshold. If any of the three indicators exceeds the limit, the algorithm is started to perform a balancing process. Under the premise of saving energy consumption, the temperature balance, liquid level balance, and energy (OCV voltage) balance indicators are achieved, thereby maximizing the capacity of the system, reducing non-chemical attenuation, and extending the life of the liquid flow energy storage system.

[0188] This embodiment applies deep reinforcement learning (DQN) to the electrolyte balancing control of liquid flow batteries, realizing intelligent management. Compared with the existing manual adjustment method, it is more convenient and quick, and also improves the control accuracy and efficiency.

[0189] The electrolyte control method of this embodiment is not only applicable to liquid flow batteries, but can also be applied to other occasions that require precise control, and has wide applicability.

[0190] Figure 4 is a block diagram of a flow battery electrolyte balance control system of this exemplary embodiment, such as Figure 4 As shown, an exemplary embodiment of the present disclosure provides a flow battery electrolyte balancing control system, comprising:

[0191] An acquisition unit 10 is used to acquire a state space of a multi-process system of an electrolyte of a flow battery;

[0192] Establishing unit 20, for matching the state space of the flow battery electrolyte multi-process system with the input dimension of the neural network, outputting the behavior space of the flow battery electrolyte multi-process system, and forming a balanced control base model;

[0193] A setting unit 30, used to set an optimization target for achieving balanced control of a multi-process system of an electrolyte of a flow battery;

[0194] The training unit 40 is used to train the balanced control base model based on the optimization target to form a balanced control model.

[0195] Specifically, the state space includes the electrolyte temperature and liquid level of each electrolyte storage tank in the liquid flow battery electrolyte multi-process system, and the open circuit voltage of the process system in the same electrical string; the behavior space includes the given pump frequency, outlet valve and overflow valve opening of each electrolyte storage tank in the liquid flow battery electrolyte multi-process system, and the thermal management system power.

[0196] Specifically, in the electrolyte balance control system of the flow battery:

[0197] The electrolyte temperature T of each electrolyte storage tank in the multi-process system of liquid flow battery electrolyte t for:

[0198]

[0199] The electrolyte level L of each electrolyte storage tank in the multi-process system of liquid flow battery electrolyte t for:

[0200]

[0201] In the multi-process system of liquid flow battery electrolyte, the open circuit voltage V of the process system in the same electrical string t for:

[0202] V t =(V t 1 ,V t 2 ,L,V t i ),i∈(1,2,L,N);

[0203] Where, T t po Indicates the temperature value of all cathode storage tanks in the same electrical string process system; T t ne It represents the temperature value of all negative electrode storage tanks in the same electrical string process system; t represents the time step; N represents the total number of sets of the same electrical string process system; Indicates the liquid level value of all cathode storage tanks in the same electrical string process system; Indicates the liquid level value of all negative electrode storage tanks in the same electrical string process system;

[0204] Given pump frequency FQS for each electrolyte tank in the multi-process system of flow battery electrolyte t for:

[0205]

[0206] PVS of the opening of the outlet valve and overflow valve of each electrolyte storage tank in the multi-process system of liquid flow battery electrolyte t for:

[0207]

[0208] Thermal management system power TPS of liquid flow battery electrolyte multi-process system t for:

[0209]

[0210] In the formula, Indicates the pump frequency setting value of all cathode storage tanks in the same electrical string process system; Indicates the pump frequency setting value of all negative electrode storage tanks in the same electrical string process system; Indicates the outlet valve opening setting value of all positive / negative storage tanks in the same electrical string process system; Indicates the overflow valve opening setting value of all positive / negative storage tanks in the same electrical string process system; It represents the operating power setting value of each thermal management system equipped with the same electrical string process system; t represents the time step; N represents the total number of the same electrical string process system; M represents the total number of thermal management systems in the same electrical string process system.

[0211] Specifically, the optimization goals of achieving balanced control of the multi-process system of the flow battery electrolyte include: minimizing the difference between the electrolyte temperature of the positive and negative electrode storage tanks and the target temperature, minimizing the temperature balance of the electrolyte of the positive and negative electrode storage tanks, minimizing the balance of the open circuit voltage, minimizing the balance of the electrolyte level of the positive and negative electrode storage tanks, and minimizing the total power of the pump valve and thermal management system;

[0212] The sub-optimization function of the difference between the electrolyte temperature of the positive and negative tanks and the target temperature is expressed as:

[0213]

[0214] In the formula, Respectively represent the upper and lower limits of the given target temperature range; T t i Indicates the electrolyte temperature value of any positive or negative electrode storage tank; Respectively represent the upper and lower limits of the temperature acquisition range, N represents the total number of process systems of the same electrical string;

[0215] The optimization function of the electrolyte temperature balance property of the positive and negative electrode storage tanks is expressed as:

[0216]

[0217] In the formula, Indicates the electrolyte temperature balance index of the positive and negative electrode storage tanks in the same process system. Indicates the electrolyte temperature balance index of the positive electrode storage tank of N process systems, It represents the electrolyte temperature balance index of the negative electrode storage tanks of N process systems; ω T ,ρ T Indicates that different indicators are in the overall The proportion of indicators; They represent the upper and lower limits of the temperature acquisition range respectively; N represents the total number of process systems of the same electrical string; It represents the average temperature value of all cathode storage tanks in the same electrical string process system; It represents the average temperature value of all negative electrode storage tanks in the same electrical string process system;

[0218] The open circuit voltage balance property optimization function is expressed as:

[0219]

[0220] In the formula, It represents the mean value of the open circuit voltage of the process system; They represent the upper and lower limits of the open circuit voltage acquisition range respectively;

[0221] The optimization function of the electrolyte temperature balance property of the positive and negative electrode storage tanks is expressed as:

[0222]

[0223] In the formula, It indicates the average value of the liquid level of all cathode storage tanks in the same electrical string process system; It indicates the average value of the liquid level of all negative electrode storage tanks in the same electrical string process system; Respectively represent the upper and lower limits of the liquid level acquisition range;

[0224] The total power sub-optimization function of the pump valve and thermal management system is expressed as:

[0225]

[0226] In the formula, TS represents the time interval within 1 time step t; Indicates the power of the positive and negative electrode pumps; Indicates the power of normal operation of the outlet valve and the relief valve; Indicates the operating power of the thermal management system; E max Indicates the set maximum tolerable energy consumption value.

[0227] Due to the advanced nature of the present disclosure, it can be widely used in application fields such as battery manufacturing, power energy storage, and industrial thermal management. First, the present disclosure can effectively solve the problem of electrolyte temperature control in flow batteries, improve the efficiency and life of the battery, and is of great significance to the field of battery manufacturing. Secondly, the present disclosure can achieve consistency and stability control of electrolyte temperature, energy, and liquid level in all process systems. For the field of power energy storage, this can improve the stability and reliability of the energy storage system, thereby improving the operating efficiency of the power system. Finally, the present disclosure can effectively utilize the energy of the thermal management system and pumps and valves to reduce energy consumption. For the field of industrial thermal management, this can reduce energy waste and improve energy utilization efficiency. Therefore, the present disclosure has broad market demand and good application prospects.

[0228] Figure 5 Schematic diagram of the structure of a device of this exemplary embodiment. Figure 5 As shown, corresponding to the above-mentioned liquid flow battery electrolyte balancing control method, the present disclosure also provides a device. Since the embodiment of the device is similar to the above-mentioned method embodiment, the description is relatively simple. Please refer to the description of the above-mentioned method embodiment for relevant parts. The device described below is only schematic. The device may include: a processor (processor) 1, a memory (memory) 2 and a communication bus (i.e., the above-mentioned device bus) and a search engine, wherein the processor 1 and the memory 2 communicate with each other through the communication bus and communicate with the outside through the communication interface. The processor 1 can call the logic instructions in the memory 2 to execute the liquid flow battery electrolyte balancing control method.

[0229] In addition, the logic instructions in the above-mentioned memory 2 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on such an understanding, the technical solution of the present disclosure is essentially or the part that contributes to the prior art or the part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the various embodiments of the present disclosure. The aforementioned storage medium includes: a storage chip, a U disk, a mobile hard disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a disk or an optical disk, and other media that can store program codes.

[0230] On the other hand, an embodiment of the present disclosure further provides a processor-readable storage medium, on which a computer program 3 is stored. When the computer program 3 is executed by the processor 1, it is implemented to execute the liquid flow battery electrolyte balancing control method provided in the above embodiments.

[0231] The processor-readable storage medium can be any available medium or data storage device that can be accessed by the processor 1, including but not limited to magnetic storage (such as floppy disks, hard disks, magnetic tapes, magneto-optical disks (MO), etc.), optical storage (such as CD, DVD, BD, HVD, etc.), and semiconductor storage (such as ROM, EPROM, EEPROM, non-volatile memory (NANDFLASH), solid-state drive (SSD)), etc.

[0232] The above are only preferred implementations of the present disclosure, and the protection scope of the present disclosure is not limited to the above embodiments. All technical solutions under the concept of the present disclosure belong to the protection scope of the present disclosure. It should be pointed out that for ordinary technicians in this technical field, some improvements and modifications without departing from the principle of the present disclosure should be regarded as the protection scope of the present disclosure.

Claims

1. A flow battery electrolyte balance control method, characterized in that: include: Obtain the state space of the multi-process system of flow battery electrolyte; Match the state space of the flow battery electrolyte multi-process system with the input dimension of the neural network, output the behavior space of the flow battery electrolyte multi-process system, and form a balanced control base model; Set optimization goals to achieve balanced control of multi-process systems for flow battery electrolytes; The balanced control base model is trained based on the optimization target to form a balanced control model.

2. The method for controlling electrolyte balance of a flow battery according to claim 1, characterized in that: The state space includes the electrolyte temperature and liquid level of each electrolyte storage tank in the multi-process system of the flow battery electrolyte, and the open circuit voltage of the process system in the same electrical string; The behavior space includes the given pump frequency, outlet valve and overflow valve opening of each electrolyte storage tank of the liquid flow battery electrolyte multi-process system, and the power of the thermal management system.

3. The method for controlling electrolyte balance of a flow battery according to claim 2, characterized in that: The electrolyte temperature T of each electrolyte storage tank in the multi-process system of liquid flow battery electrolyte t for: The electrolyte level L of each electrolyte storage tank in the multi-process system of liquid flow battery electrolyte t for: In the multi-process system of liquid flow battery electrolyte, the open circuit voltage V of the process system in the same electrical string t for: V t =(V t 1 ,V t 2 ,L,V t i ),i∈(1,2,L,N); The state space S is expressed as: Where, T t po Indicates the temperature value of all cathode storage tanks in the same electrical string process system; T t ne It represents the temperature value of all negative electrode storage tanks in the same electrical string process system; t represents the time step; N represents the total number of sets of the same electrical string process system; Indicates the liquid level value of all cathode storage tanks in the same electrical string process system; Indicates the liquid level value of all negative electrode storage tanks in the same electrical string process system; T t scal represents the normalized electrolyte temperature of each electrolyte storage tank in the multi-process system of liquid flow battery electrolyte, Normalized electrolyte level of each electrolyte storage tank in the multi-process system of liquid flow battery electrolyte, V t scal Normalized open circuit voltage of the process system in the same electrical string in the multi-process system of liquid flow battery electrolyte; Given pump frequency FQS for each electrolyte tank in the multi-process system of flow battery electrolyte t for: PVS of the opening of the outlet valve and overflow valve of each electrolyte storage tank in the multi-process system of liquid flow battery electrolyte t for: Thermal management system power TPS of liquid flow battery electrolyte multi-process system t for: The behavior space A is expressed as: A=(FQS t ,PVS t ,TPS t ),t∈(1,2,…∞); In the formula, Indicates the pump frequency setting value of all cathode storage tanks in the same electrical string process system; Indicates the pump frequency setting value of all negative electrode storage tanks in the same electrical string process system; Indicates the outlet valve opening setting value of all positive / negative storage tanks in the same electrical string process system; Indicates the overflow valve opening setting value of all positive / negative storage tanks in the same electrical string process system; It represents the operating power setting value of each thermal management system equipped with the same electrical string process system; t represents the time step; N represents the total number of the same electrical string process system; M represents the total number of thermal management systems in the same electrical string process system.

4. The method for controlling electrolyte balance of a flow battery according to claim 1, characterized in that: The optimization goals of achieving balanced control of the multi-process system of liquid flow battery electrolyte include: minimizing the difference between the electrolyte temperature of the positive and negative storage tanks and the target temperature, minimizing the temperature balance of the electrolyte of the positive and negative storage tanks, minimizing the balance of the open circuit voltage, minimizing the balance of the electrolyte level of the positive and negative storage tanks, and minimizing the total power of the pump valve and thermal management system; The sub-optimization function of the difference between the electrolyte temperature of the positive and negative tanks and the target temperature is expressed as: In the formula, Respectively represent the upper and lower limits of the given target temperature range; Indicates the electrolyte temperature value of any positive or negative electrode storage tank; Respectively represent the upper and lower limits of the temperature acquisition range, N represents the total number of process systems of the same electrical string; The optimization function of the temperature balance property of the electrolyte in the positive and negative electrode storage tanks is expressed as: In the formula, Indicates the electrolyte temperature balance index of the positive and negative electrode storage tanks in the same process system. Indicates the electrolyte temperature balance index of the positive electrode storage tank of N process systems, It represents the electrolyte temperature balance index of the negative electrode storage tanks of N process systems; ω T ,ρ T Indicates that different indicators are in the overall The proportion of indicators; They represent the upper and lower limits of the temperature acquisition range respectively; N represents the total number of process systems of the same electrical string; It represents the average temperature value of all cathode storage tanks in the same electrical string process system; It represents the average temperature value of all negative electrode storage tanks in the same electrical string process system; The open circuit voltage balance property optimization function is expressed as: In the formula, E max It represents the mean value of the open circuit voltage of the process system; They represent the upper and lower limits of the open circuit voltage acquisition range respectively; The optimization function of the electrolyte temperature balance property of the positive and negative electrode storage tanks is expressed as: In the formula, It indicates the average value of the liquid level of all cathode storage tanks in the same electrical string process system; It indicates the average value of the liquid level of all negative electrode storage tanks in the same electrical string process system; Respectively represent the upper and lower limits of the liquid level acquisition range; The total power sub-optimization function of the pump valve and thermal management system is expressed as: In the formula, TS represents the time interval within 1 time step t; Indicates the power of the positive and negative electrode pumps; Indicates the power of normal operation of the outlet valve and the relief valve; Indicates the operating power of the thermal management system; E max Indicates the set maximum tolerable energy consumption value.

5. The method for controlling electrolyte balance of a flow battery according to claim 1, characterized in that: Training the balanced control base model based on the optimization target to form a balanced control model includes: Integrate all optimization objectives to form a reward function: According to the reward function, the loss function of the equilibrium control base model is generated: In the formula, represents the sub-optimization function of the difference between the electrolyte temperature of the positive and negative electrode storage tanks and the target temperature; Represents the optimization function of the temperature balance of the electrolyte in the positive and negative electrode tanks; It represents the optimization function of open circuit voltage balance property; E represents the optimization function of the temperature balance of the electrolyte in the positive and negative electrode tanks; t represents the total power sub-optimization function of the pump, valve and thermal management system; α, β, ε, η, and λ represent the proportion of different optimization objectives in the overall objective.

6. A flow battery electrolyte balance control system, characterized in that: include: An acquisition unit, used for acquiring a state space of a multi-process system of an electrolyte of a flow battery; Establishing a unit for matching the state space of the flow battery electrolyte multi-process system with the input dimension of the neural network, outputting the behavior space of the flow battery electrolyte multi-process system, and forming a balanced control base model; A setting unit, used to set an optimization target for realizing balanced control of a multi-process system of an electrolyte of a flow battery; The training unit is used to train the balanced control base model based on the optimization target to form a balanced control model.

7. The electrolyte balance control system of a flow battery according to claim 6, characterized in that: The state space includes the electrolyte temperature and liquid level of each electrolyte storage tank in the multi-process system of the flow battery electrolyte, and the open circuit voltage of the process system in the same electrical string; The behavior space includes the given pump frequency, outlet valve and overflow valve opening of each electrolyte storage tank of the liquid flow battery electrolyte multi-process system, and the power of the thermal management system.

8. The electrolyte balance control system of a flow battery according to claim 7, characterized in that: The electrolyte temperature T of each electrolyte storage tank in the multi-process system of liquid flow battery electrolyte t for: The electrolyte level L of each electrolyte storage tank in the multi-process system of liquid flow battery electrolyte t for: In the multi-process system of liquid flow battery electrolyte, the open circuit voltage V of the process system in the same electrical string t for: V t =(V t 1 ,V t 2 ,L,V t i ),i∈(1,2,L,N); The state space S is expressed as: Where, T t po Indicates the temperature value of all cathode storage tanks in the same electrical string process system; T t ne It represents the temperature value of all negative electrode storage tanks in the same electrical string process system; t represents the time step; N represents the total number of sets of the same electrical string process system; Indicates the liquid level value of all cathode storage tanks in the same electrical string process system; Indicates the liquid level value of all negative electrode storage tanks in the same electrical string process system; T t scal represents the normalized electrolyte temperature of each electrolyte storage tank in the multi-process system of liquid flow battery electrolyte, Normalized electrolyte level of each electrolyte storage tank in the multi-process system of liquid flow battery electrolyte, V t scal Normalized open circuit voltage of the process system in the same electrical string in the multi-process system of liquid flow battery electrolyte; Given pump frequency FQS for each electrolyte tank in the multi-process system of flow battery electrolyte t for: PVS of the opening of the outlet valve and overflow valve of each electrolyte storage tank in the multi-process system of liquid flow battery electrolyte t for: Thermal management system power TPS of liquid flow battery electrolyte multi-process system t for: The behavior space A is expressed as: A=(FQS t ,PVS t ,TPS t ),t∈(1,2,…∞); In the formula, Indicates the pump frequency setting value of all cathode storage tanks in the same electrical string process system; Indicates the pump frequency setting value of all negative electrode storage tanks in the same electrical string process system; Indicates the outlet valve opening setting value of all positive / negative storage tanks in the same electrical string process system; Indicates the overflow valve opening setting value of all positive / negative storage tanks in the same electrical string process system; It represents the operating power setting value of each thermal management system equipped with the same electrical string process system; t represents the time step; N represents the total number of the same electrical string process system, and M represents the total number of thermal management systems in the same electrical string process system.

9. The liquid flow battery electrolyte equalization control system according to claim 6, characterized in that: The optimization goals of achieving balanced control of the multi-process system of liquid flow battery electrolyte include: minimizing the difference between the electrolyte temperature of the positive and negative storage tanks and the target temperature, minimizing the temperature balance of the electrolyte of the positive and negative storage tanks, minimizing the balance of the open circuit voltage, minimizing the balance of the electrolyte level of the positive and negative storage tanks, and minimizing the total power of the pump valve and thermal management system; The sub-optimization function of the difference between the electrolyte temperature of the positive and negative tanks and the target temperature is expressed as: In the formula, Respectively represent the upper and lower limits of the given target temperature range; T t i Indicates the electrolyte temperature value of any positive or negative electrode storage tank; Respectively represent the upper and lower limits of the temperature acquisition range, N represents the total number of process systems of the same electrical string; The optimization function of the electrolyte temperature balance property of the positive and negative electrode storage tanks is expressed as: In the formula, Indicates the electrolyte temperature balance index of the positive and negative electrode storage tanks in the same process system. Indicates the electrolyte temperature balance index of the positive electrode storage tank of N process systems, It represents the electrolyte temperature balance index of the negative electrode storage tanks of N process systems; ω T ,ρ T Indicates that different indicators are in the overall The proportion of indicators; They represent the upper and lower limits of the temperature acquisition range respectively; N represents the total number of process systems of the same electrical string; It represents the average temperature value of all cathode storage tanks in the same electrical string process system; It represents the average temperature value of all negative electrode storage tanks in the same electrical string process system; The open circuit voltage balance property optimization function is expressed as: In the formula, E max It represents the mean value of the open circuit voltage of the process system; They represent the upper and lower limits of the open circuit voltage acquisition range respectively; The optimization function of the electrolyte temperature balance property of the positive and negative electrode storage tanks is expressed as: In the formula, It indicates the average value of the liquid level of all cathode storage tanks in the same electrical string process system; It indicates the average value of the liquid level of all negative electrode storage tanks in the same electrical string process system; Respectively represent the upper and lower limits of the liquid level acquisition range; The total power sub-optimization function of the pump valve and thermal management system is expressed as: In the formula, TS represents the time interval within 1 time step t; Indicates the power of the positive and negative electrode pumps; Indicates the power of normal operation of the outlet valve and the relief valve; Indicates the operating power of the thermal management system; E max Indicates the set maximum tolerable energy consumption value.

10. The liquid flow battery electrolyte balance control system according to claim 6, characterized in that: The training modules include: The integration module is used to integrate all optimization objectives to form a reward function: The generation module is used to generate the loss function of the equilibrium control base model according to the reward function: In the formula, represents the sub-optimization function of the difference between the electrolyte temperature of the positive and negative electrode storage tanks and the target temperature; Represents the optimization function of the temperature balance of the electrolyte in the positive and negative electrode tanks; represents the open circuit voltage balance property optimization function; E represents the optimization function of the temperature balance of the electrolyte in the positive and negative electrode tanks; t represents the total power sub-optimization function of the pump, valve and thermal management system; α, β, ε, η, and λ represent the proportion of different optimization objectives in the overall objective.

11. A device, characterized in that: include: Processor and memory; The memory is used to store a computer program, and the processor calls the computer program stored in the memory to execute the liquid flow battery electrolyte balancing control method according to any one of claims 1 to 5.

12. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the processor is enabled to execute the liquid flow battery electrolyte balancing control method according to any one of claims 1 to 5.

Images