Charge state balance control method of organic flow battery energy storage system

Abstract

The invention provides a state-of-charge balance control method of an organic flow battery energy storage system, and relates to the technical field of state-of-charge control of battery energy storage systems, and the method comprises the steps: obtaining related parameters of the organic flow battery energy storage system; a BPNN model is constructed; through a BPNN model, outputting a state-of-charge estimation value of each battery module; determining a charge state deviation according to the charge state estimation value; determining a voltage regulation factor of a DC-DC converter corresponding to each battery module based on the charge state deviation; determining a reference voltage of the DC-DC converter; adjusting the output voltage of the DC-DC converter through a voltage PI controller according to the reference voltage; and determining the output power of each battery module according to the adjusted output voltage so as to realize state-of-charge balance control. According to the invention, the over-charge or over-discharge phenomenon of the battery module is reduced, and overload and equipment damage caused by SOC imbalance are avoided.

Description

Technical Field

[0001] The present invention relates to the technical field of charge state control of a battery energy storage system, and in particular to a charge state balancing control method for an organic liquid flow battery energy storage system. Background Art

[0002] The state of charge (SOC) balancing control method of the organic liquid flow battery energy storage system refers to real-time monitoring of the state of charge of each battery module and dynamically adjusting the voltage and power output of each module based on this information, thereby ensuring that the SOC values of each battery module in the system tend to be consistent, avoiding excessive discharge or charging of certain battery modules, and thus improving the performance, efficiency and life of the system. The organic liquid flow battery energy storage system is a battery system that uses liquid electrolytes and organic materials as active substances for energy storage and release. It has high energy density, long life and good scalability.

[0003] SOC differences between battery modules can lead to energy imbalance, thus affecting the performance and life of the entire system. Due to the different health conditions, aging levels, and capacities of each battery module, if SOC balancing is not performed in a timely manner, some batteries may be over-discharged or over-charged prematurely, resulting in reduced efficiency and damage to battery life. Through effective state of charge balancing control, the SOC of each module can be ensured to remain consistent, thereby optimizing energy utilization, extending system life, and improving the overall stability and reliability of the energy storage system.

[0004] However, existing state-of-charge balancing control methods rely solely on the battery voltage or current SOC for regulation, resulting in energy imbalance and easily accelerating the aging of battery modules. Due to the lack of accurate SOC estimation and control, energy distribution between battery modules is often unbalanced. Some battery modules may be over-discharged or over-charged, while other battery modules are not fully utilized, resulting in energy waste and reduced system efficiency. Summary of the Invention

[0005] In view of the above-mentioned deficiencies in the prior art, the purpose of the embodiments of the present invention is to provide a state of charge balancing control method for an organic liquid flow battery energy storage system, which can solve the technical problems that the existing state of charge balancing control method only relies on the battery voltage or current SOC for adjustment, resulting in energy imbalance, easily accelerating the aging of the battery module, lacking accurate SOC estimation and control, and often unbalanced energy distribution between battery modules. Some battery modules may be over-discharged or over-charged, while other battery modules are not fully utilized, resulting in energy waste and reduced system efficiency.

[0006] According to a first aspect of an embodiment of the present invention, a method for controlling a state of charge (SOC) of an organic flow battery energy storage system is provided, comprising:

[0007] S1: Obtain relevant parameters of the organic liquid flow battery energy storage system, wherein the organic liquid flow battery energy storage system includes a plurality of battery modules;

[0008] S2: Build BPNN model;

[0009] S3: using the relevant parameters as input, outputting an estimated state of charge value of each battery module through the BPNN model;

[0010] S4: determining a state of charge deviation based on the state of charge estimate;

[0011] S5: Determine a voltage regulation factor of a DC-DC converter corresponding to each of the battery modules based on the state of charge deviation;

[0012] S6: Determine a reference voltage of the DC-DC converter according to the voltage adjustment factor;

[0013] S7: Regulating the output voltage of the DC-DC converter through a voltage PI controller according to the reference voltage;

[0014] S8: Determine the output power of each battery module according to the adjusted output voltage to achieve charge state balance control.

[0015] The beneficial effects brought about by the technical solution provided by the embodiment of the present invention include at least:

[0016] In an embodiment of the present invention, the BPNN model can accurately estimate the SOC of each battery module based on the input battery parameters, thereby improving the accuracy of SOC balancing control. Based on the deviation between the SOC estimation value and the target SOC value, the voltage regulation factor is calculated to dynamically adjust the voltage reference value of each battery module. According to the current SOC difference, it is possible to avoid excessive discharge or charging of certain battery modules, extend battery life, and optimize battery utilization efficiency. By adjusting the duty cycle of the DC-DC converter through the PI controller, precise voltage regulation can be achieved to ensure that the output voltage of the battery module always remains within the ideal range, reducing energy waste and improving the overall efficiency of the system. By determining the output power of each battery module based on the adjusted voltage output, it is possible to ensure that the energy distribution of all modules is balanced, reduce overcharging or over-discharging of the battery modules, ensure the stability of the system during long-term operation, and avoid load overload and equipment damage caused by SOC imbalance. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The accompanying drawings are only for the purpose of illustrating specific embodiments and are not to be considered as limiting the present invention. Throughout the drawings, the same reference symbols represent the same components. Obviously, the drawings described below are only some embodiments of the present invention. It is clear that those skilled in the art can derive other drawings based on these drawings without inventive effort.

[0018] Figure 1 It is a flow chart of a method for controlling the state of charge balance of an organic liquid flow battery energy storage system provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0019] In order to enable those skilled in the art to better understand the technical solutions in the embodiments of the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the embodiments described are part of the embodiments of the present invention, rather than all of the embodiments. It should be understood that these descriptions are merely exemplary and are not intended to limit the scope of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative work should fall within the scope of protection of the present invention.

[0020] The state of charge balancing control method for an organic flow battery energy storage system provided by an embodiment of the present invention is described in detail below with reference to the accompanying drawings through specific embodiments and application scenarios.

[0021] Reference Manual Figure 1 , which shows a flow chart of a state of charge balancing control method for an organic liquid flow battery energy storage system provided by an embodiment of the present invention.

[0022] An embodiment of the present invention provides a method for controlling the state of charge balance of an organic flow battery energy storage system, which may include the following steps:

[0023] S1: Obtain relevant parameters of an organic liquid flow battery energy storage system, wherein the organic liquid flow battery energy storage system includes multiple battery modules.

[0024] The Organic Redox Flow Battery (ORFB) is a battery system that uses liquid electrolytes and organic materials as active substances to store and release electrical energy. It boasts high energy density, long life, and good scalability. The battery module is the basic unit in an ORFB system. Each module includes a battery stack, electrolyte, electrodes, and other components for energy storage and release.

[0025] In a possible implementation, the relevant parameters include current parameters and voltage parameters.

[0026] Among them, current parameters refer to data related to the current in the system, usually including the charging and discharging currents of the battery module. Current parameters reflect the charge transfer state of the battery module during operation and affect the battery's charging and discharging process and energy conversion efficiency. Voltage parameters refer to the voltage data of the battery module, usually including the voltage of the single cell and the total voltage of the battery module. Voltage parameters are key indicators for determining the battery state of charge (SOC) and system stability. Voltage changes can directly reflect the battery's health status and affect the charge and discharge control strategy.

[0027] In a possible implementation manner, after S1, the following steps are further included:

[0028] The relevant parameters are preprocessed including noise reduction and smoothing.

[0029] Noise reduction is the process of removing irrelevant or interfering noise from a signal or data, thereby improving signal quality. Common noise reduction methods include low-pass filtering and mean filtering. Smoothing is the process of processing data to minimize fluctuations, preventing sudden, drastic changes from impacting system analysis and decision-making.

[0030] Specifically, by performing noise reduction and smoothing on the relevant parameters of the battery module, interference signals and instantaneous fluctuations can be effectively removed, the stability and reliability of the data can be improved, and erroneous judgments or control reactions caused by data noise can be avoided, thereby improving the control accuracy and overall operating efficiency of the system.

[0031] S2: Build a BPNN model.

[0032] Among them, the BPNN model (Backpropagation Neural Network) is a deep learning model. Through the backpropagation algorithm, the BPNN model can adjust the network weights according to the error between the actual output and the target output to achieve nonlinear mapping of data.

[0033] It should be noted that by constructing a BPNN model, the complex relationship between various parameters of the battery module can be accurately captured, so that the model can provide more accurate SOC estimation, thereby providing reliable data support for charge state balancing control and improving the control accuracy and response speed of the system.

[0034] In one possible implementation, the BPNN model includes: an input layer, a first hidden layer, a second hidden layer, a residual layer, and an output layer.

[0035] The input layer is the first layer of the neural network, receiving external data input. In an organic flow battery energy storage system, the input layer may receive parameters such as the current, voltage, and temperature of the battery module. The hidden layer, located between the input and output layers, is responsible for processing the features of the input data and performing feature mapping. The first hidden layer performs weighted summation and applies an activation function to output a new set of feature data. These features are passed to the next layer. The hidden layer's role is to extract useful information from the data and perform complex nonlinear mapping. The second hidden layer further processes and transforms the data passed from the first hidden layer, performing weighted summation and transformation using the activation function. The residual layer enhances the network's expressive power, especially for deep networks. By introducing "residual connections" or skip connections, the residual layer adds the output of the previous layer to the output of the current layer, helping to address vanishing or exploding gradients and improving model training efficiency and accuracy. The output layer is the final layer of the neural network, generating the final prediction results. In an organic flow battery energy storage system, the output layer outputs an estimated state of charge (SOC) for each battery module based on the processing of the previous layers.

[0036] In a possible implementation manner, after S2, the method further includes:

[0037] The BPNN model is optimized using the crow optimization algorithm.

[0038] In one possible implementation, the BPNN model is optimized using the crow optimization algorithm, specifically including:

[0039] Set the initial parameters of the crow search algorithm, including population size, maximum number of iterations, and search range.

[0040] Initialize the positions and velocities of all crows, where the positions of the crows represent the parameters of the BPNN model.

[0041] The mean square error of the BPNN model is used as the fitness function to calculate the fitness value of each crow.

[0042] According to the fitness value, update the position of each crow:

[0043]

[0044] Among them, a p,iter+1 represents the position of the pth crow in the iter+1th iteration, a p,iter represents the position of the pth crow in the iterth iteration, ω represents the inertia weight, r represents a random number in the interval [0,1], fl p,iter represents the flight distance of the pth crow in the iterth iteration, m q,iterIt represents the optimal position of the qth crow at the iterth iteration, iter max represents the maximum number of iterations, ω max represents the maximum inertia weight value, t represents the current number of iterations, AP represents the consciousness probability, AP1 and AP2 represent the upper and lower limits of the consciousness probability respectively, λ represents a random variable, gbest represents the global optimal position, Γ represents the gamma function, C(0,1) represents a random number vector between 0 and 1, and C(0,1) is a disturbance factor, which is often used to enhance jumpiness and diversity.

[0045] Calculate the fitness value of each crow after the update.

[0046] When the updated crow's individual fitness value is greater than or equal to the current crow's fitness value, the current crow's position is updated. When the updated crow's fitness value is less than the current crow's fitness value, the current crow's position remains unchanged.

[0047] Repeat the above steps until the maximum number of iterations is reached to determine the optimal parameters of the BPNN model.

[0048] Optimize the BPNN model according to the optimal parameters.

[0049] Among them, the crow optimization algorithm is a heuristic optimization algorithm based on the foraging behavior of crows in nature. It simulates how crows use group information and individual experience to find the optimal solution during the foraging process.

[0050] It should be noted that the crow optimization algorithm can effectively search for the optimal parameter combination in the BPNN model by simulating the way crows forage, and can avoid falling into the local optimal solution, thereby improving the global optimization ability and performance of the model, ensuring the accuracy of the BPNN model, and further improving the accuracy of battery module SOC estimation.

[0051] S3: Using relevant parameters as input, the BPNN model is used to output the estimated state of charge of each battery module.

[0052] It should be noted that by inputting actual operating parameters such as voltage and current into the BPNN model, the SOC of each battery module can be estimated with high precision, which can accurately reflect the actual charge state of the battery under different operating conditions, thereby providing a reliable basis for subsequent balancing control and improving the overall energy efficiency and safety of the system.

[0053] In a possible implementation, S3 specifically includes:

[0054] S301: Input relevant parameters into the first hidden layer through the input layer to determine the total input value of the first hidden layer:

[0055]

[0056] in, represents the sum of the inputs of the jth neuron in the first hidden layer, that is, the total input value of the first hidden layer, x i represents the i-th related parameter, i=1,2,…,m, m represents the total number of related parameters, represents the connection weight of the relevant parameter i to the first hidden layer neuron j, represents the bias term of the jth neuron in the first hidden layer.

[0057] Specifically, by inputting relevant parameters into the input layer of the neural network and passing them to the first hidden layer, the features of the input data can be automatically extracted and converted. The weighted summation and activation function processing of the first hidden layer can extract more useful features from complex raw data, reducing the need for manual feature engineering, enabling the neural network to self-learn and optimize, enhancing the expressive power and accuracy of the model, and thus providing a more accurate basis for state of charge estimation.

[0058] S302: Determine the output data of the first hidden layer according to the total input value of the first hidden layer and the activation function of the first hidden layer:

[0059]

[0060] in, Represents the output of the jth neuron in the first hidden layer, that is, the output data of the first hidden layer, ReLU represents the ReLU activation function, and max represents the maximum value.

[0061] Specifically, by performing a nonlinear transformation on the total input value of the first hidden layer through the activation function, the neural network can capture complex nonlinear relationships from the input data, enabling the model to better fit complex battery behaviors and avoiding situations that the linear model cannot accurately describe. The use of the activation function improves the expressive power of the neural network, enabling the network to process more diverse input data, thereby improving the accuracy of the state of charge estimation and the adaptability of the system.

[0062] S303: Input the output data of the first hidden layer into the second hidden layer to determine the total input value of the second hidden layer.

[0063] S304: Determine the output data of the second hidden layer according to the total input value of the second hidden layer and the activation function of the second hidden layer:

[0064]

[0065] in, represents the output of the rth neuron in the second hidden layer, that is, the output data of the second hidden layer, tanh represents the hyperbolic tangent function, represents the sum of the inputs of the rth neuron in the second hidden layer, that is, the total input value of the second hidden layer, and e represents the exponential function.

[0066] Specifically, by passing the output data of the first hidden layer to the second hidden layer, the neural network can further process and combine the features extracted by the previous layer, enhancing the model's understanding of complex patterns. The introduction of the second hidden layer enables the network to capture higher-order features and nonlinear relationships, which can improve the accuracy of battery SOC estimation and enhance the model's performance when facing multi-dimensional data.

[0067] S305: Input the output data of the second hidden layer to the residual layer to determine the residual output data:

[0068]

[0069] in, represents the output of the kth neuron in the residual layer, w ik represents the weight from the i-th related parameter to the k-th residual neuron, b k The bias term of the kth residual neuron, k = 1, 2, ..., K, where K represents the total number of residual neurons.

[0070] Specifically, by passing the output data of the second hidden layer to the residual layer, the network can more effectively avoid the gradient vanishing problem in deep networks through residual connections (jump connections). The residual layer helps the model retain important information and enhances learning ability, making the network more stable during training and able to quickly adjust weights to adapt to complex nonlinear relationships.

[0071] S306: Input the residual output data into the output layer to determine the total input value of the output layer.

[0072] S307: Based on the total input value of the output layer, the state of charge estimation value of each battery module is output through the activation function of the output layer:

[0073]

[0074] Among them, SOC n It represents the estimated state of charge of the nth battery module, and s represents the total input value of the output layer.

[0075] S4: Determine a state of charge deviation based on the state of charge estimate.

[0076] Among them, the state of charge deviation (SOC deviation) refers to the difference between the actual SOC of the battery module and the target SOC (usually the reference SOC value). The SOC deviation reflects the degree of deviation between the current state of the battery and the ideal state, and is usually used to guide subsequent control adjustments.

[0077] It should be noted that by calculating the deviation between the estimated state of charge and the target SOC, the working status of the battery module can be accurately evaluated and provide a key basis for subsequent control. By real-time monitoring and adjustment of the SOC deviation, the system can accurately compensate and adjust the battery module to ensure that the SOC of all battery modules remains within the optimal range, avoiding overcharging or over-discharging, and improving the overall efficiency and stability of the system.

[0078] In a possible implementation, S4 specifically includes:

[0079] S401: Determine a state of charge reference value based on the state of charge estimate:

[0080]

[0081] Among them, SOC ref Indicates the state of charge reference value, n = 1, 2, ..., N, where N represents the total number of battery modules.

[0082] S402: Determine a state of charge deviation by combining the state of charge estimate and the state of charge reference value:

[0083] ΔSOC n =SOC ref -SOC n

[0084] Among them, ΔSOC n Indicates the state of charge deviation of the nth battery module.

[0085] S5: Determine a voltage regulation factor of a DC-DC converter corresponding to each battery module based on the state of charge deviation.

[0086] The voltage regulation factor is a value calculated based on the battery module's SOC deviation and is used to adjust the DC-DC converter's output voltage. This factor ensures that the battery module's output voltage adapts to its current SOC, thereby achieving SOC balance. A DC-DC converter is a device used to regulate the battery's output voltage, controlling it to meet load demands. The DC-DC converter achieves power control for the battery module by adjusting the ratio of input voltage to output voltage.

[0087] It should be noted that by dynamically adjusting the voltage regulation factor of the DC-DC converter corresponding to the battery module according to the state of charge deviation, the output voltage of each module can be accurately adjusted to ensure that the battery modules with lower SOC are properly supplemented, while the modules with higher SOC reduce the load to avoid overcharging or over-discharging, ensuring balanced energy distribution of the entire battery system, thereby improving the system efficiency and battery life.

[0088] In a possible implementation, S5 specifically includes:

[0089] Based on the state of charge deviation, the voltage regulation factor is determined by the SOC balancing controller:

[0090] α vn =1-e n ·G vSOC (z)

[0091]

[0092] Among them, α vn represents the voltage regulation factor of the nth battery module, e n Indicates the state of charge deviation of the nth battery module, K P-SOC Represents the proportional gain of the SOC balancing controller, K I-SOC represents the integral gain of the SOC balancing controller, z represents the discrete change, G vSOC (z) represents the transfer function of the SOC balancing controller.

[0093] Specifically, by adjusting the voltage regulation factor based on the SOC deviation, the SOC balancing controller can intelligently adjust the output voltage of each battery module, making the energy distribution between battery modules more balanced. This not only avoids overcharging and discharging of the battery and extends the battery life, but also improves the overall efficiency and stability of the system, ensuring that all battery modules always operate in the best working condition.

[0094] S6: Determine a reference voltage of the DC-DC converter according to the voltage adjustment factor.

[0095] Among them, the reference voltage is the target output voltage of the DC-DC converter, which is calculated based on the voltage regulation factor of the battery module. The reference voltage determines the operating voltage of the converter and affects the charging and discharging process of the battery module.

[0096] It should be noted that by determining the reference voltage of the DC-DC converter based on the voltage regulation factor, the voltage output of each battery module can be accurately controlled. By adjusting the reference voltage, it is possible to ensure that battery modules in different SOC states output appropriate voltages, thereby achieving balanced energy distribution, improving the overall efficiency of the system, avoiding overcharging or over-discharging, extending the battery life and improving the stability of the battery system.

[0097] In a possible implementation, S6 specifically includes:

[0098] S601: Calculate the sum of the voltage regulation factors according to the voltage regulation factors:

[0099]

[0100] Among them, M v Represents the sum of voltage regulation factors, α vn Indicates the voltage regulation factor of the nth battery module, n = 1, 2, ..., N, where N is the total number of battery modules.

[0101] S602: Determine a reference voltage according to the sum of the voltage adjustment factors.

[0102]

[0103] Among them, V n-ref Indicates the reference voltage of the nth battery module, M v Represents the sum of voltage regulation factors, V bus-ref Indicates the voltage reference value of the DC bus.

[0104] S7: According to the reference voltage, the output voltage of the DC-DC converter is adjusted through the voltage PI controller.

[0105] Among them, the voltage PI controller is a commonly used feedback controller, which consists of proportional (P) and integral (I) parts. The voltage PI controller is used to adjust the output voltage of the DC-DC converter. The proportional part directly adjusts the output according to the voltage error, and the integral part eliminates the steady-state error by accumulating the error.

[0106] It should be noted that by adjusting the output voltage of the DC-DC converter through the voltage PI controller, the voltage of the battery module can be accurately controlled to ensure that the voltage of each module matches its SOC value, avoiding overcharging or over-discharging, reducing the loss of the battery module, and improving the energy efficiency and stability of the system. The feedback mechanism of the PI controller can also correct the voltage error in real time to ensure that the battery module always operates at the optimal voltage, thereby extending the battery life and improving the performance of the overall system.

[0107] In a possible implementation, S7 specifically includes:

[0108] According to the reference voltage, the duty cycle of the DC-DC converter is adjusted through the voltage PI controller to adjust the output voltage of the DC-DC converter.

[0109] The duty cycle refers to the proportion of time the switch is in the on state during periodic switching control. The duty cycle determines the output voltage of the DC-DC converter. By adjusting the duty cycle, the controller can regulate the output voltage.

[0110] It should be noted that by adjusting the DC-DC converter's duty cycle, the PI controller can precisely regulate the output voltage to the reference voltage, ensuring that the battery module always operates within the ideal voltage range. This prevents overcharging or over-discharging of the battery module, improves the stability and safety of the battery system, and maximizes battery efficiency. By dynamically adjusting the duty cycle, the system can efficiently respond to changes in battery status, extending battery life and improving the performance of the overall energy storage system.

[0111] The DC-DC converter duty cycle is adjusted by the following formula to control the output voltage of the DC-DC converter:

[0112] D n =(V n-ref -V n )·G vb (z)

[0113]

[0114] D n represents the duty cycle of the nth DC-DC converter, V n Represents the output voltage of the nth DC-DC converter, G vb (z) represents the transfer function of the voltage PI controller, K P-vb represents the proportional gain of the PI controller, K I-vb Represents the integral gain of the PI controller.

[0115] In the present invention, the larger the duty cycle, the higher the output voltage, and the smaller the duty cycle, the lower the output voltage.

[0116] S8: Determine the output power of each battery module according to the adjusted output voltage to achieve charge state balance control.

[0117] It should be noted that by determining the output power of each battery module based on the adjusted output voltage, the energy distribution of the battery modules can be precisely controlled to ensure that the SOC of the battery modules remains balanced, avoiding damage to certain battery modules due to excessive discharge or charging, while improving the system's energy efficiency and reducing energy waste. Through precise power regulation, the system can achieve reasonable load distribution between different battery modules, extend battery life and improve the performance and stability of the overall energy storage system.

[0118] The output power of the battery module is specifically:

[0119]

[0120] Among them, P bus Represents the total output power, p n Indicates the output power of the nth battery module, Ibus Represents the bus current, n=1,2,…,N, where N represents the total number of battery modules.

[0121] In the present invention, when the voltage is high, the output power is high, the discharge is fast, and the SOC decreases quickly. When the voltage is low, the output power is low, the discharge is slow, and the SOC decreases slowly.

[0122] The beneficial effects brought about by the technical solution provided by the embodiment of the present invention include at least:

[0123] In an embodiment of the present invention, the BPNN model can accurately estimate the SOC of each battery module based on the input battery parameters, thereby improving the accuracy of SOC balancing control. Based on the deviation between the SOC estimation value and the target SOC value, the voltage regulation factor is calculated to dynamically adjust the voltage reference value of each battery module. According to the current SOC difference, it is possible to avoid excessive discharge or charging of certain battery modules, extend battery life, and optimize battery utilization efficiency. By adjusting the duty cycle of the DC-DC converter through the PI controller, precise voltage regulation can be achieved to ensure that the output voltage of the battery module always remains within the ideal range, reducing energy waste and improving the overall efficiency of the system. By determining the output power of each battery module based on the adjusted voltage output, it is possible to ensure that the energy distribution of all modules is balanced, reduce overcharging or over-discharging of the battery modules, ensure the stability of the system during long-term operation, and avoid load overload and equipment damage caused by SOC imbalance.

[0124] The above embodiments can be implemented in whole or in part through software, hardware (such as circuits), firmware, or any other combination. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer program are loaded or executed on a computer, the processes or functions described in accordance with the embodiments of the present invention are generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via a wired method (such as infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that contains a collection of one or more available media. The available medium can be a magnetic medium (such as a floppy disk, hard disk, or magnetic tape), an optical medium (such as a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state drive.

[0125] It should be understood that in various embodiments of the present invention, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0126] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present invention.

[0127] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described equipment, devices and units can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0128] In the several embodiments provided by the present invention, it should be understood that the disclosed devices, apparatuses and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interface, indirect coupling or communication connection of the device or unit, which can be electrical, mechanical or other forms.

[0129] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0130] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0131] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, 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. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0132] An embodiment of the present invention provides a readable storage medium including: a program or instruction stored on the readable storage medium, and when the program or instruction is executed by a processor, the steps of the above-mentioned method for balancing the state of charge of the organic liquid flow battery energy storage system are implemented, and the same technical effect can be achieved. To avoid repetition, the present invention will not be repeated.

Claims

1. A method for controlling the state of charge balance of an organic liquid flow battery energy storage system, characterized in that: include: S1: Obtain relevant parameters of the organic liquid flow battery energy storage system, wherein the organic liquid flow battery energy storage system includes a plurality of battery modules; S2: Build BPNN model; S3: using the relevant parameters as input, outputting an estimated state of charge value of each battery module through the BPNN model; S4: determining a state of charge deviation based on the state of charge estimate; S5: Determine a voltage regulation factor of a DC-DC converter corresponding to each of the battery modules based on the state of charge deviation; S6: Determine a reference voltage of the DC-DC converter according to the voltage adjustment factor; S7: Regulating the output voltage of the DC-DC converter through a voltage PI controller according to the reference voltage; S8: Determine the output power of each battery module according to the adjusted output voltage to achieve charge state balance control.

2. The method for controlling the state of charge balance of the organic flow battery energy storage system according to claim 1, wherein: The relevant parameters include current parameters and voltage parameters.

3. The method for controlling the state of charge balance of the organic flow battery energy storage system according to claim 1, wherein: After S1, the following steps are also included: The relevant parameters are pre-processed including noise reduction processing and smoothing processing.

4. The method for controlling the state of charge balance of the organic flow battery energy storage system according to claim 1, wherein: The BPNN model includes: an input layer, a first hidden layer, a second hidden layer, a residual layer and an output layer.

5. The method for controlling the state of charge balance of the organic flow battery energy storage system according to claim 1, wherein: After S2, the method further includes: The BPNN model is optimized using the crow optimization algorithm.

6. The method for controlling the state of charge balance of the organic flow battery energy storage system according to claim 4, characterized in that: The S3 specifically includes: S301: Inputting the relevant parameters into the first hidden layer through the input layer to determine the total input value of the first hidden layer; S302: Determine first hidden layer output data according to the total input value of the first hidden layer and the activation function of the first hidden layer; S303: Inputting the output data of the first hidden layer into the second hidden layer to determine the total input value of the second hidden layer; S304: Determine the second hidden layer output data according to the second hidden layer total input value and the activation function of the second hidden layer; S305: Inputting the second hidden layer output data into the residual layer to determine residual output data; S306: Inputting the residual output data into the output layer to determine the total input value of the output layer; S307: Outputting the estimated state of charge value of each battery module through the activation function of the output layer according to the total input value of the output layer.

7. The method for controlling the state of charge balance of the organic flow battery energy storage system according to claim 1, wherein: The S4 specifically includes: S401: Determine a state of charge reference value according to the state of charge estimation value; S402: Determine the state of charge deviation by combining the state of charge estimation value and the state of charge reference value.

8. The method for controlling the state of charge balance of the organic flow battery energy storage system according to claim 1, wherein: The S5 is specifically: Based on the state of charge deviation, the voltage adjustment factor is determined by an SOC balancing controller.

9. The method for controlling the state of charge balance of the organic flow battery energy storage system according to claim 1, wherein: The S6 specifically includes: S601: Calculating a sum of voltage regulation factors according to the voltage regulation factors; S602: Determine the reference voltage according to the sum of the voltage adjustment factors.

10. The method for controlling the state of charge balance of the organic flow battery energy storage system according to claim 1, wherein: The S7 is specifically: According to the reference voltage, the duty cycle of the DC-DC converter is adjusted by the voltage PI controller to adjust the output voltage of the DC-DC converter.

Images