Current control method and system of multi-stack reversible solid oxide battery system

Abstract

The invention discloses a current control method and system for a multi-stack reversible solid oxide battery system, and the method comprises the steps: obtaining electrode data and a YSZ electrolyte degradation degree according to a current operation mode of the multi-stack reversible solid oxide battery system; inputting the electrode data and the YSZ electrolyte degradation degree into a preset fuzzy neural network to obtain a pile relative degradation degree of each pile; according to the reactant gas flow rate of the multi-pile rSOC system, calculating the electric pile reactant flow ratio of each electric pile; calculating the current distribution ratio of each galvanic pile according to the galvanic pile reactant flow ratio and the galvanic pile relative decline degree; and controlling the current of each electric pile in the multi-pile rSOC system according to the electric pile current distribution ratio. According to the embodiment of the invention, the inconsistency of internal reactant flow distribution and recession degree of the multi-stack rSOC system in different states can be considered.

Description

Technical Field

[0001] The present invention relates to the technical field of multi-stack system control, and in particular to a current control method and system for a multi-stack reversible solid oxide battery system. Background Art

[0002] Reversible solid oxide cell (rSOC) multi-stack system can operate alternately as solid oxide fuel cell (SOFC) and solid oxide electrolysis cell (SOEC). It is difficult to precisely control the rSOC system due to the inconsistency between internal stacks and the complex reasons for the degradation of the stacks.

[0003] The traditional multi-stack rSOC system control method only aims to optimize the system efficiency, without considering the inconsistency between the stacks and its impact, nor the impact of various stack degradation factors on the overall degradation of the stack. The existing multi-stack rSOC system control method cannot effectively extend the system life and improve work efficiency in its actual application. Summary of the invention

[0004] The technical problem to be solved by the present invention is how to overcome the problem that the existing multi-stack rSOC system control method cannot fully consider the internal characteristics of the battery stack, and provide a current control method and system for a multi-stack reversible solid oxide battery system, which can consider the inconsistency of internal reactant flow distribution and the inconsistency of decay degree of the multi-stack reversible solid oxide battery system under different states, optimize the current control of the multi-stack rSOC system, and effectively improve work efficiency, extend system life and reduce economic costs.

[0005] In order to solve the above technical problems, an embodiment of the present invention provides a current control method for a multi-stack reversible solid oxide battery system, comprising: According to the current operation mode of the multi-stack reversible solid oxide battery system, obtaining electrode data and YSZ electrolyte degradation degree of the multi-stack reversible solid oxide battery system; Inputting the electrode data and the degradation degree of the YSZ electrolyte into a preset fuzzy neural network to obtain the relative degradation degree of each battery stack; Calculate the reactant flow ratio of each stack according to the reactant gas flow rate of the multi-stack reversible solid oxide battery system; Calculating the current distribution ratio of each stack according to the proportion of the stack reactant flow and the relative decay degree of the stack; The current of each battery stack in the multi-stack reversible solid oxide battery system is controlled according to the battery stack current distribution ratio.

[0006] As an improvement of the above solution, the step of obtaining electrode data of the multi-stack reversible solid oxide battery system according to the current operation mode of the multi-stack reversible solid oxide battery system includes: Acquire a current operation mode of a multi-stack reversible solid oxide battery system; the current operation mode includes a solid oxide fuel cell mode and a solid oxide electrolysis cell mode; When the current operation mode is a solid oxide fuel cell mode, obtaining the nickel particle radius of each stack in the multi-stack reversible solid oxide battery system as electrode data; When the current operation mode is the solid oxide electrolysis cell mode, the thickness of the lanthanum zirconate of each battery stack in the multi-stack reversible solid oxide battery system is obtained as electrode data.

[0007] As an improvement of the above solution, the preset method of the fuzzy neural network includes: Establishing input layer nodes according to the characteristic dimensions of input data; the characteristic dimensions include electrode dimensions and electrolyte degradation dimensions; Calculating the membership of each input layer node according to the Gaussian function to obtain a membership calculation layer node; Obtaining rule generation layer nodes according to the membership calculation layer nodes and preset fuzzy rules; Weighting the rule generation layer nodes to obtain output layer nodes; Using a back propagation algorithm, the connection weights between the rule generation layer nodes and the output layer nodes are optimized to obtain optimized connection weights; A fuzzy neural network is set according to the input layer nodes, the membership calculation layer nodes, the rule generation layer nodes, the output layer nodes and the optimized connection weights.

[0008] As an improvement of the above solution, the membership of each input layer node is calculated according to the Gaussian function to obtain the membership calculation layer node, including: pass Calculate the membership of the i-th input layer node to the j-th preset fuzzy rule; where, is the eigenvalue of the i-th feature dimension; is the center point of the Gaussian function; is the width vector of the Gaussian function; is the number of input layer nodes; is the number of preset fuzzy rules; According to the membership of each input layer node under each fuzzy rule, a membership calculation layer node is obtained.

[0009] As an improvement of the above solution, the back propagation algorithm is used to optimize the connection weights between the rule generation layer nodes and the output layer nodes to obtain the optimized connection weights, including: Using stochastic gradient descent, The connection weights between the rule generation layer nodes and the output layer nodes Optimize and get the optimized connection weight ;in, is the learning rate; is the error function.

[0010] As an improvement of the above solution, the electrode data and the degradation degree of the YSZ electrolyte are input into a preset fuzzy neural network to obtain the relative degradation degree of each stack, including: The electrode data of each battery stack and the degradation degree of the YSZ electrolyte are respectively input into a preset fuzzy neural network to obtain the degradation degree of each battery stack; According to a preset selection rule, a reference stack is selected from each stack, and the stacks other than the reference stack are used as relative stacks; The relative degradation degree of each fuel cell stack is obtained according to the degradation degree of the reference fuel cell stack and the relative fuel cell stack.

[0011] As an improvement of the above scheme, the calculation of the proportion of the reactant flow of each stack according to the reactant gas flow rate of the multi-stack reversible solid oxide battery system includes: Obtaining a total reactant gas flow rate of a multi-stack reversible solid oxide battery system and a stack reactant gas flow rate of each stack; The stack reactant gas flow rate is divided by the total reactant gas flow rate to calculate the stack reactant flow ratio of each stack.

[0012] As an improvement of the above solution, the current distribution ratio of each fuel cell stack is calculated according to the proportion of the fuel cell stack reactant flow and the relative degradation degree of the fuel cell stack, including: Determining the proportion of the flow rate of the stack reactants according to the working requirements of the multi-stack reversible solid oxide battery system; According to the proportion of the flow rate of the reactants in the stack, the proportion of the flow rate of the reactants in the stack and the relative decay degree of the stack are weighted to obtain a current distribution weighted ratio of each stack; According to the current distribution weighted ratio and the preset current adjustable ratio, by Calculate the current distribution ratio of the sth battery stack; where s is the number of battery stacks; is the current distribution weighted ratio of the sth battery stack; The current is adjustable to the preset ratio; is the current reference value of the sth battery stack; is the total current value of the multi-stack reversible solid oxide battery system.

[0013] As an improvement of the above solution, controlling the current of each battery stack in the multi-stack reversible solid oxide battery system according to the battery stack current distribution ratio includes: According to the current distribution ratio of the battery stack, a current reference value of each battery stack is obtained; Obtain the actual current value of each battery stack; According to the current reference value and the actual current value, a PID control method is adopted to control the current of each battery stack in the multi-stack reversible solid oxide battery system.

[0014] The embodiment of the present invention further provides a current control system for a multi-stack reversible solid oxide battery system, comprising: A data acquisition module, for acquiring electrode data and a degree of YSZ electrolyte degradation of the multi-stack reversible solid oxide battery system according to a current operation mode of the multi-stack reversible solid oxide battery system; A relative decay degree calculation module for a battery stack, used for inputting the electrode data and the degradation degree of the YSZ electrolyte into a preset fuzzy neural network to obtain the relative decay degree of each battery stack; A reactant flow ratio calculation module is used to calculate the reactant flow ratio of each stack according to the reactant gas flow rate of the multi-stack reversible solid oxide battery system; A current distribution ratio calculation module, used to calculate the current distribution ratio of each fuel cell according to the proportion of the fuel cell reactant flow and the relative decay degree of the fuel cell; A current control module is used to control the current of each battery stack in the multi-stack reversible solid oxide battery system according to the battery stack current distribution ratio.

[0015] Compared with the prior art, the current control method and system of a multi-stack reversible solid oxide battery system disclosed in the present invention obtains the electrode data and the degradation degree of the YSZ electrolyte of the multi-stack reversible solid oxide battery system according to the current operation mode of the multi-stack reversible solid oxide battery system; inputs the electrode data and the degradation degree of the YSZ electrolyte into a preset fuzzy neural network to obtain the relative decay degree of each battery stack; calculates the proportion of the reactant flow of each battery stack according to the reactant gas flow rate of the multi-stack reversible solid oxide battery system; calculates the current distribution ratio of each battery stack according to the proportion of the reactant flow of the battery stack and the relative decay degree of the battery stack; and controls the current of each battery stack in the multi-stack reversible solid oxide battery system according to the current distribution ratio of the battery stack. By adopting the embodiment of the present invention, the inconsistency of the internal reactant flow distribution and the inconsistency of the decay degree of the multi-stack reversible solid oxide battery system under different states can be considered, and the current control of the multi-stack rSOC system can be optimized, which can effectively improve the work efficiency, extend the system life and reduce the economic cost. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 It is a schematic flow chart of the steps of a current control method for a multi-stack reversible solid oxide battery system provided by an embodiment of the present invention; Figure 2 is a schematic diagram of the structure of a fuzzy neural network provided by an embodiment of the present invention; Figure 3 It is a structural schematic diagram of a current control system of a multi-stack reversible solid oxide battery system provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0017] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0018] In the description of the specification and claims, it is to be understood that the terms first, second, etc. in the specification and claims are only used for the purpose of describing the same technical features, and cannot be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated, nor necessarily describing the order or time sequence. The terms are interchangeable where appropriate. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include at least one of the features.

[0019] The present invention provides a current control method for a multi-stack reversible solid oxide battery system. Figure 1 In this embodiment, the current control method of the multi-stack reversible solid oxide battery system is specifically performed through steps S1 to S5: S1. According to the current operation mode of the multi-stack reversible solid oxide battery system, electrode data and YSZ electrolyte degradation degree of the multi-stack reversible solid oxide battery system are obtained.

[0020] S2. Input the electrode data and the degradation degree of the YSZ electrolyte into a preset fuzzy neural network to obtain the relative degradation degree of each battery stack.

[0021] In an embodiment of the present invention, the relative decay degree of the battery stack is obtained by comprehensively considering two aspects: one is the decay degree of the electrodes of different battery stacks, and the other is the decay degree of the electrolytes of different battery stacks. Specifically, the electrode decay degree of different battery stacks is evaluated and calculated through electrode data, and the electrolyte decay degree of different battery stacks is evaluated and calculated through the degradation degree of YSZ electrolyte. In this way, the relative decay degree of the battery stack can be comprehensively evaluated based on the internal parameters of the multi-stack reversible solid oxide battery system.

[0022] S3. Calculate the reactant flow ratio of each stack according to the reactant gas flow rate of the multi-stack reversible solid oxide battery system.

[0023] It should be noted that the inconsistency of reactant distribution between fuel cells is usually affected by a variety of complex factors, including but not limited to the physical layout of the system, operating environment and temperature. If all of the above factors are modeled, the complexity of the model will be significantly increased, while the accuracy will not be significantly improved. The embodiment of the present invention provides a technical solution for simulating the flow ratio of fuel cell reactants by gas flow rate, which is simple and effective to implement.

[0024] S4. Calculate the current distribution ratio of each fuel cell stack according to the proportion of the fuel cell stack reactant flow and the relative degradation degree of the fuel cell stack.

[0025] S5. Control the current of each battery stack in the multi-stack reversible solid oxide battery system according to the battery stack current distribution ratio.

[0026] In the above scheme, the inconsistency of the degree of degradation between the fuel cells and the inconsistency of the reactant flow distribution between the fuel cells are comprehensively considered. Using the calculated current distribution ratio for current control can reduce the negative impact of the inconsistency between the fuel cells on the system life, working efficiency and operating cost, thereby ensuring the economy of the multi-stack reversible solid oxide battery system.

[0027] As a preferred embodiment, step S1, obtaining electrode data of the multi-stack reversible solid oxide battery system according to the current operation mode of the multi-stack reversible solid oxide battery system, comprises: Acquire a current operation mode of a multi-stack reversible solid oxide battery system; the current operation mode includes a solid oxide fuel cell mode and a solid oxide electrolysis cell mode; When the current operation mode is a solid oxide fuel cell mode, obtaining the nickel particle radius of each stack in the multi-stack reversible solid oxide battery system as electrode data; When the current operation mode is the solid oxide electrolysis cell mode, the thickness of the lanthanum zirconate of each battery stack in the multi-stack reversible solid oxide battery system is obtained as electrode data.

[0028] It should be noted that the multi-stack reversible solid oxide cell (rSOC) system can be operated alternately as a solid oxide fuel cell (SOFC) and a solid oxide electrolysis cell (SOEC), so it has at least two operating modes, namely the solid oxide fuel cell mode and the solid oxide electrolysis cell mode. There are differences in electrode data under different operating modes. In the solid oxide fuel cell mode, the nickel particles will be coarsened. In the embodiment of the present invention, the degree of electrode degradation is reflected by the radius of the nickel particles; in the solid oxide electrolysis cell mode, lanthanum zirconate (LZO) will be generated. As the system continues to operate, the thickness of lanthanum zirconate will increase. In the embodiment of the present invention, the thickness of lanthanum zirconate reflects the degree of electrode degradation.

[0029] As a preferred implementation, the preset method of the fuzzy neural network includes: Establishing input layer nodes according to the characteristic dimensions of input data; the characteristic dimensions include electrode dimensions and electrolyte degradation dimensions; Calculating the membership of each input layer node according to the Gaussian function to obtain a membership calculation layer node; Obtaining rule generation layer nodes according to the membership calculation layer nodes and preset fuzzy rules; Weighting the rule generation layer nodes to obtain output layer nodes; Using a back propagation algorithm, the connection weights between the rule generation layer nodes and the output layer nodes are optimized to obtain optimized connection weights; A fuzzy neural network is set according to the input layer nodes, the membership calculation layer nodes, the rule generation layer nodes, the output layer nodes and the optimized connection weights.

[0030] In some preferred embodiments, the fuzzy neural network includes an input layer, a membership calculation layer, a rule generation layer, a normalization layer and an output layer connected in sequence. The number of nodes in the input layer is consistent with the number of feature dimensions of the input data; the total number of nodes in the membership calculation layer is the product of the number of feature dimensions of the input data and the number of preset fuzzy rules; the number of nodes in the rule generation layer and the normalization layer are both consistent with the number of preset fuzzy rules.

[0031] It should be noted that when calculating the membership of each input layer node, the membership between the input data of each feature dimension and the preset fuzzy rule is obtained, so as to determine the relative degradation degree of each battery stack through the fuzzy control method.

[0032] For example, see Figure 2 , the data input fuzzy neural network needs to go through a total of five layers of network structure, the first is the input layer, the number of nodes in this layer is the characteristic dimension of the input data, in this controller the characteristic dimension of the input data is 2, the number of nodes in the input layer is 2. Then the data is passed from the input layer to the membership function calculation layer, in this layer the membership function is needed to calculate the membership of each node, each node represents a membership function, the number of nodes in this layer is the number of fuzzy conditions that the input variable may constitute, in this controller the Gaussian function is selected for the membership function. After that, the data is passed to the rule generation layer, the number of nodes in this layer is the number of fuzzy rules, in this controller it is 16, the output of this layer is the applicability of each rule. Then the node output of the rule generation layer is normalized in the normalization layer, the nodes in this layer are the same as the rule generation layer; finally the data is weighted in the output layer to obtain the final output.

[0033] Further, preferably, the calculating the membership of each input layer node according to the Gaussian function to obtain the membership calculation layer node includes: pass Calculate the membership of the i-th input layer node to the j-th preset fuzzy rule; where, is the eigenvalue of the i-th feature dimension; is the center point of the Gaussian function; is the width vector of the Gaussian function; is the number of input layer nodes; is the number of preset fuzzy rules; According to the membership of each input layer node under each fuzzy rule, a membership calculation layer node is obtained.

[0034] It should be noted that the number of nodes in the membership calculation layer is the number of fuzzy rules that may be formed by the input variables.

[0035] For example, by Calculate the value of each node in the rule generation layer by Normalize the nodes of the rule generation layer to form a normalized layer. Get the final output; among them, is the connection weight between the normalization layer and the output layer.

[0036] In the above scheme, the effect achieved by the normalization layer is to normalize the nodes of the rule generation layer one by one, and the number of its nodes is consistent with the number of nodes in the rule generation layer. Therefore, in some preferred embodiments, the normalization process is integrated into the rule generation layer, that is, each node of the rule generation layer is directly connected to the output layer node, and there is a connection weight between the rule generation layer node and the output layer node.

[0037] Preferably, the back propagation algorithm is used to optimize the connection weights between the rule generation layer nodes and the output layer nodes to obtain the optimized connection weights, including: Using stochastic gradient descent, The connection weights between the rule generation layer nodes and the output layer nodes Optimize and get the optimized connection weight ;in, is the learning rate; is the error function.

[0038] As a preferred implementation, step S2, inputting the electrode data and the degradation degree of the YSZ electrolyte into a preset fuzzy neural network to obtain the relative degradation degree of each battery stack, includes: The electrode data of each battery stack and the degradation degree of the YSZ electrolyte are respectively input into a preset fuzzy neural network to obtain the degradation degree of each battery stack; According to a preset selection rule, a reference stack is selected from each stack, and the stacks other than the reference stack are used as relative stacks; The relative degradation degree of each fuel cell stack is obtained according to the degradation degree of the reference fuel cell stack and the relative fuel cell stack.

[0039] It should be noted that, taking the dual-stack rSOC system as an example, once the relative degradation degree of one stack is determined, the relative degradation degree of the other stack will also be determined. In the embodiment of the present invention, for the input of the fuzzy neural network, the relative degradation degree of the YSZ electrolyte of stack 1 is selected. Compared with the average radius of nickel particles in stack 1 , the LZO thickness of stack 1 is relatively , the output is the relative decay degree of the battery stack .

[0040] As a preferred embodiment, step S3, calculating the stack reactant flow ratio of each stack according to the reactant gas flow rate of the multi-stack reversible solid oxide battery system, comprises: Obtaining a total reactant gas flow rate of a multi-stack reversible solid oxide battery system and a stack reactant gas flow rate of each stack; The stack reactant gas flow rate is divided by the total reactant gas flow rate to calculate the stack reactant flow ratio of each stack.

[0041] For example, by Calculate the ratio of the stack reactant flow rate; where: is the reactant gas flow rate of the i-th stack; is the reactant gas flow rate of the entire system.

[0042] It should be noted that in the embodiment of the present invention, the difference between fuel and air is ignored when analyzing the inconsistency of the reactant flow rate in the system. .

[0043] As a preferred implementation, step S4, calculating the current distribution ratio of each stack according to the proportion of the stack reactant flow and the relative decay degree of the stack, includes: Determining the proportion of the flow rate of the stack reactants according to the working requirements of the multi-stack reversible solid oxide battery system; According to the proportion of the flow rate of the reactants in the stack, the proportion of the flow rate of the reactants in the stack and the relative decay degree of the stack are weighted to obtain a current distribution weighted ratio of each stack; According to the current distribution weighted ratio and the preset current adjustable ratio, by Calculate the current distribution ratio of the sth battery stack; where s is the number of battery stacks; is the current distribution weighted ratio of the sth battery stack; The current is adjustable to the preset ratio; is the current reference value of the sth battery stack; is the total current value of the multi-stack reversible solid oxide battery system.

[0044] In some embodiments, the current distribution weighted ratio of the first stack is ,in, is the proportion of the stack reactant flow rate; is the proportion of stack reactant flow; is the relative degradation degree of the battery stack.

[0045] It should be noted that the proportion of the stack reactant flow rate is determined according to the working requirements of the system, and its specific value does not affect the beneficial effects produced by the present invention.

[0046] For example, the preset current adjustable ratio The value of is in the interval [0.01,0.05].

[0047] As a preferred implementation, step S5, controlling the current of each battery stack in the multi-stack reversible solid oxide battery system according to the battery stack current distribution ratio, comprises: According to the current distribution ratio of the battery stack, a current reference value of each battery stack is obtained; Obtain the actual current value of each battery stack; According to the current reference value and the actual current value, a PID control method is adopted to control the current of each battery stack in the multi-stack reversible solid oxide battery system.

[0048] In the above scheme, the PID control method is used to eliminate errors and the stack current is adjusted in time to meet the load requirements.

[0049] A current control method for a multi-stack reversible solid oxide battery system provided in an embodiment of the present invention comprehensively considers the inconsistency of the degree of degradation between battery stacks and the inconsistency of the reactant flow distribution between battery stacks. Current control using the calculated current distribution ratio can reduce the negative impact of the inconsistency between battery stacks on the system life, work efficiency and operating cost, thereby ensuring the economy of the multi-stack reversible solid oxide battery system.

[0050] The present invention provides a current control system for a multi-stack reversible solid oxide battery system. Figure 3 , the current control system of the multi-stack reversible solid oxide battery system includes, wherein: A data acquisition module 11 is used to acquire electrode data and a degradation degree of the YSZ electrolyte of the multi-stack reversible solid oxide battery system according to a current operation mode of the multi-stack reversible solid oxide battery system; A relative degradation degree calculation module 12 for the battery stack is used to input the electrode data and the degradation degree of the YSZ electrolyte into a preset fuzzy neural network to obtain the relative degradation degree of each battery stack; A reactant flow ratio calculation module 13 is used to calculate the reactant flow ratio of each stack according to the reactant gas flow rate of the multi-stack reversible solid oxide battery system; A current distribution ratio calculation module 14 is used to calculate the current distribution ratio of each fuel cell according to the proportion of the fuel cell reactant flow and the relative decay degree of the fuel cell; The current control module 15 is used to control the current of each battery stack in the multi-stack reversible solid oxide battery system according to the battery stack current distribution ratio.

[0051] As a preferred implementation, the data acquisition module 11 includes: The current operation mode acquisition unit is used to acquire the current operation mode of the multi-stack reversible solid oxide battery system; the current operation mode includes a solid oxide fuel cell mode and a solid oxide electrolysis cell mode; A first electrode data acquisition unit, for obtaining, when the current operation mode is a solid oxide fuel cell mode, a nickel particle radius of each battery stack in the multi-stack reversible solid oxide battery system as electrode data; The second electrode data acquisition unit is used to obtain the lanthanum zirconate thickness of each battery stack in the multi-stack reversible solid oxide battery system as electrode data when the current operating mode is the solid oxide electrolysis battery mode.

[0052] As a preferred implementation, the preset method of the fuzzy neural network includes: Establishing input layer nodes according to the characteristic dimensions of input data; the characteristic dimensions include electrode dimensions and electrolyte degradation dimensions; Calculating the membership of each input layer node according to the Gaussian function to obtain a membership calculation layer node; Obtaining rule generation layer nodes according to the membership calculation layer nodes and preset fuzzy rules; Weighting the rule generation layer nodes to obtain output layer nodes; Using a back propagation algorithm, the connection weights between the rule generation layer nodes and the output layer nodes are optimized to obtain optimized connection weights; A fuzzy neural network is set according to the input layer nodes, the membership calculation layer nodes, the rule generation layer nodes, the output layer nodes and the optimized connection weights.

[0053] As a preferred implementation, the step of calculating the membership of each input layer node according to the Gaussian function to obtain the membership calculation layer node includes: pass Calculate the membership of the i-th input layer node to the j-th preset fuzzy rule; where, is the eigenvalue of the i-th feature dimension; is the center point of the Gaussian function; is the width vector of the Gaussian function; is the number of input layer nodes; is the number of preset fuzzy rules; According to the membership of each input layer node under each fuzzy rule, a membership calculation layer node is obtained.

[0054] As a preferred implementation, the back propagation algorithm is used to optimize the connection weights between the rule generation layer nodes and the output layer nodes to obtain the optimized connection weights, including: Using stochastic gradient descent, The connection weights between the rule generation layer nodes and the output layer nodes Optimize and get the optimized connection weight ;in, is the learning rate; is the error function.

[0055] As a preferred implementation, the stack relative degradation degree calculation module 12 includes: The electrode data of each battery stack and the degradation degree of the YSZ electrolyte are respectively input into a preset fuzzy neural network to obtain the degradation degree of each battery stack; According to a preset selection rule, a reference stack is selected from each stack, and the stacks other than the reference stack are used as relative stacks; The relative degradation degree of each fuel cell stack is obtained according to the degradation degree of the reference fuel cell stack and the relative fuel cell stack.

[0056] As a preferred implementation, the reactant flow rate ratio calculation module 13 includes: Obtaining a total reactant gas flow rate of a multi-stack reversible solid oxide battery system and a stack reactant gas flow rate of each stack; The stack reactant gas flow rate is divided by the total reactant gas flow rate to calculate the stack reactant flow ratio of each stack.

[0057] As a preferred implementation, the current distribution ratio calculation module 14 includes: Determining the proportion of the flow rate of the stack reactants according to the working requirements of the multi-stack reversible solid oxide battery system; According to the proportion of the flow rate of the reactants in the stack, the proportion of the flow rate of the reactants in the stack and the relative decay degree of the stack are weighted to obtain a current distribution weighted ratio of each stack; According to the current distribution weighted ratio and the preset current adjustable ratio, by Calculate the current distribution ratio of the sth battery stack; where s is the number of battery stacks; is the current distribution weighted ratio of the sth battery stack; The current is adjustable to the preset ratio; is the current reference value of the sth battery stack; is the total current value of the multi-stack reversible solid oxide battery system.

[0058] As a preferred implementation, the current control module 15 includes: According to the current distribution ratio of the battery stack, a current reference value of each battery stack is obtained; Obtain the actual current value of each battery stack; According to the current reference value and the actual current value, a PID control method is adopted to control the current of each battery stack in the multi-stack reversible solid oxide battery system.

[0059] A current control system for a multi-stack reversible solid oxide battery system provided by an embodiment of the present invention comprehensively considers the inconsistency in the degree of degradation between battery stacks and the inconsistency in the reactant flow distribution between battery stacks. Using the calculated current distribution ratio for current control can reduce the negative impact of the inconsistency between battery stacks on the system life, work efficiency and operating cost, thereby ensuring the economy of the multi-stack reversible solid oxide battery system.

[0060] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program, and the program can be stored in a computer-readable storage medium, and when the program is executed, it can include the processes of the embodiments of the above-mentioned methods. The storage medium can be a disk, an optical disk, a read-only memory (ROM) or a random access memory (RAM), etc.

[0061] The above is a preferred embodiment of the present invention. It should be pointed out that a person skilled in the art can make several improvements and modifications without departing from the principle of the present invention. These improvements and modifications are also considered to be within the scope of protection of the present invention.

Claims

1. A current control method for a multi-stack reversible solid oxide battery system, characterized in that: include: According to the current operation mode of the multi-stack reversible solid oxide battery system, obtaining electrode data and YSZ electrolyte degradation degree of the multi-stack reversible solid oxide battery system; Inputting the electrode data and the degradation degree of the YSZ electrolyte into a preset fuzzy neural network to obtain the relative degradation degree of each battery stack; Calculate the reactant flow ratio of each stack according to the reactant gas flow rate of the multi-stack reversible solid oxide battery system; Calculating the current distribution ratio of each stack according to the proportion of the stack reactant flow and the relative decay degree of the stack; The current of each battery stack in the multi-stack reversible solid oxide battery system is controlled according to the battery stack current distribution ratio.

2. A current control method for a multi-stack reversible solid oxide battery system according to claim 1, characterized in that: The step of obtaining electrode data of the multi-stack reversible solid oxide battery system according to the current operation mode of the multi-stack reversible solid oxide battery system comprises: Acquire a current operation mode of a multi-stack reversible solid oxide battery system; the current operation mode includes a solid oxide fuel cell mode and a solid oxide electrolysis cell mode; When the current operation mode is a solid oxide fuel cell mode, obtaining the nickel particle radius of each stack in the multi-stack reversible solid oxide battery system as electrode data; When the current operation mode is the solid oxide electrolysis cell mode, the thickness of the lanthanum zirconate of each battery stack in the multi-stack reversible solid oxide battery system is obtained as electrode data.

3. A current control method for a multi-stack reversible solid oxide battery system as claimed in claim 1, characterized in that: The preset method of the fuzzy neural network includes: Establishing input layer nodes according to the characteristic dimensions of input data; the characteristic dimensions include electrode dimensions and electrolyte degradation dimensions; Calculating the membership of each input layer node according to the Gaussian function to obtain a membership calculation layer node; Obtaining rule generation layer nodes according to the membership calculation layer nodes and preset fuzzy rules; Weighting the rule generation layer nodes to obtain output layer nodes; Using a back propagation algorithm, the connection weights between the rule generation layer nodes and the output layer nodes are optimized to obtain optimized connection weights; A fuzzy neural network is set according to the input layer nodes, the membership calculation layer nodes, the rule generation layer nodes, the output layer nodes and the optimized connection weights.

4. A current control method for a multi-stack reversible solid oxide battery system as claimed in claim 3, characterized in that: The step of calculating the membership of each input layer node according to the Gaussian function to obtain the membership calculation layer node includes: pass Calculate the membership of the i-th input layer node to the j-th preset fuzzy rule; where, is the eigenvalue of the i-th feature dimension; is the center point of the Gaussian function; is the width vector of the Gaussian function; is the number of input layer nodes; is the number of preset fuzzy rules; According to the membership of each input layer node under each fuzzy rule, a membership calculation layer node is obtained.

5. The current control method of a multi-stack reversible solid oxide battery system according to claim 3, characterized in that: The back propagation algorithm is used to optimize the connection weights between the rule generation layer nodes and the output layer nodes to obtain the optimized connection weights, including: Using stochastic gradient descent, The connection weights between the rule generation layer nodes and the output layer nodes Optimize and get the optimized connection weight ;in, is the learning rate; is the error function.

6. A current control method for a multi-stack reversible solid oxide battery system as claimed in claim 1, characterized in that: The electrode data and the degradation degree of the YSZ electrolyte are input into a preset fuzzy neural network to obtain the relative degradation degree of each battery stack, including: The electrode data of each battery stack and the degradation degree of the YSZ electrolyte are respectively input into a preset fuzzy neural network to obtain the degradation degree of each battery stack; According to a preset selection rule, a reference stack is selected from each stack, and the stacks other than the reference stack are used as relative stacks; The relative degradation degree of each fuel cell stack is obtained according to the degradation degree of the reference fuel cell stack and the relative fuel cell stack.

7. A current control method for a multi-stack reversible solid oxide battery system as claimed in claim 1, characterized in that: The method of calculating the reactant flow ratio of each stack according to the reactant gas flow rate of the multi-stack reversible solid oxide battery system includes: Obtaining a total reactant gas flow rate of a multi-stack reversible solid oxide battery system and a stack reactant gas flow rate of each stack; The stack reactant gas flow rate is divided by the total reactant gas flow rate to calculate the stack reactant flow ratio of each stack.

8. The current control method of a multi-stack reversible solid oxide battery system according to claim 1, characterized in that: The calculating the current distribution ratio of each battery stack according to the proportion of the battery stack reactant flow and the relative degradation degree of the battery stack includes: Determining the proportion of the flow rate of the stack reactants according to the working requirements of the multi-stack reversible solid oxide battery system; According to the proportion of the flow rate of the reactants in the stack, the proportion of the flow rate of the reactants in the stack and the relative decay degree of the stack are weighted to obtain a current distribution weighted ratio of each stack; According to the current distribution weighted ratio and the preset current adjustable ratio, by Calculate the current distribution ratio of the sth battery stack; where s is the number of battery stacks; is the current distribution weighted ratio of the sth battery stack; The current is adjustable to the preset ratio; is the current reference value of the sth battery stack; is the total current value of the multi-stack reversible solid oxide battery system.

9. A current control method for a multi-stack reversible solid oxide battery system as claimed in claim 1, characterized in that: The controlling the current of each battery stack in the multi-stack reversible solid oxide battery system according to the battery stack current distribution ratio comprises: According to the current distribution ratio of the battery stack, a current reference value of each battery stack is obtained; Obtain the actual current value of each battery stack; According to the current reference value and the actual current value, a PID control method is adopted to control the current of each battery stack in the multi-stack reversible solid oxide battery system.

10. A current control system for a multi-stack reversible solid oxide battery system, characterized in that: include: A data acquisition module, for acquiring electrode data and a degree of YSZ electrolyte degradation of the multi-stack reversible solid oxide battery system according to a current operation mode of the multi-stack reversible solid oxide battery system; A relative decay degree calculation module for a battery stack, used for inputting the electrode data and the degradation degree of the YSZ electrolyte into a preset fuzzy neural network to obtain the relative decay degree of each battery stack; A reactant flow ratio calculation module is used to calculate the reactant flow ratio of each stack according to the reactant gas flow rate of the multi-stack reversible solid oxide battery system; A current distribution ratio calculation module, used to calculate the current distribution ratio of each fuel cell according to the proportion of the fuel cell reactant flow and the relative decay degree of the fuel cell; A current control module is used to control the current of each battery stack in the multi-stack reversible solid oxide battery system according to the battery stack current distribution ratio.

Images