Intelligent pressure control method for multi-electrolytic-bath collaborative water electrolysis hydrogen-oxygen system based on dynamic filtering algorithm

Abstract

The invention provides a dynamic filtering algorithm-based intelligent pressure control method for a multi-electrolytic-bath collaborative water electrolysis hydrogen-oxygen system, and relates to the technical field of pressure control of an electric hydrogen production system. The method comprises the following steps: collecting operation data of each electrolytic cell in real time, wherein the operation data comprises a current value, a temperature value, a hydrogen partial pressure value and an oxygen partial pressure value; performing filtering processing on the operation data through a dynamic weighted sliding filtering algorithm to obtain filtered operation data; calculating independent target pressure of each electrolytic cell according to the filtered operation data to obtain an independent target pressure set; constructing a knowledge graph corresponding to each electrolytic cell and generating a pressure balance coefficient corresponding to each electrolytic cell; determining a set pressure value of each electrolytic cell according to the pressure balance coefficient corresponding to each electrolytic cell and the independent target pressure set; and controlling a pressure regulating valve of each electrolytic bath according to the set pressure value of each electrolytic bath. The problem of low temperature control accuracy in the prior art is solved.

Description

Technical Field

[0001] The present invention relates to the technical field of pressure control of electric hydrogen production systems, and in particular to an intelligent pressure control method for a multi-electrolyzer coordinated water electrolysis of hydrogen and oxygen system based on a dynamic filtering algorithm. Background Art

[0002] Pressure control in water electrolysis hydrogen and oxygen production systems is crucial for smooth system operation, improving gas quality, reducing energy consumption, and mitigating equipment corrosion. Existing water electrolysis hydrogen and oxygen production systems use manual pressure control, which is typically set to a fixed value.

[0003] The invention patent with publication number CN115161703B discloses an intelligent pressure control method for a multi-electrolyzer coordinated water electrolysis and hydrogen-oxygen system based on a dynamic filtering algorithm, including a control method that monitors the total current, operating temperature and operating pressure of the electrolyzer through a data acquisition device, and dynamically adjusts the set pressure in combination with the rated value. Specifically, the set pressure is calculated using a first pressure adjustment coefficient that depends on the ratio of actual and rated current and temperature; the pressure adjustment coefficient is recalculated in each iterative cycle, and the set pressure is adjusted according to the actual situation of the system.

[0004] In summary, existing patents rely on a fixed rated pressure, which does not cope well with fluctuating power supply conditions, results in low pressure control accuracy and fails to solve the problem of pressure balance control when multiple electrolytic cells are connected in parallel or series. Summary of the Invention

[0005] In order to overcome the shortcomings of the prior art, the purpose of the present invention is to provide an intelligent pressure control method for a multi-electrolyzer coordinated water electrolysis hydrogen and oxygen system based on a dynamic filtering algorithm. The present invention solves the problems of low pressure control accuracy in the prior art water electrolysis hydrogen and oxygen system and the inability to solve the pressure balance control problem when multiple electrolyzers are connected in parallel or in series.

[0006] To achieve the above object, the present invention provides the following solutions:

[0007] An intelligent pressure control method for a multi-electrolyzer coordinated water electrolysis hydrogen and oxygen system based on a dynamic filtering algorithm, comprising:

[0008] Real-time collection of operating data of each electrolyzer, including current value, temperature value, hydrogen partial pressure value and oxygen partial pressure value;

[0009] Filtering the operating data using a dynamic weighted sliding filtering algorithm to obtain filtered operating data;

[0010] Calculating the independent target pressure of each electrolytic cell according to the filtered operating data to obtain an independent target pressure set;

[0011] Construct a knowledge graph corresponding to each electrolytic cell and generate the pressure equalization coefficient corresponding to each electrolytic cell;

[0012] Determining a set pressure value for each electrolytic cell according to the pressure equalization coefficient corresponding to each electrolytic cell and the independent target pressure set;

[0013] The pressure regulating valve of each electrolytic cell is controlled according to the set pressure value of each electrolytic cell.

[0014] Preferably, filtering the operating data using a dynamic weighted sliding filtering algorithm to obtain filtered operating data includes:

[0015] Constructing a dual filtering channel, wherein the dual filtering channel includes a first filtering channel and a second filtering channel;

[0016] The operating condition of the electrolytic cell is judged. If the judgment result is stable operation, the operating data is filtered using the first filter channel using time-domain weighted averaging to obtain first filtered sub-data; if the judgment result is a sudden change in current, the operating data is filtered using the second filter channel using wavelet packet decomposition to obtain second filtered sub-data;

[0017] Weighting is performed according to the first filtered sub-data and the second filtered sub-data to determine filtered operating data.

[0018] Preferably, calculating the independent target pressure of each electrolytic cell according to the filtered operating data to obtain an independent target pressure set includes:

[0019] Using the filtered current and temperature values, a temperature-pressure relationship model is established based on Faraday's law and the gas state equation to predict the target gas production pressure of each electrolyzer under different temperature conditions.

[0020] Combined with the real-time values ​​of hydrogen and oxygen partial pressures, the target gas production pressure is automatically adjusted through correlation analysis;

[0021] An independent target pressure set is determined according to the target gas production pressure.

[0022] Preferably, the method of automatically adjusting the target gas production pressure by combining the real-time values ​​of the hydrogen partial pressure and the oxygen partial pressure through correlation analysis includes:

[0023] Determining an adjustment model for the hydrogen partial pressure, the oxygen partial pressure, and the target gas production pressure using a gas state equation and correlation analysis;

[0024] The target gas production pressure is adjusted by utilizing the adjustment to obtain an adjusted target gas production pressure.

[0025] Preferably, the expression of the relationship model between temperature and pressure is:

[0026] P=C1·I+C2·T+C3;

[0027] Where P is the target gas production pressure, I is the filtered current value, T is the filtered temperature value, C1, C2, and C3 are the first constant, second constant, and third constant obtained by experimental fitting, respectively, reflecting the degree of influence of current and temperature on pressure.

[0028] Preferably, the expression of the adjustment model is:

[0029]

[0030] Where ΔP target is the adjustment amount for the target gas production pressure, and are the partial pressures of hydrogen and oxygen, T set is the set temperature, k1, k2, and k3 are the first, second, and third adjustment coefficients, respectively, reflecting the effects of partial pressure and temperature on target pressure adjustment.

[0031] Preferably, the step of constructing a knowledge graph corresponding to each electrolytic cell and generating a pressure equalization coefficient corresponding to each electrolytic cell includes:

[0032] Determine the network connection structure, pipeline impedance parameters and corresponding operating data of each electrolytic cell;

[0033] Treat each electrolytic cell as a network node and the pipeline as the edge connecting the nodes. Define the physical connection relationship and fluid flow path between the nodes and incorporate the pipeline impedance parameters to form an initial knowledge graph.

[0034] Analyzing the coupling relationship of the electrolytic cells, and mapping each feature of the operating data to the initial knowledge graph based on the network connection structure and the initial knowledge graph to determine a final knowledge graph corresponding to each electrolytic cell;

[0035] The pressure equalization coefficient is calculated using the knowledge graph corresponding to each electrolytic cell.

[0036] Preferably, the calculation expression of the pressure equalization coefficient is:

[0037]

[0038] Among them, k′1-k′6 are the first adjustment coefficient to the sixth adjustment coefficient of the equalization coefficient, C i is the pressure equalization coefficient, R i is the health status indicator of the i-th electrolytic cell, Z iis the pipeline impedance of the th electrolytic cell.

[0039] An intelligent pressure control system for a multi-electrolyzer coordinated water electrolysis and hydrogen-oxygen system based on a dynamic filtering algorithm, comprising:

[0040] An acquisition module is used to collect the operating data of each electrolyzer in real time, wherein the operating data includes current value, temperature value, hydrogen partial pressure value and oxygen partial pressure value;

[0041] A filtering module, configured to filter the operating data using a dynamic weighted sliding filtering algorithm to obtain filtered operating data;

[0042] a first calculation module, configured to calculate an independent target pressure for each electrolytic cell based on the filtered operating data to obtain an independent target pressure set;

[0043] The second calculation module is used to construct a knowledge graph corresponding to each electrolytic cell and generate a pressure equalization coefficient corresponding to each electrolytic cell;

[0044] a third calculation module, configured to determine a set pressure value for each electrolytic cell according to a pressure equalization coefficient corresponding to each electrolytic cell and an independent target pressure set;

[0045] The control module is used to control the pressure regulating valve of each electrolytic cell according to the set pressure value of each electrolytic cell.

[0046] The present invention discloses the following technical effects:

[0047] The present invention provides an intelligent pressure control method for a multi-electrolyzer coordinated water electrolysis system based on a dynamic filtering algorithm. The method comprises: collecting operating data of each electrolyzer in real time, the operating data including current value, temperature value, hydrogen partial pressure value, and oxygen partial pressure value; filtering the operating data using a dynamic weighted sliding filtering algorithm to obtain filtered operating data; calculating an independent target pressure for each electrolyzer based on the filtered operating data to obtain an independent target pressure set; constructing a knowledge graph corresponding to each electrolyzer and generating a pressure equalization coefficient corresponding to each electrolyzer; determining a set pressure value for each electrolyzer based on the pressure equalization coefficient and the independent target pressure set; and controlling the pressure regulating valve of each electrolyzer based on the set pressure value of each electrolyzer. The present invention can effectively address the many shortcomings of the prior art that use fixed rated pressures. Under fluctuating power supply conditions, relying on real-time monitoring and dynamic adjustment mechanisms, each electrolyzer can independently calculate its target pressure, thereby significantly improving control accuracy, enhancing gas quality, and reducing energy consumption. In addition, by constructing a knowledge graph, pressure balance control between electrolytic cells is achieved, which reduces corrosion and wear of equipment and extends the overall service life of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0049] Figure 1 A flow chart of an intelligent pressure control method for a multi-electrolyzer coordinated water electrolysis and hydrogen-oxygen system based on a dynamic filtering algorithm provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0050] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. 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 making creative efforts are within the scope of protection of the present invention.

[0051] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the present invention is further described in detail below with reference to the accompanying drawings and specific embodiments.

[0052] like Figure 1 As shown, the present invention provides an intelligent pressure control method for a multi-electrolyzer coordinated water electrolysis hydrogen and oxygen system based on a dynamic filtering algorithm, comprising:

[0053] Step 100: collecting operating data of each electrolytic cell in real time, wherein the operating data includes current value, temperature value, hydrogen partial pressure value, and oxygen partial pressure value;

[0054] Specifically, the current value: the current consumed by each electrolytic cell obtained by the current sensor, reflects the working status of the electrolytic cell and the intensity of the electrolytic reaction.

[0055] Temperature value: The operating temperature in the electrolytic cell is monitored by a temperature sensor. Temperature changes will affect the efficiency of the electrolytic reaction and the quality of the product gas.

[0056] Hydrogen partial pressure and oxygen partial pressure: The partial pressure of hydrogen and oxygen in the electrolyzer is measured by a partial pressure sensor, which provides direct data support for pressure control.

[0057] Step 200: filtering the operating data using a dynamic weighted sliding filtering algorithm to obtain filtered operating data;

[0058] Specifically, a dynamic weighted sliding filter algorithm is used to process collected operational data, effectively removing random noise and sudden outliers. The algorithm dynamically adjusts filter weights based on recent data to better reflect current operational trends, generating smoother and more stable filtered data.

[0059] Step 300: Calculating the independent target pressure of each electrolytic cell based on the filtered operating data to obtain an independent target pressure set;

[0060] Step 400: Construct a knowledge graph corresponding to each electrolytic cell and generate a pressure equalization coefficient corresponding to each electrolytic cell;

[0061] Step 500: determining a set pressure value for each electrolytic cell according to the pressure equalization coefficient corresponding to each electrolytic cell and the independent target pressure set;

[0062] Step 600: Control the pressure regulating valve of each electrolytic cell according to the set pressure value of each electrolytic cell.

[0063] Specifically, the system controls the pressure regulating valve of each electrolyzer to adjust the gas pressure within the electrolyzer in real time according to the set pressure value. This process uses a closed-loop control system, which continuously monitors pressure feedback information to ensure that the pressure of each electrolyzer is maintained near the set value, achieving automated and intelligent pressure control.

[0064] The following are specific embodiments corresponding to the above content:

[0065] Step 1: Each electrolyzer is equipped with a current sensor, a temperature sensor, and a pressure sensor. The system collects current, temperature, and gas pressure data every second and transmits the data to the central control unit.

[0066] Step 2: The central control unit uses a dynamic weighted sliding filter algorithm to process the received current, temperature, and gas partial pressure data. For example, if the current hydrogen partial pressure data of the electrolyzer is 70Pa, the stable hydrogen partial pressure data after filtering is 65Pa.

[0067] Step 3: Based on the relationship between current and temperature, the target pressure for each electrolytic cell is calculated using a preset model. For example, the target pressure for electrolytic cell 1 is calculated to be 500 Pa, the target pressure for electrolytic cell 2 is 480 Pa, and so on. This forms an independent target pressure set of [500, 480, 490, 470, 460] Pa.

[0068] Step 4: Build a knowledge graph for electrolytic cells, with nodes representing each cell and edges representing their connections and interactions. Calculate the pressure equalization coefficient for each cell. Assume that the pressure equalization coefficient for cell 1 is 1.2, the pressure equalization coefficient for cell 2 is 1.1, and so on.

[0069] Step 5: By combining the independent target pressure set and the pressure equalization coefficient, the set pressure value is finally determined. For example, the set pressure of electrolytic cell 1 is 500×1.2=600500×1.2=600Pa, and the set pressure of electrolytic cell 2 is 480×1.1=528480×1.1=528Pa.

[0070] Step 6: The PLC controls the pressure regulating valves of each electrolytic cell, adjusting the valve opening in real time to maintain the pressure of each cell near the set value. If the pressure of electrolytic cell 1 falls below 600 Pa, the system will automatically open the regulating valve to increase gas flow.

[0071] Furthermore, filtering the operating data using a dynamic weighted sliding filtering algorithm to obtain filtered operating data includes:

[0072] Constructing a dual filtering channel, wherein the dual filtering channel includes a first filtering channel and a second filtering channel;

[0073] The operating condition of the electrolytic cell is judged. If the judgment result is stable operation, the operating data is filtered using the first filter channel using time-domain weighted averaging to obtain first filtered sub-data; if the judgment result is a sudden change in current, the operating data is filtered using the second filter channel using wavelet packet decomposition to obtain second filtered sub-data;

[0074] Weighting is performed according to the first filtered sub-data and the second filtered sub-data to determine filtered operating data.

[0075] Specifically, a dual filtering channel is designed, including a first filtering channel and a second filtering channel. This design allows the selection of appropriate filtering methods according to different operating conditions, thereby optimizing data processing effects;

[0076] The system monitors the working status of the electrolyzer in real time and uses pattern recognition to determine the current operating conditions. The judgment results include:

[0077] Stable operation: In this case, the working state of the electrolyzer is relatively consistent and can maintain stable current and temperature.

[0078] Current mutation: When the current of the electrolytic cell suddenly changes or fluctuates abnormally, it may cause instability in the operating data. This situation requires special treatment.

[0079] If the result is stable operation:

[0080] In the first filtering pass, the running data is filtered using the time-domain weighted average method. This method takes a weighted average of the data at consecutive time points;

[0081] If the judgment result is a sudden change in current:

[0082] In the second filtering channel, wavelet packet decomposition is used for filtering. Wavelet packet decomposition can analyze signals at different frequency and time scales. The specific process includes:

[0083] Perform wavelet transform on the original running data to obtain sub-signals of different frequencies.

[0084] Threshold processing is performed on high-frequency noise components to remove abnormal data.

[0085] The signal is reconstructed by inverse transformation to generate second filter sub-data, which is more suitable for use in the case of current mutation.

[0086] This embodiment also specifically discloses the criteria for judging a sudden change in current:

[0087] The electrolytic cell's current values ​​are collected in real time and a time series dataset is constructed. Features are extracted from this time series. A machine learning algorithm is trained using supervised learning based on historical operating data for both normal and sudden changes in current flow, identifying and distinguishing between normal and sudden changes in current flow.

[0088] Stable operation: If the current pattern matches the normal operating pattern, the electrolyzer is judged to be "stable operation".

[0089] Current mutation: If the current pattern is identified as a mutation pattern, it is considered a "current mutation." The pattern recognition model should be able to identify large current fluctuations and sudden changes.

[0090] Furthermore, the independent target pressure of each electrolytic cell is calculated based on the filtered operating data to obtain an independent target pressure set, including:

[0091] Using the filtered current and temperature values, a temperature-pressure relationship model is established based on Faraday's law and the gas state equation to predict the target gas production pressure of each electrolyzer under different temperature conditions.

[0092] Combined with the real-time values ​​of hydrogen and oxygen partial pressures, the target gas production pressure is automatically adjusted through correlation analysis;

[0093] An independent target pressure set is determined according to the target gas production pressure.

[0094] Furthermore, the method of automatically adjusting the target gas production pressure by combining the real-time values ​​of the hydrogen partial pressure and the oxygen partial pressure through correlation analysis includes:

[0095] Determining an adjustment model for the hydrogen partial pressure, the oxygen partial pressure, and the target gas production pressure using a gas state equation and correlation analysis;

[0096] The target gas production pressure is adjusted by utilizing the adjustment to obtain an adjusted target gas production pressure.

[0097] Specifically, sensors are used to monitor the hydrogen and oxygen partial pressures in real time, and these values ​​are compared and analyzed with the calculated target gas production pressure. Changes in the hydrogen and oxygen partial pressures will directly affect the gas balance and reaction efficiency within the electrolyzer.

[0098] For the real-time hydrogen and oxygen partial pressures, correlation analysis is performed to identify the relationship between them and the calculated target gas production pressure. This process can utilize data analysis methods, including statistical analysis, to identify the impact of changes in gas partial pressure on the target gas production pressure.

[0099] Analysis revealed that when the hydrogen partial pressure is too low, it usually means that the electrolyzer is producing insufficient hydrogen. In this case, it is necessary to appropriately increase the target gas production pressure to increase the gas generation rate. When the oxygen partial pressure is too high, there may be safety hazards, and it is necessary to consider reducing the pressure to avoid the risk of explosion.

[0100] Furthermore, the adjusted target gas production pressure of each electrolyzer is collected to form an independent target pressure set. The target pressure of each electrolyzer is determined based on its current operating status and real-time data, thus achieving precise control of each electrolyzer.

[0101] Such an independent target pressure set not only improves the gas yield, but also enhances the overall safety and reliability of the system, ensuring that the electrolyzer is always in optimal operating condition under fluctuating power conditions and environmental changes.

[0102] Furthermore, the expression of the relationship model between temperature and pressure is:

[0103] P=C1·I+C2·T+C3;

[0104] Where P is the target gas production pressure, I is the filtered current value, T is the filtered temperature value, C1, C2, and C3 are the first constant, second constant, and third constant obtained by experimental fitting, respectively, reflecting the degree of influence of current and temperature on pressure.

[0105] Specifically, for obtaining the first constant, the second constant and the third constant:

[0106] Variable Settings: Set current and temperature as independent variables, controlling one while changing the other to observe the effect on pressure. Select from multiple current levels (e.g., low, medium, high) and multiple temperature conditions (e.g., room temperature, heated, etc.).

[0107] Data acquisition: Under each experimental condition, the current value, temperature value and the corresponding hydrogen or oxygen production pressure are monitored and recorded in real time through sensors.

[0108] Statistical regression analysis method is used to establish a mathematical relationship model between current, temperature and pressure.

[0109] A linear relationship is selected and regression analysis is performed using experimental data to minimize the sum of squared residuals to determine the optimal fitting parameters. The fitting results yield the first, second, and third constants that reflect the effects of current and temperature on the target gas production pressure. These constants vary depending on the specific experimental data, reflecting their relative influence under specific conditions.

[0110] Furthermore, the expression of the adjustment model is:

[0111]

[0112] Where ΔP target is the adjustment amount for the target gas production pressure, and are the partial pressures of hydrogen and oxygen, T set is the set temperature, k1, k2, and k3 are the first, second, and third adjustment coefficients, respectively, reflecting the effects of partial pressure and temperature on target pressure adjustment.

[0113] Specifically, the partial pressure adjustment experiment: Design an experiment to understand the actual impact of changes in hydrogen and oxygen partial pressures on the target gas production pressure. Set different hydrogen and oxygen partial pressures and observe their effects on the electrolyzer pressure.

[0114] Temperature Condition Variation: Under different temperature settings, record the partial pressures of hydrogen and oxygen and the corresponding target gas production pressures. Use the aforementioned experimental data processing method to process them and obtain the adjustment coefficient.

[0115] Furthermore, the construction of the knowledge graph corresponding to each electrolytic cell and the generation of the pressure equalization coefficient corresponding to each electrolytic cell include:

[0116] Determine the network connection structure, pipeline impedance parameters and corresponding operating data of each electrolytic cell;

[0117] Treat each electrolytic cell as a network node and the pipeline as the edge connecting the nodes. Define the physical connection relationship and fluid flow path between the nodes and incorporate the pipeline impedance parameters to form an initial knowledge graph.

[0118] Analyzing the coupling relationship of the electrolytic cells, and mapping each feature of the operating data to the initial knowledge graph based on the network connection structure and the initial knowledge graph to determine a final knowledge graph corresponding to each electrolytic cell;

[0119] The pressure equalization coefficient is calculated using the knowledge graph corresponding to each electrolytic cell.

[0120] Specifically, the network connection structure is determined as follows:

[0121] Identify electrolytic cells: List the numbers and locations of all electrolytic cells and clearly identify the function of each electrolytic cell.

[0122] Connections: Determine the connections between the various electrolytic cells. Each electrolytic cell may have direct piping connections to one or more other electrolytic cells. Record the piping type and connection method for these connections, including parallel and series configurations.

[0123] Measurement of pipeline impedance parameters:

[0124] Pipeline impedance calibration: Measure the impedance of each pipeline, including friction loss and local resistance during fluid flow. Experimentally determine the pressure loss of the fluid as it flows through the pipeline. This can be accomplished using flow experiments and pressure sensors.

[0125] Establish a parameter database: record the impedance parameters of each pipeline in the database.

[0126] More specifically, the electrolytic cell and its interconnected pipeline models are converted into a knowledge graph:

[0127] Consider an electrolyzer as a network node:

[0128] Node definition: Each electrolytic cell is regarded as a node in the graph and assigned a unique identifier to facilitate the subsequent graph structure representation.

[0129] Attribute assignment: Add attribute information to each node, such as the actual operating data of the electrolyzer (current, temperature, partial pressure, etc.).

[0130] Use pipes as edges connecting nodes:

[0131] Edge Definition: Based on the connection between electrolytic cells, pipelines are considered edges connecting nodes. In the graph, an edge connects two nodes, identifying their corresponding impedance parameters and fluid flow direction.

[0132] Graph formation: Build an initial knowledge graph that represents the connections between nodes (electrolyzers) and fluid flow paths. The resulting graph should clearly indicate the impedance parameters of each pipeline for subsequent analysis.

[0133] Analyze the coupling relationship of each electrolytic cell:

[0134] Based on the constructed preliminary knowledge graph, the coupling relationship between different electrolyzers is further analyzed.

[0135] Coupling relationship analysis:

[0136] Feature Mapping: Use the features in the operational data (such as current, temperature, and voltage) to map them to the defined initial knowledge graph. During this process, node attributes can be used for association to ensure that each node corresponds to its latest feature data.

[0137] Analyze coupling effects: Identify the coupling effects of each electrolyzer within the entire system, including how it affects the operating status of adjacent electrolyzers. Graph theory can be used to analyze network redundancy and flow paths.

[0138] Reconstruct the knowledge graph: Based on the results of the coupling analysis, adjust the initial knowledge graph and form the final knowledge graph. Ensure that all connection relationships, node attributes, and flow paths are accurately reflected and included.

[0139] Verify the rationality of the structure: Through the simulation of actual operation data, check whether the final knowledge graph can accurately reflect the operating characteristics of the electrolyzer in actual operation.

[0140] Using the constructed knowledge graph, the pressure balance coefficient of each electrolytic cell is calculated.

[0141] Define the pressure equalization coefficient:

[0142] The significance of the pressure equalization coefficient: It indicates the contribution of a particular electrolytic cell to the overall system pressure under certain operating conditions. This coefficient can help optimize the electrolytic cell's operating state and properly regulate the overall system pressure.

[0143] Calculation process:

[0144] Fluid Dynamics Model: Using fluid dynamics principles, combined with known pipeline impedance and electrolytic cell operating data, the pressure variation of each electrolytic cell is calculated. Under the theoretical model, the pressure equalization coefficient is calculated based on the characteristics of each electrolytic cell and its position in the knowledge graph.

[0145] Coefficient Optimization: Utilize heuristic algorithms or numerical simulation methods to optimize the pressure equalization coefficient calculation process, ensuring high efficiency and accuracy of the results. For example, an iterative method can be used to adjust the operating parameters of each electrolyzer to achieve optimal pressure equalization.

[0146] Furthermore, the calculation expression of the pressure equalization coefficient is:

[0147]

[0148] Among them, k′1-k′6 are the first adjustment coefficient to the sixth adjustment coefficient of the equalization coefficient, C i is the pressure equalization coefficient, R i is the health status indicator of the i-th electrolytic cell, Z i is the pipeline impedance of the th electrolytic cell.

[0149] This embodiment also provides an intelligent pressure control system for a multi-electrolyzer coordinated water electrolysis and hydrogen-oxygen system based on a dynamic filtering algorithm, including:

[0150] An acquisition module is used to collect the operating data of each electrolyzer in real time, wherein the operating data includes current value, temperature value, hydrogen partial pressure value and oxygen partial pressure value;

[0151] A filtering module, configured to filter the operating data using a dynamic weighted sliding filtering algorithm to obtain filtered operating data;

[0152] a first calculation module, configured to calculate an independent target pressure for each electrolytic cell based on the filtered operating data to obtain an independent target pressure set;

[0153] The second calculation module is used to construct a knowledge graph corresponding to each electrolytic cell and generate a pressure equalization coefficient corresponding to each electrolytic cell;

[0154] a third calculation module, configured to determine a set pressure value for each electrolytic cell according to a pressure equalization coefficient corresponding to each electrolytic cell and an independent target pressure set;

[0155] The control module is used to control the pressure regulating valve of each electrolytic cell according to the set pressure value of each electrolytic cell.

[0156] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other.

[0157] This document uses specific examples to illustrate the principles and implementation methods of the present invention. The above examples are only intended to help understand the method and core concept of the present invention. At the same time, those skilled in the art will find that the specific implementation methods and application scopes may vary based on the concept of the present invention. In summary, the contents of this specification should not be construed as limiting the present invention.

Claims

1. An intelligent pressure control method for a multi-electrolyzer coordinated water electrolysis hydrogen and oxygen system based on a dynamic filtering algorithm, characterized in that: include: Real-time collection of operating data of each electrolyzer, including current value, temperature value, hydrogen partial pressure value and oxygen partial pressure value; Filtering the operating data using a dynamic weighted sliding filtering algorithm to obtain filtered operating data; Calculating the independent target pressure of each electrolytic cell according to the filtered operating data to obtain an independent target pressure set; Construct a knowledge graph corresponding to each electrolytic cell and generate the pressure equalization coefficient corresponding to each electrolytic cell; Determining a set pressure value for each electrolytic cell according to the pressure equalization coefficient corresponding to each electrolytic cell and the independent target pressure set; The pressure regulating valve of each electrolytic cell is controlled according to the set pressure value of each electrolytic cell.

2. The intelligent pressure control method for a multi-electrolyzer coordinated water electrolysis and hydrogen-oxygen system based on a dynamic filtering algorithm according to claim 1 is characterized in that: The filtering process of the operating data by a dynamic weighted sliding filtering algorithm to obtain filtered operating data includes: Constructing a dual filtering channel, wherein the dual filtering channel includes a first filtering channel and a second filtering channel; The operating condition of the electrolytic cell is judged. If the judgment result is stable operation, the operating data is filtered using the first filter channel using time-domain weighted averaging to obtain first filtered sub-data; if the judgment result is a sudden change in current, the operating data is filtered using the second filter channel using wavelet packet decomposition to obtain second filtered sub-data; Weighting is performed according to the first filtered sub-data and the second filtered sub-data to determine filtered operating data.

3. The intelligent pressure control method for a multi-electrolyzer coordinated water electrolysis and hydrogen-oxygen system based on a dynamic filtering algorithm according to claim 1 is characterized in that: Calculating the independent target pressure of each electrolytic cell according to the filtered operating data to obtain an independent target pressure set includes: Using the filtered current and temperature values, a temperature-pressure relationship model is established based on Faraday's law and the gas state equation to predict the target gas production pressure of each electrolyzer under different temperature conditions. Combined with the real-time values ​​of hydrogen and oxygen partial pressures, the target gas production pressure is automatically adjusted through correlation analysis; An independent target pressure set is determined according to the target gas production pressure.

4. The intelligent pressure control method for a multi-electrolyzer coordinated water electrolysis and hydrogen-oxygen system based on a dynamic filtering algorithm according to claim 3 is characterized in that: The method of automatically adjusting the target gas production pressure by combining the real-time values ​​of the hydrogen partial pressure and the oxygen partial pressure through correlation analysis includes: Determining an adjustment model for the hydrogen partial pressure, the oxygen partial pressure, and the target gas production pressure using a gas state equation and correlation analysis; The target gas production pressure is adjusted by utilizing the adjustment to obtain an adjusted target gas production pressure.

5. The intelligent pressure control method for a multi-electrolyzer coordinated water electrolysis and hydrogen-oxygen system based on a dynamic filtering algorithm according to claim 3 is characterized in that: The expression of the relationship model between temperature and pressure is: P=C1·I+C2·T+C3; Where P is the target gas production pressure, I is the filtered current value, T is the filtered temperature value, C1, C2, and C3 are the first constant, second constant, and third constant obtained by experimental fitting, respectively, reflecting the degree of influence of current and temperature on pressure.

6. The intelligent pressure control method for a multi-electrolyzer coordinated water electrolysis and hydrogen-oxygen system based on a dynamic filtering algorithm according to claim 5 is characterized in that: The expression of the adjustment model is: Where ΔP target is the adjustment amount for the target gas production pressure, and are the partial pressures of hydrogen and oxygen, T set is the set temperature, k1, k2, and k3 are the first, second, and third adjustment coefficients, respectively, reflecting the effects of partial pressure and temperature on target pressure adjustment.

7. The intelligent pressure control method for a multi-electrolyzer coordinated water electrolysis and hydrogen-oxygen system based on a dynamic filtering algorithm according to claim 1 is characterized in that: The step of constructing a knowledge graph corresponding to each electrolytic cell and generating a pressure equalization coefficient corresponding to each electrolytic cell includes: Determine the network connection structure, pipeline impedance parameters and corresponding operating data of each electrolytic cell; Treat each electrolytic cell as a network node and the pipeline as the edge connecting the nodes. Define the physical connection relationship and fluid flow path between the nodes and incorporate the pipeline impedance parameters to form an initial knowledge graph. Analyzing the coupling relationship of the electrolytic cells, and mapping each feature of the operating data to the initial knowledge graph based on the network connection structure and the initial knowledge graph to determine a final knowledge graph corresponding to each electrolytic cell; The pressure equalization coefficient is calculated using the knowledge graph corresponding to each electrolytic cell.

8. The intelligent pressure control method for a multi-electrolyzer coordinated water electrolysis and hydrogen-oxygen system based on a dynamic filtering algorithm according to claim 7 is characterized in that: The calculation expression of the pressure equalization coefficient is: Among them, k′1-k′6 are the first adjustment coefficient to the sixth adjustment coefficient of the equalization coefficient, C i is the pressure equalization coefficient, R i is the health status indicator of the i-th electrolytic cell, Z i is the pipeline impedance of the th electrolytic cell.

9. An intelligent pressure control system for a multi-electrolyzer coordinated water electrolysis and hydrogen-oxygen system based on a dynamic filtering algorithm, characterized in that: include: An acquisition module is used to collect the operating data of each electrolyzer in real time, wherein the operating data includes current value, temperature value, hydrogen partial pressure value and oxygen partial pressure value; A filtering module, configured to filter the operating data using a dynamic weighted sliding filtering algorithm to obtain filtered operating data; a first calculation module, configured to calculate an independent target pressure for each electrolytic cell based on the filtered operating data to obtain an independent target pressure set; The second calculation module is used to construct a knowledge graph corresponding to each electrolytic cell and generate a pressure equalization coefficient corresponding to each electrolytic cell; a third calculation module, configured to determine a set pressure value for each electrolytic cell according to a pressure equalization coefficient corresponding to each electrolytic cell and an independent target pressure set; The control module is used to control the pressure regulating valve of each electrolytic cell according to the set pressure value of each electrolytic cell.

Images