Control method for operation stability of water electrolysis hydrogen production system

Abstract

The invention discloses a method for controlling the operation stability of an electrolytic water hydrogen production system, the system comprises an electrolytic bath, a power supply, a gas-liquid separator, a cooler, a circulating pump and a detection and execution mechanism, and the method comprises the following steps: S1, monitoring the operation state parameters of the system in real time, the operation state parameters at least comprise the temperature of the electrolytic bath, the pressure of the electrolytic bath, the input current density, the differential pressure of the hydrogen side and the oxygen side, the flow of circulating alkali liquor or the resistivity of deionized water; and S2, on the basis of the operation state parameters, a preset system stability evaluation model is established. According to the method, the limitation and interference problems of traditional single-loop control are overcome, the system can integrally make prospective, stable and economical collaborative response when facing internal and external disturbances, global optimal stability and energy efficiency are maintained during steady-state operation, and the stability and efficiency of the system are improved through intelligent fault tolerance and operation point self-adaptive migration under transient and abnormal working conditions. And the robustness, the safety and the full-life-cycle adaptive capacity of the system are remarkably improved.

Description

Technical Field

[0001] This invention relates to the field of clean hydrogen production technology, and in particular to a method for controlling the operational stability of a water electrolysis hydrogen production system. Background Technology

[0002] The operational stability of water electrolysis hydrogen production systems, especially those using alkaline or proton exchange membrane technologies, directly affects hydrogen production efficiency, equipment lifespan, and safe production.

[0003] However, current water electrolysis hydrogen production systems largely rely on traditional single-parameter, single-loop control strategies. For example, temperature, pressure, and flow control loops often operate independently, lacking coordination. This control approach cannot effectively address the strong coupling of multiple physical fields within the electrolyzer. Furthermore, traditional control methods typically rely on feedback adjustments based on current or past parameter deviations, failing to predict future system state evolution (e.g., due to power fluctuations). This results in lag and inadequacy in handling drastic fluctuations in renewable energy, impacting both system stability and efficiency.

[0004] To address the aforementioned issues, we have developed a control method for improving the operational stability of water electrolysis hydrogen production systems. Summary of the Invention

[0005] This invention discloses a method for controlling the operational stability of a water electrolysis hydrogen production system, aiming to solve the technical problems in the background art.

[0006] To achieve the above objectives, the present invention adopts the following technical solution: A method for controlling the operational stability of a water electrolysis hydrogen production system, the system comprising an electrolyzer, a power supply, a gas-liquid separator, a cooler, a circulating pump, and detection and execution mechanisms, characterized by comprising the following steps: S1: Real-time monitoring of the system's operating status parameters, which include at least the electrolyzer temperature, electrolyzer pressure, input current density, differential pressure between the hydrogen and oxygen sides, and the circulating alkali flow rate or deionized water resistivity. S2: Based on the operating state parameters, the overall stability margin of the current system is calculated using a preset system stability evaluation model; S3: Compare the overall stability margin with the preset target stability margin range to generate a collaborative optimization instruction; S4: According to the collaborative optimization instruction, at least two control variables are adjusted synchronously, including input electrical power, cooler power, circulating pump speed and water inflow, so that the overall stability margin returns to the target stability margin range.

[0007] In a preferred embodiment, the system stability evaluation model described in step S2 is a hybrid model that combines data-driven and physical models; The physical model is used to describe the thermal balance, electrochemical reaction and two-phase flow relationship inside the electrolytic cell, and the data-driven model is used to identify the adaptive correction amount of model parameters caused by system aging or operating condition deviation in online.

[0008] In a preferred embodiment, step S2 specifically includes: S21: Input the operating state parameters into the physical model to calculate the first stability margin evaluation value; S22: Input the time series data of the operating state parameters into the pre-trained neural network model and output the second stability margin evaluation value; S23: The first stability margin assessment value and the second stability margin assessment value are weighted and fused to obtain the comprehensive stability margin.

[0009] In a preferred embodiment, the generation of collaborative optimization instructions in step S3 is based on a model predictive control algorithm; The model predictive control algorithm uses the predicted power input over a future period as feedforward and minimizes the overall stability margin deviation and system energy consumption as optimization objectives, and solves the optimal cooperative control command sequence in a rolling manner.

[0010] In a preferred embodiment, the generation of collaborative optimization instructions in step S3 further incorporates feedforward control, specifically: Based on the predicted changes in the external input power, the power of the cooler or the speed of the circulating pump are adjusted in advance to counteract the expected power disturbances on the electrolyzer temperature and gas-liquid balance.

[0011] In a preferred embodiment, the method further includes: S5: Analyze the abnormal fluctuation patterns of the operating status parameters in real time and match them with the preset fault feature library to achieve early fault diagnosis of the system. S6: When a specific fault type is diagnosed, a fault-tolerant control strategy corresponding to the fault type is triggered. The fault-tolerant control strategy includes power reduction operation mode, parameter operation range reconstruction, or subsystem redundancy switching.

[0012] In a preferred embodiment, the fault diagnosis includes identifying the efficiency degradation of the electrolyzer. When the efficiency degradation is detected to exceed a preset threshold, the fault-tolerant control strategy is as follows: While maintaining a constant hydrogen production rate, the operating temperature setpoint of the electrolyzer is adaptively increased and the current density is adjusted accordingly based on a preset efficiency, current density, and temperature relationship MAP diagram to compensate for the decrease in hydrogen production rate caused by efficiency degradation.

[0013] In a preferred embodiment, the method further includes stability control of the system start-up and shutdown process: During the system startup phase, a phased, gradually increasing current loading method is adopted, while the speed of the circulating pump and the cooler are coordinated and controlled to ensure that the temperature and current density of the electrolytic cell rise synchronously according to the preset temperature-load curve. During system shutdown, a strategy of phased current rate reduction and gas replacement is adopted to ensure that the hydrogen and oxygen concentrations remain within a safe range throughout the shutdown process.

[0014] In a preferred embodiment, step S4 involves the simultaneous adjustment of at least two control variables, specifically including precise control of the electrolytic cell temperature difference (ΔT): By jointly adjusting the input current density, cooler power, and circulating pump speed, the temperature difference (ΔT) between the inlet and outlet of the electrolytic cell is stabilized within the preset optimal range to suppress internal thermal stress and bubble effects.

[0015] In a preferred embodiment, the method further includes: Establish a digital twin model of the system's operating status, and update the digital twin model based on real-time data; The collaborative optimization instructions are verified through advanced simulation in the digital twin model. If the simulation results meet the stability requirements, the instructions are sent to the actual system for execution; otherwise, the optimization calculation is performed again.

[0016] The method for controlling the operational stability of a water electrolysis hydrogen production system provided by this invention has the following advantages: This invention calculates a unified index of "comprehensive stability margin" by real-time monitoring of multi-dimensional operating parameters such as electrolytic cell temperature, pressure, and input current density, and inputting these parameters into a hybrid evaluation model composed of a physical model and a data-driven model. Then, based on a model predictive control algorithm, with the optimization objective of minimizing the deviation between this margin and the target range, feedforward compensation for fluctuating input power is introduced. This generates and synchronously adjusts coordinated commands for at least two control variables, including input electrical power, cooler power, and circulating pump speed. This effectively decouples the strong coupling relationships of multiple physical fields within the electrolytic cell, overcoming the limitations and interference problems of traditional single-loop control. The system can then make a forward-looking, stable, and economical coordinated response to internal and external disturbances. It not only maintains globally optimal stability and energy efficiency during steady-state operation but also significantly improves the system's robustness, safety, and life-cycle adaptability through intelligent fault tolerance and adaptive migration of operating points under transient and abnormal conditions. Attached Figure Description

[0017] Figure 1 This is a schematic diagram of the overall process of a method for controlling the operational stability of a water electrolysis hydrogen production system proposed in this invention.

[0018] Figure 2 This is a detailed flowchart of step S2 of the method for controlling the operational stability of a water electrolysis hydrogen production system proposed in this invention. Detailed Implementation

[0019] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. The components of the embodiments of this application described and marked in the accompanying drawings can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of this application provided in the accompanying drawings is not intended to limit the scope of the claimed application, but merely represents selected embodiments of this application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without inventive effort are within the scope of protection of this application.

[0020] This invention discloses a method for controlling the operational stability of a water electrolysis hydrogen production system.

[0021] Reference Figure 1 and Figure 2 As shown, a method for controlling the operational stability of a water electrolysis hydrogen production system is disclosed. The system includes an electrolyzer, a power supply, a gas-liquid separator, a cooler, a circulating pump, and detection and execution mechanisms. The method includes the following steps: S1: Real-time monitoring of the system's operating status parameters, which include at least the electrolyzer temperature, electrolyzer pressure, input current density, differential pressure between the hydrogen and oxygen sides, and the circulating alkali flow rate or deionized water resistivity. S2: Based on the operating state parameters, the overall stability margin of the current system is calculated using a preset system stability evaluation model; S3: Compare the overall stability margin with the preset target stability margin range to generate a collaborative optimization instruction; S4: According to the collaborative optimization instruction, at least two control variables are adjusted synchronously, including input electrical power, cooler power, circulating pump speed and water inflow, so that the overall stability margin returns to the target stability margin range; This embodiment introduces a unified index called comprehensive stability margin, transforming the previously isolated control of multiple parameters into a collaborative control problem aimed at the overall stability of the system. When this margin deviates from the preset target range, the controller does not independently adjust a single variable as in traditional methods, but simultaneously adjusts at least two control variables (such as input electrical power, cooler power, and circulating pump speed). This multi-variable collaborative adjustment mechanism ensures that the system can respond quickly and consistently from multiple aspects, including thermal balance, electrochemical reaction efficiency, and fluid dynamics, when dealing with internal and external disturbances. It effectively decouples the control loop interference caused by strong coupling of multiple physics fields, thereby maintaining the system in a globally optimal stable operating state.

[0022] Reference Figure 1 and Figure 2 As shown, in a preferred embodiment, the system stability evaluation model described in step S2 is a hybrid model that combines data-driven and physical models; The physical model is used to describe the thermal balance, electrochemical reaction and two-phase flow relationship inside the electrolyzer, and the data-driven model is used to identify the adaptive correction amount of model parameters caused by system aging or operating condition deviation online. In this embodiment, the physical model, based on the inherent thermal equilibrium, electrochemistry, and two-phase flow mechanism of the electrolyzer, provides a theoretical benchmark and robustness for the evaluation. The data-driven model, on the other hand, can identify and correct model errors caused by system aging, changes in catalyst activity, or deviations in operating conditions online. The combination of these two approaches allows the calculation of the overall stability margin to dynamically and adaptively track the actual state of the system, significantly improving the reliability and accuracy of the evaluation index throughout the entire system lifecycle and avoiding evaluation biases caused by parameter mismatches in pure physical models.

[0023] Reference Figure 1 and Figure 2 As shown, in a preferred embodiment, step S2 specifically includes: S21: Input the operating state parameters into the physical model to calculate the first stability margin evaluation value; S22: Input the time series data of the operating state parameters into the pre-trained neural network model and output the second stability margin evaluation value; S23: The first stability margin assessment value and the second stability margin assessment value are weighted and fused to obtain the comprehensive stability margin; In this embodiment, the first evaluation value is derived from the physical mechanism, ensuring the physical clarity of the evaluation results and their reliability under normal operating conditions. The second evaluation value is generated by a neural network, which is particularly good at capturing complex, nonlinear instability precursor patterns from the historical trends of parameter changes.

[0024] By weighting and fusing the two factors, the resulting comprehensive stability margin combines the determinism of the mechanism with the sensitivity of data-driven analysis. This enables the system not only to identify obvious steady-state deviations but also to proactively identify early signs of gradual performance degradation and sudden disturbances, providing a more comprehensive and timely basis for control decisions.

[0025] Reference Figure 1 and Figure 2 As shown, in a preferred embodiment, the generation of collaborative optimization instructions in step S3 is based on a model predictive control algorithm; The model predictive control algorithm uses the predicted power input over a future period as feedforward and minimizes the overall stability margin deviation and system energy consumption as optimization objectives, and solves the optimal cooperative control command sequence in a rolling manner. In this embodiment, the Model Predictive Control (MMCC) algorithm, through its "rolling optimization and feedforward prediction" mechanism, can simulate the dynamic behavior of the system over a future period based on the current system state and predictions of future input power. By optimizing the solution with the goal of minimizing stability margin deviation and system energy consumption, MMCC can generate a forward-looking sequence of control commands. This allows the system to prepare and adjust in advance for its own dynamic characteristics such as thermal inertia and fluid inertia, thereby achieving smoother, more stable, and more economical operation than traditional feedback control, making it particularly suitable for dealing with fluctuations in renewable energy input.

[0026] Reference Figure 1 and Figure 2 As shown, in a preferred embodiment, the generation of collaborative optimization instructions in step S3 further incorporates feedforward control, specifically: Based on the predicted changes in the external input power, the power of the cooler or the speed of the circulating pump are adjusted in advance to counteract the effects of the anticipated power disturbance on the electrolyzer temperature and gas-liquid balance. In this embodiment, the introduction of feedforward control constitutes a "feedforward-feedback" composite control architecture. The feedforward channel directly adjusts the cooler power or circulating pump speed in advance based on the predicted changes in external input power. Its mechanism generates a reverse control action to offset most of the impact of power disturbances before they actually affect the electrolyzer temperature and gas-liquid balance. This significantly reduces the fluctuation amplitude and response lag of key system parameters (such as temperature), allowing the feedback controller to perform only fine-tuning. This structure significantly improves the system's speed and stability in responding to rapid, large-amplitude power fluctuations.

[0027] Reference Figure 1 and Figure 2 As shown, in a preferred embodiment, the method further includes: S5: Analyze the abnormal fluctuation patterns of the operating status parameters in real time and match them with the preset fault feature library to achieve early fault diagnosis of the system. S6: When a specific fault type is diagnosed, a fault-tolerant control strategy corresponding to the fault type is triggered. The fault-tolerant control strategy includes power reduction operation mode, parameter operation range reconstruction, or subsystem redundancy switching. This embodiment extends the control scope from normal operating conditions to abnormal operating conditions. By matching real-time data with a preset fault feature library, early fault diagnosis (such as component performance degradation or sensor failure) can be achieved. Once a specific fault is diagnosed, the system does not simply execute shutdown protection, but intelligently triggers preset fault-tolerant control strategies (such as reduced power operation and parameter operating range reconstruction). This transforms the system from a passive "fault-shutdown" mode to an active "fault-adaptation-maintain operation" mode, greatly improving the system's availability, reliability, and continuous production capacity.

[0028] Reference Figure 1 and Figure 2 As shown, in a preferred embodiment, the fault diagnosis includes identifying the efficiency degradation of the electrolyzer. When the efficiency degradation is detected to exceed a preset threshold, the fault-tolerant control strategy is as follows: While maintaining a constant hydrogen production rate, the operating temperature setpoint of the electrolyzer is adaptively increased and the current density is adjusted accordingly based on the preset efficiency, current density, and temperature relationship MAP diagram to compensate for the decrease in hydrogen production rate caused by efficiency degradation. In this embodiment, the fault-tolerant control strategy provides an intelligent compensation scheme for adaptive operating point optimization to address the slow performance degradation of the electrolyzer. By querying a high-precision efficiency-current density-temperature MAP, the system dynamically finds the optimal operating point that can maintain the rated hydrogen production at a new efficiency level and automatically migrates to that point. This intelligently compensates for the performance loss caused by aging, effectively extending the system's effective service life and improving its economic efficiency.

[0029] Reference Figure 1 and Figure 2 As shown, in a preferred embodiment, the method further includes stability control of the system start-up and shutdown process: During the system startup phase, a phased, gradually increasing current loading method is adopted, while the speed of the circulating pump and the cooler are coordinated and controlled to ensure that the temperature and current density of the electrolytic cell rise synchronously according to the preset temperature-load curve. During system shutdown, a strategy of phased current slope reduction and gas replacement is adopted to ensure that the hydrogen and oxygen concentrations remain within a safe range throughout the shutdown process. This embodiment ensures a safe and smooth start-up and shutdown process through programmed and coordinated management of high-risk transient conditions. During startup, the phased, progressively increasing current loading, along with the coordinated control of the circulating pump and cooler, matches the temperature and current density, avoiding unfavorable conditions such as high current in the cold cell or low current in the hot cell, achieving a soft start and reducing impact on the electrode materials. During shutdown, the precise timing coordination of the phased, progressively decreasing current and gas replacement ensures that the explosive gas mixture in the electrolysis zone is sufficiently diluted before the current drops to the point of stopping gas production, eliminating the potential risk of deflagration during shutdown.

[0030] Reference Figure 1 and Figure 2 As shown, in a preferred embodiment, step S4 involves the simultaneous adjustment of at least two control variables, specifically including precise control of the electrolytic cell temperature difference (ΔT): By jointly adjusting the input current density, cooler power and circulating pump speed, the temperature difference (ΔT) between the inlet and outlet of the electrolytic cell is stabilized within the preset optimal range to suppress internal thermal stress and bubble effect. In this embodiment, by using the temperature difference (ΔT) between the inlet and outlet as the core controlled variable, and jointly adjusting three strongly coupled variables—the heat source (current density), the radiator (cooler), and the stirrer (circulation pump)—precise decoupled control of ΔT through multiple paths is achieved. This stabilizes ΔT within a relatively ideal range, effectively suppressing internal thermal stress, accelerated material aging, and unfavorable bubble adhesion effects caused by uneven temperature, fundamentally improving the internal working environment of the electrolyzer, thereby enhancing hydrogen evolution efficiency and equipment lifespan.

[0031] Reference Figure 1 and Figure 2 As shown, in a preferred embodiment, the method further includes: Establish a digital twin model of the system's operating status, and update the digital twin model based on real-time data; The collaborative optimization instructions are verified through advanced simulation in the digital twin model. If the simulation results meet the stability requirements, the instructions are sent to the actual system for execution; otherwise, the optimization calculation is performed again. This embodiment demonstrates how advanced simulation verification in a digital twin model can be performed before instructions are issued, enabling the prediction of potential consequences of the control strategy in the future. If the simulation results meet stability requirements, the instructions are executed; otherwise, they are intercepted and re-optimized. This mechanism significantly reduces the risk of damage to actual hardware due to model uncertainties or algorithmic risks, providing a high level of assurance for the safe and reliable operation of the system, especially when performing aggressive optimizations or dealing with extreme conditions.

[0032] The above description is merely a preferred embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. The substitutions may be replacements of some structures, devices, or method steps, or they may be complete technical solutions. Equivalent substitutions or modifications made to the technical solutions and inventive concepts of the present invention should all be covered within the scope of protection of the present invention.

Claims

1. A method for controlling the operational stability of a water electrolysis hydrogen production system, the system comprising an electrolyzer, a power supply, a gas-liquid separator, a cooler, a circulating pump, and detection and execution mechanisms, characterized in that, Includes the following steps: S1: Real-time monitoring of the system's operating status parameters, which include at least the electrolyzer temperature, electrolyzer pressure, input current density, differential pressure between the hydrogen and oxygen sides, and the circulating alkali flow rate or deionized water resistivity. S2: Based on the operating state parameters, the overall stability margin of the current system is calculated using a preset system stability evaluation model; S3: Compare the overall stability margin with the preset target stability margin range to generate a collaborative optimization instruction; S4: According to the collaborative optimization instruction, at least two control variables are adjusted synchronously, including input electrical power, cooler power, circulating pump speed and water inflow, so that the overall stability margin returns to the target stability margin range.

2. The method for controlling the operational stability of a water electrolysis hydrogen production system according to claim 1, characterized in that, The system stability evaluation model described in step S2 is a hybrid model that combines data-driven and physical models; The physical model is used to describe the thermal balance, electrochemical reaction and two-phase flow relationship inside the electrolytic cell, and the data-driven model is used to identify the adaptive correction amount of model parameters caused by system aging or operating condition deviation in online.

3. The method for controlling the operational stability of a water electrolysis hydrogen production system according to claim 2, characterized in that, Step S2 specifically includes: S21: Input the operating state parameters into the physical model to calculate the first stability margin evaluation value; S22: Input the time series data of the operating state parameters into the pre-trained neural network model and output the second stability margin evaluation value; S23: The first stability margin assessment value and the second stability margin assessment value are weighted and fused to obtain the comprehensive stability margin.

4. The method for controlling the operational stability of a water electrolysis hydrogen production system according to claim 1, characterized in that, The generation of collaborative optimization instructions in step S3 is based on the model predictive control algorithm; The model predictive control algorithm uses the predicted power input over a future period as feedforward and minimizes the overall stability margin deviation and system energy consumption as optimization objectives, and solves the optimal cooperative control command sequence in a rolling manner.

5. The method for controlling the operational stability of a water electrolysis hydrogen production system according to claim 1, characterized in that, The generation of collaborative optimization instructions in step S3 also introduces feedforward control, specifically: Based on the predicted changes in the external input power, the power of the cooler or the speed of the circulating pump are adjusted in advance to counteract the expected power disturbances on the electrolyzer temperature and gas-liquid balance.

6. The method for controlling the operational stability of a water electrolysis hydrogen production system according to claim 1, characterized in that, The method further includes: S5: Analyze the abnormal fluctuation patterns of the operating status parameters in real time and match them with the preset fault feature library to achieve early fault diagnosis of the system. S6: When a specific fault type is diagnosed, a fault-tolerant control strategy corresponding to the fault type is triggered. The fault-tolerant control strategy includes power reduction operation mode, parameter operation range reconstruction, or subsystem redundancy switching.

7. The method for controlling the operational stability of a water electrolysis hydrogen production system according to claim 6, characterized in that, The fault diagnosis includes identifying the efficiency degradation of the electrolyzer. When the efficiency degradation is detected to exceed a preset threshold, the fault-tolerant control strategy is as follows: While maintaining a constant hydrogen production rate, the operating temperature setpoint of the electrolyzer is adaptively increased and the current density is adjusted accordingly based on a preset efficiency, current density, and temperature relationship MAP diagram to compensate for the decrease in hydrogen production rate caused by efficiency degradation.

8. The method for controlling the operational stability of a water electrolysis hydrogen production system according to claim 1, characterized in that, The method also includes stability control during system startup and shutdown: During the system startup phase, a phased, gradually increasing current loading method is adopted, while the speed of the circulating pump and the cooler are coordinated and controlled to ensure that the temperature and current density of the electrolytic cell rise synchronously according to the preset temperature-load curve. During system shutdown, a strategy of phased current rate reduction and gas replacement is adopted to ensure that the hydrogen and oxygen concentrations remain within a safe range throughout the shutdown process.

9. The method for controlling the operational stability of a water electrolysis hydrogen production system according to claim 1, characterized in that, In step S4, at least two control variables are adjusted simultaneously, specifically including precise control of the electrolytic cell temperature difference (ΔT): By jointly adjusting the input current density, cooler power, and circulating pump speed, the temperature difference (ΔT) between the inlet and outlet of the electrolytic cell is stabilized within the preset optimal range to suppress internal thermal stress and bubble effects.

10. The method for controlling the operational stability of a water electrolysis hydrogen production system according to claim 1, characterized in that, The method further includes: Establish a digital twin model of the system's operating status, and update the digital twin model based on real-time data; The collaborative optimization instructions are verified through advanced simulation in the digital twin model. If the simulation results meet the stability requirements, the instructions are sent to the actual system for execution; otherwise, the optimization calculation is performed again.

Images