Production control method and system for water electrolysis hydrogen production catalyst

Abstract

The invention belongs to the technical field of preparation of new energy materials, and particularly provides a production control method and system for a catalyst for hydrogen production through electrolysis of water. The method comprises the following steps: collecting dynamic parameters of a precursor solution in real time; performing time sequence feature extraction on the dynamic parameters through an edge calculation node, and calculating a current density variation coefficient; the dynamic parameters and the current density variable coefficient are input into a multi-objective optimization model, and a real-time regulation and control instruction of the electro-deposition duty ratio and the annealing temperature gradient is generated; the duty ratio and the temperature gradient are adjusted according to the real-time regulation and control instruction, and the water electrolysis hydrogen production catalyst is produced based on the adjusted parameters; the distribution uniformity of elements on the surface of the catalyst is verified through a spectral analysis technology, and a verification result is fed back to the multi-objective optimization model for parameter iterative optimization. Dynamic parameters of a precursor solution are collected in real time, time sequence characteristics are extracted in combination with edge calculation nodes, a current density variable coefficient is calculated, and dynamic sensing and stability quantitative evaluation of the process state are achieved.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of new energy material preparation, and particularly relates to a production control method and system of a water electrolysis hydrogen production catalyst. BACKGROUND

[0002] Water electrolysis hydrogen production is a process of decomposing water into hydrogen and oxygen by using electric energy, and the performance key thereof depends on the catalyst efficiency of hydrogen evolution reaction (HER) and oxygen evolution reaction (OER), that is, the efficiency and cost thereof are highly dependent on the performance of the catalyst. At present, the electrodeposition method is widely used in catalyst production due to the controllable cost and adjustable composition, but there are still some limitations in actual industrial application.

[0003] For example, the dynamic adjustment capability is insufficient in the production process, which is specifically embodied in that: the existing process is operated with fixed parameters, and it is difficult to optimize in real time according to the raw material state and equipment state, resulting in low utilization rate of noble metals, poor product batch stability and other problems.

[0004] Based on this, the application provides a production control method and system of a water electrolysis hydrogen production catalyst to solve the above problems. SUMMARY

[0005] In order to overcome the deficiencies of the prior art, the application provides a production control method and system of a water electrolysis hydrogen production catalyst to solve the problems in the prior art.

[0006] One embodiment of the application provides a production control method of a water electrolysis hydrogen production catalyst, comprising the steps of:

[0007] Real-time acquisition of dynamic parameters of a precursor solution, the dynamic parameters at least including pH value, metal ion concentration and pulse frequency;

[0008] Time sequence feature extraction of the dynamic parameters by an edge computing node, calculation of a current density variation coefficient;

[0009] Input of the acquired dynamic parameters and the calculated current density variation coefficient into a multi-objective optimization model, generation of real-time regulation instructions of electrodeposition duty cycle and annealing temperature gradient;

[0010] Adjustment of the duty cycle of the electrodeposition process and the temperature gradient of the annealing process according to the real-time regulation instructions, production of a water electrolysis hydrogen production catalyst based on the adjusted parameters;

[0011] Verification of the uniformity of the element distribution on the surface of the catalyst by a spectrum analysis technology, and feedback of the verification result to the multi-objective optimization model for parameter iterative optimization.

[0012] In one of the embodiments, after the step of producing the hydrogen production catalyst for water electrolysis based on the adjusted duty cycle of the electrodeposition process and the temperature gradient of the annealing process according to the real-time control instruction, the method further comprises the following steps:

[0013] Real-time acquisition of the conductivity decay rate of the adjusted electrodeposition process, and dynamic switching of the preset deposition process according to the conductivity decay rate; wherein the dynamic switching of the preset deposition process comprises:

[0014] When it is detected that the conductivity decay exceeds the preset concentration threshold, the electrodeposition process is stopped and the preset deposition process is enabled.

[0015] In one of the embodiments, the dynamic parameters further include impurity ion concentration, and in the step of producing the hydrogen production catalyst for water electrolysis based on the adjusted duty cycle of the electrodeposition process and the temperature gradient of the annealing process according to the real-time control instruction, the method further comprises the following steps:

[0016] Real-time monitoring of the impurity ion concentration in the precursor solution;

[0017] When it is detected that the impurity ion concentration exceeds the preset concentration threshold, at least one of the following operations is performed:

[0018] Sending an enabling instruction to the filtration module to purify the precursor solution by the filtration module;

[0019] Identifying the impurity characteristics of the impurity ions, adjusting the electrodeposition duty cycle according to the impurity characteristics, and generating an updated real-time control instruction.

[0020] In one of the embodiments, in the step of producing the hydrogen production catalyst for water electrolysis based on the adjusted duty cycle of the electrodeposition process and the temperature gradient of the annealing process according to the real-time control instruction, when the temperature gradient of the annealing process is adjusted, the oxygen partial pressure and the nitrogen flow rate of the inert atmosphere in the annealing module are simultaneously controlled, specifically as follows:

[0021] When the annealing temperature is in a first temperature interval, the oxygen partial pressure is controlled to be ≤10ppm, and the nitrogen flow rate is 10-50L / min;

[0022] When the annealing temperature is in a second temperature interval, the oxygen partial pressure is controlled to be ≤100ppm, and the nitrogen flow rate is 5-20L / min;

[0023] Wherein, the nitrogen flow rate is dynamically adjusted according to the temperature gradient change rate, so that the gas pressure fluctuation in the annealing module is within a preset range;

[0024] When it is detected that the gas pressure deviation is greater than the preset range, the gas pressure balancing module is triggered for dynamic compensation.

[0025] In one embodiment, the step of inputting the collected dynamic parameters and the calculated current density variation coefficient into a multi-objective optimization model to generate real-time control commands for the electrodeposition duty cycle and annealing temperature gradient, wherein the multi-objective optimization model is jointly constructed by a multi-objective optimization algorithm and a time-series prediction model, specifically including the following steps:

[0026] Several optimization objectives are defined, including at least precious metal utilization rate, catalytic activity, and deposition layer uniformity;

[0027] A multi-objective optimization algorithm is used to generate a Pareto optimal solution set and extract the equilibrium constraint relationship between each optimization objective.

[0028] A time-series prediction model is constructed, with dynamic parameters and time-series characteristics as inputs and initial control commands for electrodeposition duty cycle and annealing temperature gradient as outputs.

[0029] The time series prediction model is co-trained based on the Pareto optimal solution set, enabling the time series prediction model to generate optimized control commands that satisfy multi-objective equilibrium constraints.

[0030] In one embodiment, the step of co-training the time series prediction model based on the Pareto optimal solution set specifically includes:

[0031] The Pareto optimal solution set is split into a training subset and a validation subset, which are used for parameter updates and hyperparameter tuning of the time series prediction model, respectively.

[0032] Constructing the decomposition loss function in, The mean square error between the predicted command and the measured data; The penalty term is for the control instruction deviating from the Pareto front; α and β are dynamically adjusted weighting coefficients.

[0033] The parameters of the time series prediction model are iteratively updated using the gradient descent algorithm until the decomposed loss function converges to a preset threshold.

[0034] This application also relates to a production control system for a water electrolysis hydrogen production catalyst, including:

[0035] The acquisition module is used to acquire dynamic parameters of the precursor solution in real time, including at least pH value, metal ion concentration and pulse frequency.

[0036] The calculation module is used to extract the time-series features of the dynamic parameters through edge computing nodes and calculate the current density variation coefficient.

[0037] The input module is used to input the collected dynamic parameters and the calculated current density variation coefficient into the multi-objective optimization model to generate real-time control commands for electrodeposition duty cycle and annealing temperature gradient.

[0038] The adjustment module is used to adjust the duty cycle of the electrodeposition process and the temperature gradient of the annealing process according to the real-time control command, and to produce a water electrolysis hydrogen production catalyst based on the adjusted parameters.

[0039] The feedback module is used to verify the uniformity of element distribution on the catalyst surface through spectral analysis and to feed the verification results back to the multi-objective optimization model for parameter iterative optimization.

[0040] This application also relates to a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the above-described method for controlling the production of hydrogen production catalyst by water electrolysis.

[0041] This application also relates to a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the above-described method for controlling the production of a water electrolysis hydrogen production catalyst.

[0042] The production control method and system for water electrolysis hydrogen production catalyst provided in the above embodiments have the following beneficial effects:

[0043] 1. By real-time acquisition of dynamic parameters of the precursor solution and extraction of temporal features and calculation of current density variation coefficient by edge computing nodes, dynamic perception and quantitative assessment of process status are achieved. By inputting dynamic parameters and variation coefficients into a multi-objective optimization model, real-time control commands for electrodeposition duty cycle and annealing temperature gradient are generated, breaking through the rigid constraints of traditional fixed parameter modes and achieving dynamic balance among multiple objectives such as precious metal utilization, catalytic activity and energy consumption. The uniformity of catalyst element distribution is verified by spectral analysis technology and fed back to model iterative optimization, forming a full-process control link of "parameter acquisition - intelligent decision-making - precise execution - closed-loop verification", ultimately improving catalyst production efficiency, batch consistency and resource utilization.

[0044] 2. In one embodiment, by acquiring the conductivity decay rate of the adjusted electrodeposition process in real time and setting a dynamic switching threshold, the risk of substrate degradation can be perceived and quantitatively assessed in real time. By using a preset intelligent switching mechanism for the deposition process (such as switching from electrodeposition to chemical vapor deposition), the process can seamlessly switch to an adaptive process when an abnormal conductivity is detected, thus overcoming the strong dependence of a single process on the substrate state. Through adaptive process switching under abnormal conditions, the continuous operation of the production line and the uniformity of the catalyst active layer are taken into account, thereby reducing downtime losses, improving equipment utilization, and ensuring product quality stability under extreme conditions.

[0045] 3. In one embodiment, by real-time monitoring of the impurity concentration in the precursor solution and setting a dynamic threshold, an immediate response to the risk of impurity accumulation is achieved; harmful impurities are removed through purification and selective adsorption to block active site contamination; co-deposition is suppressed by dynamically adjusting the electrodeposition duty cycle to improve component purity; a closed loop of "monitoring-purification-feedback" is formed, which significantly improves the purity of catalyst production and resource utilization.

[0046] 4. In one embodiment, by controlling the oxygen partial pressure threshold in the annealing temperature range in stages, the risk of lattice oxygen escape and material oxidation is suppressed in a targeted manner; by dynamically adjusting the nitrogen flow rate to match the rate of temperature change, the pressure fluctuations caused by thermal expansion are offset; and by combining the pressure compensation mechanism to maintain a stable environment inside the furnace, a multi-dimensional synergistic control of temperature, atmosphere, and pressure is formed, thereby ensuring the integrity of the catalyst active components, the stability of the support structure, and the uniformity of the microstructure, significantly improving the yield and material durability of the high-temperature annealing process. Attached Figure Description

[0047] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on the structures shown in these drawings without creative effort.

[0048] Figure 1 A flowchart of a production control method for a water electrolysis hydrogen production catalyst provided in an embodiment of the present invention;

[0049] Figure 2 This is a flowchart illustrating step S300 of a method for controlling the production of a hydrogen production catalyst via water electrolysis, as provided in an embodiment of the present invention.

[0050] Figure 3 A flowchart illustrating step S340 of a method for controlling the production of hydrogen production catalyst by water electrolysis, as provided in an embodiment of the present invention;

[0051] Figure 4 This is a schematic block diagram of a computer device provided in an embodiment of the present invention. Detailed Implementation

[0052] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present invention.

[0053] It should be noted that if the embodiments of the present invention involve directional indicators (such as up, down, left, right, front, back, etc.), the directional indicators are only used to explain the relative positional relationship and movement of the components in a specific posture. If the specific posture changes, the directional indicators will also change accordingly.

[0054] Furthermore, if the embodiments of this invention involve descriptions such as "first" or "second," these descriptions are for descriptive purposes only and should not be construed as indicating or implying their relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined with "first" or "second" may explicitly or implicitly include at least one of those features. Additionally, the use of "and / or" or "and / or" throughout the text includes three parallel solutions. For example, "A and / or B" includes solution A, solution B, or a solution where both A and B are satisfied simultaneously. Furthermore, the technical solutions of the various embodiments can be combined with each other, but this must be based on the ability of those skilled in the art to implement them. When the combination of technical solutions is contradictory or impossible to implement, it should be considered that such a combination of technical solutions does not exist and is not within the scope of protection claimed by this invention.

[0055] Reference Figures 1-3 One embodiment of the present invention provides a method for controlling the production of a catalyst for hydrogen production through water electrolysis, comprising the following steps:

[0056] S100. Real-time acquisition of dynamic parameters of the precursor solution, wherein the dynamic parameters include at least pH value, metal ion concentration and pulse frequency.

[0057] S200. The dynamic parameters are extracted using time-series features through edge computing nodes, and the current density variation coefficient is calculated.

[0058] S300: Input the collected dynamic parameters and the calculated current density variation coefficient into the multi-objective optimization model to generate real-time control commands for electrodeposition duty cycle and annealing temperature gradient.

[0059] The multi-objective optimization model is jointly constructed by the multi-objective optimization algorithm (NSGA-II) and the time series prediction model (LSTM neural network), and specifically includes the following steps:

[0060] S310. Define several optimization objectives, including at least precious metal utilization rate, catalytic activity and deposition layer uniformity;

[0061] (1) Regarding the utilization rate of precious metals:

[0062] The quantification formula is:

[0063]

[0064] Where, m deposited For the quality of deposited metal, m input This represents the total amount of metal in the precursor solution;

[0065] Constraint target: η≥95%.

[0066] (2) Regarding catalytic activity:

[0067] Evaluation index: OER (Oxygen Evolution Reaction) overpotential (@10mA / cm) 2 The determination was performed using linear sweep voltammetry (LSV).

[0068] Constraint target: Overpotential ≤ 250mV.

[0069] (3) Regarding the homogeneity of the sedimentary layer:

[0070] Quantitative indicator: Coefficient of variation (CV) of surface elemental distribution, calculated based on EDS energy dispersive spectroscopy data;

[0071] Objective: CV ≤ 2.5%.

[0072] S320. Use a multi-objective optimization algorithm to generate a Pareto optimal solution set and extract the equilibrium constraint relationship between each optimization objective;

[0073] (1) NSGA-II algorithm execution flow:

[0074] Population initialization: Randomly generate 100 candidate solutions (combinations of parameters such as duty cycle, temperature gradient, and nitrogen flow rate);

[0075] Non-dominated sorting: The solution set is sorted hierarchically according to the objective function values ​​(η, overpotential, CV value);

[0076] Crowding calculation: Ensures the diversity of the solution set distribution in the target space;

[0077] Iterative evolution: A new generation of population is generated through crossover (probability 0.8) and mutation (probability 0.1), and the Pareto front is output after 1000 cycles.

[0078] (2) Extraction of equilibrium constraint relationships:

[0079] Extract conflict rules between parameters from the Pareto solution set, for example:

[0080] Increased duty cycle (↑) → increased utilization of precious metals, but increased porosity of the deposited layer (CV value ↑);

[0081] An increase in annealing temperature gradient (↑) leads to increased catalytic activity, but also increases the risk of lattice defects.

[0082] S330. Construct a time-series prediction model, with dynamic parameters and time-series characteristics as inputs and initial control commands for electrodeposition duty cycle and annealing temperature gradient as outputs.

[0083] (1) LSTM network structure:

[0084] Input layer: dynamic parameters (pH value, metal ion concentration, pulse frequency) and time series features (mean and variance of CV value), with a dimension of 5×10 (10 historical time steps);

[0085] Hidden layers: 2 layers of LSTM units (64 neurons per layer), Dropout rate 0.2;

[0086] Output layer: electrodeposition duty cycle (regression value), annealing temperature gradient (segmented classification labels).

[0087] (2) Initial control command generation:

[0088] The model predicts process parameter requirements for the next 5 minutes based on historical data, for example:

[0089] Input: pH = 9.5, Ni 2 +=0.15mol / L, CV=5.0%;

[0090] Output: Duty cycle 35%, temperature gradient 200℃→600℃.

[0091] S340. Based on the Pareto optimal solution set, the time series prediction model is co-trained to generate optimized control commands that satisfy multi-objective equilibrium constraints. Step S340 specifically includes:

[0092] S341. Split the Pareto optimal solution set into a training subset and a validation subset, which are used for parameter updates and hyperparameter tuning of the time series prediction model, respectively.

[0093] Training set (80% Pareto solution): used to update LSTM weight parameters and learn the parameter mapping rules under multi-objective constraints;

[0094] Validation set (20% Pareto solution): Used to tune hyperparameters (learning rate, batch size) and prevent overfitting.

[0095] S342. Constructing the decomposition loss function

[0096] Where α and β are dynamically adjusted weighting coefficients;

[0097] To ensure the accuracy of basic predictions, the mean square error between the prediction instructions and the measured data is calculated.

[0098]

[0099] To regulate the penalty term for instructions that deviate from the Pareto front, the model output is forced to approximate the Pareto front.

[0100] Where, p j The nearest dominant solution in the Pareto solution set, ∈ = 0.1 is the tolerance threshold;

[0101] Dynamic weight adjustment:

[0102] Initial stage: α = 0.7, β = 0.3 (focusing on prediction accuracy);

[0103] Later stage of iteration: α = 0.3, β = 0.7 (strengthening multi-objective constraints).

[0104] S343. Iteratively update the parameters of the time series prediction model using the gradient descent algorithm until the decomposed loss function converges to the preset threshold.

[0105] Optimizer: Adam algorithm (learning rate 0.001, decay rate 0.9);

[0106] Convergence condition: Rate of change of the loss function Lasting for 10 epochs;

[0107] Training results: Model performance on the validation set The convergence to 0.15 indicates that the Pareto approximation of the control command is 92%.

[0108] S400. Adjust the duty cycle of the electrodeposition process and the temperature gradient of the annealing process according to the real-time control command, and produce the water electrolysis hydrogen production catalyst based on the adjusted parameters.

[0109] S500 verifies the uniformity of element distribution on the catalyst surface using spectral analysis technology, and feeds the verification results back to a multi-objective optimization model for parameter iterative optimization.

[0110] In this embodiment, we take the production of NiFe-LDH catalyst as an example:

[0111] (1) As described in step S100 above, dynamic parameters are collected in real time:

[0112] Precursor solution preparation: The molar ratio of nickel nitrate (Ni(NO3)2) to ferric nitrate (Fe(NO3)3) is 3:1, and the total metal ion concentration is 0.2 mol / L; urea is used as the precipitant, and the pH of the solution is maintained at 9.5±0.2 (alkaline environment promotes the growth of LDH layered structure); the electrodeposition pulse frequency is set to 20 Hz, and the pulse waveform is a square wave.

[0113] Parameter acquisition equipment: pH value acquisition uses a high-precision sensor, metal ion concentration acquisition uses a spectrometer, and pulse frequency acquisition uses a digital pulse generator.

[0114] By collecting dynamic parameters in real time, a real-time data foundation is provided for production process optimization, ensuring the continuity of parameter collection and response speed, and supporting subsequent multi-objective decision-making.

[0115] (2) As described in step S200 above, time-series feature extraction and current density variation coefficient (CV value) calculation:

[0116] Edge computing module: Deploy NVIDIA Jetson Xavier with a time window set to 5 minutes; extract the average current density (μ = 15 mA / cm²). 2 ), standard deviation (σ=0.75mA / cm) 2 ), pulse frequency main frequency energy (20Hz accounts for 85%).

[0117] Calculation of current density coefficient of variation (CV value):

[0118] The formula for calculating the coefficient of variation (CV) of current density is as follows:

[0119]

[0120] Where σ is the standard deviation of current density; μ is the mean.

[0121] CV = 0.75 / 15 × 100% = 5.0%. That is, when CV > 5%, an early warning is triggered, indicating a risk to the homogeneity of the sedimentary layer.

[0122] (3) As described in step S300 above, the multi-objective optimization model generates control commands:

[0123] Model input: Dynamic parameters (pH = 9.5, Ni) 2+ =0.15mol / L, Fe 3+ =0.05mol / L, pulse frequency =20Hz), timing characteristics (CV =5.0%).

[0124] Optimization goals and outputs:

[0125] Objective 1 (precious metal utilization rate): Ni / Fe atomic ratio close to 3:1 (precious metal utilization rate ≥95%);

[0126] Target 2 (catalytic activity): OER overpotential ≤ 250mV @ 10mA / cm 2 ;

[0127] Objective 3 (Uniformity): Surface element distribution CV ≤ 2.5%;

[0128] Output instructions:

[0129] The duty cycle was adjusted from 30% to 35%, and the annealing temperature gradient was changed from 200℃ to 400℃ to 600℃ (heating rate 5℃ / min).

[0130] (4) As described in step S400 above, process control and catalyst production:

[0131] Electrodeposition process:

[0132] A titanium mesh substrate (1cm×2cm) was immersed in a precursor solution and deposited at a duty cycle of 35% for 30 minutes, with a deposition thickness of ≈500nm.

[0133] Pulse current density 15mA / cm 2 The sedimentary layer exhibits a uniform porous structure.

[0134] Annealing treatment:

[0135] The annealing furnace (nitrogen atmosphere, O2 partial pressure ≤10ppm) was used to process the mixture at 200℃ (1h) → 400℃ (1h) → 600℃ (2h) to form a NiFe-LDH / oxide mixed phase.

[0136] (5) As described in step S500 above, uniformity verification and feedback optimization:

[0137] Surface analysis:

[0138] EDS energy dispersive spectroscopy: Ni / Fe atomic ratio = 2.95:1 (close to the target 3:1), surface elemental distribution CV = 2.3%;

[0139] Electrochemical test: OER overpotential 245mV@10mA / cm 2 (1M KOH, vs. RHE).

[0140] Model feedback:

[0141] The CV = 2.3% and the overpotential data are fed back into the multi-objective optimization model;

[0142] The model reduced the weight of precious metal utilization (from 0.5 to 0.4) and increased the weight of uniformity (from 0.3 to 0.5), and the duty cycle was fine-tuned to 33% after iteration.

[0143] This embodiment achieves dynamic perception and quantitative assessment of process status by real-time acquisition of dynamic parameters of the precursor solution and extraction of temporal features and calculation of current density variation coefficient by edge computing nodes. By inputting dynamic parameters and variation coefficients into a multi-objective optimization model, real-time control commands for electrodeposition duty cycle and annealing temperature gradient are generated, breaking through the rigid constraints of traditional fixed parameter modes and achieving dynamic balance among multiple objectives such as precious metal utilization, catalytic activity, and energy consumption. The uniformity of catalyst element distribution is verified by spectral analysis technology and fed back to the model for iterative optimization, forming a full-process control link of "parameter acquisition - intelligent decision-making - precise execution - closed-loop verification", ultimately improving catalyst production efficiency, batch consistency, and resource utilization.

[0144] In one embodiment, after step S400, the following steps are further included:

[0145] S410. Real-time acquisition of the conductivity decay rate of the adjusted electrodeposition process, and dynamic switching of the preset deposition process based on the conductivity decay rate; wherein, dynamic switching of the preset deposition process includes:

[0146] When conductivity decay is detected to exceed a preset concentration threshold, the electrodeposition process is stopped and a preset deposition process is started.

[0147] In this embodiment, the production of NiFe-LDH catalyst is taken as an example:

[0148] Based on the above step S400:

[0149] Electrodeposition parameters: duty cycle 35%, pulse frequency 20Hz, deposition time 30 minutes, to generate a porous NiFe-LDH precursor layer;

[0150] Annealing process: Nitrogen annealing at 600℃ for 2 hours to form a NiFe-LDH / oxide mixed phase.

[0151] Based on step S400, conductivity decay monitoring and process switching are added. Conductivity decay monitoring is used to capture process anomalies (such as electrode contamination and solution impurities) in real time to avoid the generation of inefficient catalysts. Dynamic process switching is used to clean contaminated electrodes, restore the production baseline, and switch processes to compensate for the instantaneous defects in electrodeposition and ensure production continuity.

[0152] (1) For conductivity attenuation monitoring, a four-probe resistor was used to measure the resistivity of the deposited layer in real time, with a sampling interval of 5 seconds; the initial conductivity reference value was 1.2×10-3S / cm (corresponding to a deposited layer thickness of 500nm).

[0153] Attenuation rate calculation:

[0154]

[0155] Where σ0 is the initial conductivity, σ t For real-time conductivity.

[0156] (2) For dynamic switching logic:

[0157] Preset threshold: Conductivity attenuation rate > 5% (corresponding to σ) t <1.14×10-3S / cm);

[0158] Abnormal scenario: A decay rate of 6.8% (σ) was detected after 30 minutes of deposition. t =1.12×10-3S / cm), which was determined to be due to electrode contamination leading to conductivity degradation;

[0159] Switching actions:

[0160] (i) Immediately stop the electrodeposition process and start the automatic electrode cleaning program (ultrasonic cleaning + dilute hydrochloric acid immersion);

[0161] (ii) Utilize a pre-defined chemical vapor deposition (CVD) process as an alternative:

[0162] Precursor: Ni(acac)2 / Fe(acac)3 mixed vapor;

[0163] Deposition temperature: 300℃, carrier gas (N2) flow rate: 50L / min;

[0164] Deposition time: 20 minutes, generating an LDH substrate modified with NiFe alloy nanoparticles.

[0165] This embodiment achieves real-time perception and quantitative assessment of substrate degradation risk by acquiring the conductivity decay rate of the adjusted electrodeposition process in real time and setting a dynamic switching threshold. Through a preset intelligent switching mechanism for the deposition process (such as switching from electrodeposition to chemical vapor deposition), it seamlessly switches to an adaptive process when an abnormal conductivity is detected, breaking through the strong dependence of a single process on the substrate state. Through adaptive process switching under abnormal operating conditions, it takes into account both continuous production line operation and catalyst active layer uniformity, thereby reducing downtime losses, improving equipment utilization, and ensuring product quality stability under extreme operating conditions.

[0166] In one embodiment, the dynamic parameter in step S100 further includes the impurity ion concentration; step S400 further includes:

[0167] S401. Real-time monitoring of impurity ion concentration in precursor solution;

[0168] S402. When the concentration of impurity ions is detected to exceed a preset concentration threshold, perform at least one of the following operations:

[0169] (i) Send a start command to the filtration module so that the filtration module can purify the precursor solution;

[0170] (ii) Identify the impurity characteristics of impurity ions, adjust the electrodeposition duty cycle according to the impurity characteristics, and generate updated real-time control commands.

[0171] In this embodiment, the production of NiFe-LDH catalyst is taken as an example:

[0172] For the preparation of the precursor solution in step S100: the molar ratio of nickel nitrate (Ni(NO3)2) to iron nitrate (Fe(NO3)3) is 3:1, and the total metal ion concentration is 0.2 mol / L; urea is used as the precipitant, and the pH value of the solution is maintained at 9.5±0.2 (alkaline environment promotes the growth of LDH layered structure); the electrodeposition pulse frequency is set to 20Hz, and the pulse waveform is a square wave.

[0173] The impurity monitoring targets are: Cl- (from raw material impurities), Fe... 2+ (byproducts of incomplete oxidation).

[0174] The impurity monitoring equipment includes: an ion chromatograph (for monitoring Cl- concentration) and a spectrophotometer (for monitoring Fe). 2+ concentration).

[0175] Based on step S400, impurity concentration monitoring and processing are added;

[0176] S401: Real-time monitoring of impurity concentration

[0177] If the monitored real-time data is:

[0178] Cl- concentration: 60ppm (exceeds the limit, preset threshold 50ppm);

[0179] Fe 2+ Concentration: 2.3 ppm (compliant, threshold 5 ppm).

[0180] S402: Procedure for handling excessive impurities:

[0181] (1) Operation (i) Start the filtering module:

[0182] The 0.22μm ceramic membrane filter was activated at a flow rate of 50L / h for 30 minutes of circulation filtration; the Cl- concentration after treatment was 10ppm (meeting the standard).

[0183] (2) Operation (ii) Adjusting electrodeposition parameters:

[0184] Impurity characteristics identification: Excessive Cl- leads to a loose deposit layer (SEM shows a 15% increase in porosity);

[0185] Duty cycle adjustment: reduced from 35% to 28%, pulse frequency increased to 25Hz to suppress Cl- co-deposition;

[0186] Model instruction update: The multi-objective optimization model regenerates the annealing gradient to repair porosity defects, such as (200℃→500℃→700℃).

[0187] This embodiment achieves immediate response to the risk of impurity accumulation by real-time monitoring of the impurity concentration in the precursor solution and setting a dynamic threshold; it removes harmful impurities through purification to block contamination of active sites; it suppresses co-deposition by dynamically adjusting the electrodeposition duty cycle to improve component purity; and it forms a closed loop of "monitoring-purification-feedback" to significantly improve the purity of catalyst production and resource utilization.

[0188] In one embodiment, during step S400, when adjusting the temperature gradient of the annealing process, the oxygen partial pressure and nitrogen flow rate of the inert atmosphere within the annealing module are simultaneously controlled, specifically as follows:

[0189] When the annealing temperature is in the first temperature range, control the oxygen partial pressure to be ≤10ppm and the nitrogen flow rate to be 10-50L / min.

[0190] When the annealing temperature is in the second temperature range, control the oxygen partial pressure to be ≤100ppm and the nitrogen flow rate to be 5-20L / min.

[0191] The nitrogen flow rate is dynamically adjusted according to the temperature gradient change rate to keep the pressure fluctuation in the annealing module within a preset range.

[0192] When a pressure deviation is detected to be greater than the preset range, the pressure balance module is triggered to perform dynamic compensation.

[0193] In this embodiment, the production of NiFe-LDH catalyst is taken as an example:

[0194] (1) Annealing process design:

[0195] First temperature range: 200℃→400℃ (heating rate 5℃ / min), used to remove precursor water of crystallization and organic residue;

[0196] Second temperature range: 400℃→800℃ (heating rate 3℃ / min), promoting the transformation of NiFe-LDH to NiFeO. x Spinel phase transformation.

[0197] (2) Atmosphere control logic:

[0198]

[0199] (3) Dynamic air pressure compensation:

[0200] Preset pressure range: atmospheric pressure ±100Pa;

[0201] Abnormal scenario: When the temperature rises to 600℃, the gas pressure increases by 150Pa due to gas expansion;

[0202] Compensation measures:

[0203] Trigger the air pressure balance module and start the auxiliary air pump (air pumping rate 10L / min, for 2 minutes);

[0204] Simultaneously reduce the nitrogen flow rate to 12L / min to restore the gas pressure to +20Pa (meeting the standard).

[0205] The device is described in detail below:

[0206] (1) Annealing equipment:

[0207] Tubular annealing furnace (temperature resistance 1200℃), with built-in multi-channel gas mass flow controller (MFC);

[0208] Oxygen partial pressure monitoring: Electrochemical oxygen sensor (accuracy ±1ppm);

[0209] Pressure sensor: Piezoresistive pressure transmitter (accuracy ±5Pa).

[0210] (2) Gas control process:

[0211] First range (200-400℃):

[0212] The nitrogen flow rate was linearly reduced from 30 L / min to 18 L / min (total time 40 minutes);

[0213] Oxygen partial pressure was maintained at ≤8ppm (measured average 5ppm).

[0214] Second range (400-800℃):

[0215] The nitrogen flow rate was linearly reduced from 15 L / min to 9 L / min (total time 133 minutes);

[0216] The peak partial pressure of oxygen is 45 ppm (the standard is ≤50 ppm).

[0217] This embodiment suppresses the risk of lattice oxygen escape and material oxidation by controlling the oxygen partial pressure threshold in the annealing temperature range in a tiered manner; it offsets the pressure fluctuations caused by thermal expansion by dynamically adjusting the nitrogen flow rate to match the temperature change rate; and it maintains a stable environment inside the furnace by combining a pressure compensation mechanism, thus forming a multi-dimensional synergistic control of temperature, atmosphere, and pressure. This ensures the integrity of the catalyst active components, the stability of the support structure, and the uniformity of the microstructure, significantly improving the yield and material durability of the high-temperature annealing process.

[0218] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0219] In one embodiment, a production control system for a water electrolysis hydrogen production catalyst is provided, which corresponds to the production control method for a water electrolysis hydrogen production catalyst described in the above embodiments. The production control system for the water electrolysis hydrogen production catalyst includes:

[0220] The acquisition module is used to acquire dynamic parameters of the precursor solution in real time, including at least pH value, metal ion concentration and pulse frequency.

[0221] The calculation module is used to extract the time-series features of the dynamic parameters through edge computing nodes and calculate the current density variation coefficient.

[0222] The input module is used to input the collected dynamic parameters and the calculated current density variation coefficient into the multi-objective optimization model to generate real-time control commands for electrodeposition duty cycle and annealing temperature gradient.

[0223] The adjustment module is used to adjust the duty cycle of the electrodeposition process and the temperature gradient of the annealing process according to the real-time control command, and to produce a water electrolysis hydrogen production catalyst based on the adjusted parameters.

[0224] The feedback module is used to verify the uniformity of element distribution on the catalyst surface through spectral analysis and to feed the verification results back to the multi-objective optimization model for parameter iterative optimization.

[0225] Furthermore, it also includes:

[0226] The process switching module is used to obtain the conductivity decay rate of the adjusted electrodeposition process in real time and dynamically switch the preset deposition process according to the conductivity decay rate.

[0227] Furthermore, it also includes:

[0228] The monitoring module is used to monitor the concentration of impurity ions in the precursor solution in real time. When the concentration of impurity ions exceeds the preset concentration threshold, it controls the filtration module / ion exchange module / regulation submodule to start.

[0229] A filtration module is used to purify the precursor solution;

[0230] The first adjustment submodule is used to adjust the electrodeposition duty cycle according to the characteristics of impurities and generate updated real-time control commands.

[0231] Furthermore, it also includes:

[0232] The second regulation submodule is used to control the oxygen partial pressure to be ≤10ppm and the nitrogen flow rate to be 10-50L / min when the annealing temperature is in the first temperature range.

[0233] The third adjustment submodule is used to control the oxygen partial pressure to ≤100ppm and the nitrogen flow rate to 5-20L / min when the annealing temperature is in the second temperature range.

[0234] The air pressure balancing module is used to dynamically compensate for air pressure fluctuations within the annealing module, so that the air pressure fluctuations within the annealing module are within a preset range.

[0235] Specific limitations regarding the production control system for a water electrolysis hydrogen production catalyst can be found in the above description of the production control method for a water electrolysis hydrogen production catalyst, and will not be repeated here. Each module in the aforementioned production control system for a water electrolysis hydrogen production catalyst can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the memory of a computer device as software, so that the processor can call and execute the corresponding operations of each module.

[0236] In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows. Figure 4 The computer device includes a processor, memory, network interface, and database connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and database. The internal memory provides the environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The database is used for data storage, data processing, and data analysis. The network interface is used for communication with external terminals via a network connection. When the computer program is executed by the processor, it implements a production control method for a water electrolysis hydrogen production catalyst.

[0237] In one embodiment, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements a method for controlling the production of a water electrolysis hydrogen production catalyst.

[0238] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements a method for controlling the production of a water electrolysis hydrogen production catalyst.

[0239] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), Rambus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0240] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is used as an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above.

[0241] The above-described embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application, and should all be included within the protection scope of this application.

Claims

1. A method for controlling the production of a catalyst for hydrogen production through water electrolysis, characterized in that, Including the following steps: The dynamic parameters of the precursor solution are collected in real time, including at least pH value, metal ion concentration and pulse frequency; The dynamic parameters are extracted using time-series features through edge computing nodes, and the current density variation coefficient is calculated. The collected dynamic parameters and the calculated current density variation coefficient are input into a multi-objective optimization model to generate real-time control commands for electrodeposition duty cycle and annealing temperature gradient. The duty cycle of the electrodeposition process and the temperature gradient of the annealing process are adjusted according to the real-time control command, and the water electrolysis hydrogen production catalyst is produced based on the adjusted parameters. The uniformity of elemental distribution on the catalyst surface was verified using spectral analysis, and the verification results were fed back into a multi-objective optimization model for parameter iterative optimization.

2. The production control method for the water electrolysis hydrogen production catalyst as described in claim 1, characterized in that, After the step of adjusting the duty cycle of the electrodeposition process and the temperature gradient of the annealing process according to the real-time control command, and producing the water electrolysis hydrogen production catalyst based on the adjusted parameters, the method further includes the following steps: The conductivity decay rate of the adjusted electrodeposition process is acquired in real time, and the preset deposition process is dynamically switched according to the conductivity decay rate; wherein, the dynamic switching of the preset deposition process includes: When conductivity decay is detected to exceed a preset concentration threshold, the electrodeposition process is stopped and a preset deposition process is started.

3. The production control method for the water electrolysis hydrogen production catalyst as described in claim 1, characterized in that, The dynamic parameters also include impurity ion concentration. The step of adjusting the duty cycle of the electrodeposition process and the temperature gradient of the annealing process according to the real-time control command, and producing the water electrolysis hydrogen production catalyst based on the adjusted parameters, further includes: Real-time monitoring of impurity ion concentrations in the precursor solution; When the concentration of impurity ions exceeds a preset concentration threshold, perform at least one of the following operations: A start command is sent to the filtration module, which then purifies the precursor solution. The impurity characteristics of impurity ions are identified, the electrodeposition duty cycle is adjusted according to the impurity characteristics, and updated real-time control commands are generated.

4. The production control method for the water electrolysis hydrogen production catalyst as described in claim 1, characterized in that, In the step of adjusting the duty cycle of the electrodeposition process and the temperature gradient of the annealing process according to the real-time control command, and producing the electrolytic hydrogen production catalyst based on the adjusted parameters, when adjusting the temperature gradient of the annealing process, the oxygen partial pressure and nitrogen flow rate of the inert atmosphere in the annealing module are simultaneously controlled, specifically: When the annealing temperature is in the first temperature range, control the oxygen partial pressure to be ≤10ppm and the nitrogen flow rate to be 10-50L / min. When the annealing temperature is in the second temperature range, control the oxygen partial pressure to be ≤100ppm and the nitrogen flow rate to be 5-20L / min. The nitrogen flow rate is dynamically adjusted according to the temperature gradient change rate to keep the pressure fluctuation in the annealing module within a preset range. When a pressure deviation is detected to be greater than the preset range, the pressure balance module is triggered to perform dynamic compensation.

5. The production control method for the water electrolysis hydrogen production catalyst according to any one of claims 1-4, characterized in that, In the step of inputting the collected dynamic parameters and the calculated current density variation coefficient into the multi-objective optimization model to generate real-time control commands for electrodeposition duty cycle and annealing temperature gradient, the multi-objective optimization model is jointly constructed by a multi-objective optimization algorithm and a time-series prediction model, and specifically includes the following steps: Several optimization objectives are defined, including at least precious metal utilization rate, catalytic activity, and deposition layer uniformity; A multi-objective optimization algorithm is used to generate a Pareto optimal solution set and extract the equilibrium constraint relationship between each optimization objective. A time-series prediction model is constructed, with dynamic parameters and time-series characteristics as inputs and initial control commands for electrodeposition duty cycle and annealing temperature gradient as outputs. The time series prediction model is co-trained based on the Pareto optimal solution set, enabling the time series prediction model to generate optimized control commands that satisfy multi-objective equilibrium constraints.

6. The production control method for the water electrolysis hydrogen production catalyst as described in claim 5, characterized in that, The step of co-training the time series prediction model based on the Pareto optimal solution set specifically includes: The Pareto optimal solution set is split into a training subset and a validation subset, which are used for parameter updates and hyperparameter tuning of the time series prediction model, respectively. Constructing the decomposition loss function in, The mean square error between the predicted command and the measured data; The penalty term is for the control instruction deviating from the Pareto front; α and β are dynamically adjusted weighting coefficients. The parameters of the time series prediction model are iteratively updated using the gradient descent algorithm until the decomposed loss function converges to a preset threshold.

7. A production control system for a water electrolysis hydrogen production catalyst, used to implement the steps of the production control method for a water electrolysis hydrogen production catalyst as described in any one of claims 1-6, characterized in that, include: The acquisition module is used to acquire dynamic parameters of the precursor solution in real time, including at least pH value, metal ion concentration and pulse frequency. The calculation module is used to extract the time-series features of the dynamic parameters through edge computing nodes and calculate the current density variation coefficient. The input module is used to input the collected dynamic parameters and the calculated current density variation coefficient into the multi-objective optimization model to generate real-time control commands for electrodeposition duty cycle and annealing temperature gradient. The adjustment module is used to adjust the duty cycle of the electrodeposition process and the temperature gradient of the annealing process according to the real-time control command, and to produce a water electrolysis hydrogen production catalyst based on the adjusted parameters. The feedback module is used to verify the uniformity of element distribution on the catalyst surface through spectral analysis and to feed the verification results back to the multi-objective optimization model for parameter iterative optimization.

8. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the production control method for a water electrolysis hydrogen production catalyst as described in any one of claims 1-6.

9. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the steps of the production control method for a water electrolysis hydrogen production catalyst as described in any one of claims 1-6.

Images