A method and system for optimizing hydrogen production by water electrolysis based on big data analysis

Abstract

The present invention relates to the technical field of hydrogen production by electrolysis of water, and specifically to a method and system for optimizing hydrogen production by electrolysis of water based on big data analysis, comprising the following steps: S1, data acquisition: real-time acquisition of operating data in the process of hydrogen production by electrolysis of water through sensors; S2, data preprocessing and feature extraction: extracting features related to electrolysis efficiency and electrode life; S3, bubble management based on adaptive acoustic wave control: dynamically adjusting the frequency and intensity of acoustic waves using an adaptive acoustic wave control algorithm to optimize the distribution and discharge path of bubbles on the electrode surface; S4, electrode material fatigue prediction and optimization: real-time analysis of performance changes of electrode materials, prediction of fatigue life of electrodes, and automatic adjustment of electrolysis operating parameters or intelligent scheduling of electrode replacement operations based on prediction results. The present invention ensures the stability of the electrolysis process and avoids the problem of performance degradation caused by bubble accumulation.

Description

Technical Field

[0001] The present invention relates to the technical field of hydrogen production by water electrolysis, and in particular to an optimization method and system for hydrogen production by water electrolysis based on big data analysis. Background Art

[0002] With the continuous increase in global energy demand and increasingly stringent environmental protection requirements, water electrolysis has attracted widespread attention as a clean and efficient hydrogen production technology. The process of water electrolysis uses electricity to decompose water into hydrogen and oxygen, which is one of the important ways to achieve green energy. Especially in the context of the rapid development of renewable energy, water electrolysis is regarded as an important part of the future hydrogen energy supply chain. However, the efficiency and stability of the water electrolysis process are directly affected by bubble behavior, electrode material fatigue and electrolysis operating conditions. Therefore, how to optimize the various parameters in the electrolysis process and improve the overall performance of the system has become an important issue in the industry.

[0003] However, the existing water electrolysis hydrogen production technology has significant deficiencies in bubble management and fatigue prediction of electrode materials. The existing technology usually only relies on fixed parameters for electrolysis operations and lacks dynamic management of bubble behavior, which easily leads to the accumulation of bubbles on the electrode surface, increasing the electrolysis impedance and reducing the electrolysis efficiency. In addition, the traditional electrode material fatigue life prediction method fails to fully consider multiple factors such as the corrosion environment, current density and stress concentration effect, making it difficult to accurately predict the service life of the material, resulting in premature failure of the electrode or untimely maintenance, thereby affecting the continuity and safety of the system.

[0004] The purpose of the present invention is to provide an optimization method for hydrogen production by water electrolysis based on big data analysis, which can significantly improve the electrolysis efficiency, extend the service life of the electrode, optimize the electrolysis operation and maintenance management, ensure the stability and economy of the system, and thus provide a reliable and efficient technical solution for the industrial application of hydrogen production by water electrolysis. Summary of the invention

[0005] Based on the above objectives, the present invention provides a method and system for optimizing hydrogen production by water electrolysis based on big data analysis.

[0006] A method for optimizing hydrogen production by water electrolysis based on big data analysis comprises the following steps:

[0007] S1, data collection: real-time collection of operating data during the process of water electrolysis to produce hydrogen through sensors, including voltage, current, temperature, pressure, bubble behavior, and electrode material properties;

[0008] S2, data preprocessing and feature extraction: preprocess the collected operation data, and extract features related to electrolysis efficiency and electrode life based on the preprocessed operation data, including bubble features and electrolysis features. Bubble features include bubble generation rate, size, and local pressure on the electrode surface. Electrolysis features include current density, temperature change, chemical reaction activity, voltage fluctuation, and stress distribution of electrode materials.

[0009] S3, Bubble management based on adaptive acoustic wave control: Based on the extracted bubble features, the frequency and intensity of the acoustic wave are dynamically adjusted using the adaptive acoustic wave control algorithm to optimize the distribution and discharge path of bubbles on the electrode surface, including:

[0010] S31, initialization of acoustic wave control parameters: initializing the parameters of the acoustic wave control mechanism according to the extracted bubble characteristics, including the initial frequency and intensity of the acoustic wave;

[0011] S32, Adaptive sound wave regulation: During the electrolysis process, the frequency and intensity of the sound waves are dynamically adjusted using an adaptive sound wave control algorithm to continuously optimize the effect of the sound waves on the bubbles;

[0012] S33, Bubble distribution optimization and emission management: By adjusting the propagation path and action time of the sound wave, the distribution of bubbles on the electrode surface is optimized, and the bubbles are guided to quickly leave the electrode surface along the set emission path;

[0013] S4, electrode material fatigue prediction and optimization: Based on the extracted electrolysis characteristics, the performance changes of the electrode material are analyzed in real time, the fatigue life of the electrode is predicted, and the electrolysis operation parameters are automatically adjusted or the electrode replacement operation is intelligently scheduled according to the prediction results.

[0014] Optionally, the data collection in S1 includes:

[0015] S11, sensor module arrangement: installing multiple sensors inside and outside the electrolytic cell, including a voltage sensor, a current sensor, a temperature sensor, a pressure sensor, an optical sensor, and a strain sensor;

[0016] S12, voltage and current acquisition: connecting the voltage sensor and current sensor to the electrodes of the electrolytic cell respectively, and measuring the voltage and current of the electrodes during the electrolysis process in real time;

[0017] S13, temperature and pressure monitoring: temperature sensors and pressure sensors are arranged at different positions of the electrolytic cell to monitor the temperature distribution and pressure changes inside the electrolytic cell;

[0018] S14, bubble behavior monitoring: the bubble generation process and the distribution of bubbles on the electrode surface are collected through optical sensors;

[0019] S15, electrode material performance detection: attach the strain sensor to the surface of the electrode material to detect the stress change of the electrode material.

[0020] Optionally, the data preprocessing and feature extraction in S2 includes:

[0021] S21, data preprocessing: preprocessing the collected operation data, including data cleaning and data normalization;

[0022] S22, bubble feature extraction: extracting bubble features from the running data, specifically including:

[0023] Calculation of bubble generation rate: Using the image of the bubble generation process obtained by the optical sensor, the bubble generation rate is calculated using the image processing algorithm;

[0024] Bubble size measurement: Separate the bubble area from the bubble generation process image and measure the bubble diameter or volume;

[0025] Electrode surface local pressure analysis: The effect of bubbles on the electrode surface local pressure is estimated through a fluid dynamics model;

[0026] S23, electrolysis feature extraction: extracting electrolysis features from the operation data, specifically including:

[0027] Current density calculation: Calculate current density based on current sensor data and electrode area;

[0028] Temperature change analysis: By performing differential calculation on the data of multiple temperature sensors, the temperature gradient and its change trend in the electrolytic cell can be obtained;

[0029] Chemical reaction activity evaluation: Combined with voltage and current density, the activity of electrode reaction in electrolysis process is evaluated by Tafel plot;

[0030] Voltage fluctuation analysis: Perform frequency domain analysis on voltage data through fast Fourier transform (FFT) to extract the frequency and amplitude characteristics of voltage fluctuation;

[0031] Stress distribution calculation: Using strain sensor data, the stress distribution of the electrode material is calculated through the stress-strain relationship.

[0032] Optionally, the initialization of the sound wave control parameters in S31 includes:

[0033] S311, frequency parameter initialization: According to the bubble generation rate and size, the initial frequency f0 of the sound wave is determined, which is expressed as:

[0034]

[0035] Among them, k and c are constants, Bubble Size is the size of the bubble;

[0036] S312, intensity parameter initialization: Combine the local pressure on the electrode surface and the bubble generation rate to determine the initial intensity I0 of the sound wave, expressed as:

[0037]

[0038] Among them, P local is the local pressure on the electrode surface, R bubble is the bubble generation rate.

[0039] Optionally, the adaptive sound wave adjustment in S32 includes:

[0040] S321, real-time bubble behavior monitoring: During the electrolysis process, the bubble generation rate, size and distribution on the electrode surface are obtained in real time;

[0041] S322, adaptive control algorithm: The proportional-integral-derivative (PID) control algorithm is used to dynamically adjust the frequency and intensity of the sound wave to optimize the effect of bubbles detaching from the electrode surface, which is expressed as:

[0042]

[0043] Among them, f(t) and I(t) are the frequency and intensity of the sound wave at time t, f0 and I0 are the frequency and intensity at initialization, e(t) is the deviation of the bubble behavior, K p ,K i ,K d and K p ′,K i ′,K d ′ are the proportional, integral and differential gain coefficients for frequency and intensity regulation respectively;

[0044] S323, dynamic adjustment: adjusting the output parameters of the sound wave in real time according to the frequency and intensity adjustment values ​​calculated by the proportional-integral-derivative (PID) control algorithm.

[0045] Optionally, the bubble distribution optimization and emission management in S33 includes:

[0046] S331, sound wave propagation path adjustment: through real-time monitoring of bubble distribution, the sound wave propagation path is dynamically adjusted using the beamforming algorithm, which is expressed as:

[0047]

[0048] Where w is the beamforming weight vector, w m is the weight of the mth sensor, x m(t) is the signal received by the mth sensor, τ m is the delay time of signal propagation;

[0049] S332, sound wave action time control: by real-time calculation of the time the bubble stays on the electrode surface, combined with the propagation speed and path length of the sound wave, the sound wave action time is dynamically adjusted, expressed as:

[0050]

[0051] Among them, T optimal is the optimized sound wave action time, L path is the length of the sound wave propagation path, v sound is the propagation speed of the sound wave in the electrolyte, Δt is the time correction factor based on the bubble size and generation rate;

[0052] S333, bubble discharge path guidance: Combined with the adjusted sound wave propagation path and action time, the bubble discharge path is set through feedback regulation of the bubble behavior, and the bubble is guided to quickly leave the electrode surface along a predetermined direction, which is expressed as:

[0053]

[0054] Among them, F radiation is the acoustic radiation force, R is the bubble radius, ρ is the liquid density, and Φ is the acoustic wave potential function;

[0055] F buoyancy =ρgV bubble ;

[0056] Among them, F buoyancy is the buoyancy, g is the acceleration due to gravity, V bubble is the volume of the bubble;

[0057]

[0058] Among them, F drag is the resistance, C d is the drag coefficient, A is the frontal area of ​​the bubble, and v is the velocity of the bubble;

[0059]

[0060] Where m is the mass of the bubble, x is the position of the bubble, and t is the time;

[0061]

[0062] Among them, Φ total is the total acoustic wave potential function, A i is the amplitude of the ith sound wave, ω i is the angular frequency of the ith sound wave, is the phase of the ith sound wave.

[0063] Optionally, the electrode material fatigue prediction and optimization in S4 includes:

[0064] S41, Fatigue life prediction: By real-time monitoring of the electrolysis characteristics during the electrolysis process, the electrode material fatigue prediction model is used to analyze the performance changes of the electrode material, predict its fatigue life, and identify potential fatigue risks;

[0065] S42, operation adjustment and electrode replacement: According to the prediction results of fatigue life, the electrolysis operation parameters are automatically adjusted to delay the material fatigue process, and the electrode replacement operation is intelligently scheduled when the material life is close to the usage threshold.

[0066] Optionally, the electrode material fatigue prediction model in S41 adopts a Coffin-Manson model, and the Coffin-Manson model includes:

[0067] S411, introduction of corrosion influencing factor: During the electrolysis process, the fatigue life of the electrode material is affected by the corrosive environment. The corrosion influencing factor C is introduced. cor The original strain amplitude of the modified Coffin-Manson model is expressed as:

[0068] ∈=C cor ·(∈ e +∈ p );

[0069] Among them, C cor is the corrosion impact factor, ∈ e is the elastic strain amplitude, ∈ p is the plastic strain amplitude;

[0070] S412, introduce current density influence factor: introduce current density influence factor J eff The strain amplitude in the modified model is expressed as:

[0071] J eff = J·(1+αJ 2 );

[0072] Where J is the current density and α is a constant related to material properties;

[0073] S413, introduce stress concentration effect: introduce stress concentration factor ∈ eff , corrected strain amplitude, expressed as:

[0074] ∈ eff =K t ·∈;

[0075] Among them, K tis the stress concentration factor;

[0076] S414, Fatigue life prediction: Integrate the corrosion influence factor, current density influence factor and stress concentration factor to predict the fatigue life of electrode materials in the process of hydrogen production by electrolysis of water, expressed as:

[0077]

[0078] Among them, ∈ eff is the corrected effective strain amplitude, σ f ′ is the fatigue strength coefficient, E is the elastic modulus of the material, N f is the fatigue life of the material, b is the fatigue strength index, ∈ f ′ is the fatigue ductility coefficient, and c is the fatigue ductility index.

[0079] Optionally, the operation adjustment and electrode replacement in S42 include:

[0080] S421, automatic adjustment of electrolysis operating parameters: Based on the fatigue life prediction results of the Coffin-Manson model, the fatigue state of the electrode material is monitored in real time. When it is detected that the fatigue life of the material is gradually decreasing, the electrolysis operating parameters, including current density, temperature and electrolyte concentration, are automatically adjusted;

[0081] S422, intelligent scheduling of electrode replacement: When the material fatigue life predicted by the Coffin-Manson model is close to the preset usage threshold, the electrode replacement instruction is automatically generated and the electrode replacement operation is intelligently scheduled.

[0082] A water electrolysis hydrogen production optimization system based on big data analysis, used to implement the above-mentioned water electrolysis hydrogen production optimization method based on big data analysis, includes the following modules:

[0083] Data acquisition module: collects real-time operating data during the process of electrolysis of water to produce hydrogen through sensors. The operating data includes voltage, current, temperature, pressure, bubble behavior, and electrode material performance;

[0084] Data preprocessing and feature extraction module: preprocesses the collected operation data, and extracts features related to electrolysis efficiency and electrode life based on the preprocessed operation data, including bubble features and electrolysis features. Bubble features include bubble generation rate, size, and local pressure on the electrode surface. Electrolysis features include current density, temperature change, chemical reaction activity, voltage fluctuation, and stress distribution of electrode materials.

[0085] Adaptive acoustic wave control module: Based on the extracted bubble characteristics, the frequency and intensity of the acoustic wave are dynamically adjusted using the adaptive acoustic wave control algorithm to optimize the distribution and discharge path of the bubbles on the electrode surface;

[0086] Electrode material fatigue prediction and optimization module: Based on the extracted electrolysis characteristics, it analyzes the performance changes of electrode materials in real time, predicts the fatigue life of the electrode, and automatically adjusts the electrolysis operation parameters or intelligently schedules the electrode replacement operation according to the prediction results.

[0087] Beneficial effects of the present invention:

[0088] The present invention, through real-time data acquisition and precise feature extraction, utilizes the bubble management technology of adaptive acoustic wave control, effectively optimizes the distribution and discharge path of bubbles on the electrode surface, reduces bubble accumulation and electrolysis impedance, thereby significantly improving the efficiency of the hydrogen production process by electrolyzing water. At the same time, through fine bubble management and dynamic acoustic wave regulation, the stability of the electrolysis process is ensured, avoiding the problem of performance degradation caused by bubble accumulation.

[0089] The present invention, through the electrode material fatigue prediction and optimization technology of the Coffin-Manson model, comprehensively considers the corrosion environment, current density and stress concentration effect, can more accurately predict the fatigue life of the electrode material, delay the fatigue process of the material by adjusting the electrolysis operation parameters in real time, and intelligently schedule the electrode replacement operation, thereby extending the service life of the electrode, reducing the maintenance frequency and cost, and ensuring the long-term and efficient operation of the equipment.

[0090] The present invention, through intelligent operation adjustment and electrode replacement management strategy, automatically adjusts electrolysis operation parameters based on fatigue life prediction results, and intelligently schedules electrode replacement operations when the material life is close to the threshold. This method not only improves the reliability of the electrolysis system and prevents production interruptions due to material failure, but also optimizes maintenance plans, reduces unnecessary downtime, reduces operating costs, and improves overall production efficiency and safety. BRIEF DESCRIPTION OF THE DRAWINGS

[0091] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only for the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0092] Figure 1 A schematic diagram of the optimization method flow of an embodiment of the present invention;

[0093] Figure 2 Schematic diagram of system function modules according to an embodiment of the present invention. DETAILED DESCRIPTION

[0094] The present invention is described in detail below in conjunction with the accompanying drawings and specific embodiments. At the same time, it is explained here that in order to make the embodiments more detailed, the following embodiments are the best and preferred embodiments, and those skilled in the art may also adopt other alternatives to implement some known technologies; and the accompanying drawings are only for more specific description of the embodiments, and are not intended to specifically limit the present invention.

[0095] It should be noted that the references to "one embodiment", "an embodiment", "an exemplary embodiment", "some embodiments" and the like in the specification indicate that the embodiments described may include specific features, structures or characteristics, but not every embodiment may include the specific features, structures or characteristics. In addition, when a specific feature, structure or characteristic is described in conjunction with an embodiment, it should be within the knowledge of a person skilled in the art to implement such feature, structure or characteristic in conjunction with other embodiments (whether or not explicitly described).

[0096] In general, a term can be understood, at least in part, from its use in context. For example, depending, at least in part, on the context, the term "one or more" as used herein can be used to describe any feature, structure, or characteristic in the singular sense, or can be used to describe a combination of features, structures, or characteristics in the plural sense. Additionally, the term "based on" can be understood as not necessarily intended to convey an exclusive set of factors, but can instead, depending, at least in part, on the context, allow for the presence of other factors that are not necessarily explicitly described.

[0097] like Figure 1 As shown, a method for optimizing hydrogen production by water electrolysis based on big data analysis comprises the following steps:

[0098] S1, data collection: real-time collection of operating data during the process of water electrolysis to produce hydrogen through sensors, including voltage, current, temperature, pressure, bubble behavior, and electrode material properties;

[0099] S2, data preprocessing and feature extraction: preprocess the collected operation data, and extract features related to electrolysis efficiency and electrode life based on the preprocessed operation data, including bubble features and electrolysis features. Bubble features include bubble generation rate, size, and local pressure on the electrode surface. Electrolysis features include current density, temperature change, chemical reaction activity, voltage fluctuation, and stress distribution of electrode materials.

[0100] S3, Bubble management based on adaptive acoustic wave control: Based on the extracted bubble features, the frequency and intensity of the acoustic wave are dynamically adjusted using the adaptive acoustic wave control algorithm to optimize the distribution and discharge path of bubbles on the electrode surface, reduce bubble accumulation on the electrode surface, and reduce electrolysis impedance, thereby improving electrolysis efficiency. Specifically, it includes:

[0101] S31, initialization of acoustic wave control parameters: initializing the parameters of the acoustic wave control mechanism according to the extracted bubble characteristics, including the initial frequency and intensity of the acoustic wave, to ensure that the acoustic wave can effectively act on the bubble;

[0102] S32, Adaptive sound wave regulation: During the electrolysis process, the frequency and intensity of the sound waves are dynamically adjusted using an adaptive sound wave control algorithm to continuously optimize the effect of the sound waves on the bubbles, ensuring that the bubbles can effectively detach from the electrode surface and reduce bubble accumulation;

[0103] S33, Bubble distribution optimization and emission management: By adjusting the propagation path and action time of the sound wave, the distribution of bubbles on the electrode surface is optimized, and the bubbles are guided to quickly leave the electrode surface along the set emission path, thereby reducing the electrolysis impedance and improving the electrolysis efficiency;

[0104] S4, electrode material fatigue prediction and optimization: Based on the extracted electrolysis characteristics, the performance changes of the electrode materials are analyzed in real time, the fatigue life of the electrode is predicted, and the electrolysis operation parameters are automatically adjusted or the electrode replacement operation is intelligently scheduled according to the prediction results to avoid the efficiency loss caused by material fatigue and extend the service life of the electrode;

[0105] Through the above steps, precise control and optimization of bubble management and electrode material fatigue are achieved, which can significantly improve the electrolysis efficiency, extend the service life of the equipment, and ensure the stability and efficiency of the electrolysis process, thereby providing a reliable and efficient technical solution for the industrial application of hydrogen production by water electrolysis.

[0106] Data collection in S1 includes:

[0107] S11, sensor module arrangement: installing multiple sensors inside and outside the electrolytic cell, including a voltage sensor, a current sensor, a temperature sensor, a pressure sensor, an optical sensor, and a strain sensor;

[0108] S12, voltage and current acquisition: connecting the voltage sensor and current sensor to the electrodes of the electrolytic cell respectively, and measuring the voltage and current of the electrodes during the electrolysis process in real time;

[0109] S13, temperature and pressure monitoring: temperature sensors and pressure sensors are arranged at different positions of the electrolytic cell to monitor the temperature distribution and pressure changes inside the electrolytic cell;

[0110] S14, bubble behavior monitoring: the bubble generation process and the distribution of bubbles on the electrode surface are collected through optical sensors;

[0111] S15, electrode material performance detection: attaching the strain sensor to the surface of the electrode material to detect the stress change of the electrode material;

[0112] Through the above content, detailed operating status information can be provided, laying a reliable foundation for subsequent optimization analysis and control.

[0113] Data preprocessing and feature extraction in S2 include:

[0114] S21, data preprocessing: preprocessing the collected operation data, including data cleaning and data normalization;

[0115] S22, bubble feature extraction: extracting bubble features from the running data, specifically including:

[0116] Calculation of bubble generation rate: The bubble generation process image obtained by the optical sensor is used to calculate the bubble generation rate using an image processing algorithm, which is expressed as:

[0117]

[0118] Among them, R bubble is the bubble generation rate, N bubble is the number of bubbles generated in time T;

[0119] Bubble size measurement: Separate the bubble area from the bubble generation process image and measure the bubble diameter or volume;

[0120] Electrode surface local pressure analysis: The effect of bubbles on the electrode surface local pressure is estimated by the fluid dynamics model, which is expressed as:

[0121]

[0122] Where P is the pressure of the fluid, ρ is the density of the electrolyte, v is the flow rate, h is the height, g is the acceleration of gravity, and constant is a constant, which represents that the total mechanical energy of the fluid remains unchanged along a streamline (i.e. the path of the fluid flow);

[0123] S23, electrolysis feature extraction: extracting electrolysis features from the operation data, specifically including:

[0124] Current density calculation: The current density is calculated based on the current sensor data and the electrode area, expressed as:

[0125]

[0126] Where J is the current density, I is the measured current, and A is the effective area of ​​the electrode;

[0127] Temperature change analysis: By performing differential calculation on the data of multiple temperature sensors, the temperature gradient and its change trend in the electrolytic cell are obtained, which can be expressed as:

[0128]

[0129] Where ΔT is the temperature difference between the two temperature sensors and Δx is the distance between them;

[0130]

[0131] Where T(t) is the temperature at time t, and Δt is the time step;

[0132] Chemical reaction activity evaluation: The activity of the electrode reaction during electrolysis is evaluated by combining voltage and current density through the Tafel curve, which is expressed as:

[0133] η=a+blogJ;

[0134] Where η is the overpotential, a and b are constants, and J is the current density;

[0135] Voltage fluctuation analysis: The voltage data is analyzed in the frequency domain by fast Fourier transform (FFT) to extract the frequency and amplitude characteristics of voltage fluctuation, which are expressed as:

[0136]

[0137] Where N is the number of sampling points, Δt is the sampling interval, f is the frequency, and V(nΔt) is the voltage value at the nth moment;

[0138] Stress distribution calculation: Using the strain sensor data, the stress distribution of the electrode material is calculated through the stress-strain relationship, which is expressed as:

[0139] σ=E·∈;

[0140] Where σ is stress, E is the Young's modulus of the material, and ∈ is the measured strain;

[0141] Through the above content, not only the accuracy of data analysis is ensured, but also a reliable decision-making basis is provided for subsequent optimization and control, which helps to significantly improve the efficiency and stability of the hydrogen production process by water electrolysis, while extending the service life of the equipment.

[0142] The initialization of the acoustic wave control parameters in S31 includes:

[0143] S311, frequency parameter initialization: According to the bubble generation rate and size, the initial frequency f0 of the sound wave is determined, which is expressed as:

[0144]

[0145] Among them, k and c are constants, Bubble Size is the size of the bubble;

[0146] S312, intensity parameter initialization: Combine the local pressure on the electrode surface and the bubble generation rate to determine the initial intensity I0 of the sound wave, expressed as:

[0147]

[0148] Among them, P local is the local pressure on the electrode surface, R bubble is the bubble generation rate;

[0149] Through the above content, the effective management of bubbles by sound waves in the process of hydrogen production by water electrolysis is achieved, the efficiency of bubbles detaching from the electrode surface is improved, the electrolysis impedance is reduced, and thus the overall electrolysis efficiency is improved.

[0150] The constants k and c are determined based on a machine learning prediction model, including:

[0151] Data collection: Collect data sets related to bubble behavior and acoustic wave parameters, including bubble size, bubble generation rate, local pressure on the electrode surface, acoustic wave frequency, and acoustic wave intensity;

[0152] Train the machine learning model: The predicted acoustic wave parameters k and c are output by the linear regression model, expressed as:

[0153]

[0154]

[0155] in, is the predicted sound wave frequency parameter, α0 and β0 are intercept terms (bias), α1, α2, α3 and β1, β2, β3 are regression coefficients. During the training process, the linear regression model determines the regression coefficients through the mean square error;

[0156] Model validation: Use cross-validation method to validate the model and evaluate the generalization ability of the model;

[0157] Determine constants k and c: Use the trained model to predict new bubble characteristic data to obtain the acoustic wave control parameters.

[0158] Adaptive sound wave tuning in S32 includes:

[0159] S321, real-time bubble behavior monitoring: During the electrolysis process, the bubble generation rate, size and distribution on the electrode surface are obtained in real time;

[0160] S322, adaptive control algorithm: The proportional-integral-derivative (PID) control algorithm is used to dynamically adjust the frequency and intensity of the sound wave to optimize the effect of bubbles detaching from the electrode surface, which is expressed as:

[0161]

[0162] Where f(t) and I(t) are the frequency and intensity of the sound wave at time t, respectively; f0 and I0 are the frequency and intensity at initialization; e(t) is the deviation of the bubble behavior, indicating the difference between the actual bubble detachment effect and the ideal effect; K p ,K i ,K d and K p ′,K i ′,K d ′ are the proportional, integral and differential gain coefficients for frequency and intensity regulation respectively;

[0163] S323, dynamic adjustment: according to the frequency and intensity adjustment values ​​calculated by the proportional-integral-differential (PID) control algorithm, the output parameters of the sound wave are adjusted in real time, so that the bubbles can effectively detach from the electrode surface and reduce the accumulation of bubbles on the electrode surface. Through continuous feedback and adjustment, the effect of the sound wave is always in the optimal state, thereby reducing the electrolysis impedance and improving the electrolysis efficiency;

[0164] Through the above content, the bubbles can be more effectively acted on, ensuring the high efficiency of bubble management during the electrolysis process, reducing the accumulation of bubbles on the electrode surface, and thereby improving the overall efficiency and stability of hydrogen production by water electrolysis.

[0165] Bubble distribution optimization and emission management in S33 include:

[0166] S331, sound wave propagation path adjustment: through real-time monitoring of the bubble distribution, the beamforming algorithm is used to dynamically adjust the sound wave propagation path so that the sound wave can focus on the bubble-dense area, thereby optimizing the distribution of bubbles on the electrode surface, which is expressed as:

[0167]

[0168] Where w is the beamforming weight vector, w m is the weight of the mth sensor, x m (t) is the signal received by the mth sensor, τ m is the delay time of signal propagation;

[0169] S332, sound wave action time control: by real-time calculation of the time the bubbles stay on the electrode surface, combined with the propagation speed and path length of the sound wave, the sound wave action time is dynamically adjusted so that the bubbles can leave the electrode surface in the shortest time, expressed as:

[0170]

[0171] Among them, T optimalis the optimized sound wave action time, L path is the length of the sound wave propagation path, v sound is the propagation speed of the sound wave in the electrolyte, Δt is the time correction factor based on the bubble size and generation rate;

[0172] S333, bubble discharge path guidance: Combined with the adjusted sound wave propagation path and action time, the bubble discharge path is set through feedback regulation of the bubble behavior, and the bubble is guided to quickly leave the electrode surface along a predetermined direction, which is expressed as:

[0173]

[0174] Among them, F radiation is the acoustic radiation force, R is the bubble radius, ρ is the liquid density, and Φ is the acoustic wave potential function;

[0175] F buoyancy =ρgV bubble ;

[0176] Among them, F buoyancy is the buoyancy, g is the acceleration due to gravity, V bubble is the volume of the bubble;

[0177]

[0178] Among them, F drag is the resistance, C d is the drag coefficient, A is the frontal area of ​​the bubble, and v is the velocity of the bubble;

[0179]

[0180] Where m is the mass of the bubble, x is the position of the bubble, and t is the time;

[0181]

[0182] Among them, Φ total is the total acoustic wave potential function, A i is the amplitude of the ith sound wave, ω i is the angular frequency of the ith sound wave, is the phase of the i-th sound wave;

[0183] Through the above content, the acoustic wave energy can be effectively concentrated in the bubble-dense area, the distribution of bubbles on the electrode surface can be optimized, and the bubbles can be guided to quickly leave the electrode surface along a predetermined path, thereby reducing bubble accumulation, lowering electrolysis impedance, and significantly improving electrolysis efficiency and system stability.

[0184] Electrode material fatigue prediction and optimization in S4 include:

[0185] S41, Fatigue life prediction: By real-time monitoring of the electrolysis characteristics during the electrolysis process, the electrode material fatigue prediction model is used to analyze the performance changes of the electrode material, predict its fatigue life, and identify potential fatigue risks;

[0186] S42, operation adjustment and electrode replacement: according to the fatigue life prediction results, the electrolysis operation parameters are automatically adjusted to delay the material fatigue process, and the electrode replacement operation is intelligently scheduled when the material life is close to the use threshold to ensure the continuity and stability of the electrolysis process;

[0187] Through the above content, the fatigue process of the material can be effectively delayed. When the material life is close to the threshold, the electrode replacement operation is intelligently scheduled to ensure the continuity and stability of the electrolysis process. This not only improves the reliability and efficiency of the system, but also extends the service life of the electrode, reduces maintenance costs, and realizes the optimized management of the water electrolysis hydrogen production process.

[0188] The electrode material fatigue prediction model in S41 adopts the Coffin-Manson model, which includes:

[0189] S411, introduction of corrosion influencing factor: During the electrolysis process, the fatigue life of the electrode material is affected by the corrosive environment. The corrosion influencing factor C is introduced. cor The original strain amplitude of the Coffin-Manson model is modified to reflect the weakening effect of the corrosive environment on fatigue life, which is expressed as:

[0190] ∈=C cor ·(∈ e +∈ p );

[0191] Among them, C cor is the corrosion influencing factor (C cor ≥1),∈ e is the elastic strain amplitude, ∈ p is the plastic strain amplitude;

[0192] S412, introduce current density influence factor: introduce current density influence factor J eff The strain amplitude in the modified model is expressed as:

[0193] J eff = J·(1+αJ 2 );

[0194] Where J is the current density, and α is a constant related to material properties, which is used to adjust the nonlinear effect of current density;

[0195] S413, introduce stress concentration effect: introduce stress concentration factor ∈ eff , corrected strain amplitude, expressed as:

[0196] ∈ eff =K t ·∈;

[0197] Among them, K t is the stress concentration factor (usually K t ≥1), indicating stress concentration on the material surface or microscopic defects;

[0198] S414, Fatigue life prediction: Integrate the corrosion influence factor, current density influence factor and stress concentration factor to predict the fatigue life of electrode materials in the process of hydrogen production by electrolysis of water, expressed as:

[0199]

[0200] Among them, ∈ eff is the corrected effective strain amplitude, σ f ′ is the fatigue strength coefficient, E is the elastic modulus of the material, which indicates the stiffness of the material, N f is the fatigue life of the material, b is the fatigue strength index, ∈ f ′ is the fatigue ductility coefficient, c is the fatigue ductility index;

[0201] Through the above content, the fatigue life of electrode materials under complex operating conditions can be predicted more accurately, which helps optimize electrolysis operating parameters, extend electrode service life, reduce maintenance costs, and improve the stability and efficiency of the overall system.

[0202] Operational adjustments and electrode replacement in S42 include:

[0203] S421, automatic adjustment of electrolysis operating parameters: Based on the fatigue life prediction results of the Coffin-Manson model, the fatigue state of the electrode material is monitored in real time. When it is detected that the fatigue life of the material is gradually decreasing, the electrolysis operating parameters, including current density, temperature and electrolyte concentration, are automatically adjusted to reduce the stress level of the material and delay the fatigue process of the material, thereby extending the service life of the electrode;

[0204] S422, intelligent scheduling of electrode replacement: When the material fatigue life predicted by the Coffin-Manson model is close to the preset usage threshold, the electrode replacement instruction is automatically generated and the electrode replacement operation is intelligently scheduled to ensure the continuity and safety of the electrolysis process and avoid production interruption or equipment damage caused by electrode failure;

[0205] The usage threshold is set based on the fatigue life prediction results of the electrode material and the operating requirements of the electrolysis process, and is expressed as:

[0206]

[0207] Among them, N threshold is the threshold value, N f is the predicted fatigue life of the electrode material, S f is the safety factor, M t is the expected remaining running time (number of cycles);

[0208] Through the above, the electrode replacement operation can be intelligently scheduled to ensure the continuity and safety of the electrolysis process. The advantage of this method is that it significantly improves the reliability and efficiency of the electrolysis system, reduces the risk of failure caused by material fatigue, optimizes maintenance plans, and reduces operating costs.

[0209] like Figure 2 As shown, a water electrolysis hydrogen production optimization system based on big data analysis is used to implement the above-mentioned water electrolysis hydrogen production optimization method based on big data analysis, including the following modules:

[0210] Data acquisition module: collects real-time operating data during the process of electrolysis of water to produce hydrogen through sensors. The operating data includes voltage, current, temperature, pressure, bubble behavior, and electrode material performance;

[0211] Data preprocessing and feature extraction module: preprocesses the collected operation data, and extracts features related to electrolysis efficiency and electrode life based on the preprocessed operation data, including bubble features and electrolysis features. Bubble features include bubble generation rate, size, and local pressure on the electrode surface. Electrolysis features include current density, temperature change, chemical reaction activity, voltage fluctuation, and stress distribution of electrode materials.

[0212] Adaptive acoustic wave control module: Based on the extracted bubble characteristics, the frequency and intensity of the acoustic wave are dynamically adjusted using the adaptive acoustic wave control algorithm to optimize the distribution and discharge path of the bubbles on the electrode surface;

[0213] Electrode material fatigue prediction and optimization module: Based on the extracted electrolysis characteristics, it analyzes the performance changes of electrode materials in real time, predicts the fatigue life of the electrode, and automatically adjusts the electrolysis operation parameters or intelligently schedules the electrode replacement operation according to the prediction results.

[0214] The present invention covers any substitution, modification, equivalent method and scheme made on the essence and scope of the present invention. In order to make the public have a thorough understanding of the present invention, specific details are described in detail in the following preferred embodiments of the present invention, but those skilled in the art can fully understand the present invention without the description of these details. In addition, in order to avoid unnecessary confusion about the essence of the present invention, well-known methods, processes, procedures, components and circuits are not described in detail.

[0215] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A method for optimizing hydrogen production by water electrolysis based on big data analysis, characterized in that: The following steps are involved: S1, data collection: real-time collection of operating data during the process of water electrolysis to produce hydrogen through sensors, including voltage, current, temperature, pressure, bubble behavior, and electrode material properties; S2, data preprocessing and feature extraction: preprocess the collected operation data, and extract features related to electrolysis efficiency and electrode life based on the preprocessed operation data, including bubble features and electrolysis features. Bubble features include bubble generation rate, size, and local pressure on the electrode surface. Electrolysis features include current density, temperature change, chemical reaction activity, voltage fluctuation, and stress distribution of electrode materials. S3, Bubble management based on adaptive acoustic wave control: Based on the extracted bubble features, the frequency and intensity of the acoustic wave are dynamically adjusted using the adaptive acoustic wave control algorithm to optimize the distribution and discharge path of bubbles on the electrode surface, including: S31, initialization of acoustic wave control parameters: initializing the parameters of the acoustic wave control mechanism according to the extracted bubble characteristics, including the initial frequency and intensity of the acoustic wave; S32, Adaptive sound wave regulation: During the electrolysis process, the frequency and intensity of the sound waves are dynamically adjusted using an adaptive sound wave control algorithm to continuously optimize the effect of the sound waves on the bubbles; S33, Bubble distribution optimization and emission management: By adjusting the propagation path and action time of the sound wave, the distribution of bubbles on the electrode surface is optimized, and the bubbles are guided to quickly leave the electrode surface along the set emission path; S4, electrode material fatigue prediction and optimization: Based on the extracted electrolysis characteristics, the performance changes of the electrode material are analyzed in real time, the fatigue life of the electrode is predicted, and the electrolysis operation parameters are automatically adjusted or the electrode replacement operation is intelligently scheduled according to the prediction results.

2. The optimization method for producing hydrogen from water electrolysis based on big data analysis according to claim 1, characterized in that: The data collection in S1 includes: S11, sensor module arrangement: installing multiple sensors inside and outside the electrolytic cell, including a voltage sensor, a current sensor, a temperature sensor, a pressure sensor, an optical sensor, and a strain sensor; S12, voltage and current acquisition: connecting the voltage sensor and current sensor to the electrodes of the electrolytic cell respectively, and measuring the voltage and current of the electrodes during the electrolysis process in real time; S13, temperature and pressure monitoring: temperature sensors and pressure sensors are arranged at different positions of the electrolytic cell to monitor the temperature distribution and pressure changes inside the electrolytic cell; S14, bubble behavior monitoring: the bubble generation process and the distribution of bubbles on the electrode surface are collected through optical sensors; S15, electrode material performance detection: attach the strain sensor to the surface of the electrode material to detect the stress change of the electrode material.

3. The optimization method for producing hydrogen from water electrolysis based on big data analysis according to claim 1, characterized in that: The data preprocessing and feature extraction in S2 include: S21, data preprocessing: preprocessing the collected operation data, including data cleaning and data normalization; S22, bubble feature extraction: extracting bubble features from the running data, specifically including: Calculation of bubble generation rate: Using the image of the bubble generation process obtained by the optical sensor, the bubble generation rate is calculated using the image processing algorithm; Bubble size measurement: Separate the bubble area from the bubble generation process image and measure the bubble diameter or volume; Electrode surface local pressure analysis: The effect of bubbles on the electrode surface local pressure is estimated through a fluid dynamics model; S23, electrolysis feature extraction: extracting electrolysis features from the operation data, specifically including: Current density calculation: Calculate current density based on current sensor data and electrode area; Temperature change analysis: By performing differential calculation on the data of multiple temperature sensors, the temperature gradient and its change trend in the electrolytic cell can be obtained; Chemical reaction activity evaluation: Combined with voltage and current density, the activity of electrode reaction in electrolysis process is evaluated by Tafel plot; Voltage fluctuation analysis: Perform frequency domain analysis on voltage data through fast Fourier transform to extract the frequency and amplitude characteristics of voltage fluctuation; Stress distribution calculation: Using strain sensor data, the stress distribution of the electrode material is calculated through the stress-strain relationship.

4. The optimization method for producing hydrogen from water electrolysis based on big data analysis according to claim 3, characterized in that: The initialization of the sound wave control parameters in S31 includes: S311, frequency parameter initialization: According to the bubble generation rate and size, the initial frequency f0 of the sound wave is determined, which is expressed as: Among them, k and c are constants, Bubble Size is the size of the bubble; S312, intensity parameter initialization: Combine the local pressure on the electrode surface and the bubble generation rate to determine the initial intensity I0 of the sound wave, expressed as: Among them, P local is the local pressure on the electrode surface, R bubble is the bubble generation rate.

5. The optimization method for producing hydrogen by electrolysis of water based on big data analysis according to claim 4, characterized in that: The adaptive sound wave adjustment in S32 includes: S321, real-time bubble behavior monitoring: During the electrolysis process, the bubble generation rate, size and distribution on the electrode surface are obtained in real time; S322, adaptive control algorithm: The proportional-integral-differential control algorithm is used to dynamically adjust the frequency and intensity of the sound wave to optimize the effect of bubbles detaching from the electrode surface, expressed as: Among them, f(t) and I(t) are the frequency and intensity of the sound wave at time t, f0 and I0 are the frequency and intensity at initialization, e(t) is the deviation of the bubble behavior, and K p ,K i ,K d and K p ′,K i ′,K d ′ are the proportional, integral and differential gain coefficients for frequency and intensity regulation respectively; S323, dynamic adjustment: adjusting the output parameters of the sound wave in real time according to the frequency and intensity adjustment values ​​calculated by the proportional-integral-differential control algorithm.

6. The optimization method for producing hydrogen from water electrolysis based on big data analysis according to claim 5, characterized in that: The bubble distribution optimization and emission management in S33 include: S331, sound wave propagation path adjustment: through real-time monitoring of bubble distribution, the sound wave propagation path is dynamically adjusted using the beamforming algorithm, which is expressed as: Where w is the beamforming weight vector, w m is the weight of the mth sensor, x m (t) is the signal received by the mth sensor, τ m is the delay time of signal propagation; S332, sound wave action time control: by real-time calculation of the time the bubble stays on the electrode surface, combined with the propagation speed and path length of the sound wave, the sound wave action time is dynamically adjusted, expressed as: Among them, T optimal is the optimized sound wave action time, L path is the length of the sound wave propagation path, v sound is the propagation speed of the sound wave in the electrolyte, Δt is the time correction factor based on the bubble size and generation rate; S333, bubble discharge path guidance: Combined with the adjusted sound wave propagation path and action time, the bubble discharge path is set through feedback regulation of the bubble behavior, and the bubble is guided to quickly leave the electrode surface along a predetermined direction, which is expressed as: Among them, F radiation is the acoustic radiation force, R is the bubble radius, ρ is the liquid density, and Φ is the acoustic wave potential function; F buoyancy =ρgV bubble ; Among them, F buoyancy is the buoyancy, g is the acceleration due to gravity, V bubble is the volume of the bubble; Among them, F drag is the resistance, C d is the drag coefficient, A is the frontal area of ​​the bubble, and v is the velocity of the bubble; Where m is the mass of the bubble, x is the position of the bubble, and t is the time; Among them, Φ total is the total acoustic wave potential function, A i is the amplitude of the ith sound wave, ω i is the angular frequency of the ith sound wave, is the phase of the ith sound wave.

7. The optimization method for producing hydrogen from water electrolysis based on big data analysis according to claim 1, characterized in that: The electrode material fatigue prediction and optimization in S4 includes: S41, Fatigue life prediction: By real-time monitoring of the electrolysis characteristics during the electrolysis process, the electrode material fatigue prediction model is used to analyze the performance changes of the electrode material, predict its fatigue life, and identify potential fatigue risks; S42, operation adjustment and electrode replacement: According to the prediction results of fatigue life, the electrolysis operation parameters are automatically adjusted to delay the material fatigue process, and the electrode replacement operation is intelligently scheduled when the material life is close to the usage threshold.

8. The optimization method for producing hydrogen from water electrolysis based on big data analysis according to claim 7, characterized in that: The electrode material fatigue prediction model in S41 adopts the Coffin-Manson model, and the Coffin-Manson model includes: S411, introduction of corrosion influencing factor: During the electrolysis process, the fatigue life of the electrode material is affected by the corrosive environment. The corrosion influencing factor C is introduced. cor The original strain amplitude of the modified Coffin-Manson model is expressed as: ∈＝C cor ·(∈ e +∈ p )； Among them, C cor is the corrosion impact factor, ∈ e is the elastic strain amplitude, ∈ p is the plastic strain amplitude; S412, introduce current density influence factor: introduce current density influence factor J eff The strain amplitude in the modified model is expressed as: I eff =J·(1+αJ 2 ); Where J is the current density and α is a constant related to material properties; S413, introduce stress concentration effect: introduce stress concentration factor ∈ eff , corrected strain amplitude, expressed as: ∈ eff ＝K t ·∈； Among them, K t is the stress concentration factor; S414, Fatigue life prediction: Integrate the corrosion influence factor, current density influence factor and stress concentration factor to predict the fatigue life of electrode materials in the process of hydrogen production by electrolysis of water, expressed as: Among them, ∈ eff is the corrected effective strain amplitude, σ f ′ is the fatigue strength coefficient, E is the elastic modulus of the material, N f is the fatigue life of the material, b is the fatigue strength index, ∈ f ′ is the fatigue ductility coefficient, and c is the fatigue ductility index.

9. The optimization method for producing hydrogen from water electrolysis based on big data analysis according to claim 8, characterized in that: The operation adjustment and electrode replacement in S42 include: S421, automatic adjustment of electrolysis operating parameters: Based on the fatigue life prediction results of the Coffin-Manson model, the fatigue state of the electrode material is monitored in real time. When it is detected that the fatigue life of the material is gradually decreasing, the electrolysis operating parameters, including current density, temperature and electrolyte concentration, are automatically adjusted; S422, intelligent scheduling of electrode replacement: When the material fatigue life predicted by the Coffin-Manson model is close to the preset usage threshold, the electrode replacement instruction is automatically generated and the electrode replacement operation is intelligently scheduled.

10. A water electrolysis hydrogen production optimization system based on big data analysis, used to implement a water electrolysis hydrogen production optimization method based on big data analysis as described in any one of claims 1 to 9, characterized in that: Includes the following modules: Data acquisition module: collects real-time operating data during the process of electrolysis of water to produce hydrogen through sensors. The operating data includes voltage, current, temperature, pressure, bubble behavior, and electrode material performance; Data preprocessing and feature extraction module: preprocesses the collected operation data, and extracts features related to electrolysis efficiency and electrode life based on the preprocessed operation data, including bubble features and electrolysis features. Bubble features include bubble generation rate, size, and local pressure on the electrode surface. Electrolysis features include current density, temperature change, chemical reaction activity, voltage fluctuation, and stress distribution of electrode materials. Adaptive acoustic wave control module: Based on the extracted bubble characteristics, the frequency and intensity of the acoustic wave are dynamically adjusted using the adaptive acoustic wave control algorithm to optimize the distribution and discharge path of the bubbles on the electrode surface; Electrode material fatigue prediction and optimization module: Based on the extracted electrolysis characteristics, it analyzes the performance changes of electrode materials in real time, predicts the fatigue life of the electrode, and automatically adjusts the electrolysis operation parameters or intelligently schedules the electrode replacement operation according to the prediction results.

Images