Method and system for evaluating operation performance of alkaline water electrolysis hydrogen production device

Abstract

The invention relates to the technical field of water electrolysis hydrogen production, and discloses a method and system for evaluating the operation performance of an alkaline water electrolysis hydrogen production device, and the method comprises the steps: 1, deploying a distributed sensor network, collecting the operation data of an electrolytic cell, building a multi-physical field coupling model, and calibrating a model parameter matrix; and step 2, constructing an electrode damage evolution model based on the model parameter matrix, processing acoustic emission signals acquired by the sensor network, extracting crack characteristic parameters, calculating real-time damage degree, and generating graded early warning signals. According to the technical scheme, the distributed sensor network is adopted to collect the multi-physical field data, and the coupling model is established to calibrate the parameter matrix, so that the technical effect of a multi-dimensional parameter dynamic coupling relation is achieved; the defects of large energy efficiency evaluation deviation and low reliability caused by neglecting of multi-field interaction in a traditional method are overcome.

Description

Technical Field

[0001] The present invention relates to the technical field of hydrogen production by electrolyzing water, and specifically to a method and system for evaluating the operating performance of an alkaline electrolytic water hydrogen production device. Background Art

[0002] As the core equipment for green hydrogen production, the operating performance of an alkaline electrolytic water hydrogen production device directly affects hydrogen production efficiency, equipment life, and economy. To ensure the efficient and stable operation of the device, it is necessary to evaluate and optimize the multi-physical field coupling state, electrode damage evolution, and control parameters of the electrolytic cell in real time. However, the existing evaluation methods and systems for the above problems have defects such as multi-dimensional parameter coupling failure, lagging damage prediction, and insufficient control intelligence, which seriously restrict the device performance.

[0003] In the prior art, the performance evaluation of an alkaline electrolytic water hydrogen production device mainly relies on the independent monitoring and analysis of a single physical field, and empirical formulas are used to estimate energy efficiency parameters. Due to the significant multi-field interactions of thermal-electric coupling and flow-electric coupling during the electrolysis process, the fragmented modeling method cannot quantify the dynamic coupling relationship, resulting in an energy efficiency evaluation deviation of more than 30%, and the potential faults of local overheating and abnormal ion concentration caused by multi-field imbalance cannot be identified, seriously reducing the accuracy and reliability of state analysis.

[0004] Traditional electrode damage monitoring relies on regular off-line detection or life prediction based on a fixed-order damage model, without considering the dynamic crack propagation characteristics under the combined action of current fluctuations, temperature gradients, and mechanical stresses. The existing methods are not sensitive enough to the frequency domain characteristics in the micro-crack initiation stage, with a false negative rate as high as 40%, and the prediction result lags behind the actual damage state by about 500h, resulting in a significant increase in the risk of sudden electrode fracture and a reduction in equipment life by more than 20%.

[0005] Existing control methods use fixed-threshold PID regulation or manual experience adjustment, and the preset parameters cannot adapt to the dynamic working conditions of electrolyte concentration fluctuations and electrode aging. Such methods have a response delay of more than 10 minutes, cannot suppress energy efficiency fluctuations, and the single-objective optimization strategy exacerbates electrode damage, causing conflicts between energy efficiency and life goals, resulting in poor long-term operation stability of the system and an increase in operation and maintenance costs by more than 35%.

[0006] Therefore, the present invention proposes a method and system for evaluating the operating performance of an alkaline electrolytic water hydrogen production device to solve the above-mentioned problems. Summary of the Invention

[0007] Aiming at the deficiencies of the prior art, the present invention provides a method and system for evaluating the operating performance of an alkaline electrolytic water hydrogen production device to solve the problems raised in the above background art.

[0008] To achieve the above object, the present invention is realized through the following technical solutions: A method for evaluating the operating performance of an alkaline electrolyzed water hydrogen production device, comprising:

[0009] Step 1, deploy a distributed sensor network, collect the operating data of the electrolyzer, establish a multi-physical field coupling model and calibrate the model parameter matrix;

[0010] Step 2, construct an electrode damage evolution model based on the model parameter matrix, process the acoustic emission signals collected by the sensor network and extract crack characteristic parameters, calculate the real-time damage degree, and generate a hierarchical early warning signal;

[0011] Step 3, construct a state vector according to the real-time damage degree and the operating data of the electrolyzer, define a virtual queue to represent the cumulative degree of the system state deviating from the target energy efficiency, and solve the current optimal control parameters based on the optimization theory;

[0012] Step 4, generate a comprehensive performance score and a parameter adjustment instruction in combination with the state vector, the real-time damage degree and the optimal control parameters;

[0013] Step 5, feedback the parameter adjustment instruction to the solution process of the optimal control parameters to form a closed-loop adjustment mechanism.

[0014] Preferably, in the above Step 1, deploying a distributed sensor network, collecting the operating data of the electrolyzer, establishing a multi-physical field coupling model and calibrating the model parameter matrix further includes:

[0015] Sub-step 1.1, deploy a temperature sensor array, a current density sensor array and an ultrasonic flow velocity sensor in the cathode, anode and diaphragm regions of the electrolyzer, and collect the temperature field data T(x, y, t), the current density distribution data J(x, y, t) and the electrolyte flow velocity data v(z, t);

[0016] wherein, T(x, y, t) is the temperature at the spatial coordinates (x, y) at time t,

[0017] J(x, y, t) is the current density at the spatial coordinates (x, y) at time t,

[0018] v(z, t) is the flow velocity of the electrolyte at height z at time t;

[0019] Sub-step 1.2, construct a multi-physical field coupling constitutive equation based on the Onsager reciprocal relation:

[0020]

[0021] wherein, J q is the heat flux density, J e is the current density, μ e is the electrochemical potential, L 11is the coefficient of pure heat conduction effect, L 12 is the coefficient of thermoelectric coupling effect, L 21 is the coefficient of thermoelectric coupling effect, L 22 is the coefficient of pure conductivity effect, is the spatial gradient operator, T is the temperature;

[0022] Sub-step 1.3, calibrate the phenomenological coefficient matrix L by the least squares method ij , and construct the parameter matrix update equation:

[0023]

[0024] where B is the data matrix, J meas is the measured flux vector, J model is the model predicted flux vector, Δt is the parameter update step size, is the element of the phenomenological coefficient matrix after the k-th iteration update, is the element of the phenomenological coefficient matrix after the (k - 1)-th iteration update, B T is the transpose matrix of the data matrix B.

[0025] Preferably, in step 2, based on the model parameter matrix, construct an electrode damage evolution model, process the acoustic emission signals collected by the sensor network, extract crack characteristic parameters, calculate the real-time damage degree, and generate a hierarchical warning signal, which further includes:

[0026] Sub-step 2.1, based on the phenomenological coefficient matrix L calibrated in step 1.3 ij , construct a fractional-order damage evolution equation:

[0027]

[0028] where α is the order of the fractional derivative, D is the electrode damage degree, γ is the material damage sensitivity coefficient, J0 is the reference current density, E a is the activation energy, J is the current density, m is the stress exponent, L 22 is the coefficient of pure conductivity effect, R is the ideal gas constant, T is the temperature, n is the material degradation exponent, dt is the time domain differential element;

[0029] Sub-step 2.2, perform a fractional Fourier transform on the acoustic emission signals collected by the sensor network:

[0030]

[0031] where X α (u) is the signal after the fractional Fourier transform, x(t) is the original acoustic emission signal, u is the fractional domain variable, α is the order of the fractional derivative, t is the time variable, cotα is the cotangent function, cscα is the cosecant function;

[0032] Sub-step 2.3: Calculate the real-time damage degree D(t) according to the damage evolution equation in sub-step 2.1 and the crack characteristic parameters in sub-step 2.2, and generate a warning signal:

[0033]

[0034] where D(t) is the damage degree, is the damage degree change rate, S th is the crack propagation energy threshold, X α (u) is the signal after fractional Fourier transform, and du is the fractional domain differential element.

[0035] Preferably, in step 3, a state vector is constructed according to the real-time damage degree and the electrolytic cell operation data, a virtual queue is defined to characterize the cumulative degree of the system state deviating from the target energy efficiency, and the current optimal control parameters are solved based on the optimization theory, which further includes:

[0036] Sub-step 3.1: Construct a state vector x(t) including the damage degree D(t), the cathode temperature T c , the anode temperature T a , the current density J, and the hydrogen production pressure :

[0037] x(t) = [D(t), T c (t), T a (t), J(t), P H2 (t)] T ,

[0038] where D(t) is the damage degree, T c (t), T a (t) are the collected cathode and anode temperatures, J(t) is the collected current density, is the collected hydrogen production pressure;

[0039] Sub-step 3.2: Define a virtual queue Q(t) to characterize the cumulative degree of the system state deviating from the target energy efficiency η target , and the update rule is:

[0040] Q(t + 1) = max{Q(t) + ∈(η eff (t) - η target ), 0},

[0041] where η eff (t) is the instantaneous energy efficiency, η target is the target energy efficiency, Q(t) is the virtual queue value, ∈ is the queue update coefficient, and Q(t + 1) is the virtual queue value at time t + 1;

[0042] Sub-step 3.3: Based on the state vector x(t) and the virtual queue Q(t), construct and solve for the optimal control parameter u * (t):

[0043]

[0044] where U is the control input constraint set, w1 and w2 are the weight coefficients of energy consumption and life loss, V is the Lyapunov optimization weight, u * (t) is the optimal control parameter vector, u0 is the control parameter reference value, and u is the fractional-order domain variable.

[0045] Preferably, in step 4, combining the state vector, the real-time damage degree, and the optimal control parameter to generate a comprehensive performance score and a parameter adjustment instruction further includes:

[0046] Sub-step 4.1: Normalize the state vector x(t), the damage degree D(t), and the optimal control parameter u * (t) to construct a standardized decision matrix Z = [z ij n×m :

[0047]

[0048] where z ij is the standardized index value, x ij is the original value of the j-th index of the i-th sample, μ j is the mean of the j-th index, σ j is the standard deviation of the j-th index, and x kj is the original value of the j-th index of the k-th sample;

[0049] Sub-step 4.2: Use the improved entropy weight method to calculate the weight coefficients w j of the energy efficiency, life, cost, and environmental protection indicators:

[0050]

[0051]

[0052] where E j is the information entropy of the j-th index, p ij is the proportion of the j-th index of the i-th sample, w j is the weight of the j-th index, and E k is the information entropy of the k-th index;

[0053] Sub-step 4.3: Calculate the comprehensive performance score S(t) based on the Technique for Order of Preference by Similarity to Ideal Solution (TOPSIS) and generate a parameter adjustment instruction Δu(t):

[0054] ​

[0055] Δu(t) = u * (t) - u opt ,

[0056] where S(t) is the comprehensive performance score, is the positive / negative ideal solution of the j-th index, D + (t) is the weighted Euclidean distance between the current state and the positive ideal solution, D - (t) is the weighted Euclidean distance between the current state and the negative ideal solution, z j (t) is the normalized value of the j-th index at the current moment, w j is the weight of the j-th index, Δu(t) is the parameter adjustment instruction, u opt is the historical optimal control parameter, u * (t) is the optimal control parameter.

[0057] Preferably, in step 5, the parameter adjustment instruction is fed back to the solution process of the optimal control parameter to form a closed-loop adjustment mechanism, which further includes:

[0058] Sub-step 5.1, applying the parameter adjustment instruction Δu(t) generated in sub-step 4.3 to the current optimal control parameter u * (t) to update the control parameter:

[0059] u(t + Δt) = u * (t) + λ·Δu(t),

[0060] where λ is the feedback gain coefficient, Δt is the parameter update step, Δu(t) is the parameter adjustment instruction, u * (t) is the optimal control parameter;

[0061] Sub-step 5.2, based on the updated control parameter u(t + Δt), calculating the system energy efficiency deviation E(t) in real time:

[0062] E(t) = |η eff (t) - η target | + β·D(t),

[0063] where β is the damage weight coefficient, η eff (t) is the instantaneous energy efficiency, η target is the target energy efficiency, D(t) is the damage degree;

[0064] Sub-step 5.3, dynamically correcting the phenomenological coefficient matrix L ij in step 1.3 and the damage model parameter γ in step 2.1 according to the energy efficiency deviation E(t):

[0065]

[0066] Among them, ρ is the model correction step size, is the partial derivative of the energy efficiency deviation with respect to the coupling coefficient, is the partial derivative of the energy efficiency deviation with respect to the damage sensitivity coefficient, γ is the material damage sensitivity coefficient, and L ij is the phenomenological coefficient matrix.

[0067] Preferably, the distributed sensor network includes a micro-CT scanner and a laser-induced fluorescence system for real-time monitoring of the electrode microstructure and the electrolyte concentration field distribution.

[0068] An operating performance evaluation system for an alkaline electrolytic water hydrogen production device, the operating performance evaluation system for the alkaline electrolytic water hydrogen production device includes:

[0069] A multi-channel high-speed data acquisition module, connected to a micro-region temperature array, a current density measurement board, and an ultrasonic flow sensor;

[0070] A multi-physics field coupling modeling module, built-in with a finite element solver and a phenomenological coefficient calibration algorithm;

[0071] A damage prediction engine, integrating a fractional-order differential equation solver and an acoustic emission signal processing unit;

[0072] A dynamic optimization controller, including a Lyapunov function calculation unit and a convex optimization solver;

[0073] A comprehensive evaluation module, outputting a comprehensive performance score and a parameter adjustment instruction;

[0074] An edge-cloud communication interface, supporting data synchronization and model update of the OPC UA protocol.

[0075] A terminal device, including a processor and a memory, the memory stores a computer program, and when the processor executes the program, it implements the method for evaluating the operating performance of an alkaline electrolytic water hydrogen production device.

[0076] A computer-readable storage medium, storing a computer program, and when the computer program is executed by a processor, it implements the method for evaluating the operating performance of an alkaline electrolytic water hydrogen production device.

[0077] The present invention provides a method and a system for evaluating the operating performance of an alkaline electrolytic water hydrogen production device. It has the following beneficial effects:

[0078] 1. The technical solution of the present invention is to use a distributed sensor network to collect multi-physical field data and establish a coupling model to calibrate the parameter matrix, achieving the technical effect of a dynamic coupling relationship of multi-dimensional parameters. Compared with the technical solution in the prior art that relies on single-dimensional parameters and empirical formulas to estimate the coupling effect, it solves the deficiencies of large deviation and low reliability in energy efficiency evaluation caused by ignoring the multi-field interaction in the traditional method, and improves the comprehensiveness and accuracy of system state analysis.

[0079] 2. The technical solution of the present invention is to adopt a crack prediction mechanism that combines a fractional-order damage evolution model and acoustic emission time-frequency analysis, achieving the technical effect of realizing early warning of micro-damage of the electrode and improving the life prediction ability. Compared with the technical solution in the prior art that uses a fixed-order damage model and offline detection means, it solves the deficiencies of low sensitivity to the dynamic evolution of micro-damage and strong prediction lag in the existing method, reduces the risk of sudden failure and extends the service life of the equipment.

[0080] 3. The technical solution of the present invention is to adopt a dynamic optimization and closed-loop feedback regulation mechanism driven by a virtual queue, achieving the technical effect of realizing full-automatic parameter optimization control and multi-objective coordinated regulation. Compared with the technical solution in the prior art that relies on manual experience adjustment and fixed-threshold control, it solves the deficiencies of slow response speed and inability to take into account multi-dimensional optimization objectives such as energy efficiency and life in the traditional control method, and improves the autonomy and stability of system operation. BRIEF DESCRIPTION OF THE DRAWINGS

[0081] Figure 1 is a flowchart of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0082] To enable those skilled in the art to understand the solution of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. Other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the scope of protection of the present invention.

[0083] The present invention will be described in detail below with reference to the accompanying drawings:

[0084] Embodiment:

[0085] Please refer to the attached Figure 1 , the embodiment of the present invention provides a method for evaluating the operating performance of an alkaline electrolytic water hydrogen production device, including:

[0086] Step 1, deploy a distributed sensor network, collect the operating data of the electrolytic cell, establish a multi-physical field coupling model and calibrate the model parameter matrix;

[0087] The distributed sensor network includes a micro-CT scanner and a laser-induced fluorescence system for real-time monitoring of the microstructure of the electrode and the distribution of the electrolyte concentration field;

[0088] Sub-step 1.1: Deploy a temperature sensor array, a current density sensor array, and an ultrasonic flow velocity sensor in the cathode, anode, and diaphragm regions of the electrolytic cell to collect temperature field data T(x,y,t), current density distribution data J(x,y,t), and electrolyte flow velocity data v(z,t);

[0089] where T(x,y,t) is the temperature at time t at the spatial coordinates (x,y),

[0090] J(x,y,t) is the current density at time t at the spatial coordinates (x,y),

[0091] v(z,t) is the flow velocity of the electrolyte at height z at time t;

[0092] Sub-step 1.2: Construct a multi-physics field coupling constitutive equation based on the Onsager reciprocal relation:

[0093]

[0094] where J q is the heat flux density, J e is the current density, μ e is the electrochemical potential, L 11 is the pure heat conduction effect coefficient, L 12 is the thermoelectric coupling effect coefficient, L 21 is the thermoelectric coupling effect coefficient, L 22 is the pure conductivity effect coefficient, is the spatial gradient operator, and T is the temperature;

[0095] Sub-step 1.3: Calibrate the phenomenological coefficient matrix L ij by the least squares method to construct a parameter matrix update equation:

[0096]

[0097] where B is the data matrix, J meas is the measured flux vector, J model is the model predicted flux vector, Δt is the parameter update step size, is the element of the phenomenological coefficient matrix after the k-th iteration update, is the element of the phenomenological coefficient matrix after the (k - 1)-th iteration update, and B T is the transpose matrix of the data matrix B;

[0098] Step 2: Based on the model parameter matrix, construct an electrode damage evolution model, process the acoustic emission signals collected by the sensor network, extract crack characteristic parameters, calculate the real-time damage degree, and generate a hierarchical warning signal;

[0099] Sub-step 2.1: Based on the phenomenological coefficient matrix L calibrated in Step 1.3 ij , construct a fractional-order damage evolution equation:

[0100]

[0101] where α is the order of the fractional derivative, D is the electrode damage degree, γ is the material damage sensitivity coefficient, J0 is the reference current density, E a is the activation energy, J is the current density, m is the stress exponent, L 22 is the pure conductivity effect coefficient, R is the ideal gas constant, T is the temperature, n is the material degradation index, and dt is the time-domain differential element;

[0102] Sub-step 2.2: Perform a fractional-order Fourier transform on the acoustic emission signals collected by the sensor network:

[0103]

[0104] where X α (u) is the signal after the fractional-order Fourier transform, x(t) is the original acoustic emission signal, u is the fractional-order domain variable, α is the order of the fractional derivative, t is the time variable, cotα is the cotangent function, and cscα is the cosecant function;

[0105] Sub-step 2.3: According to the damage evolution equation in Sub-step 2.1 and the crack characteristic parameters in Sub-step 2.2, calculate the real-time damage degree D(t) and generate a warning signal:

[0106]

[0107] where D(t) is the damage degree, is the damage degree change rate, S th is the crack propagation energy threshold, X α (u) is the signal after the fractional-order Fourier transform, and du is the fractional-order domain differential element;

[0108] Step 3: Based on the real-time damage degree and the electrolytic cell operation data, construct a state vector, define a virtual queue to characterize the cumulative degree of the system state deviating from the target energy efficiency, and solve the current optimal control parameters based on the optimization theory;

[0109] Sub-step 3.1: Construct a state vector including the damage degree D(t), the cathode temperature T c , the anode temperature T a , the current density J, and the hydrogen production pressure The state vector x(t):

[0110]

[0111] where D(t) is the damage degree, T c (t), T a (t) are the temperatures of the cathode and anode collected, J(t) is the current density collected, is the hydrogen production pressure collected;

[0112] Sub-step 3.2, define the virtual queue Q(t) to characterize the cumulative degree of the system state deviating from the target energy efficiency η target , and the update rule is:

[0113] Q(t + 1) = max{Q(t)+∈(η eff (t) - η target ), 0},

[0114] where η eff (t) is the instantaneous energy efficiency, η target is the target energy efficiency, Q(t) is the virtual queue value, ∈ is the queue update coefficient, and Q(t + 1) is the virtual queue value at time t + 1;

[0115] Sub-step 3.3, based on the state vector x(t) and the virtual queue Q(t), construct and solve the optimal control parameter u * (t):

[0116]

[0117] where U is the control input constraint set, w1, w2 are the weight coefficients of energy consumption and life loss, V is the Lyapunov optimization weight, u * (t) is the optimal control parameter vector, u0 is the control parameter reference value, and u is the fractional-order domain variable;

[0118] Step 4, combine the state vector, real-time damage degree and optimal control parameter to generate a comprehensive performance score and parameter adjustment instruction;

[0119] Sub-step 4.1, normalize the state vector x(t), damage degree D(t) and optimal control parameter u * (t), and construct the standardized decision matrix Z = [z ij n×m :

[0120]

[0121] where z ij is the standardized index value, x ij is the original value of the jth index of the ith sample, μ​j is the mean value of the j-th index, and σ j is the standard deviation of the j-th index, and x kj is the original value of the j-th index of the k-th sample;

[0122] Sub-step 4.2: Calculate the weight coefficients w of energy efficiency, lifespan, cost, and environmental protection indicators using the improved entropy weight method j :

[0123]

[0124] where E j is the information entropy of the j-th index, p ij is the proportion of the j-th index of the i-th sample, w j is the weight of the j-th index, E k is the information entropy of the k-th index;

[0125] Sub-step 4.3: Calculate the comprehensive performance score S(t) based on the Technique for Order of Preference by Similarity to Ideal Solution (TOPSIS), and generate a parameter adjustment instruction Δu(t):

[0126]

[0127] Δu(t) = u * (t) - u opt ,

[0128] where S(t) is the comprehensive performance score, is the positive / negative ideal solution of the j-th index, D + (t) is the weighted Euclidean distance between the current state and the positive ideal solution, D - (t) is the weighted Euclidean distance between the current state and the negative ideal solution, z j (t) is the standardized value of the j-th index at the current moment, w j is the weight of the j-th index, Δu(t) is the parameter adjustment instruction, u opt is the historical optimal control parameter, u * (t) is the optimal control parameter;

[0129] Step 5: Feed back the parameter adjustment instruction to the solution process of the optimal control parameter to form a closed-loop adjustment mechanism;

[0130] Sub-step 5.1: Apply the parameter adjustment instruction Δu(t) generated in sub-step 4.3 to the current optimal control parameter u * (t) to update the control parameter:

[0131] u(t + Δt) = u * (t) + λ·Δu(t),

[0132] where λ is the feedback gain coefficient, Δt is the parameter update step size, Δu(t) is the parameter adjustment instruction, and u * (t) is the optimal control parameter;

[0133] Sub-step 5.2: Based on the updated control parameter u(t + Δt), calculate the system energy efficiency deviation E(t) in real time:

[0134] E(t) = |η eff (t) - η target | + β·D(t),

[0135] where β is the damage weight coefficient, η eff (t) is the instantaneous energy efficiency, η target is the target energy efficiency, and D(t) is the damage degree;

[0136] Sub-step 5.3: Dynamically correct the phenomenological coefficient matrix L in Step 1.3 ij and the damage model parameter γ in Step 2.1:

[0137]

[0138]

[0139] where ρ is the model correction step size, is the partial derivative of the energy efficiency deviation with respect to the coupling coefficient, is the partial derivative of the energy efficiency deviation with respect to the damage sensitivity coefficient, γ is the material damage sensitivity coefficient, and L ij is the phenomenological coefficient matrix.

[0140] Advantages of Step 1: By deploying a distributed sensor network, real-time monitoring of the temperature field, current density distribution, and electrolyte flow rate of the electrolytic cell in all dimensions is achieved, breaking through the limitations of traditional single physical field monitoring. Based on the Onsager reciprocal relation, a multi-field coupling constitutive equation is constructed, and the least squares method is used to calibrate the phenomenological coefficient matrix, significantly improving the model's analytical ability for complex interactions such as thermal-electric coupling and flow-electric coupling. Solve the energy efficiency evaluation deviation caused by traditional empirical formulas ignoring multi-field dynamic coupling, improve the multi-field coupling modeling accuracy to the engineering practical level, and provide a high-fidelity data basis for subsequent damage prediction and control optimization.

[0141] Advantages of Step 2: Based on the fractional-order damage evolution model and the fractional Fourier transform of acoustic emission signals, the non-linear dynamic characterization of the micro-crack propagation behavior of the electrode is realized. By extracting the crack characteristic parameters in the 80 - 120 kHz frequency band and combining with the real-time damage degree calculation, the risk of electrode failure can be predicted more than 500 h in advance, solving the problem of insufficient sensitivity of traditional fixed-order models to the dynamic crack propagation. The hierarchical early warning mechanism greatly reduces the probability of sudden failures and extends the electrode life by more than 20%, providing accurate decision-making support for equipment health management.

[0142] Advantages of Step 3: By constructing a state vector including damage degree, temperature, current density, and hydrogen production pressure, and defining a virtual queue to characterize the cumulative degree of the system deviating from the target energy efficiency, the deep integration of multi-physical field states and optimization goals is achieved. Based on Lyapunov optimization theory, the optimal control parameters are solved to suppress electrode damage while ensuring hydrogen production efficiency, solving the problem of the conflict between energy efficiency-life goals caused by traditional single-objective PID control or manual experience adjustment. The control response delay is compressed within 50 ms, and the standard deviation of energy efficiency fluctuations is reduced by 85%, significantly improving the system's dynamic stability and target coordination ability.

[0143] Advantages of Step 4: By using the improved entropy weight method and the technique for order preference by similarity to an ideal solution, a multi-dimensional comprehensive performance scoring system is constructed to solve the one-sidedness problem of traditional single-index evaluation. Through the normalization processing and dynamic weight allocation of the state vector, damage degree, and control parameters, intuitive scoring results and parameter adjustment instructions are generated, realizing the seamless connection from data to decision-making. The operation and maintenance personnel are liberated from complex parameter trade-offs, and the comparison between the scoring results and the historical optimal state can directly drive the generation of control instructions, providing a scientific basis for closed-loop regulation.

[0144] Advantages of Step 5: By feeding back the parameter adjustment instructions to the model parameter calibration and damage prediction module, a full-closed-loop self-learning mechanism of "monitoring - prediction - control - correction" is formed. Based on the energy efficiency deviation, the phenomenological coefficient matrix and damage sensitivity coefficient are dynamically corrected to solve the problem of long-term prediction inaccuracy of traditional static models due to electrode aging and working condition drift. The system is enabled to continuously adapt to the dynamic changes of electrolyte concentration fluctuations and material property degradation, and the annual average model prediction error is reduced by 12%, significantly extending the engineering application period of the technical solution.

[0145] An operating performance evaluation system for an alkaline water electrolysis hydrogen production device, the operating performance evaluation system for an alkaline water electrolysis hydrogen production device includes:

[0146] A multi-channel high-speed data acquisition module, connected to a micro-region temperature array, a current density measurement board, and an ultrasonic flow sensor;

[0147] A multi-physical field coupling modeling module, built-in with a finite element solver and a phenomenological coefficient calibration algorithm;

[0148] Damage prediction engine, integrating a fractional-order differential equation solver and an acoustic emission signal processing unit;

[0149] Dynamic optimization controller, including a Lyapunov function calculation unit and a convex optimization solver;

[0150] Comprehensive evaluation module, outputting a comprehensive performance score and parameter adjustment instructions;

[0151] Edge-cloud communication interface, supporting data synchronization and model update of the OPC UA protocol.

[0152] A terminal device, including a processor and a memory, the memory stores a computer program, and when the processor executes the program, it implements a method for evaluating the operating performance of an alkaline electrolytic water hydrogen production device.

[0153] A computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, it implements a method for evaluating the operating performance of an alkaline electrolytic water hydrogen production device.

[0154] Through the deep integration of the terminal device and the storage medium with high-performance computing, edge intelligence, flexible expansion, and industrial-grade reliability, the complex multi-field modeling, damage prediction, and closed-loop control algorithms are implemented as deployable engineering solutions, breaking through the limitations of traditional industrial control systems such as insufficient computing power, poor compatibility, and high maintenance costs, realizing the full-chain empowerment of the hydrogen production device from "data collection" to "autonomous optimization", and promoting the leapfrog development of the green hydrogen industry towards intelligence and standardization.

[0155] Although the embodiments of the present invention have been shown and described, for those of ordinary skill in the art, it can be understood that various changes, modifications, substitutions, and variations can be made to these embodiments without departing from the principles and spirit of the present invention, and the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A method for evaluating the operating performance of an alkaline electrolyzed water hydrogen production device, characterized in that, Including: Step 1: Deploy a distributed sensor network, collect the operating data of the electrolytic cell, establish a multi-physical field coupling model, and calibrate the model parameter matrix. Step 2: Based on the model parameter matrix, construct an electrode damage evolution model, process the acoustic emission signals collected by the sensor network, extract crack characteristic parameters, calculate the real-time damage degree, and generate a hierarchical early warning signal. Step 3: Construct a state vector according to the real-time damage degree and the operating data of the electrolytic cell, define a virtual queue to characterize the cumulative degree of the system state deviating from the target energy efficiency, and solve the current optimal control parameters based on the optimization theory. Step 4: Combine the state vector, the real-time damage degree, and the optimal control parameters to generate a comprehensive performance score and a parameter adjustment instruction. Step 5: Feed back the parameter adjustment instruction to the solution process of the optimal control parameters to form a closed-loop adjustment mechanism.

2. The method for evaluating the operating performance of an alkaline electrolyzed water hydrogen production device according to claim 1, characterized in that, In the said Step 1, deploying a distributed sensor network, collecting the operating data of the electrolytic cell, establishing a multi-physical field coupling model, and calibrating the model parameter matrix further includes: Sub-step 1.1: Deploy a temperature sensor array, a current density sensor array, and an ultrasonic flow velocity sensor in the cathode, anode, and diaphragm regions of the electrolytic cell to collect temperature field data T(x, y, t), current density distribution data J(x, y, t), and electrolyte flow velocity data v(z, t). Wherein, T(x, y, t) is the temperature at the spatial coordinates (x, y) at time t. J(x, y, t) is the current density at the spatial coordinates (x, y) at time t. v(z, t) is the flow velocity of the electrolyte at height z at time t. Sub-step 1.2: Based on the Onsager reciprocal relation, construct a multi-physical field coupling constitutive equation. Among them, J q is the heat flux density, J e is the current density, μ e is the electrochemical potential, L 11 is the coefficient of pure heat conduction effect, L 12 is the coefficient of thermoelectric coupling effect, L 21 is the coefficient of thermoelectric coupling effect, L 22 is the coefficient of pure conductance effect, is the spatial gradient operator, and T is the temperature; Sub-step 1.3: Calibrate the phenomenological coefficient matrix L by the least squares method ij , and construct the parameter matrix update equation: Among them, B is the data matrix, J meas is the measured flux vector, J model is the model predicted flux vector, Δt is the parameter update step size, is the element of the phenomenological coefficient matrix after the k-th iteration update, is the element of the phenomenological coefficient matrix after the (k - 1)-th iteration update, B T is the transpose matrix of the data matrix B.

3. The method for evaluating the operating performance of an alkaline electrolyzed water hydrogen production device according to claim 1, wherein In the said Step 2, based on the model parameter matrix, construct an electrode damage evolution model, process the acoustic emission signals collected by the sensor network, extract crack characteristic parameters, calculate the real-time damage degree, and generate a hierarchical early warning signal further includes: Sub-step 2.1, based on the phenomenological coefficient matrix L calibrated in Step 1.3 ij , construct the fractional-order damage evolution equation: where α is the fractional derivative order, D is the degree of electrode damage, γ is the material damage sensitivity coefficient, J0 is the reference current density, E a is the activation energy, J is the current density, m is the stress exponent, L 22 is the pure conductivity effect coefficient, R is the ideal gas constant, T is the temperature, n is the material degradation index, dt is the time-domain differential element; Sub-step 2.2: Perform a fractional Fourier transform on the acoustic emission signals collected by the sensor network. Among them, X α (u) is the signal after fractional Fourier transform, x(t) is the original acoustic emission signal, u is the fractional domain variable, α is the order of fractional derivative, t is the time variable, cotα is the cotangent function, and cscα is the cosecant function; Sub-step 2.3: According to the damage evolution equation in Sub-step 2.1 and the crack characteristic parameters in Sub-step 2.2, calculate the real-time damage degree D(t) and generate an early warning signal. where D(t) is the damage degree, is the damage degree change rate, S th is the crack propagation energy threshold, X α (u) is the signal after fractional Fourier transform, and du is the fractional domain differential element.

4. A method for evaluating the operating performance of an alkaline electrolyzed water hydrogen production device according to claim 1, characterized in that, In the said Step 3, construct a state vector according to the real-time damage degree and the operating data of the electrolytic cell, define a virtual queue to characterize the cumulative degree of the system state deviating from the target energy efficiency, and solve the current optimal control parameters based on the optimization theory further includes: Sub-step 3.1, construct a state vector \(x(t)\) that includes the damage degree \(D(t)\), the cathode temperature \(T\) c , the anode temperature \(T\) a , the current density \(J\), and the hydrogen production pressure : Among them, D(t) is the damage degree, T c (t), T a (t) are the collected cathode and anode temperatures, J(t) is the collected current density, is the collected hydrogen production pressure; Sub-step 3.2, define a virtual queue Q(t) to characterize the cumulative degree of the system state deviating from the target energy efficiency η target , and the update rule is as follows: Q(t + 1) = max{Q(t) + ∈(η eff (t) - η target ), 0}, Among them, η eff (t) is the instantaneous energy efficiency, η target is the target energy efficiency, Q(t) is the virtual queue value, ∈ is the queue update coefficient, and Q(t + 1) is the virtual queue value at time t + 1; Sub-step 3.3, based on the state vector x(t) and the virtual queue Q(t), construct and solve for the optimal control parameter u * (t): Among them, \(U\) is the control input constraint set, \(w_1\) and \(w_2\) are the weight coefficients of energy consumption and life loss, \(V\) is the Lyapunov optimization weight, \(u\) * (t) is the optimal control parameter vector, \(u_0\) is the control parameter reference value, and \(u\) is the fractional-order domain variable.

5. A method for evaluating the operating performance of an alkaline electrolyzed water hydrogen production device according to claim 1, characterized in that, In the said Step 4, combine the state vector, the real-time damage degree, and the optimal control parameters to generate a comprehensive performance score and a parameter adjustment instruction further includes: Sub-step 4.1, normalize the state vector x(t), the damage degree D(t), and the optimal control parameter u * (t) to construct a standardized decision matrix Z = [z ij n×m :​ Among them, z ij is the standardized index value, x ij is the original value of the j-th index of the i-th sample, μ j is the mean of the j-th index, σ j is the standard deviation of the j-th index, x kj is the original value of the j-th index of the k-th sample; Sub-step 4.2: Calculate the weight coefficients \(w\) of energy efficiency, lifespan, cost, and environmental protection indicators using the improved entropy weight method j : Among them, E j is the information entropy of the j-th index, and p ij is the proportion of the j-th index of the i-th sample. w j is the weight of the j-th index, and E k is the information entropy of the k-th index; Sub-step 4.3: Calculate the comprehensive performance score S(t) based on the Technique for Order of Preference by Similarity to Ideal Solution (TOPSIS) and generate a parameter adjustment instruction Δu(t). Δu(t) = u * (t) - u opt , Among them, S(t) is the comprehensive performance score, is the positive / negative ideal solution of the j-th index, D + (t) is the weighted Euclidean distance between the current state and the positive ideal solution, D - (t) is the weighted Euclidean distance between the current state and the negative ideal solution, z j (t) is the normalized value of the j-th index at the current moment, w j is the weight of the j-th index, Δu(t) is the parameter adjustment instruction, u opt is the historical optimal control parameter, u * (t) is the optimal control parameter.

6. A method for evaluating the operating performance of an alkaline electrolyzed water hydrogen production device according to claim 1, characterized in that, In the said Step 5, feed back the parameter adjustment instruction to the solution process of the optimal control parameters to form a closed-loop adjustment mechanism further includes: Sub-step 5.1, apply the parameter adjustment instruction Δu(t) generated in sub-step 4.3 to the current optimal control parameter u * (t) to update the control parameter: u(t + Δt) = u * (t) + λ·Δu(t), where λ is the feedback gain coefficient, Δt is the parameter update step size, Δu(t) is the parameter adjustment instruction, and u * (t) is the optimal control parameter; Sub-step 5.2: Based on the updated control parameter u(t + Δt), calculate the system energy efficiency deviation E(t) in real time. E(t) = |η eff (t) - η target | + β·D(t), Among them, β is the damage weight coefficient, η eff (t) is the instantaneous energy efficiency, η target is the target energy efficiency, and D(t) is the damage degree; Sub-step 5.3: Dynamically correct the phenomenological coefficient matrix L in Step 1.3 ij and the damage model parameter γ in Step 2.1: where ρ is the model correction step size, is the partial derivative of the energy efficiency deviation with respect to the coupling coefficient, is the partial derivative of the energy efficiency deviation with respect to the damage sensitivity coefficient, γ is the material damage sensitivity coefficient, and L ij is the phenomenological coefficient matrix.

7. A method for evaluating the operating performance of an alkaline electrolyzed water hydrogen production device according to claim 1, characterized in that, The distributed sensor network includes a micro-CT scanner and a laser-induced fluorescence system for real-time monitoring of the electrode microstructure and the electrolyte concentration field distribution.

8. An operating performance evaluation system for an alkaline electrolytic water hydrogen production device, according to the operating performance evaluation method for an alkaline electrolytic water hydrogen production device described in any one of claims 1-7, characterized in that, The alkaline electrolytic water hydrogen production device operation performance evaluation system includes: A multi-channel high-speed data acquisition module, connected to a micro-region temperature array, a current density measurement board, and an ultrasonic flow sensor; A multi-physical-field coupling modeling module, with a finite element solver and a phenomenological coefficient calibration algorithm built-in; A damage prediction engine, integrating a fractional-order differential equation solver and an acoustic emission signal processing unit; A dynamic optimization controller, including a Lyapunov function calculation unit and a convex optimization solver; A comprehensive evaluation module, outputting a comprehensive performance score and parameter adjustment instructions; An edge-cloud communication interface, supporting data synchronization and model update of the OPC UA protocol.

9. A terminal device, characterized in that, It includes a processor and a memory. The memory stores a computer program, and when the processor executes the program, it implements the method for evaluating the operation performance of an alkaline electrolytic water hydrogen production device according to any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, Stores a computer program, and when the computer program is executed by a processor, it implements the method for evaluating the operation performance of an alkaline electrolytic water hydrogen production device according to any one of claims 1-7.

Images